sneak/routewatch
1
0 Fork 0
Code Issues 1 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Compare commits

merge into: sneak/routewatch:main
sneak/routewatch:main sneak/routewatch:next sneak/routewatch:issue-255-todo-open-work sneak/routewatch:issue-256-load-independent-tests sneak/routewatch:issue-245-go-sqlite3-1.14.53 sneak/routewatch:issue-251-prose-read sneak/routewatch:issue-248-useradd-uid sneak/routewatch:issue-239-geolocation sneak/routewatch:issue-237-icloud-private-relay sneak/routewatch:issue-236-protonvpn-list sneak/routewatch:issue-238-ptr-doh sneak/routewatch:issue-240-test-time-allowances sneak/routewatch:issue-235-vpn-lists sneak/routewatch:issue-234-tor-exits-onionoo sneak/routewatch:issue-233-ip-lists sneak/routewatch:prod sneak/routewatch:issue-27-cached-stats
...
pull from: sneak/routewatch:issue-239-geolocation
sneak/routewatch:next sneak/routewatch:issue-255-todo-open-work sneak/routewatch:issue-256-load-independent-tests sneak/routewatch:issue-245-go-sqlite3-1.14.53 sneak/routewatch:issue-251-prose-read sneak/routewatch:issue-248-useradd-uid sneak/routewatch:issue-239-geolocation sneak/routewatch:issue-237-icloud-private-relay sneak/routewatch:issue-236-protonvpn-list sneak/routewatch:issue-238-ptr-doh sneak/routewatch:issue-240-test-time-allowances sneak/routewatch:issue-235-vpn-lists sneak/routewatch:issue-234-tor-exits-onionoo sneak/routewatch:issue-233-ip-lists sneak/routewatch:prod sneak/routewatch:main sneak/routewatch:issue-27-cached-stats
26 Commits
main ... issue-239-geolocation
Author SHA1 Message Date
sneak fe392db4fc Add best-effort geolocation to the IP lookup from geojs and DB-IP City Lite (closes #239)
check / check (push) Successful in 4m19s
Details 
Each result gains `geo`. One request to geojs carries every address, 1 second in all. On a timeout, an error or an answer with no country, city or coordinates, the lookup reads DB-IP City Lite, downloaded monthly into the state directory. geojs answers stay in memory (250,000, least recently used dropped) and in a new `cache.db` table for 7 days.

Judgement call: a reserved address goes to neither source, and its `geo` is null.
Judgement call: `updated` for DB-IP is when the copy was downloaded.
Deviation: the cache is SQLite, by sneak's words.

Model: opus-5-5
 2026-11-10 14:31:47 +00:00
clawbot 2c3f6f71dc Add the iCloud Private Relay list to the IP lookup, with is_relay (closes #237)
check / check (push) Failing after 17m2s
Details 
Adds Apple's iCloud Private Relay egress list as `icloud_private_relay`, downloaded once a day, and `flags.is_relay`, true when an address is on it. Loaded, the list adds about 0.3 MiB to the Go heap; parsing it allocates about 94 MiB, freed by the next garbage collection.

Judgement call: a line with no comma fails the parse, so a plain network list served at Apple's URL cannot replace a good copy.

Model: opus-5-5
 2026-11-10 15:13:55 +01:00
clawbot b2553f044d Add the ProtonVPN server networks and addresses to the IP lookup (closes #236)
check / check (push) Successful in 1m27s
Details 
Proton's own server list answers only a logged-in session, so the lists come from the public mirror https://github.com/tn3w/ProtonVPN-IPs, downloaded once a day: `protonvpn`, its /24 networks, and `protonvpn_entry`, its servers' IPv4 and IPv6 addresses. Both feed `flags.is_vpn` and `vpn_providers`.

Judgement call: the /24 networks are listed as well as the exact addresses, because coverage matters more than attribution, so neighbouring addresses in those networks count too.
Risk: the mirror is one person's repository; if it stops updating, downloads keep succeeding with old data.

Model: opus-5-5
 2026-11-10 14:14:06 +01:00
clawbot 0cbd9cd943 Resolve PTR names over DNS-over-HTTPS and cache them for the record TTL (closes #238)
check / check (push) Successful in 4m39s
Details 
`ptr` keeps its field and shape. It now comes from Google, Cloudflare, AdGuard and Quad9 over RFC 8484, tried in turn within 2 seconds, in place of the host's resolver with no cache. Answers stay in memory and in a new `cache.db` for the record's TTL, at most 250,000 addresses. A reserved address is not sent to any resolver and has an empty `ptr`.

Judgement call: each resolver gets an equal share of the time left, so a hung one does not use up the limit.
Judgement call: the negative TTL is the smaller of the SOA minimum and the SOA's own TTL.
Deviation: the cache is SQLite, by sneak's words, not the JSON file the standing rule asks for.

Model: opus-5-5
 2026-11-10 13:48:06 +01:00
clawbot 641798bb22 Make the tests pass on a busy host (closes #240)
check / check (push) Successful in 1m51s
Details 
Tests that wait on the real clock failed when the host stalled for a few seconds, although the code was right. Waits for something that should happen are now mostly 15 seconds. Tests whose result depends on a short idle timeout or a production request limit run under `synctest.Test`, on a fake clock, with a fake transport where a real connection would stop that clock. Test code only.

Judgement call: the 5-second waits in three `internal/streamer` tests also became 15 seconds.

Model: opus-5-5
 2026-11-10 12:48:07 +01:00
clawbot 28ef0275ba Add the public VPN server lists, with is_vpn and vpn_providers (closes #235)
check / check (push) Failing after 4m35s
Details 
The IP lookup now checks the public VPN server lists of Mullvad, NordVPN, Private Internet Access and IVPN, and X4BNet's community list, each downloaded once a day. `List` gains `VPN`. Every result gains `flags.is_vpn` and `vpn_providers`, which is empty when no list holds the address.

Judgement call: X4BNet's IPv4 and IPv6 files are two lists, `x4bnet` and `x4bnet_v6`, as Spamhaus's are.
Judgement call: Private Internet Access's signature is neither read nor checked.
Judgement call: a document with no addresses fails the parse.
Rule suppressed: `tagliatelle` on the structs holding the publishers' field names.

Model: opus-5-5
 2026-11-10 12:15:32 +01:00
clawbot 3204b7ee4b Take the Tor exit list from Onionoo, which has the IPv6 exits (closes #234)
check / check (push) Failing after 1m50s
Details 
`check.torproject.org` lists IPv4 exits only, so `is_tor` was false for an IPv6 exit. `tor_exits` now comes from Onionoo through a new format that reads `relays[].exit_addresses` and `relays[].or_addresses`. IPv6 addresses come only from `or_addresses`, the address a relay accepts Tor connections on, so an exit leaving from another IPv6 address still has `is_tor` false.

Judgement call: a document with no addresses fails the parse.
Rule suppressed: `tagliatelle` on the struct holding Onionoo's field names.

Model: opus-5-5
 2026-11-10 11:47:56 +01:00
clawbot cf50d195ad Rename blocklists to IP lists, add IP lookup flags, raise the download limit to 200 MiB (closes #233)
check / check (push) Failing after 10m45s
Details 
The lists are not only used for blocking, so the package, the `blocklists` field of the IP lookup answer and the state directory are now IP lists (`internal/iplist`, `ip_lists`, `iplists`). Every result gains a `flags` object with `is_tor` and `is_bogon`. The largest list file accepted is 200 MiB.

Judgement call: the dated 2026-10-27 `TODO.md` entry keeps the old word.
Rule suppressed: `tagliatelle` on the two result structs, for snake_case keys.

Model: opus-5-5
 2026-11-10 10:48:23 +01:00
clawbot e58c6635e7 Record origin changes and show them on the prefix page (closes #161)
check / check (push) Successful in 1m3s
Details 
The routing table records a row each time a prefix and origin AS gets its first peer (announced) or loses its last (withdrawn), with the time and how many peers carry the prefix just after. The prefix handler writes the rows to a new origin_changes table, apart from routes. Every hour the database maintainer keeps each prefix's rows from the last 72 hours or its newest 500, whichever keeps more. The prefix page lists them newest first, at most 5,000.

At most 100,000 rows wait in memory to be written; past that the oldest are dropped and logged. A stop loses the rows past its last write.

Model: deepseek-v4-pro (implementation); opus-5-5 (commit message)
 2026-11-05 06:57:41 +01:00
clawbot 15bf20a894 Drop an update only when its handler's queue is full (closes #229)
check / check (push) Canceled after 0s
Details 
The streamer dropped a random share of a handler's updates once its
queue was half full. When the feed paused and then sent its backlog
while the routing table's Overview walked every prefix, the prefix
handler lost about 10,000 updates with its queue never full.

The streamer now drops an update only when the queue is full. The
prefix handler's queue holds 100,000 messages, about 100 MiB, so it
can hold such a backlog. The README's Memory and Feed handling
sections give the new sizes and the rule.

Model: opus-5-5
 2026-11-03 18:27:09 +01:00
clawbot 742e75914c Rewrite the README sentence by sentence (closes #157)
check / check (push) Canceled after 0s
Details 
The README is rewritten from scratch against the prose rules of
#157: every sentence under
about 30 words, lists as bullets, every technical term defined where it
first appears, and every statement checked against the code on next. It
leads with what RouteWatch is and how to run it, then the pages, the API
and the blocklists, then the settings, memory and upaas, and last the
design and the development workflow. The dated entry goes into TODO.md.

Model: fable-5-1
 2026-11-03 00:10:08 +01:00
clawbot 37cecedc5b Rewrite TODO.md sentence by sentence (part of #157)
check / check (push) Canceled after 0s
Details 
Every sentence of TODO.md is rewritten from scratch against the rules
of #157: about 30 words at
most, one idea each, subject and verb early, identifiers in backticks.
Status and Next Step describe the repo as the tracker shows it now.
Every Completed Steps entry keeps its date, its facts and its issue
reference, checked against the commit it names. The Workflow section
keeps its meaning. The entry for this rewrite is added.

Model: fable-5-1
 2026-11-02 23:44:09 +01:00
clawbot e5afd94a39 Take every down peer out of the table in one walk (closes #225)
check / check (push) Canceled after 0s
Details 
The prefix handler ran one PeerDown per peer, one after another. When
the sessions of several peers went down together, their walks queued up.
A returning full-table peer's messages stayed held back while the walks
ahead of its own ran, and could reach the limit of 20,000.

The table's PeersDown now takes several peers out of every prefix in one
walk. One walk runs at a time. The next one takes every peer whose
session went down since the previous one began. The doc of
maxHeldBackMessages says how long a peer's messages are held back. The
limit is now 150,000 messages, about 150 MiB. The status page shows how
many messages each handler holds back.

Model: opus-5-5
 2026-11-02 23:10:09 +01:00
clawbot 9bd0e91a3b Let the lock go for as long as it was held during Overview's walk (closes #226)
check / check (push) Canceled after 0s
Details 
The home page's cards are worked out once a minute by Overview, which
walks every prefix of the routing table under the table's read lock.
After each batch of 10,000 prefixes, the walk let the lock go and took
it back at once. The prefix handler, waiting for the write lock, then got
in only once per batch. During a walk, its queue could fill, and the
streamer then dropped updates for it.

The walk now lets the lock go for as long as it held the lock for the
batch, as PeerDown does. A test applies another peer's 1,000
announcements while Overview walks a table with more prefixes than five
of the walk's batches.

Model: opus-5-5
 2026-11-02 08:00:00 +01:00
clawbot d66c59ef07 Lengthen the WHOIS fetcher's wait after a skipped lookup (closes #222)
check / check (push) Canceled after 0s
Details 
A lookup whose RIR is paused is skipped. The skip left the fetcher's wait
as it was. Each lookup asks IANA before it finds its RIR paused. So while
most stale ASes belonged to a paused RIR, the fetcher could ask IANA every
second.

Like a failure, a skipped lookup now makes the wait 1.5 times as long, up
to one minute. The skip is still not counted as a failure, so the status
page's failure figures leave it out.

Model: opus-5-5
 2026-11-02 03:59:47 +01:00
clawbot 26d939ad72 Keep taking messages while a peer's session goes down (closes #216)
check / check (push) Canceled after 0s
Details 
The table's PeerDown visits every prefix under the write lock, which
takes over a second on a full table. The prefix handler called it
inline, so its queue filled and the streamer dropped updates.

PeerDown now holds the lock for 10,000 prefixes at a time, then lets
the lock go for as long again. The handler runs PeerDown on a separate
goroutine, one peer at a time. The handler holds back the down peer's
later messages until that PeerDown returns. Then the handler applies
them in order, one at a time, and takes new messages in between. It
holds back at most 20,000 messages. Stop waits for all of this before
its last flush.

Model: opus-5-5
 2026-11-02 03:27:10 +01:00
clawbot df15e2b2cd Pause a registry's WHOIS server after it refuses a query (closes #218)
check / check (push) Canceled after 0s
Details 
The fetcher kept one interval for every registry, so a registry that
refused a query was asked again within seconds. RIPE blocked the test
host's address that way.

The WHOIS client now pauses an RIR's or NIC.br's server for an hour
after the server refuses a query. A refused or reset connection is a
refusal, and so is an %ERROR:201: or %ERROR:202: line. Lookups at the
other servers go on. A lookup whose RIR is paused leaves the AS stale,
and counts as neither a success nor a failure. IANA is never paused,
because a pause of IANA would stop every lookup. NIC.br's hour-long
skip after its over-limit answer is now the same pause.

Model: opus-5-5
 2026-11-02 02:59:57 +01:00
clawbot 6b004dfbc3 Keep one entry per AS in the AS handler's batch (closes #217)
check / check (push) Canceled after 0s
Details 
HandleMessage added one entry to the batch for every AS of every path,
and waited for the write in progress once the batch held 300,000. In a
burst of the feed its queue then filled, and the streamer dropped
messages.

The batch is now a map from AS number to the earliest and the latest
time of its updates. It holds one entry per AS, so it no longer grows
with the feed's rate. HandleMessage never waits for a write.
asnBatchSize now counts ASes. Stop logs the entries of the batch being
written and of the next batch under "batch_entries". An AS in both
counts twice.

Model: opus-5-5
 2026-11-02 02:10:17 +01:00
clawbot 38b43549b9 Make the routewatch tests pass on a loaded host (closes #213)
check / check (push) Canceled after 0s
Details 
Five prefix handler tests gave HandleMessage two seconds to apply a full
batch of 25,000 prefixes, which under the race detector on a loaded host
takes longer. A test now waits up to stepTimeout, 15 seconds, for each step
it expects.

The slowest tests filled production limits, such as the peering handler's
500,000 paths. The peering handler now takes its path limit, and the prefix
handler its limit on one write of the table's changes, as they take their
timer interval. Those tests give small limits, and the tests of the maximum
batch size lower it to one batch. This also fixes
#215.

The test helpers bound every wait, Stop included, so a test that hangs in
one fails with its own message.

Model: opus-5-5
 2026-10-28 01:44:47 +01:00
clawbot 5ea1bb17fe Keep working out the home page cards after startup (closes #211)
check / check (push) Canceled after 0s
Details 
Server.Start ran the loop that works out the home page's cards on the
context it was given. fx ends that context once start-up is done, so the
cards were worked out once and never again. The loop now runs on a
context that only Stop ends, as the other background parts do. Stop
waits for the loop to return, until its own context ends, before it
stops the HTTP server.

A new test starts a server in a synctest bubble and ends its context at
once. On the bubble's fake clock, the cards must be worked out again a
minute later, and not after Stop.

Model: opus-5-5
 2026-10-27 22:55:17 +01:00
clawbot 6d4f3e3419 Say in README why RouteWatch exists (closes #204)
check / check (push) Canceled after 0s
Details 
The Rationale section now gives the owner's reason for the program: it
is an internal API that our other services ask about IP addresses. It
sees which AS routes each address and which announced prefix holds it
from its own routing table. WHOIS details of each AS, kept in its
database, add to that.

What RIS Live does and does not give stays, shortened. Planned geojs
lookups are left out, because the README describes only what is built.

Model: opus-5-5
 2026-10-27 21:34:08 +01:00
clawbot 47aed8761e Give every JSON answer @meta, errors included (closes #201)
check / check (push) Canceled after 0s
Details 
A panic in a JSON route's handler answered 500 with an empty body,
because the router's recoverer sits outside the middleware that adds
`@meta`. `JSONValidationMiddleware` now wraps the handler in the same
recoverer, and answers the panic with the JSON error body.

`/status.json` and the health check answered chi's empty 405 to any
method they do not take. They now answer with the same JSON 405 as the
routes under `/api/v1` and `/ip`.

The home page's IP lookup card showed only the answer's `data`. It now
shows the whole answer, `@meta` included.

A table test checks `@meta` on every JSON route, in its successes and
its errors.

Model: opus-5-5
 2026-10-27 21:20:07 +01:00
clawbot e8d04f1304 Give every API value with a unit as a number (closes #199)
check / check (push) Canceled after 0s
Details 
A value with a unit is now a number, and its field name ends in the
unit, as the vendored API_POLICIES.md requires. @meta.execution_time
becomes execution_time_ms. In the stats answers, uptime,
connection_duration, memory_usage and whois_stats.current_interval
become uptime_seconds, connection_duration_seconds, memory_usage_bytes
and whois_stats.current_interval_seconds. connection_duration_seconds
is null while the feed is not connected. The status page formats the
numbers itself. REPO_POLICIES.md is re-vendored from the same
sneak/prompts commit.

Model: opus-5-5
 2026-10-27 20:19:01 +01:00
clawbot a671b8a0b0 Give every IP lookup result the same fields (closes #200)
check / check (push) Canceled after 0s
Details 
Every result of /ip/, /ip/{addr} and /api/v1/ip/{ip} now has every
field. A field without a value is null instead of left out, so an
address with no live route has all its route and AS fields set to null.
ptr is an empty list when there are no PTR names.

Two new fields, num_origins and origin_asns, give how many origin ASes
peers carry the netblock with, and which. The routing table's prefix
summary now lists them. asn still names the origin that most peers
carry.

first_seen is null, no longer the zero time, when the database has not
stored the netblock yet.

Model: opus-5-5
 2026-10-27 19:54:02 +01:00
clawbot fb5e98feab Trust reverse proxies at private addresses by default (closes #198)
check / check (push) Canceled after 0s
Details 
With TRUSTED_PROXIES unset, the server now trusts reverse proxies in the
private ranges of RFC 1918. A proxy such as traefik on a Docker network is
then believed. /ip/, the home page's curl card and the request log give the
client's address from X-Forwarded-For instead of the proxy's address.

A list in TRUSTED_PROXIES replaces the default. TRUSTED_PROXIES set but
empty trusts no proxy, so the config package reads it with os.LookupEnv.
A direct client at a public address still cannot choose its address with
a forged header.

Model: opus-5-5
 2026-10-27 19:18:34 +01:00
clawbot 281d162e27 Show figures of the routing table on the home page (closes #154)
check / check (push) Canceled after 0s
Details 
The home page gets cards for the newest and oldest kept route, the newest
and oldest updated AS, the AS with the most prefixes, the ASes with a
single prefix and fifteen well-known networks. Two more cards count the
bogon announcements and the prefixes with several origin ASes. They link
to the new pages /bogons and /multiple-origins, which list up to 1,000
entries each.

The new package internal/bogon tells reserved prefixes and AS numbers,
from the IANA special-purpose and address space registries. Table.Overview
walks the table and lets the read lock go every 10,000 prefixes. The
server works the cards out once a minute and serves that copy. A new index
on asns(last_seen) finds the newest and oldest updated AS.

Model: opus-5-5
 2026-10-27 18:27:01 +01:00
90 changed files with 14510 additions and 2394 deletions
Expand all files Collapse all files

No files matched your search

.dockerignore
+3 -2
View File
@@ -93,11 +93,12 @@
**/*.dylib **/*.dylib
# Local databases. The image carries a source archive of the whole build # Local databases. The image carries a source archive of the whole build
# context, so these would otherwise ship inside it. The daemon's database # context, so these would otherwise ship inside it. The daemon's databases
# is db.sqlite, with its -wal and -shm files while it runs. # are db.sqlite and cache.db, with their -wal and -shm files while it runs.
**/*.db **/*.db
**/*.db-journal **/*.db-journal
**/*.db-wal **/*.db-wal
**/*.db-shm
**/*.sqlite **/*.sqlite
**/*.sqlite-wal **/*.sqlite-wal
**/*.sqlite-shm **/*.sqlite-shm
.gitignore
+3 -1
View File
@@ -68,10 +68,12 @@ go.work
go.work.sum go.work.sum
# Local databases, temporary files and debug output. The daemon's # Local databases, temporary files and debug output. The daemon's
# database is db.sqlite, with its -wal and -shm files while it runs. # databases are db.sqlite and cache.db, with their -wal and -shm files
# while it runs.
*.db *.db
*.db-journal *.db-journal
*.db-wal *.db-wal
*.db-shm
*.sqlite *.sqlite
*.sqlite-wal *.sqlite-wal
*.sqlite-shm *.sqlite-shm
API_POLICIES.md
+20
View File
@@ -0,0 +1,20 @@
---
title: API Policies
last_modified: 2026-10-27
---
A value in an API response is never a string with a label or unit in it. A value
of a native type is sent as that type, and its unit goes in the field name, for
example `_ms`.
Wrong:
```json
{ "execution_time": "0 ms" }
```
Right:
```json
{ "execution_time_ms": 0 }
```
README.md
+956 -488
View File
File diff suppressed because it is too large. Load diff
REPO_POLICIES.md
+92 -22
View File
@@ -1,6 +1,6 @@
--- ---
title: Repository Policies title: Repository Policies
last_modified: 2026-10-18 last_modified: 2026-10-27
--- ---
This document covers repository structure, tooling, and workflow standards. Code This document covers repository structure, tooling, and workflow standards. Code
@@ -12,6 +12,7 @@ style conventions are in separate documents:
- [JavaScript](https://git.eeqj.de/sneak/prompts/raw/branch/main/prompts/CODE_STYLEGUIDE_JS.md) - [JavaScript](https://git.eeqj.de/sneak/prompts/raw/branch/main/prompts/CODE_STYLEGUIDE_JS.md)
- [Python](https://git.eeqj.de/sneak/prompts/raw/branch/main/prompts/CODE_STYLEGUIDE_PYTHON.md) - [Python](https://git.eeqj.de/sneak/prompts/raw/branch/main/prompts/CODE_STYLEGUIDE_PYTHON.md)
- [Go HTTP Server Conventions](https://git.eeqj.de/sneak/prompts/raw/branch/main/prompts/GO_HTTP_SERVER_CONVENTIONS.md) - [Go HTTP Server Conventions](https://git.eeqj.de/sneak/prompts/raw/branch/main/prompts/GO_HTTP_SERVER_CONVENTIONS.md)
- [API Policies](https://git.eeqj.de/sneak/prompts/raw/branch/main/prompts/API_POLICIES.md)
--- ---
@@ -174,27 +175,32 @@ style conventions are in separate documents:
`script/cibuild`. `script/lint`, `script/test`, `script/cibuild` and `script/cibuild`. `script/lint`, `script/test`, `script/cibuild` and
`script/docker` are the four, and there is no fifth — `script/check` runs the `script/docker` are the four, and there is no fifth — `script/check` runs the
two gate phases and `script/fmt-check`, and builds no image of its own. In two gate phases and `script/fmt-check`, and builds no image of its own. In
every stage of the `Dockerfile`, `ARG CACHEBUST` comes right after the steps every stage of the `Dockerfile`, every step that lints, tests or compiles
that install system packages and download Go's modules, or right after `FROM` comes after `ARG CACHEBUST`. `ARG CACHEBUST` comes right after these steps:
in a stage with neither, and every step that lints, tests or compiles comes - the steps that install system packages
after it. A step that installs anything else as well, such as a - the steps that download Go's modules
`script/bootstrap` that also installs node packages, comes after it too. A new - the step that runs `script/bootstrap` to install a Python `test` phase's
value reruns every `RUN` step after that line; `COPY` steps are compared by packages from `Pipfile.lock`
content and need nothing. Docker keeps the layers above the line until the
base image, their own lines or the files they copy change. A stage without the A stage with none of these steps declares `ARG CACHEBUST` right after
`ARG` line is served from cache on an unchanged tree, so a repository `FROM`. A step that installs anything else as well, such as a
re-vendors the scripts and adds the `ARG` lines in one commit. The scripts do `script/bootstrap` that also installs node packages, comes after it too. A
not pass `--no-cache`: it reruns every step too, but it also builds the layers new value reruns every `RUN` step after that line; `COPY` steps are compared
above the line again and empties every cache mount, so Go's build cache and by content and need nothing. Docker keeps the layers above the line until
golangci-lint's, which the canonical Go `Dockerfile` below mounts so that they the base image, their own lines or the files they copy change. A stage
survive between check builds, would start empty every time. A bare without the `ARG` line is served from cache on an unchanged tree, so a
`docker build .` is not evidence that anything ran: a sub-second build repository re-vendors the scripts and adds the `ARG` lines in one commit.
reporting success is a cache hit, not a result. Never invalidate by pruning — The scripts do not pass `--no-cache`: it reruns every step too, but it also
`docker builder prune` and friends destroy a build cache shared with every builds the layers above the line again and empties every cache mount, so
other build on the host. When a check is added or changed, prove it works by Go's build cache and golangci-lint's, which the canonical Go `Dockerfile`
planting a defect it must catch and watching the run fail on it, then revert below mounts so that they survive between check builds, would start empty
the defect. A green run alone shows neither that the check ran nor that it every time. A bare `docker build .` is not evidence that anything ran: a
covers what it should. sub-second build reporting success is a cache hit, not a result. Never
invalidate by pruning — `docker builder prune` and friends destroy a build
cache shared with every other build on the host. When a check is added or
changed, prove it works by planting a defect it must catch and watching the
run fail on it, then revert the defect. A green run alone shows neither that
the check ran nor that it covers what it should.
- **The gate phases are separate stages, and the build stage depends on both.** - **The gate phases are separate stages, and the build stage depends on both.**
The lint phase is based on the `golangci/golangci-lint` image (pinned by The lint phase is based on the `golangci/golangci-lint` image (pinned by
@@ -309,6 +315,9 @@ style conventions are in separate documents:
a package's findings only when the package's files and those of every a package's findings only when the package's files and those of every
package it imports, `go.mod`, the linters and their settings in package it imports, `go.mod`, the linters and their settings in
`.golangci.yml`, and the golangci-lint version are all unchanged. `.golangci.yml`, and the golangci-lint version are all unchanged.
- In a Python `test` phase, the layer of the step that runs
`script/bootstrap` to install the packages from `Pipfile.lock`, as
described for that phase below.
- If the project uses `//go:embed` directives that reference build artifacts - If the project uses `//go:embed` directives that reference build artifacts
(e.g. a web frontend compiled in a separate stage), the lint phase must (e.g. a web frontend compiled in a separate stage), the lint phase must
create placeholder files so the embed directives resolve. Example: create placeholder files so the embed directives resolve. Example:
@@ -363,6 +372,67 @@ style conventions are in separate documents:
`--build-arg VERSION=...`, as `script/docker` and `script/cibuild` already `--build-arg VERSION=...`, as `script/docker` and `script/cibuild` already
do. do.
- **A Python `test` phase that installs its packages from `Pipfile.lock` does it
above `ARG CACHEBUST`, so check builds keep them.** The steps are
`COPY script/ script/`, `COPY Pipfile Pipfile.lock ./` and
`RUN script/bootstrap`, with `ARG CACHEBUST` right after them. Docker keeps
what that `RUN` installed until the base image, `script/`, `Pipfile`,
`Pipfile.lock` or a line up to and including the `RUN` changes. The tests run
after `ARG CACHEBUST`, on every check build. In every other stage, a step that
installs Python packages comes after `ARG CACHEBUST`.
- When `script/bootstrap` runs in that step, it installs nothing beyond
system packages, pipenv and its dependencies, and the packages from
`Pipfile.lock`. It installs no Python there: the tests use the base
image's Python, which the image's hash pins. If it installs anything else
there, the step goes after `ARG CACHEBUST`.
- Every external reference must be pinned by hash, so `script/bootstrap`
installs pipenv and its dependencies by hash. It does so with
`pip install --require-hashes -r` and a requirements file in `script/`
that lists each of them with `==` and its `--hash`. pip refuses to install
a dependency the file does not list.
- It then runs `pipenv install --deploy`, with `--dev` when the tests need
the development packages. `--deploy` installs only what `Pipfile.lock`
names, checks every package against the lockfile's hashes, and fails when
the lockfile is out of date with `Pipfile`.
- A kept layer holds nothing a new install would refuse: pip checked pipenv
and its dependencies, and pipenv checked the lockfile's packages, against
their hashes. pipenv creates its virtual environment with the `virtualenv`
package. The packages that `virtualenv` adds come from wheels inside that
package, so the hash pip checked for it covers them. Two things in the
layer are not fixed by a hash. A package with no ready-built wheel for the
image is built from source. pip downloads the build tools without a hash
check, so a kept layer's build of such a package may differ from a new
one. And system packages keep the versions the package manager gave when
the layer was built; a new install may get newer ones.
- As with Go's modules, the packages are kept in a layer, not a cache mount.
A cache mount is shared by every build on the host, and nothing checks its
files again.
In this example, `script/bootstrap` finds `make` and `git` already
installed, installs pipenv and its dependencies by hash, and runs
`pipenv install --dev --deploy`:
```dockerfile
# Test phase. The 90-second timeout covers both pytest runs.
# python:3.x-slim, YYYY-MM-DD
FROM python@sha256:... AS test
# make and git are base tools that script/bootstrap installs when they
# are missing. Installed here, they stay in their own layer when
# script/ changes.
RUN apt-get update \
&& apt-get install -y --no-install-recommends make git \
&& rm -rf /var/lib/apt/lists/*
WORKDIR /app
COPY script/ script/
COPY Pipfile Pipfile.lock ./
RUN script/bootstrap
ARG CACHEBUST
COPY . .
RUN timeout 90 sh -c 'pipenv run pytest || { \
echo "--- Rerunning with -v for details ---"; \
pipenv run pytest -v; exit 1; }'
```
- Every repo should have a Gitea Actions workflow (`.gitea/workflows/`) that - Every repo should have a Gitea Actions workflow (`.gitea/workflows/`) that
runs `script/cibuild` on push, and checks out the repo as its only other step, runs `script/cibuild` on push, and checks out the repo as its only other step,
with `persist-credentials: false`: `script/cibuild` needs no token, and with `persist-credentials: false`: `script/cibuild` needs no token, and
TODO.md
+401 -218
View File
@@ -10,96 +10,269 @@
# Status # Status
pre-1.0. No git tags. `main` last took `next` on 2026-10-06, through RouteWatch is pre-1.0, with no git tags. `main` last took `next` on 2026-10-27,
https://git.eeqj.de/sneak/routewatch/pulls/6. The linter and the tests are through https://git.eeqj.de/sneak/routewatch/pulls/166.
phases of the Docker build, and the Gitea workflow runs `script/cibuild` (the https://git.eeqj.de/sneak/routewatch/pulls/202 carries the commits since then
format check of the Go code and the markdown, both phases, then the image) on into `main`. It is labelled `merge-ready` and waits for sneak.
every push. The image sets memory ceilings for a 5 GiB container (README
"Memory") and the README says how to run it under upaas (README "Running under The linter and the tests are phases of the Docker build. The Gitea workflow runs
upaas"). A 25-hour run of `a9b6860` on the live feed peaked at about 0.6 GiB `script/cibuild` on every push. That script runs the two phases and checks the
(https://git.eeqj.de/sneak/routewatch/issues/3). A run of `825afa2` on the live formatting of the Go code and the markdown. Then it builds the image.
feed found the prefix handler dropping about a quarter of its updates because
its route writes were slower than the feed The image sets memory ceilings for a 5 GiB container (README "Memory"). README
(https://git.eeqj.de/sneak/routewatch/issues/96); the cheaper writes since then "Running under upaas" says how to run it.
are measured by a benchmark, not yet on the live feed.
A five-day run of `1c65656` on the live feed, from 2026-10-27 to 2026-11-01,
found three problems:
- The prefix handler dropped updates while a peer's session went down
(https://git.eeqj.de/sneak/routewatch/issues/216).
- The AS handler dropped updates when the feed burst
(https://git.eeqj.de/sneak/routewatch/issues/217).
- The WHOIS fetcher kept asking a registry that had refused it
(https://git.eeqj.de/sneak/routewatch/issues/218).
All three are fixed on `next`. So is
https://git.eeqj.de/sneak/routewatch/issues/222, which the third fix brought up.
A run of `26d939a` on the live feed showed the prefix handler still dropping
updates while the home page's cards were worked out.
https://git.eeqj.de/sneak/routewatch/issues/226 fixed that on `next`.
https://git.eeqj.de/sneak/routewatch/issues/225, also on `next`, takes the peers
whose sessions go down together out of the table in one walk. A 24-hour run of
`9bd0e91` on the live feed is checking whether any handler still drops updates.
The order of the project's remaining work is kept on
https://git.eeqj.de/sneak/routewatch/issues/86.
# Next Step # Next Step
Run `next` on the live feed, as README "Running under upaas" describes, until Post the outcome of the 24-hour run of `9bd0e91` on
the routing table stops growing. Post its size and memory figures on https://git.eeqj.de/sneak/routewatch/issues/226: whether any handler still drops
https://git.eeqj.de/sneak/routewatch/issues/122. The same run makes the final updates, and the process's peak memory against 5 GiB. File an issue for each
check https://git.eeqj.de/sneak/routewatch/issues/96 names: whether the prefix problem the run finds.
handler still drops updates after the first hour. If it does, a new issue
follows with the numbers. Then an audit of the code at the commit that run
tested.
# Completed Steps # Completed Steps
- 2026-10-27: the per-peer route tables are gone, with the code that wrote, - 2026-11-10: each result of the IP lookup has `geo`, where the address is. It
comes from geojs, with DB-IP's City Lite database as the fallback. The geojs
answers stay in memory and in `cache.db` for 7 days (closes
https://git.eeqj.de/sneak/routewatch/issues/239).
- 2026-11-10: the IP lookup checks the `icloud_private_relay` list of Apple's
iCloud Private Relay networks, downloaded once a day. Each result has
`flags.is_relay` (closes https://git.eeqj.de/sneak/routewatch/issues/237).
- 2026-11-10: the IP lookup checks the `protonvpn` list of ProtonVPN's /24
networks and the `protonvpn_entry` list of its servers' IPv4 and IPv6
addresses, from a public mirror of Proton's server list (closes
https://git.eeqj.de/sneak/routewatch/issues/236).
- 2026-11-10: the IP lookup finds PTR names over DNS-over-HTTPS and caches them
for the record's TTL, in memory and in `cache.db` (closes
https://git.eeqj.de/sneak/routewatch/issues/238).
- 2026-11-10: the tests no longer fail when a busy host stalls for several
seconds. Most such waits are now 15 seconds. The test of the stream's idle
timeout runs on a fake clock (closes #240)
- 2026-11-10: the IP lookup checks the public VPN server lists of Mullvad,
NordVPN, Private Internet Access and IVPN, and X4BNet's community list. Each
result has `flags.is_vpn` and `vpn_providers` (closes
https://git.eeqj.de/sneak/routewatch/issues/235).
- 2026-11-10: `tor_exits` comes from Onionoo, so it holds IPv6 exits and
`is_tor` is true for them (closes
https://git.eeqj.de/sneak/routewatch/issues/234).
- 2026-11-10: each result of the IP lookup has a `flags` object with `is_tor`
and `is_bogon`. The public IP lists are named `ip_lists` in the answer,
`internal/iplist` in the code and `iplists` in the state directory. A list
file may be up to 200 MiB (closes
https://git.eeqj.de/sneak/routewatch/issues/233).
- 2026-11-05: the prefix page lists the prefix's origin changes, newest first.
The routing table records each change, and the prefix handler writes them to a
new `origin_changes` table. The database maintainer prunes each prefix to its
newest 500 rows or its rows from the last 72 hours, whichever keeps more. The
page shows at most the newest 5,000. Each row shows:
- the time
- announced or withdrawn
- the origin AS
- the peer count
A row's peer count is how many peers carry the prefix just after the change,
with any origin AS (closes #161).
- 2026-11-03: the streamer drops an update for a handler only when that
handler's queue is full. It used to drop a random share of the updates once
the queue was half full. The prefix handler's queue now holds 100,000
messages, about 100 MiB. It used to hold 20,000. While the routing table's
`Overview` walks every prefix, the prefix handler applies updates more slowly.
In a run on the live feed, the feed paused during such a walk and then sent
its backlog. The streamer then dropped about 10,000 of the prefix handler's
updates (closes #229)
- 2026-11-02: `README.md` is rewritten from scratch, sentence by sentence,
against the rules of https://git.eeqj.de/sneak/routewatch/issues/157. Every
statement was checked against the code on `next` (closes #157)
- 2026-11-02: `TODO.md` is rewritten from scratch, sentence by sentence, against
the rules of https://git.eeqj.de/sneak/routewatch/issues/157. Every Completed
Steps entry keeps its date, its facts and its issue. Status and Next Step
describe the repo as the tracker shows it (part of #157)
- 2026-11-02: when the sessions of several peers go down, the prefix handler
takes the peers out of the routing table together. The table's `PeersDown`
takes several peers out of every prefix in one walk. One walk runs at a time.
The next one takes every peer whose session went down since the previous one
began. Each peer used to have a walk of its own. A peer's messages stayed held
back while the walks queued ahead of its own ran. The handler holds back at
most 150,000 messages, about 150 MiB. It used to hold back at most 20,000. The
status page shows how many messages the handler holds back (closes #225)
- 2026-11-02: working out the home page's cards no longer stops the prefix
handler. The walk over the routing table holds the table's lock for 10,000
prefixes at a time, then lets the lock go for as long again, as `PeerDown`
does. It used to take the lock back at once. The prefix handler then applied
about one update per 10,000 prefixes walked. During a walk, its queue could
fill, and the streamer then dropped updates for it (closes #226)
- 2026-11-02: A skipped WHOIS lookup now makes the fetcher wait longer before
the next one, as a failed lookup does. A lookup is skipped when its RIR is
paused. An RIR is one of the five regional Internet registries. The longest
wait is one minute. The status page does not count a skip as a failure. A skip
used to leave the wait as it was. Each lookup asks IANA which RIR holds the AS
before it finds that RIR paused. So while most stale ASes belonged to a paused
RIR, the fetcher could ask IANA every second (closes #222)
- 2026-11-02: A peer's session going down no longer stops the prefix handler.
The handler runs the routing table's `PeerDown` on a goroutine of its own, one
peer at a time. Meanwhile it goes on taking messages. `PeerDown` holds the
table's lock for 10,000 prefixes at a time, then lets the lock go for as long
again. The handler holds back the down peer's later messages until that peer's
`PeerDown` returns. Then the handler applies them in order, one at a time, and
takes new messages in between. It holds back at most 20,000 messages. At that
number, `HandleMessage` waits until one of them is applied. When `Stop` runs
past its deadline, it logs how many held-back messages were not applied
(closes #216)
- 2026-11-02: RouteWatch pauses an RIR's or NIC.br's WHOIS server for an hour
after the server refuses a query. NIC.br is Brazil's registry. A refused or
reset connection is a refusal. So is an answer with an `%ERROR:201:` or
`%ERROR:202:` line. Lookups at the other servers go on. An AS whose RIR is
paused is looked up after the pause. While NIC.br is paused, a Brazilian AS
gets the details from LACNIC's answer. IANA is never paused, because a pause
of IANA would stop every lookup. A refusal by IANA is an ordinary failure.
NIC.br is also paused for an hour after it says RouteWatch has passed its
query limit. Before, the fetcher asked a server again within seconds of a
refusal (closes #218)
- 2026-11-02: The AS handler never waits for a database write. Its batch holds
one entry per AS, with the earliest and the latest time of its updates. So the
batch no longer grows with the feed's rate. It used to hold one entry for each
AS of each path. At 300,000 entries it waited for the write in progress. In a
burst of the feed its queue then filled, and the streamer dropped messages for
it (closes #217)
- 2026-10-27: The tests of `internal/routewatch` no longer fail on a loaded
host. Five of them gave `HandleMessage` two seconds to apply a full prefix
batch. Under the race detector that can take longer. A test now waits up to 15
seconds for each step it expects. The tests of the handlers' limits now give
the handlers small limits. So the package no longer runs past its 90-second
limit (closes #213, #215)
- 2026-10-27: The server works out the home page's cards every minute until it
stops. It used to work them out only once, at startup. The end of the context
given to `Start` stopped the refreshes (closes #211)
- 2026-10-27: README "Rationale" says why RouteWatch exists. RouteWatch answers
our other services' questions about IP addresses, from its own routing table
and the WHOIS details it keeps. The section still says what RIS Live does not
give (closes #204)
- 2026-10-27: Every JSON answer carries `@meta`. A panic on a JSON route answers
500 with the JSON error body. `/status.json` and the health check answer 405
with the JSON error body to any method they do not take. The 500 and the 405
used to have an empty body. The home page's IP lookup shows the whole JSON
answer, `@meta` included. It used to show only the answer's `data`, or only
the message of an error answer. A test checks `@meta` on every JSON route, in
its successes and its errors (closes #201)
- 2026-10-27: Every value with a unit in a JSON answer is a number. The unit is
at the end of the field name. `@meta.execution_time` is now
`execution_time_ms`. In the stats, `uptime` is now `uptime_seconds`,
`connection_duration` is now `connection_duration_seconds`, and `memory_usage`
is now `memory_usage_bytes`. `whois_stats.current_interval` is now
`whois_stats.current_interval_seconds`. They used to be strings such as "12
ms", "1h18m34s" or "1.1 GB". `connection_duration_seconds` is null while the
feed is not connected. `API_POLICIES.md` is vendored from `sneak/prompts`, and
`REPO_POLICIES.md` is re-vendored (closes #199)
- 2026-10-27: Every result of the IP lookup has the same fields. A field without
a value is null. It used to be left out. An address with no route in the
routing table has every route and AS field set to null. `ptr` is an empty list
when there are no PTR names. The new field `num_origins` gives the number of
origin ASes of the netblock, and `origin_asns` gives which they are (closes
#200)
- 2026-10-27: With `TRUSTED_PROXIES` unset, the server trusts reverse proxies at
the private addresses of RFC 1918. `/ip/`, the home page's `curl` card and the
request log then give the client's address from `X-Forwarded-For`. They used
to give the proxy's address. A list in `TRUSTED_PROXIES` replaces the default.
`TRUSTED_PROXIES` set but empty trusts no proxy (closes #198)
- 2026-10-27: The home page has cards with figures of the routing table. One
card shows the newest and the oldest kept route. One shows the newest and the
oldest updated AS. One shows the AS with the most prefixes. One shows the ASes
with a single prefix. One shows fifteen well-known networks. Two cards count
the bogon announcements and the prefixes with more than one origin AS. They
link to the new pages `/bogons` and `/multiple-origins`, which list them. A
new package, `internal/bogon`, tells which prefixes and AS numbers are
reserved. The server works the figures out once a minute (closes #154)
- 2026-10-27: The per-peer route tables are gone, with the code that wrote,
counted and read them. The prefix handler applies each update to the routing counted and read them. The prefix handler applies each update to the routing
table in memory and writes the table's changes every second. It also stores table in memory. It writes the table's changes every second. It also stores
each new prefix with its first-seen time. The image's memory limits are set each new prefix with its first-seen time. The image's memory limits fit a full
for a full routing table of about 1 GB: `GOMEMLIMIT` is 2.5 GiB, the writing routing table of about 1 GB. `GOMEMLIMIT` is 2.5 GiB. The writing connection's
connection's page cache 512 MiB, and SQLite's heap limits 768 MiB and 1 GiB page cache is 512 MiB. SQLite's soft and hard heap limits are 768 MiB and 1
(closes #122) GiB (closes #122)
- 2026-10-27: the pages, the API and the stats read every route from the routing - 2026-10-27: The pages, the API and the stats read every route from the routing
table in memory. For a prefix with several origin ASes, the IP lookup gives table in memory. For a prefix with several origin ASes, the IP lookup gives
the one most peers carry. Its `last_seen` is the newest kept route's time. The the one most peers carry. Its `last_seen` is the newest kept route's time. The
prefix page and API list every peer that carries the prefix, with an AS path, prefix page and API list every peer that carries the prefix. Only the kept
next hop and time only for the kept routes. The stats count the origins whose routes show an AS path, a next hop and a time. The stats count the origins
kept routes were all withdrawn, in `origins_without_kept_route` (part of #122) whose kept routes were all withdrawn, in `origins_without_kept_route` (part of
- 2026-10-27: the prefix, AS and peer handlers make a timed write on every tick
of their timers, every 1, 2 and 2 seconds. They used to skip every other tick.
A full batch's write restarts the timer, so the next timed write comes one
interval after that write began (closes #192)
- 2026-10-27: once the stop deadline has passed, the AS, peer and peering
handlers start no write either. A full batch or a tick of the timer that
waited while a write ran past the deadline could still start one. The flush
goroutines of the prefix, AS and peer handlers now run the same code (closes
#189)
- 2026-10-27: once the stop deadline has passed, the prefix handler starts no
flush. A batch that filled while a write ran past the deadline could still be
written after it (closes #188)
- 2026-10-27: the prefix handler applies each update to the routing table in
memory, and writes the table's changes to the database every second. A write
takes at most 20,000 changed pairs, and the rest follow in the next writes. A
failed write is written again later. Startup reads the table before the
streamer connects. The pages still read the per-peer route tables (part of
#122) #122)
- 2026-10-27: the database keeps a copy of the whole routing table in a new - 2026-10-27: The prefix, AS and peer handlers make a timed write on every tick
of their timers. The prefix handler's timer ticks every second. The other two
tick every two seconds. They used to skip every other tick. A full batch's
write restarts the timer. So the next timed write comes one interval after
that write began (closes #192)
- 2026-10-27: Once the stop deadline has passed, the AS, peer and peering
handlers start no write either. Before, a full batch or a timer tick could
wait while a write ran past the deadline. Either could then start one more
write. The flush goroutines of the prefix, AS and peer handlers now run the
same code (closes #189)
- 2026-10-27: Once the stop deadline has passed, the prefix handler starts no
flush. Before, a batch that filled during a late write could still be written
after the deadline (closes #188)
- 2026-10-27: The prefix handler applies each update to the routing table in
memory. It writes the table's changes to the database every second. A write
takes at most 20,000 changed pairs of prefix and origin AS. The rest follow in
the next writes. A failed write is written again later. Startup reads the
table before the streamer connects. The pages still read the per-peer route
tables (part of #122)
- 2026-10-27: The database keeps a copy of the whole routing table in a new
`routes` table, one row per prefix and origin AS. The peers' numbers are in a `routes` table, one row per prefix and origin AS. The peers' numbers are in a
new `route_peers` table. One function writes the pairs that changed in memory, new `route_peers` table. One function writes the pairs that changed in memory.
and another reads the whole table back into memory at startup. Nothing uses Another reads the whole table back into memory at startup. Nothing uses them
them yet (part of #122) yet (part of #122)
- 2026-10-27: a new package, `internal/routetable`, holds the whole routing - 2026-10-27: A new package, `internal/routetable`, holds the whole routing
table in memory. For each prefix and origin AS it keeps the peers that carry table in memory. For each prefix and origin AS it keeps the peers that carry
it, one bit per peer, and the two newest of their routes. Nothing uses it yet it, one bit per peer. It also keeps the two newest of their routes. Nothing
(part of #122) uses it yet (part of #122)
- 2026-10-27: each result of the IP lookup lists the public blocklists the - 2026-10-27: Each result of the IP lookup lists the public blocklists the
address is on, in `blocklists`. The lists are DShield, Feodo Tracker, two address is on, in `blocklists`. The lists are DShield, Feodo Tracker, two
FireHOL lists, Spamhaus DROP and the Tor exit list. RouteWatch downloads each FireHOL lists, two Spamhaus DROP lists and the Tor exit list. RouteWatch
list on its own schedule and answers from copies in memory. The copies are downloads each list on its own schedule and answers from copies in memory. The
also kept in the state directory's `blocklists` directory. IP lookup answers copies are also kept in the state directory's `blocklists` directory. IP
carry `Cache-Control`. An address with no live route now has a result too, lookup answers carry `Cache-Control`. An address with no route now has a
without route fields, so the IP lookup no longer answers 404 (closes #158) result too, without route fields. So the IP lookup no longer answers 404
- 2026-10-27: the home page has an IP information API card. It shows the `curl` (closes #158)
command that looks up the visitor's own address at `/ip/{addr}`, and that - 2026-10-27: The home page has an IP information API card. It shows the `curl`
command's live answer (closes #156) command that looks up the visitor's own address at `/ip/{addr}`. It also shows
- 2026-10-27: on the AS page, a click on the heading of the IPv4 or the IPv6 that command's live answer (closes #156)
- 2026-10-27: On the AS page, a click on the heading of the IPv4 or the IPv6
prefix list folds or unfolds the list. Both lists start open (closes #155) prefix list folds or unfolds the list. Both lists start open (closes #155)
- 2026-10-27: the AS page lists its IPv4 and its IPv6 prefixes by mask length, - 2026-10-27: The AS page lists its IPv4 and its IPv6 prefixes by mask length,
shortest first, and prefixes of one mask length by address. They used to be shortest first. Prefixes of one mask length are listed by address. They used
listed by address (closes #153) to be sorted by address first, then by mask length (closes #153)
- 2026-10-27: on `/` and `/status`, a spinner beside the status turns one frame - 2026-10-27: The connection status on `/` and `/status` gets a spinner. It
each time the stats show more messages than the time before. A page that has turns one frame each time the stats show more messages than the time before.
not seen more messages for three refreshes shows "stale" and the time since After three refreshes with no new messages, the page shows "stale" in red
then instead, in red (closes #152) instead. Next to it is the time since the last fresh answer (closes #152)
- 2026-10-27: the WHOIS details of a Brazilian AS keep their accented letters. - 2026-10-27: The WHOIS details of a Brazilian AS keep their accented letters.
LACNIC's answer for such an AS comes from NIC.br, Brazil's registry, with each LACNIC's answer for such an AS is NIC.br's answer with each accented letter
accented letter replaced. The details now come from NIC.br's own server, replaced. NIC.br is Brazil's registry. The details now come from NIC.br's own
`whois.registro.br`. When that query fails, the details from LACNIC's answer server, `whois.registro.br`. When that query fails, the details from LACNIC's
are kept and a warning is logged. After NIC.br answers that RouteWatch is over answer are kept and a warning is logged. RouteWatch stops asking NIC.br for an
its query limit, RouteWatch stops asking NIC.br for an hour (closes #174) hour after NIC.br says RouteWatch is over its query limit (closes #174)
- 2026-10-27: `make asupdate` stops with an error when the download of `as.csv` - 2026-10-27: `make asupdate` stops with an error when the download of `as.csv`
breaks off. The generator used to retry the failed read forever. A record that breaks off. The generator used to retry the failed read forever. A record that
does not parse is still logged and skipped (closes #177) does not parse is still logged and skipped (closes #177)
@@ -108,182 +281,192 @@ tested.
one AS. A failed download used to replace the list with an empty file. The one AS. A failed download used to replace the list with an empty file. The
generator reads `as.csv` from `ipverse/as-metadata`, the source's new name generator reads `as.csv` from `ipverse/as-metadata`, the source's new name
(closes #173) (closes #173)
- 2026-10-27: the WHOIS details of an AS at RIPE, APNIC or AFRINIC come only - 2026-10-27: The WHOIS details of an AS at RIPE, APNIC or AFRINIC come only
from its `aut-num` object and the organisation object it names. RIPE and APNIC from its `aut-num` object and the organisation object it names. RIPE and APNIC
start their answer with the `as-block` object of the AS's block. Its dates start their answer with the `as-block` object of the AS's block. Its dates
were stored as the AS's (closes #168) were stored as the AS's (closes #168)
- 2026-10-27: AS names keep their accented letters. The AS list built into - 2026-10-27: AS names keep their accented letters. The AS list built into
RouteWatch is rebuilt from today's `as.csv`, which added a country code RouteWatch is rebuilt from today's `as.csv`, which added a country code
column. That file no longer lists AS 0 or the documentation AS numbers. A column. That file no longer lists AS 0 or the documentation AS numbers. A
WHOIS answer that is not valid UTF-8 is decoded as Latin-1, which RIPE and WHOIS answer that is not valid UTF-8 is decoded as Latin-1 before it is parsed
APNIC send, before it is parsed and stored (closes #165) and stored. RIPE and APNIC send Latin-1 (closes #165)
- 2026-10-27: the Age column on the AS and prefix pages reads in words, such as - 2026-10-27: The Age column on the AS and prefix pages reads in words, such as
"5 minutes ago" or "2 weeks ago", instead of Go durations such as "360h0m0s "5 minutes ago" or "2 weeks ago". It used to print Go durations such as
ago". An age under a minute reads in seconds, and one over a month in months "360h0m0s ago". An age under a minute reads "now" or in seconds. An age over a
or years instead of a date (closes #163) month reads in months or years instead of a date (closes #163)
- 2026-10-26: a write to a stored AS, peering or peer keeps the earlier of the - 2026-10-26: A write to a stored AS, peering or peer keeps the earlier of the
two first-seen times and the later of the two last-seen times. An old update two first-seen times. It keeps the later of the two last-seen times. An old
from a collector catching up on a backlog no longer moves last seen back update from a collector catching up on a backlog no longer moves last seen
(closes #162) back (closes #162)
- 2026-10-26: the status page shows "Route Churn/min", the number of prefix - 2026-10-26: The status page shows "Route Churn/min". That is the number of
announcements and withdrawals, from all peers, in the last full clock minute. prefix announcements and withdrawals from all peers in the last full clock
`/api/v1/stats` reports it as `route_churn_per_min` in `stream`, which minute. `/api/v1/stats` reports it as `route_churn_per_min` in `stream`. It
replaces the moving average `route_churn_per_sec`. The messages and updates replaces the moving average `route_churn_per_sec`. The messages and updates
per second on `/` and `/status` are whole numbers (closes #160) per second on `/` and `/status` are whole numbers (closes #160)
- 2026-10-26: the WHOIS fetcher backs off more slowly. A failure makes its wait - 2026-10-26: The WHOIS fetcher backs off more slowly. A failure makes its wait
1.5 times as long, up to one minute instead of five. Its queries to RIPE, 1.5 times as long, up to one minute instead of five. Its queries to RIPE,
APNIC and AFRINIC leave out person and role objects, which RIPE counts against APNIC and AFRINIC leave out person and role objects. RIPE counts those objects
a daily limit per address. A refused query is logged with the RIR's error line against a daily limit per address. A refused query is logged with the RIR's
(closes #159) error line (closes #159)
- 2026-10-26: the home page's AS name search lists the ASes whose handle or - 2026-10-26: The home page's AS name search works. It lists the ASes whose
description holds the text, as links to their pages, from the new handle or description holds the text, as links to their pages. The new
`/api/v1/search/as`; the search ignores case. When the database has no record `/api/v1/search/as` answers it. The search ignores case. When the database has
of an AS, its page takes the handle and description from the AS list built no record of an AS, its page takes the handle and description from the AS list
into RouteWatch and still lists the AS's prefixes (closes #151) built into RouteWatch. It still lists the AS's prefixes (closes #151)
- 2026-10-19: README "HTTP Endpoints" lists every route with what it answers, - 2026-10-19: README "HTTP Endpoints" lists every route with what it answers.
"Database Schema" matches `schema.sql`, and the rest of the README matches the README "Database Schema" matches `schema.sql`. The rest of the README matches
code; this file brought up to date (closes #72) the code. This file is brought up to date (closes #72)
- 2026-10-19: route writes are cheaper: the live route and prefix tables lose - 2026-10-19: Route writes are cheaper. The live route and prefix tables lose
their random UUID keys and the prefix tables their duplicate index, a route their random UUID keys. The prefix tables lose their duplicate index. A route
update sets only the columns that change, and every write goes through one update sets only the columns that change. Every write goes through one
connection with a page cache of 1 GiB (README "Memory"). A benchmark writes connection with a page cache of 1 GiB (README "Memory"). A benchmark writes
the prefix handler's largest batch faster than the feed sends it (closes #96) the prefix handler's largest batch faster than the feed sends it (closes #96)
- 2026-10-19: the WAL checkpoint, the incremental vacuum and ANALYZE take the - 2026-10-19: The checkpoint of the WAL (SQLite's write-ahead log), the
database lock every batch write holds, so a vacuum no longer fails with incremental vacuum and `ANALYZE` take the database lock that every batch write
"database is locked" and an ANALYZE no longer makes a batch write lose its holds. So a vacuum no longer fails with "database is locked". An `ANALYZE` no
updates; ANALYZE runs as `PRAGMA optimize` with an analysis limit (closes #94) longer makes a batch write lose its updates. `ANALYZE` runs as
- 2026-10-19: shutdown stops the streamer first, and each handler writes `PRAGMA optimize` with an analysis limit (closes #94)
everything left on its queue before it stops, so the updates waiting there are - 2026-10-19: Shutdown stops the streamer first. Each handler then writes
everything left on its queue before it stops. So the updates waiting there are
no longer lost (closes #69) no longer lost (closes #69)
- 2026-10-19: a path that ends in an AS set of several members has origin AS 0, - 2026-10-19: A path that ends in an AS set of several members has origin AS 0,
no known origin, instead of the set's last member, and the set adds no which means no known origin. It used to have the set's last member as its
peerings; the pages show such a route as having no known origin (closes #75) origin. The set adds no peerings. The pages show such a route as having no
known origin (closes #75)
- 2026-10-19: `bgp_peer_count` drops to 0 when the last peer goes down (closes - 2026-10-19: `bgp_peer_count` drops to 0 when the last peer goes down (closes
#92) #92)
- 2026-10-19: `bgp_peer_count` counts every peer the feed has heard from, not - 2026-10-19: `bgp_peer_count` counts every peer the feed has heard from. It
only those whose session opened since startup, and drops a peer whose session used to count only the peers whose session opened since startup. It drops a
goes down (closes #74) peer whose session goes down (closes #74)
- 2026-10-19: the shared files are re-vendored from `sneak/prompts` at - 2026-10-19: The shared files are re-vendored from `sneak/prompts` at
`0653579`: golangci-lint v2.14.0 and its configuration, lint and test as `0653579`. The linter is `golangci-lint` v2.14.0 with its configuration. Lint
`Dockerfile` phases that keep Go's and golangci-lint's caches, markdown and test are `Dockerfile` phases that keep Go's and `golangci-lint`'s caches.
formatted with prettier, agent guidance in `AGENTS.md`; the code is fixed for `make fmt` also formats the markdown with `prettier`. The agent guidance moves
what the new linter configuration finds (closes #52) to `AGENTS.md`. The code is fixed for what the new linter configuration finds
- 2026-10-19: the streamer reads feed lines up to 1 MiB, so a line over 64 KiB (closes #52)
no longer ends the connection (closes #76) - 2026-10-19: The streamer reads feed lines up to 1 MiB. A line over 64 KiB used
- 2026-10-19: a peer's live routes are removed when its BGP session goes down; to end the connection (closes #76)
`STATE` messages are never dropped for backpressure, and one that finds its - 2026-10-19: A peer's live routes are removed when its BGP session goes down.
`STATE` messages are never dropped when a queue is full. One that finds its
queue full waits for room ahead of the handler's other messages (closes #56) queue full waits for room ahead of the handler's other messages (closes #56)
- 2026-10-19: the prefix-length pages pick their sample with a bounded number of - 2026-10-19: The prefix-length pages pick their sample with a bounded number of
index lookups instead of reading every route of that length, and list each index lookups. They used to read every route of that length. They list each
prefix once (closes #66) prefix once (closes #66)
- 2026-10-19: a request past its time limit answers 504 instead of 408, and - 2026-10-19: A request past its time limit answers 504 instead of 408.
`/api/v1/stats` answers 504 instead of 500 when its read runs out of time `/api/v1/stats` answers 504 instead of 500 when its read runs out of time
(closes #70) (closes #70)
- 2026-10-19: the AS, peer and prefix handlers write each batch outside the lock - 2026-10-19: The AS, peer and prefix handlers write each batch outside the lock
their message handling needs, so messages keep coming off their queues during their message handling needs. So messages keep coming off their queues during
a write; meanwhile the next batch grows to at most ten batch sizes (closes a write. Meanwhile the next batch grows to at most ten batch sizes (closes
#65) #65)
- 2026-10-19: a live route is identified by prefix and peer, so an announcement - 2026-10-19: A live route is identified by prefix and peer. So an announcement
with a new origin AS replaces the peer's route and a withdrawal removes it with a new origin AS replaces the peer's route. A withdrawal removes it
whatever its origin AS (closes #55) whatever its origin AS (closes #55)
- 2026-10-14: the streamer reconnects when RIS Live ends the stream or sends - 2026-10-14: The streamer reconnects when RIS Live ends the stream or sends
nothing for 60 seconds, and the health check reports the feed disconnected nothing for 60 seconds. The health check reports the feed disconnected
meanwhile (closes #53) meanwhile (closes #53)
- 2026-10-14: the prefix page takes the names of the origin ASes from the prefix - 2026-10-14: The prefix page takes the names of the origin ASes from the prefix
query instead of reading every route of each origin AS (closes #67) query. It used to read every route of each origin AS (closes #67)
- 2026-10-14: the daemon exits with status 1 when its web server cannot listen - 2026-10-14: The daemon exits with status 1 when its web server cannot listen
on its port, instead of running on without it (closes #73) on its port. It used to run on without a web server (closes #73)
- 2026-10-14: the prefix pages parse the prefix before looking it up: one that - 2026-10-14: The prefix pages parse the prefix before looking it up. One that
does not parse answers 400, and any valid way of writing a prefix finds its does not parse answers 400. Any valid way of writing a prefix finds its routes
routes (closes #71) (closes #71)
- 2026-10-14: the IP lookup ignores routes shorter than /8 for IPv4 and /16 for - 2026-10-14: The IP lookup ignores routes shorter than /8 for IPv4 and /16 for
IPv6, so a default route is no longer named as an address's owner (closes #57) IPv6. So a default route is no longer named as an address's owner (closes #57)
- 2026-10-14: a prefix batch keeps each peer's last update for a prefix, instead - 2026-10-14: A prefix batch keeps each peer's last update for a prefix. It used
of one update per prefix across all peers (closes #54) to keep one update per prefix across all peers (closes #54)
- 2026-10-14: `reconnect_count` in `/api/v1/stats` counts every reconnect - 2026-10-14: `reconnect_count` in `/api/v1/stats` counts every reconnect
(closes #68) (closes #68)
- 2026-10-03: `/api/v1/stats` serves the prefix distribution from memory, seeded - 2026-10-03: `/api/v1/stats` serves the prefix distribution from memory. The
at startup and adjusted on every live-route write, so a request no longer distribution is seeded at startup and adjusted on every live-route write. So a
reads every live route (closes #30) request no longer reads every live route (closes #30)
- 2026-10-03: a new database is created with `auto_vacuum` set to incremental, - 2026-10-03: A new database is created with `auto_vacuum` set to incremental.
through the connection string so it is set before the file is first written, The setting goes in the connection string, so it is set before the file is
and each periodic incremental vacuum now returns up to 1000 free pages; the first written. Each periodic incremental vacuum now returns up to 1000 free
late `PRAGMA auto_vacuum` in `Initialize`, which SQLite ignored, is gone pages. The late `PRAGMA auto_vacuum` in `Initialize`, which SQLite ignored, is
(closes #43) gone (closes #43)
- 2026-10-03: looking up an IP address no longer reads every IPv6 route: both - 2026-10-03: Looking up an IP address no longer reads every IPv6 route. Both
families find the most specific live route with at most 33 or 129 lookups on families find the most specific live route with at most 33 or 129 lookups on
the prefix index, and the IPv4 range columns are gone. Prefixes from the feed the prefix index. The IPv4 range columns are gone. Prefixes from the feed are
are stored in one text form, so an IPv6 withdrawal, which the feed sends stored in one text form. So an IPv6 withdrawal, which the feed sends
uncompressed, now removes its route (closes #48) uncompressed, now removes its route (closes #48)
- 2026-10-02: a plain `docker build .` stamps the commit's tag or short commit - 2026-10-02: A plain `docker build .` stamps the commit's tag or short commit
(`git describe --tags --always`) into the page footer instead of `unknown`: into the page footer. It used to stamp `unknown`. The value comes from
`.dockerignore` sends `.git` without `.git/config`, a `VERSION` build argument `git describe --tags --always`. `.dockerignore` sends `.git` without
takes precedence, and `make build` stamps the same value (closes #46) `.git/config`. A `VERSION` build argument takes precedence. `make build`
- 2026-09-29: the entrypoint creates the data directory if it is missing and stamps the same value (closes #46)
stops the start if a step fails; README "Running under upaas" no longer asks - 2026-09-29: The entrypoint creates the data directory if it is missing. It
stops the start if a step fails. README "Running under upaas" no longer asks
for the host directory to be created first (closes #42) for the host directory to be created first (closes #42)
- 2026-09-29: `.dockerignore` keeps `.git`, local build output, local databases - 2026-09-29: `.dockerignore` keeps `.git`, local build output, local databases
and `.env` out of the Docker build context, and so out of the source archive and `.env` out of the Docker build context. So they stay out of the source
in the image (closes #39) archive in the image (closes #39)
- 2026-09-29: README first line names the MIT license and the author; the - 2026-09-29: The README's first line names the MIT licence and the author. The
License section now says MIT and links `LICENSE`, and an Author section was License section says MIT and links `LICENSE`. An Author section is added. This
added; this file brought up to date (closes #38) file is brought up to date (closes #38)
- 2026-09-29: MIT `LICENSE` (closes #1) - 2026-09-29: `LICENSE` is added, with the MIT licence (closes #1)
- 2026-09-28: stopping the daemon while the feed is flowing no longer panics - 2026-09-28: Stopping the daemon while the feed is flowing no longer panics
with "send on closed channel": the read loop checks for a stop just before with "send on closed channel". The read loop checks for a stop just before
handing a message to the handler queues, and a second `Stop` no longer closes handing a message to the handler queues. A second `Stop` no longer closes the
the queues again (closes #34) queues again (closes #34)
- 2026-09-28: `docker stop` no longer kills the daemon 2 seconds after the stop - 2026-09-28: `docker stop` no longer kills the daemon 2 seconds after the stop
signal: the entrypoint switches to the `routewatch` user with `setpriv` signal. The entrypoint switches to the `routewatch` user with `setpriv`
instead of `runuser`, so the daemon receives the signal itself and gets the instead of `runuser`. So the daemon receives the signal itself. It gets the
whole wait `docker stop` allows, up to its own 60-second limit (closes #33) whole wait `docker stop` allows, up to its own 60-second limit (closes #33)
- 2026-09-28: ready to run under upaas: a set but invalid `PORT`, - 2026-09-28: RouteWatch is ready to run under upaas. A set but invalid `PORT`,
`XDG_DATA_HOME` or `MALLOC_ARENA_MAX` stops the start, the health check `XDG_DATA_HOME` or `MALLOC_ARENA_MAX` stops the start. The health check
follows `PORT`, README "Running under upaas" section (closes #31) follows `PORT`. README gains a "Running under upaas" section (closes #31)
- 2026-09-22: realtime in-memory database statistics: counts seeded at startup - 2026-09-22: The database statistics are kept in memory. The counts are seeded
and adjusted on every write, oldest/newest route timestamps via index-end at startup and adjusted on every write. The oldest and newest route times come
lookups; `/api/v1/stats` no longer scans the tables (closes #27) from a lookup at each end of an index. `/api/v1/stats` no longer scans the
- 2026-09-21: batch writes take the write lock when their transaction begins tables (closes #27)
(`_txlock=immediate`), so they wait out a WAL checkpoint instead of failing - 2026-09-21: Batch writes take the write lock when their transaction begins
(`_txlock=immediate`). So they wait out a WAL checkpoint instead of failing
with "database is locked" (closes #25) with "database is locked" (closes #25)
- 2026-09-21: `MALLOC_ARENA_MAX=2` in the image caps glibc malloc arenas, so - 2026-09-21: `MALLOC_ARENA_MAX=2` in the image caps the number of glibc malloc
memory outside the Go runtime no longer grows with the core count (closes #23) arenas. So memory outside the Go runtime no longer grows with the core count
- 2026-09-21: `GOMEMLIMIT=1536MiB` in the image; README Memory section with the (closes #23)
- 2026-09-21: The image sets `GOMEMLIMIT=1536MiB`. README "Memory" gives the
memory budget and the 5 GiB container limit (closes #13) memory budget and the 5 GiB container limit (closes #13)
- 2026-09-21: the four handler queues hold at most 20,000 messages each, down - 2026-09-21: The four handler queues hold at most 20,000 messages each, down
from 100,000 (closes #11) from 100,000 (closes #11)
- 2026-09-21: two goroutine leaks fixed: the stats handlers after a timeout and - 2026-09-21: Two goroutine leaks are fixed. The stats handlers leaked after a
the streamer's tickers on every reconnect (closes #12) timeout. The streamer's tickers leaked on every reconnect (closes #12)
- 2026-09-21: parsed RIS messages no longer keep the unused `Community` and - 2026-09-21: Parsed RIS messages no longer keep the unused `Community` and
`Raw` fields (closes #9) `Raw` fields (closes #9)
- 2026-09-21: `.editorconfig`, and a Gitea workflow that runs `script/cibuild` - 2026-09-21: `.editorconfig` is added. A Gitea workflow runs `script/cibuild`
on every push (closes #14) on every push (closes #14)
- 2026-09-21: the peering handler's AS-path map holds at most 500,000 paths and - 2026-09-21: The peering handler's AS-path map holds at most 500,000 paths.
is swapped for an empty one every 30 seconds instead of copied (closes #10) Every 30 seconds it is swapped for an empty one instead of copied (closes #10)
- 2026-09-21: SQLite memory bounded across the whole connection pool: a 64 MiB - 2026-09-21: SQLite's memory is bounded across the whole connection pool. Each
page cache on each connection, 1 GiB soft and 1.5 GiB hard heap limits (closes connection has a 64 MiB page cache. The heap limits are 1 GiB soft and 1.5 GiB
#8) hard (closes #8)
- 2026-09-21: the Docker build runs the format check, the linter and the tests, - 2026-09-21: The Docker build runs the format check, the linter and the tests.
linting in a separate stage on a golangci-lint image pinned by digest (closes Linting runs in a separate stage on a `golangci-lint` image pinned by digest
#5) (closes #5)
- 2026-09-21: `make test` skips the live-network feed test (`-short`), so - 2026-09-21: `make test` skips the live feed test, with `-short`. So
`make check` no longer depends on the network (closes #2) `make check` no longer depends on the network (closes #2)
- 2026-07-07 Adopted scripts-to-rule-them-all: `script/` entrypoints, Makefile - 2026-07-07: The scripts-to-rule-them-all layout is adopted. `script/` holds
shims, README Entrypoints section the entrypoints. The `Makefile` targets `check`, `test`, `lint`, `fmt` and
- 2026-02-22: repo policy compliance: required policy files, .gitignore update, `fmt-check` call them. So do `bootstrap`, `setup`, `docker` and `hooks`.
Makefile fmt-check/check/docker/hooks targets, gofmt pass README gains an "Entrypoints" section
(repo-policies-compliance, unmerged) - 2026-02-22: The repo is brought in line with the repo policies. The required
- 2026-01-01: WAL checkpointing: periodic (5s), on startup with logging, policy files are added. `.gitignore` is updated. The `Makefile` gains
TRUNCATE mode; fixed slow queries `fmt-check`, `check`, `docker` and `hooks` targets. The Go code is formatted
- 2025-12-31: status page: navbar, home page with search, oldest/newest route with `gofmt`. The work was on the branch `repo-policies-compliance`, unmerged
timestamps, NULL handling in WHOIS stats; container runs as routewatch user when this entry was written
with proper state dir - 2026-01-01: The WAL is checkpointed every 5 seconds, and at startup with a log
- 2025-12-30: structured HTTP request logging, increased timeouts, CIDR prefix line. Checkpoints run in `TRUNCATE` mode. This fixed slow queries
URL routing fixes, status page metrics and footer - 2025-12-31: The pages get a navigation bar and a home page with a search. The
- 2025-12-29: Dockerfile multi-stage build with source archive; SQLite status page shows the oldest and newest route times. The WHOIS stats query
incremental vacuum for non-blocking space reclamation handles `NULL`. The container runs as the `routewatch` user with the right
- 2025-07-27: initial RouteWatch BGP stream monitor state directory
- 2025-12-30: HTTP requests are logged as structured log lines. The HTTP
timeouts are longer. Prefix URLs with a slash in them route correctly. The
status page gets more metrics and a footer
- 2025-12-29: The `Dockerfile` builds in stages and puts a source archive in the
image. SQLite reclaims space with incremental vacuum, which does not block
- 2025-07-27: The first commit: RouteWatch, a BGP stream monitor
# Future Steps # Future Steps
None.
cmd/asinfo-gen/main_test.go
+1 -1
View File
@@ -12,7 +12,7 @@ import (
// parseTimeLimit is how long a test waits for parseCSV to return before it // parseTimeLimit is how long a test waits for parseCSV to return before it
// fails. // fails.
const parseTimeLimit = 2 * time.Second const parseTimeLimit = 15 * time.Second
// TestParseCSVReadsTodaysLayout parses an as.csv with the country code column // TestParseCSVReadsTodaysLayout parses an as.csv with the country code column
// that the source added after the description. It expects each AS with its // that the source added after the description. It expects each AS with its
go.mod
+7 -2
View File
@@ -8,11 +8,15 @@ require (
github.com/go-chi/chi/v5 v5.2.2 github.com/go-chi/chi/v5 v5.2.2
github.com/google/btree v1.1.3 github.com/google/btree v1.1.3
github.com/google/uuid v1.6.0 github.com/google/uuid v1.6.0
github.com/hashicorp/golang-lru/v2 v2.0.7
github.com/mattn/go-sqlite3 v1.14.29 github.com/mattn/go-sqlite3 v1.14.29
github.com/maxmind/mmdbwriter v1.2.0
github.com/miekg/dns v1.1.73
github.com/oschwald/maxminddb-golang/v2 v2.9.0
github.com/rcrowley/go-metrics v0.0.0-20250401214520-65e299d6c5c9 github.com/rcrowley/go-metrics v0.0.0-20250401214520-65e299d6c5c9
go.uber.org/fx v1.24.0 go.uber.org/fx v1.24.0
go4.org/netipx v0.0.0-20260823151212-3075585bcbeb go4.org/netipx v0.0.0-20260823151212-3075585bcbeb
golang.org/x/term v0.33.0 golang.org/x/term v0.45.0
golang.org/x/text v0.43.0 golang.org/x/text v0.43.0
) )
@@ -20,5 +24,6 @@ require (
go.uber.org/dig v1.19.0 // indirect go.uber.org/dig v1.19.0 // indirect
go.uber.org/multierr v1.10.0 // indirect go.uber.org/multierr v1.10.0 // indirect
go.uber.org/zap v1.26.0 // indirect go.uber.org/zap v1.26.0 // indirect
golang.org/x/sys v0.34.0 // indirect golang.org/x/net v0.57.0 // indirect
golang.org/x/sys v0.49.0 // indirect
) )
go.sum
+20 -10
View File
@@ -1,7 +1,5 @@
github.com/bits-and-blooms/bitset v1.26.0 h1:WPvcPZbP1yuKofmjs2SYIFO1EjzIGhCP9ducElLsh5Q= github.com/bits-and-blooms/bitset v1.26.0 h1:WPvcPZbP1yuKofmjs2SYIFO1EjzIGhCP9ducElLsh5Q=
github.com/bits-and-blooms/bitset v1.26.0/go.mod h1:7hO7Gc7Pp1vODcmWvKMRA9BNmbv6a/7QIWpPxHddWR8= github.com/bits-and-blooms/bitset v1.26.0/go.mod h1:7hO7Gc7Pp1vODcmWvKMRA9BNmbv6a/7QIWpPxHddWR8=
github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY= github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY=
github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto= github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto=
github.com/go-chi/chi/v5 v5.2.2 h1:CMwsvRVTbXVytCk1Wd72Zy1LAsAh9GxMmSNWLHCG618= github.com/go-chi/chi/v5 v5.2.2 h1:CMwsvRVTbXVytCk1Wd72Zy1LAsAh9GxMmSNWLHCG618=
@@ -10,14 +8,20 @@ github.com/google/btree v1.1.3 h1:CVpQJjYgC4VbzxeGVHfvZrv1ctoYCAI8vbl07Fcxlyg=
github.com/google/btree v1.1.3/go.mod h1:qOPhT0dTNdNzV6Z/lhRX0YXUafgPLFUh+gZMl761Gm4= github.com/google/btree v1.1.3/go.mod h1:qOPhT0dTNdNzV6Z/lhRX0YXUafgPLFUh+gZMl761Gm4=
github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0= github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo= github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
github.com/hashicorp/golang-lru/v2 v2.0.7 h1:a+bsQ5rvGLjzHuww6tVxozPZFVghXaHOwFs4luLUK2k=
github.com/hashicorp/golang-lru/v2 v2.0.7/go.mod h1:QeFd9opnmA6QUJc5vARoKUSoFhyfM2/ZepoAG6RGpeM=
github.com/mattn/go-sqlite3 v1.14.29 h1:1O6nRLJKvsi1H2Sj0Hzdfojwt8GiGKm+LOfLaBFaouQ= github.com/mattn/go-sqlite3 v1.14.29 h1:1O6nRLJKvsi1H2Sj0Hzdfojwt8GiGKm+LOfLaBFaouQ=
github.com/mattn/go-sqlite3 v1.14.29/go.mod h1:Uh1q+B4BYcTPb+yiD3kU8Ct7aC0hY9fxUwlHK0RXw+Y= github.com/mattn/go-sqlite3 v1.14.29/go.mod h1:Uh1q+B4BYcTPb+yiD3kU8Ct7aC0hY9fxUwlHK0RXw+Y=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM= github.com/maxmind/mmdbwriter v1.2.0 h1:hyvDopImmgvle3aR8AaddxXnT0iQH2KWJX3vNfkwzYM=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= github.com/maxmind/mmdbwriter v1.2.0/go.mod h1:EQmKHhk2y9DRVvyNxwCLKC5FrkXZLx4snc5OlLY5XLE=
github.com/miekg/dns v1.1.73 h1:uhT8nJxmTrPJYClxVxTCX+CVn6qnzSiybRk72Z6DgrE=
github.com/miekg/dns v1.1.73/go.mod h1:RW2Obtfd5NZHvOFe3zYG0W8koWOQtAzyHaLo8vASBuQ=
github.com/oschwald/maxminddb-golang/v2 v2.9.0 h1:YpIl3WoA9oIuNvqNaO/aD1N/7Ci2wOqoKH5GWo53H5Y=
github.com/oschwald/maxminddb-golang/v2 v2.9.0/go.mod h1:3TxexMBcR0ss3SbyYvnqfsDzDjN4o1KCg/nTsaMAivU=
github.com/rcrowley/go-metrics v0.0.0-20250401214520-65e299d6c5c9 h1:bsUq1dX0N8AOIL7EB/X911+m4EHsnWEHeJ0c+3TTBrg= github.com/rcrowley/go-metrics v0.0.0-20250401214520-65e299d6c5c9 h1:bsUq1dX0N8AOIL7EB/X911+m4EHsnWEHeJ0c+3TTBrg=
github.com/rcrowley/go-metrics v0.0.0-20250401214520-65e299d6c5c9/go.mod h1:bCqnVzQkZxMG4s8nGwiZ5l3QUCyqpo9Y+/ZMZ9VjZe4= github.com/rcrowley/go-metrics v0.0.0-20250401214520-65e299d6c5c9/go.mod h1:bCqnVzQkZxMG4s8nGwiZ5l3QUCyqpo9Y+/ZMZ9VjZe4=
github.com/stretchr/testify v1.8.1 h1:w7B6lhMri9wdJUVmEZPGGhZzrYTPvgJArz7wNPgYKsk= github.com/stretchr/testify v1.12.1 h1:EuwCh5fleGS7H32xRwO3wRGT7DxrDhLAT6FF8MpWDWE=
github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4= github.com/stretchr/testify v1.12.1/go.mod h1:MDEgiDPPsNp5cuIrHPPCyornHKgEVbtFUmoNlxoYthg=
go.uber.org/dig v1.19.0 h1:BACLhebsYdpQ7IROQ1AGPjrXcP5dF80U3gKoFzbaq/4= go.uber.org/dig v1.19.0 h1:BACLhebsYdpQ7IROQ1AGPjrXcP5dF80U3gKoFzbaq/4=
go.uber.org/dig v1.19.0/go.mod h1:Us0rSJiThwCv2GteUN0Q7OKvU7n5J4dxZ9JKUXozFdE= go.uber.org/dig v1.19.0/go.mod h1:Us0rSJiThwCv2GteUN0Q7OKvU7n5J4dxZ9JKUXozFdE=
go.uber.org/fx v1.24.0 h1:wE8mruvpg2kiiL1Vqd0CC+tr0/24XIB10Iwp2lLWzkg= go.uber.org/fx v1.24.0 h1:wE8mruvpg2kiiL1Vqd0CC+tr0/24XIB10Iwp2lLWzkg=
@@ -28,12 +32,18 @@ go.uber.org/multierr v1.10.0 h1:S0h4aNzvfcFsC3dRF1jLoaov7oRaKqRGC/pUEJ2yvPQ=
go.uber.org/multierr v1.10.0/go.mod h1:20+QtiLqy0Nd6FdQB9TLXag12DsQkrbs3htMFfDN80Y= go.uber.org/multierr v1.10.0/go.mod h1:20+QtiLqy0Nd6FdQB9TLXag12DsQkrbs3htMFfDN80Y=
go.uber.org/zap v1.26.0 h1:sI7k6L95XOKS281NhVKOFCUNIvv9e0w4BF8N3u+tCRo= go.uber.org/zap v1.26.0 h1:sI7k6L95XOKS281NhVKOFCUNIvv9e0w4BF8N3u+tCRo=
go.uber.org/zap v1.26.0/go.mod h1:dtElttAiwGvoJ/vj4IwHBS/gXsEu/pZ50mUIRWuG0so= go.uber.org/zap v1.26.0/go.mod h1:dtElttAiwGvoJ/vj4IwHBS/gXsEu/pZ50mUIRWuG0so=
go.yaml.in/yaml/v3 v3.0.5 h1:N6y/pJk8buWs9NY5ERU2HSMfm+IuD/OtfdAnq6kESPw=
go.yaml.in/yaml/v3 v3.0.5/go.mod h1:HVTZu1O7/Vkt2N+BFy8Zza+lnLsABggaTM2ZpNIGuKg=
go4.org/netipx v0.0.0-20260823151212-3075585bcbeb h1:XBM4hvfwGAttkkiTIFfeigdfcL1xIfdKXqFdgiHGtDs= go4.org/netipx v0.0.0-20260823151212-3075585bcbeb h1:XBM4hvfwGAttkkiTIFfeigdfcL1xIfdKXqFdgiHGtDs=
go4.org/netipx v0.0.0-20260823151212-3075585bcbeb/go.mod h1:PLyyIXexvUFg3Owu6p/WfdlivPbZJsZdgWZlrGope/Y= go4.org/netipx v0.0.0-20260823151212-3075585bcbeb/go.mod h1:PLyyIXexvUFg3Owu6p/WfdlivPbZJsZdgWZlrGope/Y=
golang.org/x/sys v0.34.0 h1:H5Y5sJ2L2JRdyv7ROF1he/lPdvFsd0mJHFw2ThKHxLA= golang.org/x/net v0.57.0 h1:K5+3DljvIuDG9/Jv9rvyMywYNFCQ9RSUY6OOTTkT+tE=
golang.org/x/sys v0.34.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k= golang.org/x/net v0.57.0/go.mod h1:KpXc8iv+r3XplLAG/f7Jsf9RPszJzdR0f58q9vGOuEU=
golang.org/x/term v0.33.0 h1:NuFncQrRcaRvVmgRkvM3j/F00gWIAlcmlB8ACEKmGIg= golang.org/x/sync v0.24.0 h1:iqiDrGoDgyuvAKrhLQthUEzU/R378N78gXbBjxed7oA=
golang.org/x/term v0.33.0/go.mod h1:s18+ql9tYWp1IfpV9DmCtQDDSRBUjKaw9M1eAv5UeF0= golang.org/x/sync v0.24.0/go.mod h1:sUUOizhqBxiL6pEWpqNLUiaJn1ShEbZ6BBqskPbjZm0=
golang.org/x/sys v0.49.0 h1:XbzkgYJHdqh/8m2Uu0W/dQv8nktxx4BFHp1M0gROTXA=
golang.org/x/sys v0.49.0/go.mod h1:hNLxWAXmnKAxqDtdwIYC4bM9oQPEecfsnNMuSxOs3og=
golang.org/x/term v0.45.0 h1:NwWyBmoJCbfTHpxrWoZ9C6/VxOf7ic219I8xZZFdrf0=
golang.org/x/term v0.45.0/go.mod h1:9aqxs0blBcrm/n0L9QW0aRVD+ktan8ssZromtqJC43w=
golang.org/x/text v0.43.0 h1:1QivrlhwAsnMOcqgOdl9my7s9OyZl8O5/UGUTJVXoWc= golang.org/x/text v0.43.0 h1:1QivrlhwAsnMOcqgOdl9my7s9OyZl8O5/UGUTJVXoWc=
golang.org/x/text v0.43.0/go.mod h1:hbSIYA/amXcRXTFSZqh8tWHEoqRvvbKPJ2uz/KU+a+s= golang.org/x/text v0.43.0/go.mod h1:hbSIYA/amXcRXTFSZqh8tWHEoqRvvbKPJ2uz/KU+a+s=
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA= gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
internal/blocklist/blocklist_internal_test.go
-494
View File
@@ -1,494 +0,0 @@
package blocklist
import (
"context"
"errors"
"io"
"io/fs"
"log/slog"
"net/http"
"net/http/httptest"
"net/netip"
"os"
"path/filepath"
"strings"
"sync"
"testing"
"time"
)
// The test list's name and description, the address its good version lists,
// and the address a newer version lists instead.
const (
testListName = "test_list"
testListDescription = "On the test list"
listedAddr = "192.0.2.1"
goodListBody = "# A test list\n" + listedAddr + "\n"
newListedAddr = "192.0.2.2"
newListBody = "# A test list\n" + newListedAddr + "\n"
)
// testETag is the ETag a publisher sends with a version of the test list.
const testETag = `"v1"`
// maxWait is how long a test waits for the download goroutine.
const maxWait = 10 * time.Second
// publisher stands in for a list's publisher. It answers every request with
// its status and body, and keeps the headers of each request. A 200 answer
// carries lastModified and etag, when set, as Last-Modified and ETag. As
// from a real publisher, a request whose If-None-Match or If-Modified-Since
// matches them is answered "not modified".
type publisher struct {
mu sync.Mutex
status int
body string
lastModified time.Time
etag string
headers []http.Header
}
// newPublisher starts a publisher that answers 200 with body, and returns it
// and its URL.
func newPublisher(t *testing.T, body string) (*publisher, string) {
t.Helper()
p := &publisher{status: http.StatusOK, body: body}
srv := httptest.NewServer(p)
t.Cleanup(srv.Close)
return p, srv.URL
}
func (p *publisher) ServeHTTP(w http.ResponseWriter, r *http.Request) {
p.mu.Lock()
defer p.mu.Unlock()
p.headers = append(p.headers, r.Header.Clone())
if p.status != http.StatusOK {
w.WriteHeader(p.status)
_, _ = io.WriteString(w, p.body)
return
}
if p.etag != "" {
w.Header().Set(etagHeader, p.etag)
}
// ServeContent sends Last-Modified unless lastModified is zero, and
// answers "not modified" when the request's conditions match.
http.ServeContent(w, r, testListName, p.lastModified,
strings.NewReader(p.body))
}
// answer makes the publisher answer later requests with status and body.
func (p *publisher) answer(status int, body string) {
p.mu.Lock()
defer p.mu.Unlock()
p.status, p.body = status, body
}
// publish makes the publisher answer later requests with a version of the
// list: body, with lastModified and etag. A zero lastModified or an empty
// etag is not sent.
func (p *publisher) publish(body string, lastModified time.Time, etag string) {
p.mu.Lock()
defer p.mu.Unlock()
p.status, p.body = http.StatusOK, body
p.lastModified, p.etag = lastModified, etag
}
// requests returns the headers of the requests the publisher has had.
func (p *publisher) requests() []http.Header {
p.mu.Lock()
defer p.mu.Unlock()
return append([]http.Header(nil), p.headers...)
}
// testList returns a list served at url, written in format.
func testList(url string, format Format) List {
return List{
Name: testListName,
Description: testListDescription,
URL: url,
Interval: time.Hour,
Format: format,
}
}
func newTestBlocklists(dir string, list List) *Blocklists {
return New(Params{
Dir: dir,
Lists: []List{list},
Logger: slog.New(slog.DiscardHandler),
})
}
// lookup looks addr up in b.
func lookup(t *testing.T, b *Blocklists, addr string) []Listing {
t.Helper()
return b.Lookup(netip.MustParseAddr(addr))
}
// TestLookupFindsListedAddresses downloads a list in each format and looks
// up addresses on it, inside its networks, and off it, in IPv4 and IPv6.
// A listed address has one listing that names the list; any other has an
// empty list of listings.
func TestLookupFindsListedAddresses(t *testing.T) {
t.Parallel()
tests := []struct {
name string
format Format
body string
listed []string
unlisted []string
}{
{
name: "single addresses",
format: FormatLines,
body: "# comment\n192.0.2.1\n\n2001:db8::1\n",
listed: []string{"192.0.2.1", "::ffff:192.0.2.1", "2001:db8::1"},
unlisted: []string{"192.0.2.2", "2001:db8::2"},
},
{
name: "networks",
format: FormatLines,
body: "# comment\n198.51.100.0/24\n2001:db8:1::/48\n",
listed: []string{"198.51.100.0", "198.51.100.255", "2001:db8:1::5"},
unlisted: []string{"198.51.101.0", "2001:db8:2::1"},
},
{
name: "Spamhaus networks",
format: FormatSpamhausJSON,
body: `{"cidr":"203.0.113.0/25","sblid":"SBL1","rir":"arin"}` + "\n" +
`{"cidr":"2001:db8:3::/48","sblid":"SBL2","rir":"ripencc"}` + "\n" +
`{"type":"metadata","timestamp":1793074442,"records":2}` + "\n",
listed: []string{"203.0.113.1", "2001:db8:3::1"},
unlisted: []string{"203.0.113.200", "2001:db8:4::1"},
},
{
name: "DShield networks",
format: FormatDShield,
body: "# DShield.org Recommended Block List\n" +
"192.0.2.0\t192.0.2.255\t24\t327\tEXAMPLE\tUS\tNone\n",
listed: []string{"192.0.2.0", "192.0.2.77"},
unlisted: []string{"192.0.3.1", "2001:db8::1"},
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
_, url := newPublisher(t, tt.body)
b := newTestBlocklists(t.TempDir(), testList(url, tt.format))
err := b.download(t.Context(), b.lists[0])
if err != nil {
t.Fatalf("download: %v", err)
}
for _, addr := range tt.listed {
listings := lookup(t, b, addr)
if len(listings) != 1 || listings[0].Name != testListName ||
listings[0].Description != testListDescription ||
listings[0].Updated.IsZero() {
t.Errorf("%s: listings %+v, want one for %s", addr,
listings, testListName)
}
}
for _, addr := range tt.unlisted {
listings := lookup(t, b, addr)
if listings == nil || len(listings) != 0 {
t.Errorf("%s: listings %#v, want an empty list", addr, listings)
}
}
})
}
}
// TestFailedDownloadKeepsThePreviousCopy downloads a good version of a list,
// then one that fails. The good copy stays in memory and on disk, and no
// part of the failed download is left beside it.
func TestFailedDownloadKeepsThePreviousCopy(t *testing.T) {
t.Parallel()
tests := []struct {
name string
status int
body string
}{
{"server error", http.StatusInternalServerError, "unavailable"},
{"not a list", http.StatusOK, "<!DOCTYPE html>\n<html></html>\n"},
{
"over the size limit", http.StatusOK,
strings.Repeat(listedAddr+"\n", maxDownloadSize/len(listedAddr)),
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
dir := t.TempDir()
p, url := newPublisher(t, goodListBody)
b := newTestBlocklists(dir, testList(url, FormatLines))
err := b.download(t.Context(), b.lists[0])
if err != nil {
t.Fatalf("first download: %v", err)
}
before := lookup(t, b, listedAddr)
p.answer(tt.status, tt.body)
err = b.download(t.Context(), b.lists[0])
if err == nil {
t.Fatal("second download returned no error")
}
after := lookup(t, b, listedAddr)
if len(after) != 1 || len(before) != 1 ||
!after[0].Updated.Equal(before[0].Updated) {
t.Errorf("listings %+v after the failure, want %+v", after, before)
}
copies := os.DirFS(dir)
onDisk, err := fs.ReadFile(copies, testListName)
if err != nil || string(onDisk) != goodListBody {
t.Errorf("copy on disk %q (%v), want %q", onDisk, err, goodListBody)
}
_, err = fs.Stat(copies, testListName+downloadSuffix)
if !errors.Is(err, fs.ErrNotExist) {
t.Errorf("the failed download's file is still there (%v)", err)
}
})
}
}
// TestRestartLoadsCopiesFromDisk downloads a list, then starts a new
// Blocklists on the same directory, as a restart does. The new one answers
// from the copy on disk at once, and does not download the list again while
// the copy is younger than the list's interval.
func TestRestartLoadsCopiesFromDisk(t *testing.T) {
t.Parallel()
dir := t.TempDir()
p, url := newPublisher(t, goodListBody)
list := testList(url, FormatLines)
first := newTestBlocklists(dir, list)
err := first.download(t.Context(), list)
if err != nil {
t.Fatalf("download: %v", err)
}
downloaded := lookup(t, first, listedAddr)[0].Updated
second := newTestBlocklists(dir, list)
second.Start(t.Context())
second.Stop(t.Context())
listings := lookup(t, second, listedAddr)
if len(listings) != 1 ||
listings[0].Updated.Sub(downloaded).Abs() > time.Second {
t.Errorf("after the restart, listings %+v, want one updated at %s",
listings, downloaded)
}
if got := len(p.requests()); got != 1 {
t.Errorf("the publisher had %d requests, want 1", got)
}
}
// TestStartRefreshesAnOldCopy starts on a copy older than its list's
// interval. The list is downloaded at once, with routewatch's User-Agent and
// the Last-Modified and ETag the publisher sent with the copy, kept on disk.
// The publisher answers that the copy is still current, so the copy is kept
// and marked as updated now.
func TestStartRefreshesAnOldCopy(t *testing.T) {
t.Parallel()
dir := t.TempDir()
p, url := newPublisher(t, goodListBody)
list := testList(url, FormatLines)
lastModified := time.Now().Add(-3 * list.Interval).UTC().Truncate(time.Second)
p.publish(goodListBody, lastModified, testETag)
err := newTestBlocklists(dir, list).download(t.Context(), list)
if err != nil {
t.Fatalf("download: %v", err)
}
old := time.Now().Add(-2 * list.Interval).UTC().Truncate(time.Second)
err = os.Chtimes(filepath.Join(dir, testListName), old, old)
if err != nil {
t.Fatalf("Chtimes: %v", err)
}
b := newTestBlocklists(dir, list)
b.Start(t.Context())
deadline := time.Now().Add(maxWait)
for !lookup(t, b, listedAddr)[0].Updated.After(old) {
if time.Now().After(deadline) {
t.Fatalf("the copy was not marked updated within %s", maxWait)
}
time.Sleep(time.Millisecond)
}
b.Stop(t.Context())
requests := p.requests()
last := requests[len(requests)-1]
want := lastModified.Format(http.TimeFormat)
if got := last.Get(ifModifiedSinceHeader); got != want {
t.Errorf("If-Modified-Since %q, want %q", got, want)
}
if got := last.Get(ifNoneMatchHeader); got != testETag {
t.Errorf("If-None-Match %q, want %q", got, testETag)
}
if got := last.Get(userAgentHeader); got != userAgent {
t.Errorf("User-Agent %q, want %q", got, userAgent)
}
}
// TestNewVersionOlderThanTheLastDownloadReplacesTheCopy downloads a list.
// The publisher then puts out a new version whose Last-Modified is earlier
// than that download, as when a cache in front of the publisher passes the
// version on late. The next download sends the Last-Modified of the copy,
// not the time of the download, so it gets the new version.
func TestNewVersionOlderThanTheLastDownloadReplacesTheCopy(t *testing.T) {
t.Parallel()
p, url := newPublisher(t, goodListBody)
list := testList(url, FormatLines)
b := newTestBlocklists(t.TempDir(), list)
firstVersion := time.Now().Add(-2 * list.Interval).UTC().Truncate(time.Second)
p.publish(goodListBody, firstVersion, "")
err := b.download(t.Context(), list)
if err != nil {
t.Fatalf("first download: %v", err)
}
p.publish(newListBody, firstVersion.Add(list.Interval), "")
err = b.download(t.Context(), list)
if err != nil {
t.Fatalf("second download: %v", err)
}
if listings := lookup(t, b, newListedAddr); len(listings) != 1 {
t.Errorf("%s: listings %+v, want one from the new version",
newListedAddr, listings)
}
want := firstVersion.Format(http.TimeFormat)
if got := p.requests()[1].Get(ifModifiedSinceHeader); got != want {
t.Errorf("If-Modified-Since %q, want %q", got, want)
}
}
// TestDownloadWithoutLastModifiedOrETagSendsNoCondition downloads a list
// twice from a publisher that sends neither Last-Modified nor ETag. Neither
// request carries If-Modified-Since or If-None-Match, so the second download
// gets the whole list again.
func TestDownloadWithoutLastModifiedOrETagSendsNoCondition(t *testing.T) {
t.Parallel()
p, url := newPublisher(t, goodListBody)
list := testList(url, FormatLines)
b := newTestBlocklists(t.TempDir(), list)
err := b.download(t.Context(), list)
if err != nil {
t.Fatalf("first download: %v", err)
}
err = b.download(t.Context(), list)
if err != nil {
t.Fatalf("second download: %v", err)
}
for i, request := range p.requests() {
if request.Get(ifModifiedSinceHeader) != "" ||
request.Get(ifNoneMatchHeader) != "" {
t.Errorf("request %d has a condition: %v", i, request)
}
}
}
// TestStopCancelsADownloadInProgress stops while the publisher has not
// answered. Stop cancels the download and returns once the download
// goroutine has stopped.
func TestStopCancelsADownloadInProgress(t *testing.T) {
t.Parallel()
arrived := make(chan struct{})
var once sync.Once
srv := httptest.NewServer(http.HandlerFunc(
func(_ http.ResponseWriter, r *http.Request) {
once.Do(func() { close(arrived) })
<-r.Context().Done()
}))
t.Cleanup(srv.Close)
b := newTestBlocklists(t.TempDir(), testList(srv.URL, FormatLines))
b.Start(t.Context())
select {
case <-arrived:
case <-time.After(maxWait):
t.Fatalf("no download began within %s", maxWait)
}
ctx, cancel := context.WithTimeout(t.Context(), maxWait)
defer cancel()
b.Stop(ctx)
select {
case <-b.done:
default:
t.Error("Stop returned before the download goroutine stopped")
}
}
// TestPublicListsAreComplete checks that every public list has what a
// download and a lookup answer need, and a unique name.
func TestPublicListsAreComplete(t *testing.T) {
t.Parallel()
names := make(map[string]bool)
for _, list := range Lists() {
if list.Name == "" || list.Description == "" || list.URL == "" ||
list.Interval <= 0 || names[list.Name] {
t.Errorf("list %+v is incomplete or has a name used before", list)
}
names[list.Name] = true
}
}
internal/blocklist/lists.go
-93
View File
@@ -1,93 +0,0 @@
package blocklist
import "time"
// How often each list is downloaded. No list is downloaded more often than
// its publisher updates it or allows.
const (
// DShield asks that its feeds be downloaded at most once an hour:
// https://isc.sans.edu/feeds_doc.html
dshieldInterval = time.Hour
// abuse.ch makes the list every 5 minutes and recommends a download at
// least every 15: https://feodotracker.abuse.ch/blocklist/
feodoTrackerInterval = 15 * time.Minute
// FireHOL's page for each list gives how often the list changes on
// average: about every 5 hours for abusers and every 3 hours for level
// 3. FireHOL sets no download limit.
// https://iplists.firehol.org/?ipset=firehol_abusers_30d
// https://iplists.firehol.org/?ipset=firehol_level3
fireHOLAbusersInterval = 5 * time.Hour
fireHOLLevel3Interval = 3 * time.Hour
// Spamhaus asks that DROP be downloaded at most once a day:
// https://www.spamhaus.org/blocklists/do-not-route-or-peer/
spamhausDROPInterval = 24 * time.Hour
// Tor publishes a new exit list every hour and sets no download limit:
// https://collector.torproject.org/recent/exit-lists/
torExitsInterval = time.Hour
)
// Lists returns the public blocklists routewatch downloads. Each can be
// downloaded whole without an account or a key. Spamhaus merged its EDROP
// list into DROP, so DROP covers both.
func Lists() []List {
return []List{
{
Name: "dshield",
Description: "In one of the 20 networks that DShield saw scan " +
"the most targets in the last three days",
URL: "https://feeds.dshield.org/block.txt",
Interval: dshieldInterval,
Format: FormatDShield,
},
{
Name: "feodo_tracker",
Description: "A botnet command-and-control server",
URL: "https://feodotracker.abuse.ch/downloads/ipblocklist.txt",
Interval: feodoTrackerInterval,
Format: FormatLines,
},
{
Name: "firehol_abusers_30d",
Description: "Reported for comment, form or forum spam in the " +
"last 30 days",
URL: "https://iplists.firehol.org/files/firehol_abusers_30d.netset",
Interval: fireHOLAbusersInterval,
Format: FormatLines,
},
{
Name: "firehol_level3",
Description: "Reported for attacks, spyware or viruses in the " +
"last 30 days",
URL: "https://iplists.firehol.org/files/firehol_level3.netset",
Interval: fireHOLLevel3Interval,
Format: FormatLines,
},
{
Name: "spamhaus_drop",
Description: "In an IPv4 network that Spamhaus says spammers " +
"or cyber criminals have hijacked or lease",
URL: "https://www.spamhaus.org/drop/drop_v4.json",
Interval: spamhausDROPInterval,
Format: FormatSpamhausJSON,
},
{
Name: "spamhaus_dropv6",
Description: "In an IPv6 network that Spamhaus says spammers " +
"or cyber criminals have hijacked or lease",
URL: "https://www.spamhaus.org/drop/drop_v6.json",
Interval: spamhausDROPInterval,
Format: FormatSpamhausJSON,
},
{
Name: "tor_exits",
Description: "A Tor exit node, where traffic from the Tor network leaves",
URL: "https://check.torproject.org/torbulkexitlist",
Interval: torExitsInterval,
Format: FormatLines,
},
}
}
internal/blocklist/parse.go
-158
View File
@@ -1,158 +0,0 @@
package blocklist
import (
"bufio"
"encoding/json"
"errors"
"fmt"
"io"
"net/netip"
"strings"
"go4.org/netipx"
)
const (
// commentPrefix starts a comment line in a list file.
commentPrefix = "#"
// networkSeparator separates the address and the mask length of a
// network, as in 192.0.2.0/24.
networkSeparator = "/"
// dshieldFieldSeparator separates the fields of a DShield line.
dshieldFieldSeparator = "\t"
// spamhausMetadataType is the type of the line that ends a Spamhaus
// file. That line holds the file's metadata and no network.
spamhausMetadataType = "metadata"
)
var (
errUnknownFormat = errors.New("unknown list format")
errNoNetwork = errors.New("no network on the line")
errBadRange = errors.New("first and last address make no range")
)
// parse reads a list file written in format and returns the addresses it
// holds. A line it cannot read fails the whole file, so a file that is not
// the list, such as an error page, never replaces a good copy.
func parse(r io.Reader, format Format) (*netipx.IPSet, error) {
var builder netipx.IPSetBuilder
scanner := bufio.NewScanner(r)
for lineNumber := 1; scanner.Scan(); lineNumber++ {
line := strings.TrimSpace(scanner.Text())
if line == "" || strings.HasPrefix(line, commentPrefix) {
continue
}
err := addLine(&builder, line, format)
if err != nil {
return nil, fmt.Errorf("line %d: %w", lineNumber, err)
}
}
err := scanner.Err()
if err != nil {
return nil, err
}
return builder.IPSet()
}
// addLine adds the address or network on one line of a list file to builder.
func addLine(builder *netipx.IPSetBuilder, line string, format Format) error {
switch format {
case FormatLines:
return addAddressOrNetwork(builder, line)
case FormatSpamhausJSON:
return addSpamhausNetwork(builder, line)
case FormatDShield:
return addDShieldNetwork(builder, line)
default:
return errUnknownFormat
}
}
// addAddressOrNetwork adds an address, such as 192.0.2.1, or a network, such
// as 192.0.2.0/24, to builder.
func addAddressOrNetwork(builder *netipx.IPSetBuilder, text string) error {
if strings.Contains(text, networkSeparator) {
network, err := netip.ParsePrefix(text)
if err != nil {
return err
}
builder.AddPrefix(network)
return nil
}
addr, err := netip.ParseAddr(text)
if err != nil {
return err
}
builder.Add(addr)
return nil
}
// addSpamhausNetwork adds the network on a line of a Spamhaus file to
// builder. The metadata line adds nothing.
func addSpamhausNetwork(builder *netipx.IPSetBuilder, line string) error {
var entry struct {
CIDR string `json:"cidr"`
Type string `json:"type"`
}
err := json.Unmarshal([]byte(line), &entry)
if err != nil {
return err
}
if entry.Type == spamhausMetadataType {
return nil
}
network, err := netip.ParsePrefix(entry.CIDR)
if err != nil {
return err
}
builder.AddPrefix(network)
return nil
}
// addDShieldNetwork adds the network on a line of a DShield file to builder.
// The line's first two fields are the network's first and last address.
func addDShieldNetwork(builder *netipx.IPSetBuilder, line string) error {
firstField, rest, found := strings.Cut(line, dshieldFieldSeparator)
if !found {
return errNoNetwork
}
lastField, _, _ := strings.Cut(rest, dshieldFieldSeparator)
first, err := netip.ParseAddr(firstField)
if err != nil {
return err
}
last, err := netip.ParseAddr(lastField)
if err != nil {
return err
}
network := netipx.IPRangeFrom(first, last)
if !network.IsValid() {
return errBadRange
}
builder.AddRange(network)
return nil
}
internal/bogon/bogon.go
+211
View File
@@ -0,0 +1,211 @@
// Package bogon tells whether a prefix, an address or an AS number is reserved:
// set aside for a special purpose, so that no network should announce it on the
// internet. A route is a bogon announcement when its prefix is reserved or its
// origin AS is.
//
// Most reserved prefixes come from the IANA special-purpose address registries
// for IPv4 and IPv6. The two multicast blocks, 224.0.0.0/4 and ff00::/8, come
// from the IANA IPv4 and IPv6 address space registries. The reserved AS
// numbers come from the IANA special-purpose AS numbers registry:
// - the AS numbers for private use
// - the AS numbers for documentation
// - AS 23456, which stands in for a 32-bit AS number
// - the last AS number of the 16-bit and of the 32-bit range
//
// Address space and AS numbers that the IANA has not handed out yet are not
// counted.
package bogon
import (
"net/netip"
"strconv"
)
// Prefix returns why prefix is reserved, and true, when it lies inside a
// reserved block. The most specific registry block that holds prefix decides,
// because some blocks that may be announced lie inside reserved ones. It
// returns "" and false when prefix is not reserved.
func Prefix(prefix netip.Prefix) (string, bool) {
var holder *block
for i, b := range registryBlocks {
inside := b.prefix.Bits() <= prefix.Bits() && b.prefix.Contains(prefix.Addr())
if inside && (holder == nil || b.prefix.Bits() > holder.prefix.Bits()) {
holder = &registryBlocks[i]
}
}
if holder == nil || !holder.reserved {
return "", false
}
return holder.name + " (" + holder.prefix.String() + ")", true
}
// Addr returns why addr is reserved, and true, when it lies inside a reserved
// block, as Prefix decides. An IPv4 address written in IPv6 form counts as the
// IPv4 address it holds. It returns "" and false when addr is not reserved.
func Addr(addr netip.Addr) (string, bool) {
addr = addr.Unmap()
return Prefix(netip.PrefixFrom(addr, addr.BitLen()))
}
// ASN returns why asn is reserved, and true, when it is. It returns "" and
// false when asn is not reserved.
func ASN(asn int) (string, bool) {
for _, r := range reservedASRanges {
if asn < r.first || asn > r.last {
continue
}
if r.first == r.last {
return r.name + " (AS" + strconv.Itoa(asn) + ")", true
}
return r.name + " (AS" + strconv.Itoa(r.first) + "-AS" +
strconv.Itoa(r.last) + ")", true
}
return "", false
}
// The names that the registries give to more than one row.
const (
privateUse = "Private-Use"
documentation = "Documentation"
benchmarking = "Benchmarking"
ietfProtocolAssignments = "IETF Protocol Assignments"
portControlAnycast = "Port Control Protocol Anycast"
natTraversalAnycast = "Traversal Using Relays around NAT Anycast"
nat64Discovery = "NAT64/DNS64 Discovery"
amt = "AMT"
as112DirectDelegation = "Direct Delegation AS112 Service"
ipv4IPv6Translation = "IPv4-IPv6 Translat."
multicast = "Multicast"
)
// block is one row of an IANA address registry.
type block struct {
prefix netip.Prefix
name string
// reserved says that no network should announce the row's addresses on
// the internet.
reserved bool
}
// reservedBlock returns a reserved row: a multicast block, or a special-purpose
// row whose Globally Reachable column is False.
func reservedBlock(prefix, name string) block {
return block{prefix: netip.MustParsePrefix(prefix), name: name, reserved: true}
}
// reachableBlock returns a special-purpose row whose Globally Reachable column
// is True or N/A. Such a row matters only inside a reserved block, whose
// addresses it lets be announced.
func reachableBlock(prefix, name string) block {
return block{prefix: netip.MustParsePrefix(prefix), name: name}
}
// registryBlocks are the rows of the IANA special-purpose address registries,
// without the deprecated ones:
// - https://www.iana.org/assignments/iana-ipv4-special-registry/
// - https://www.iana.org/assignments/iana-ipv6-special-registry/
//
// They also hold the multicast blocks, which the IANA address space registries
// list as Multicast:
// - https://www.iana.org/assignments/ipv4-address-space/
// - https://www.iana.org/assignments/ipv6-address-space/
//
//nolint:gochecknoglobals // a fixed list, parsed once
var registryBlocks = []block{
reservedBlock("0.0.0.0/8", "This network"),
reservedBlock("0.0.0.0/32", "This host on this network"),
reservedBlock("10.0.0.0/8", privateUse),
reservedBlock("100.64.0.0/10", "Shared Address Space"),
reservedBlock("127.0.0.0/8", "Loopback"),
reservedBlock("169.254.0.0/16", "Link Local"),
reservedBlock("172.16.0.0/12", privateUse),
reservedBlock("192.0.0.0/24", ietfProtocolAssignments),
reservedBlock("192.0.0.0/29", "IPv4 Service Continuity Prefix"),
reservedBlock("192.0.0.8/32", "IPv4 dummy address"),
reachableBlock("192.0.0.9/32", portControlAnycast),
reachableBlock("192.0.0.10/32", natTraversalAnycast),
reservedBlock("192.0.0.170/32", nat64Discovery),
reservedBlock("192.0.0.171/32", nat64Discovery),
reservedBlock("192.0.2.0/24", "Documentation (TEST-NET-1)"),
reachableBlock("192.31.196.0/24", "AS112-v4"),
reachableBlock("192.52.193.0/24", amt),
reservedBlock("192.88.99.2/32", "6a44-relay anycast address"),
reservedBlock("192.168.0.0/16", privateUse),
reachableBlock("192.175.48.0/24", as112DirectDelegation),
reservedBlock("198.18.0.0/15", benchmarking),
reservedBlock("198.51.100.0/24", "Documentation (TEST-NET-2)"),
reservedBlock("203.0.113.0/24", "Documentation (TEST-NET-3)"),
reservedBlock("224.0.0.0/4", multicast),
reservedBlock("240.0.0.0/4", "Reserved"),
reservedBlock("255.255.255.255/32", "Limited Broadcast"),
reservedBlock("::1/128", "Loopback Address"),
reservedBlock("::/128", "Unspecified Address"),
reservedBlock("::ffff:0:0/96", "IPv4-mapped Address"),
reachableBlock("64:ff9b::/96", ipv4IPv6Translation),
reservedBlock("64:ff9b:1::/48", ipv4IPv6Translation),
reservedBlock("100::/64", "Discard-Only Address Block"),
reservedBlock("100:0:0:1::/64", "Dummy IPv6 Prefix"),
reservedBlock("2001::/23", ietfProtocolAssignments),
reachableBlock("2001::/32", "TEREDO"),
reachableBlock("2001:1::1/128", portControlAnycast),
reachableBlock("2001:1::2/128", natTraversalAnycast),
reachableBlock("2001:1::3/128", "DNS-SD Service Registration Protocol Anycast"),
reservedBlock("2001:2::/48", benchmarking),
reachableBlock("2001:3::/32", amt),
reachableBlock("2001:4:112::/48", "AS112-v6"),
reachableBlock("2001:20::/28", "ORCHIDv2"),
reachableBlock("2001:30::/28", "Drone Remote ID Protocol Entity Tags (DETs) Prefix"),
reservedBlock("2001:db8::/32", documentation),
reachableBlock("2002::/16", "6to4"),
reachableBlock("2620:4f:8000::/48", as112DirectDelegation),
reservedBlock("3fff::/20", documentation),
reservedBlock("5f00::/16", "Segment Routing (SRv6) SIDs"),
reservedBlock("fc00::/7", "Unique-Local"),
reservedBlock("fe80::/10", "Link-Local Unicast"),
reservedBlock("ff00::/8", multicast),
}
// asRange is a range of reserved AS numbers, first to last.
type asRange struct {
first, last int
name string
}
// The reserved AS numbers of the IANA special-purpose AS numbers registry.
const (
asTrans = 23456
firstDocumentationAS16 = 64496
lastDocumentationAS16 = 64511
firstPrivateUseAS16 = 64512
lastPrivateUseAS16 = 65534
lastAS16 = 65535
firstDocumentationAS32 = 65536
lastDocumentationAS32 = 65551
firstPrivateUseAS32 = 4200000000
lastPrivateUseAS32 = 4294967294
lastAS32 = 4294967295
)
// reservedASRanges are the reserved rows of the IANA special-purpose AS numbers
// registry, https://www.iana.org/assignments/iana-as-numbers-special-registry/.
// AS 0 is left out: RouteWatch uses it for a route with no known origin. AS 112
// is left out because the AS112 project announces routes with it.
//
//nolint:gochecknoglobals // a fixed list
var reservedASRanges = []asRange{
{first: asTrans, last: asTrans, name: "AS_TRANS"},
{first: firstDocumentationAS16, last: lastDocumentationAS16, name: documentation},
{first: firstPrivateUseAS16, last: lastPrivateUseAS16, name: privateUse},
{first: lastAS16, last: lastAS16, name: "Last 16-bit AS number"},
{first: firstDocumentationAS32, last: lastDocumentationAS32, name: documentation},
{first: firstPrivateUseAS32, last: lastPrivateUseAS32, name: privateUse},
{first: lastAS32, last: lastAS32, name: "Last 32-bit AS number"},
}
internal/bogon/bogon_test.go
+131
View File
@@ -0,0 +1,131 @@
package bogon_test
import (
"net/netip"
"strconv"
"testing"
"git.eeqj.de/sneak/routewatch/internal/bogon"
)
// privateUseTen is why a prefix or an address inside 10.0.0.0/8 is reserved.
const privateUseTen = "Private-Use (10.0.0.0/8)"
func TestPrefix(t *testing.T) {
t.Parallel()
tests := []struct {
prefix string
// want is why the prefix is reserved, or "" when it is not.
want string
}{
{"10.1.2.0/24", privateUseTen},
{"10.0.0.0/8", privateUseTen},
{"192.0.2.0/24", "Documentation (TEST-NET-1) (192.0.2.0/24)"},
{"2001:db8:1::/48", "Documentation (2001:db8::/32)"},
{"fd00::/8", "Unique-Local (fc00::/7)"},
// Multicast space, from the IANA address space registries.
{"224.0.0.0/4", "Multicast (224.0.0.0/4)"},
{"239.255.0.0/16", "Multicast (224.0.0.0/4)"},
{"ff00::/8", "Multicast (ff00::/8)"},
{"ff02::/16", "Multicast (ff00::/8)"},
// The most specific block names the reason.
{"0.0.0.0/32", "This host on this network (0.0.0.0/32)"},
{"2001:2::/48", "Benchmarking (2001:2::/48)"},
// Blocks that may be announced, inside reserved blocks.
{"192.0.0.9/32", ""},
{"2001:4:112::/48", ""},
// Blocks that may be announced, inside no reserved block.
{"192.175.48.0/24", ""},
{"2002::/16", ""},
// A prefix that holds a reserved block is not inside it.
{"192.0.0.0/16", ""},
{"0.0.0.0/0", ""},
// Prefixes anyone may announce.
{"8.8.8.0/24", ""},
{"2001:4860::/32", ""},
}
for _, tc := range tests {
t.Run(tc.prefix, func(t *testing.T) {
t.Parallel()
reason, reserved := bogon.Prefix(netip.MustParsePrefix(tc.prefix))
if reason != tc.want || reserved != (tc.want != "") {
t.Errorf("Prefix(%s) = %q, %v; want %q", tc.prefix, reason,
reserved, tc.want)
}
})
}
}
func TestAddr(t *testing.T) {
t.Parallel()
tests := []struct {
addr string
// want is why the address is reserved, or "" when it is not.
want string
}{
{"10.0.0.1", privateUseTen},
{"fd00::1", "Unique-Local (fc00::/7)"},
// An IPv4 address written in IPv6 form counts as the IPv4 address.
{"::ffff:10.0.0.1", privateUseTen},
{"::ffff:8.8.8.8", ""},
// An address that may be announced, inside a reserved block.
{"192.0.0.9", ""},
// Addresses anyone may announce.
{"8.8.8.8", ""},
{"2001:4860:4860::8888", ""},
}
for _, tc := range tests {
t.Run(tc.addr, func(t *testing.T) {
t.Parallel()
reason, reserved := bogon.Addr(netip.MustParseAddr(tc.addr))
if reason != tc.want || reserved != (tc.want != "") {
t.Errorf("Addr(%s) = %q, %v; want %q", tc.addr, reason,
reserved, tc.want)
}
})
}
}
func TestASN(t *testing.T) {
t.Parallel()
tests := []struct {
asn int
// want is why the AS number is reserved, or "" when it is not.
want string
}{
{23456, "AS_TRANS (AS23456)"},
{64496, "Documentation (AS64496-AS64511)"},
{64512, "Private-Use (AS64512-AS65534)"},
{65534, "Private-Use (AS64512-AS65534)"},
{65535, "Last 16-bit AS number (AS65535)"},
{65551, "Documentation (AS65536-AS65551)"},
{4200000000, "Private-Use (AS4200000000-AS4294967294)"},
{4294967295, "Last 32-bit AS number (AS4294967295)"},
// AS 0 means no known origin, and the AS112 project uses AS 112.
{0, ""},
{112, ""},
// Not handed out yet, which is not counted.
{65552, ""},
{15169, ""},
{64495, ""},
}
for _, tc := range tests {
t.Run(strconv.Itoa(tc.asn), func(t *testing.T) {
t.Parallel()
reason, reserved := bogon.ASN(tc.asn)
if reason != tc.want || reserved != (tc.want != "") {
t.Errorf("ASN(%d) = %q, %v; want %q", tc.asn, reason, reserved,
tc.want)
}
})
}
}
internal/cachedb/cachedb.go
+51
View File
@@ -0,0 +1,51 @@
// Package cachedb opens cache.db, the SQLite file in the state directory that
// holds RouteWatch's caches of answers from outside services. It is separate
// from the routes database so that a cache write never queues behind a write
// to that database.
package cachedb
import (
"context"
"database/sql"
_ "embed" // for schema.sql
"fmt"
"path/filepath"
_ "github.com/mattn/go-sqlite3" // CGO SQLite driver
)
const (
// fileName is the database's file in the state directory.
fileName = "cache.db"
// busyTimeoutMs is how long a write waits for another write to finish.
busyTimeoutMs = 5000
)
//go:embed schema.sql
var schema string
// Open opens cache.db in stateDir, creating the file and its tables when they
// do not exist. The caller closes the database.
func Open(ctx context.Context, stateDir string) (*sql.DB, error) {
dsn := fmt.Sprintf(
"file:%s?_journal_mode=WAL&_synchronous=NORMAL&_busy_timeout=%d"+
"&_txlock=immediate",
filepath.Join(stateDir, fileName),
busyTimeoutMs,
)
db, err := sql.Open("sqlite3", dsn)
if err != nil {
return nil, fmt.Errorf("opening the cache database: %w", err)
}
_, err = db.ExecContext(ctx, schema)
if err != nil {
_ = db.Close()
return nil, fmt.Errorf("creating the cache database's tables: %w", err)
}
return db, nil
}
internal/cachedb/cachedb_internal_test.go
+64
View File
@@ -0,0 +1,64 @@
package cachedb
import (
"os"
"path/filepath"
"testing"
)
// TestOpenCreatesTheFileInWALMode opens a new database, and then opens it
// again, as a restart does.
func TestOpenCreatesTheFileInWALMode(t *testing.T) {
t.Parallel()
dir := t.TempDir()
for range 2 {
db, err := Open(t.Context(), dir)
if err != nil {
t.Fatalf("Open: %v", err)
}
var mode string
err = db.QueryRowContext(t.Context(), "PRAGMA journal_mode").Scan(&mode)
if err != nil {
t.Fatalf("reading the journal mode: %v", err)
}
if mode != "wal" {
t.Errorf("journal mode %q, want wal", mode)
}
var rows int
err = db.QueryRowContext(t.Context(),
"SELECT COUNT(*) FROM hostnames").Scan(&rows)
if err != nil {
t.Fatalf("reading the hostnames table: %v", err)
}
err = db.Close()
if err != nil {
t.Fatalf("Close: %v", err)
}
}
_, err := os.Stat(filepath.Join(dir, fileName))
if err != nil {
t.Errorf("the file is not in the state directory: %v", err)
}
}
// TestOpenFailsWhenTheDirectoryDoesNotExist checks that a state directory that
// is not there is reported, not ignored.
func TestOpenFailsWhenTheDirectoryDoesNotExist(t *testing.T) {
t.Parallel()
db, err := Open(t.Context(), filepath.Join(t.TempDir(), "missing"))
if err == nil {
_ = db.Close()
t.Fatal("Open succeeded in a directory that does not exist")
}
}
internal/cachedb/schema.sql
+24
View File
@@ -0,0 +1,24 @@
-- hostnames holds the PTR names of addresses. names has the names separated by
-- spaces, and is empty for an address with no PTR names. expires_at is in
-- seconds since 1970.
CREATE TABLE IF NOT EXISTS hostnames (
address TEXT PRIMARY KEY,
names TEXT NOT NULL,
expires_at INTEGER NOT NULL
);
-- geolocations holds the answers of geojs. A part geojs does not know is NULL.
-- fetched_at is in seconds since 1970.
CREATE TABLE IF NOT EXISTS geolocations (
address TEXT PRIMARY KEY,
country_code TEXT,
country TEXT,
continent_code TEXT,
region TEXT,
city TEXT,
latitude REAL,
longitude REAL,
accuracy_radius_km INTEGER,
time_zone TEXT,
fetched_at INTEGER NOT NULL
);
internal/config/config.go
+22 -4
View File
@@ -30,6 +30,14 @@ const (
maxPort = 65535 maxPort = 65535
) )
// The private address ranges of RFC 1918. The HTTP server trusts a reverse
// proxy in any of them when TRUSTED_PROXIES is not set.
const (
privateRange10 = "10.0.0.0/8"
privateRange172 = "172.16.0.0/12"
privateRange192 = "192.168.0.0/16"
)
var ( var (
errRelativeXDGDataHome = errors.New("XDG_DATA_HOME must be an absolute path") errRelativeXDGDataHome = errors.New("XDG_DATA_HOME must be an absolute path")
errUnsupportedOS = errors.New("unsupported operating system") errUnsupportedOS = errors.New("unsupported operating system")
@@ -159,11 +167,21 @@ func getPort() (int, error) {
return int(port), nil return int(port), nil
} }
// getTrustedProxies returns the addresses and CIDR ranges listed in // getTrustedProxies returns the reverse proxies the HTTP server trusts. When
// TRUSTED_PROXIES, such as "10.0.0.0/8,192.0.2.1", or none when it is not set. // TRUSTED_PROXIES is not set, they are the private ranges of RFC 1918. When it
// An address is returned as a range holding only that address. // is set, they are the addresses and CIDR ranges it lists, such as
// "10.0.0.0/8,192.0.2.1", and none when it is empty. An address is returned as
// a range holding only that address.
func getTrustedProxies() ([]netip.Prefix, error) { func getTrustedProxies() ([]netip.Prefix, error) {
value := os.Getenv("TRUSTED_PROXIES") value, set := os.LookupEnv("TRUSTED_PROXIES")
if !set {
return []netip.Prefix{
netip.MustParsePrefix(privateRange10),
netip.MustParsePrefix(privateRange172),
netip.MustParsePrefix(privateRange192),
}, nil
}
if value == "" { if value == "" {
return nil, nil return nil, nil
} }
internal/config/config_internal_test.go
+40 -5
View File
@@ -2,6 +2,7 @@ package config
import ( import (
"net/netip" "net/netip"
"os"
"runtime" "runtime"
"slices" "slices"
"testing" "testing"
@@ -46,25 +47,47 @@ func TestNewRefusesInvalidPort(t *testing.T) {
} }
} }
func TestNewReadsTrustedProxies(t *testing.T) { // TestNewTrustsPrivateRangesByDefault checks that with TRUSTED_PROXIES unset
// the trusted proxies are the private ranges of RFC 1918. Before the fix no
// proxy was trusted, so a reverse proxy at a private address was taken for the
// client (https://git.eeqj.de/sneak/routewatch/issues/198).
func TestNewTrustsPrivateRangesByDefault(t *testing.T) {
t.Setenv("PORT", "") t.Setenv("PORT", "")
t.Setenv("XDG_DATA_HOME", "") t.Setenv("XDG_DATA_HOME", "")
// t.Setenv puts the variable back when the test ends.
t.Setenv("TRUSTED_PROXIES", "") t.Setenv("TRUSTED_PROXIES", "")
err := os.Unsetenv("TRUSTED_PROXIES")
if err != nil {
t.Fatal(err)
}
cfg, err := New() cfg, err := New()
if err != nil { if err != nil {
t.Fatalf("New() without TRUSTED_PROXIES: %v", err) t.Fatalf("New() without TRUSTED_PROXIES: %v", err)
} }
if len(cfg.TrustedProxies) != 0 { want := []netip.Prefix{
t.Errorf("New() without TRUSTED_PROXIES: TrustedProxies = %v, want none", netip.MustParsePrefix("10.0.0.0/8"),
cfg.TrustedProxies) netip.MustParsePrefix("172.16.0.0/12"),
netip.MustParsePrefix("192.168.0.0/16"),
} }
if !slices.Equal(cfg.TrustedProxies, want) {
t.Errorf("New() without TRUSTED_PROXIES: TrustedProxies = %v, want %v",
cfg.TrustedProxies, want)
}
}
// TestNewReadsTrustedProxies checks that a list in TRUSTED_PROXIES replaces
// the default, and that TRUSTED_PROXIES set but empty trusts no proxy.
func TestNewReadsTrustedProxies(t *testing.T) {
t.Setenv("PORT", "")
t.Setenv("XDG_DATA_HOME", "")
t.Setenv("TRUSTED_PROXIES", "10.0.0.0/8, 192.0.2.1,2001:db8::/32") t.Setenv("TRUSTED_PROXIES", "10.0.0.0/8, 192.0.2.1,2001:db8::/32")
cfg, err = New() cfg, err := New()
if err != nil { if err != nil {
t.Fatalf("New() with TRUSTED_PROXIES: %v", err) t.Fatalf("New() with TRUSTED_PROXIES: %v", err)
} }
@@ -77,6 +100,18 @@ func TestNewReadsTrustedProxies(t *testing.T) {
if !slices.Equal(cfg.TrustedProxies, want) { if !slices.Equal(cfg.TrustedProxies, want) {
t.Errorf("TrustedProxies = %v, want %v", cfg.TrustedProxies, want) t.Errorf("TrustedProxies = %v, want %v", cfg.TrustedProxies, want)
} }
t.Setenv("TRUSTED_PROXIES", "")
cfg, err = New()
if err != nil {
t.Fatalf("New() with TRUSTED_PROXIES set but empty: %v", err)
}
if len(cfg.TrustedProxies) != 0 {
t.Errorf("New() with TRUSTED_PROXIES set but empty: TrustedProxies = %v, "+
"want none", cfg.TrustedProxies)
}
} }
func TestNewRefusesInvalidTrustedProxies(t *testing.T) { func TestNewRefusesInvalidTrustedProxies(t *testing.T) {
internal/database/database.go
+51
View File
@@ -972,6 +972,34 @@ func (d *Database) GetAS(ctx context.Context, asn int) (*ASN, bool, error) {
return &asnInfo, true, nil return &asnInfo, true, nil
} }
// The queries of GetLastSeenASes. The index on last_seen answers each without
// reading the whole table.
const (
newestLastSeenASQuery = `
SELECT asn, handle, description, first_seen, last_seen
FROM asns ORDER BY last_seen DESC LIMIT 1`
oldestLastSeenASQuery = `
SELECT asn, handle, description, first_seen, last_seen
FROM asns ORDER BY last_seen ASC LIMIT 1`
)
// GetLastSeenASes returns two ASes of the asns table, with their handles,
// descriptions and seen times: the one last seen most recently, and the one
// last seen longest ago. Both are nil when the table holds no AS.
func (d *Database) GetLastSeenASes(ctx context.Context) (*ASN, *ASN, error) {
newest, found, err := d.readOneAS(ctx, newestLastSeenASQuery)
if err != nil || !found {
return nil, nil, err
}
oldest, _, err := d.readOneAS(ctx, oldestLastSeenASQuery)
if err != nil {
return nil, nil, err
}
return newest, oldest, nil
}
// asWHOISQuery reads the handle, description and WHOIS details of one AS, and // asWHOISQuery reads the handle, description and WHOIS details of one AS, and
// when the WHOIS details were fetched. // when the WHOIS details were fetched.
const asWHOISQuery = ` const asWHOISQuery = `
@@ -1379,6 +1407,29 @@ func (d *Database) Ping(ctx context.Context) error {
return nil return nil
} }
// readOneAS returns the AS that query reads, and whether it read one.
func (d *Database) readOneAS(ctx context.Context, query string) (*ASN, bool, error) {
var (
asnInfo ASN
handle, description sql.NullString
)
err := d.db.QueryRowContext(ctx, query).Scan(&asnInfo.ASN, &handle,
&description, &asnInfo.FirstSeen, &asnInfo.LastSeen)
if errors.Is(err, sql.ErrNoRows) {
return nil, false, nil
}
if err != nil {
return nil, false, fmt.Errorf("failed to query AS by last seen: %w", err)
}
asnInfo.Handle = handle.String
asnInfo.Description = description.String
return &asnInfo, true, nil
}
// truncateWAL runs the TRUNCATE checkpoint of Checkpoint on a WAL file of // truncateWAL runs the TRUNCATE checkpoint of Checkpoint on a WAL file of
// walBytes, with the writing connection's busy timeout lowered to // walBytes, with the writing connection's busy timeout lowered to
// truncateBusyTimeoutMs for it, and logs how long it took. The caller holds the // truncateBusyTimeoutMs for it, and logs how long it took. The caller holds the
internal/database/database_internal_test.go
+82 -6
View File
@@ -72,17 +72,34 @@ const (
// lockTestPrefix is the prefix the batch writes in the checkpoint tests // lockTestPrefix is the prefix the batch writes in the checkpoint tests
// store. // store.
lockTestPrefix = "192.0.2.0/24" lockTestPrefix = "192.0.2.0/24"
// longBusyTimeoutMs is the busy timeout setLongBusyTimeout gives the
// writing connection. A checkpoint that waits for an open read takes this
// long.
longBusyTimeoutMs = 30000
// readerCheckpointLimit is how long a checkpoint, and a batch write // readerCheckpointLimit is how long a checkpoint, and a batch write
// waiting for it, may take while a reader is open: well under the busy // waiting for it, may take while a reader is open: well under
// timeout, which a checkpoint that waits for the reader takes. // longBusyTimeoutMs, with room for a stall on a busy host.
readerCheckpointLimit = time.Second readerCheckpointLimit = 15 * time.Second
// truncateCheckpointLimit is how long a checkpoint of a WAL file over // truncateCheckpointLimit is how long a checkpoint of a WAL file over
// sqliteWALSizeLimitBytes may take to give up while a reader is open: its // sqliteWALSizeLimitBytes may take to give up while a reader is open: its
// wait for the reader plus a second, well under the busy timeout. // wait for the reader plus readerCheckpointLimit.
truncateCheckpointLimit = truncateBusyTimeoutMs*time.Millisecond + truncateCheckpointLimit = truncateBusyTimeoutMs*time.Millisecond +
time.Second readerCheckpointLimit
) )
// setLongBusyTimeout gives the writing connection of db longBusyTimeoutMs, so
// that a checkpoint that waits for an open read takes far longer than a stall
// on a busy host.
func setLongBusyTimeout(ctx context.Context, t *testing.T, db *Database) {
t.Helper()
_, err := db.writer.ExecContext(ctx,
fmt.Sprintf("PRAGMA busy_timeout=%d", longBusyTimeoutMs))
if err != nil {
t.Fatalf("failed to set the busy timeout: %v", err)
}
}
// TestConnectionPoolPragmas holds several pooled connections open at once and // TestConnectionPoolPragmas holds several pooled connections open at once and
// checks each one carries the per-connection settings from the DSN, plus the // checks each one carries the per-connection settings from the DSN, plus the
// process-wide heap limits, and sees the new file with auto_vacuum // process-wide heap limits, and sees the new file with auto_vacuum
@@ -273,7 +290,7 @@ func TestVacuumReturnsFreePages(t *testing.T) {
writeTableChanges(t, db, table) writeTableChanges(t, db, table)
// The peer going down removes every prefix, and so every row. // The peer going down removes every prefix, and so every row.
table.PeerDown(peerA) table.PeersDown([]string{peerA})
writeTableChanges(t, db, table) writeTableChanges(t, db, table)
var before int var before int
@@ -579,6 +596,8 @@ func TestCheckpointDoesNotWaitForReader(t *testing.T) {
ctx := context.Background() ctx := context.Background()
ts := time.Now().UTC() ts := time.Now().UTC()
setLongBusyTimeout(ctx, t, db)
err = db.UpdatePrefixesBatch(map[string]time.Time{"198.51.100.0/24": ts}) err = db.UpdatePrefixesBatch(map[string]time.Time{"198.51.100.0/24": ts})
if err != nil { if err != nil {
t.Fatalf("failed to store the prefix the reader reads: %v", err) t.Fatalf("failed to store the prefix the reader reads: %v", err)
@@ -690,6 +709,7 @@ func TestCheckpointEmptiesWALOnceNoReadIsOpen(t *testing.T) {
} }
fillWALPastLimit(ctx, t, db) fillWALPastLimit(ctx, t, db)
setLongBusyTimeout(ctx, t, db)
started := time.Now() started := time.Now()
@@ -1003,6 +1023,62 @@ func TestGetASReadsTheRecordOrTheBuiltInList(t *testing.T) {
} }
} }
// TestGetLastSeenASes stores three ASes, each last seen at another time, and
// expects the one last seen most recently and the one last seen longest ago.
// An empty asns table gives neither.
func TestGetLastSeenASes(t *testing.T) {
t.Parallel()
db, err := New(&config.Config{StateDir: t.TempDir()}, logger.New())
if err != nil {
t.Fatalf("failed to create database: %v", err)
}
defer func() { _ = db.Close() }()
newest, oldest, err := db.GetLastSeenASes(t.Context())
if err != nil || newest != nil || oldest != nil {
t.Fatalf("GetLastSeenASes() on an empty table = %+v, %+v, %v; want "+
"neither", newest, oldest, err)
}
const (
newestASN = 13335
middleASN = 15169
oldestASN = 3
)
start := time.Date(2026, 1, 2, 3, 4, 5, 0, time.UTC)
err = db.GetOrCreateASNBatch(map[int]SeenTimes{
middleASN: {First: start, Last: start.Add(time.Hour)},
newestASN: {First: start, Last: start.Add(2 * time.Hour)},
oldestASN: {First: start, Last: start.Add(time.Minute)},
})
if err != nil {
t.Fatalf("GetOrCreateASNBatch: %v", err)
}
newest, oldest, err = db.GetLastSeenASes(t.Context())
if err != nil {
t.Fatalf("GetLastSeenASes: %v", err)
}
listed, _ := asinfo.Get(newestASN)
if newest == nil || newest.ASN != newestASN ||
!newest.LastSeen.Equal(start.Add(2*time.Hour)) ||
newest.Description != listed.Description {
t.Errorf("newest = %+v, want AS%d (%s) last seen %v", newest, newestASN,
listed.Description, start.Add(2*time.Hour))
}
if oldest == nil || oldest.ASN != oldestASN ||
!oldest.LastSeen.Equal(start.Add(time.Minute)) {
t.Errorf("oldest = %+v, want AS%d last seen %v", oldest, oldestASN,
start.Add(time.Minute))
}
}
// TestGetASWHOISReadsTheStoredDetails stores an AS with WHOIS details and asks // TestGetASWHOISReadsTheStoredDetails stores an AS with WHOIS details and asks
// GetASWHOIS for it and for an AS the asns table does not hold. The first gets // GetASWHOIS for it and for an AS the asns table does not hold. The first gets
// its stored handle, description and details, and the time they were fetched. // its stored handle, description and details, and the time they were fetched.
internal/database/interface.go
+12 -2
View File
@@ -1,6 +1,7 @@
// Package database provides SQLite storage for BGP routing data: ASNs, // Package database provides SQLite storage for BGP routing data: ASNs,
// prefixes, announcements, peerings and BGP peers. Its routes table holds a // prefixes, announcements, peerings, BGP peers and origin changes. Its routes
// copy of the whole routing table that internal/routetable keeps in memory. // table holds a copy of the whole routing table that internal/routetable
// keeps in memory.
package database package database
import ( import (
@@ -55,6 +56,14 @@ type Store interface {
WriteRouteChanges(changes []routetable.Change, newPeers map[string]uint) error WriteRouteChanges(changes []routetable.Change, newPeers map[string]uint) error
ReadRouteTable(ctx context.Context) (*routetable.Table, error) ReadRouteTable(ctx context.Context) (*routetable.Table, error)
// Origin change operations: the prefix and origin AS pairs' first and
// last peers, as the routing table records them.
WriteOriginChanges(changes []routetable.OriginChange) error
GetOriginChanges(
ctx context.Context, prefix netip.Prefix, limit int,
) ([]routetable.OriginChange, error)
PruneOriginChanges(ctx context.Context) error
// ASN WHOIS operations // ASN WHOIS operations
GetNextStaleASN(ctx context.Context, staleThreshold time.Duration) (int, error) GetNextStaleASN(ctx context.Context, staleThreshold time.Duration) (int, error)
UpdateASNWHOIS(ctx context.Context, update *ASNWHOISUpdate) error UpdateASNWHOIS(ctx context.Context, update *ASNWHOISUpdate) error
@@ -62,6 +71,7 @@ type Store interface {
// AS and prefix detail operations // AS and prefix detail operations
GetAS(ctx context.Context, asn int) (*ASN, bool, error) GetAS(ctx context.Context, asn int) (*ASN, bool, error)
GetLastSeenASes(ctx context.Context) (*ASN, *ASN, error)
GetASWHOIS(ctx context.Context, asn int) (*ASN, error) GetASWHOIS(ctx context.Context, asn int) (*ASN, error)
GetPrefixFirstSeen(ctx context.Context, prefix netip.Prefix) (time.Time, error) GetPrefixFirstSeen(ctx context.Context, prefix netip.Prefix) (time.Time, error)
GetASPeers(asn int) ([]ASPeer, error) GetASPeers(asn int) ([]ASPeer, error)
internal/database/originchanges.go
+172
View File
@@ -0,0 +1,172 @@
package database
import (
"context"
"fmt"
"net/netip"
"time"
"git.eeqj.de/sneak/routewatch/internal/routetable"
)
// minOriginChangesPerPrefix is how many of a prefix's newest origin changes
// the prune always keeps, whatever their age.
const minOriginChangesPerPrefix = 500
// originChangesRetention is how long the prune keeps an origin change: rows
// older than this are deleted, unless they are among the prefix's newest
// minOriginChangesPerPrefix.
const originChangesRetention = 72 * time.Hour
// The statements of the origin_changes table (schema.sql).
const (
insertOriginChangeSQL = `INSERT INTO origin_changes
(prefix, origin_asn, announced, peer_count, time)
VALUES (?, ?, ?, ?, ?)`
originChangesSQL = `SELECT prefix, origin_asn, announced, peer_count, time
FROM origin_changes WHERE prefix = ? ORDER BY id DESC LIMIT ?`
prunePrefixesSQL = `SELECT prefix FROM origin_changes
GROUP BY prefix HAVING COUNT(*) > ?`
pruneOriginChangesSQL = `DELETE FROM origin_changes
WHERE prefix = ? AND time < ? AND id < (
SELECT id FROM origin_changes WHERE prefix = ?
ORDER BY id DESC LIMIT 1 OFFSET ?)`
)
// WriteOriginChanges writes, in one transaction, the origin changes the
// routing table handed over. When it fails, it writes nothing; the caller then
// writes them again.
func (d *Database) WriteOriginChanges(changes []routetable.OriginChange) error {
if len(changes) == 0 {
return nil
}
d.lock("WriteOriginChanges")
defer d.unlock()
tx, err := d.beginTx()
if err != nil {
return fmt.Errorf("failed to begin transaction: %w", err)
}
defer d.rollback(tx)
ctx := context.Background()
stmt, err := tx.PrepareContext(ctx, insertOriginChangeSQL)
if err != nil {
return fmt.Errorf("failed to prepare origin change insert: %w", err)
}
defer func() { _ = stmt.Close() }()
for _, change := range changes {
_, err := stmt.ExecContext(ctx, change.Prefix.String(),
change.OriginASN, change.Announced, change.PeerCount,
change.Time.Unix())
if err != nil {
return fmt.Errorf("failed to write origin change %s: %w",
change.Prefix, err)
}
}
err = tx.Commit()
if err != nil {
return fmt.Errorf("failed to commit transaction: %w", err)
}
return nil
}
// GetOriginChanges returns at most limit of prefix's origin changes, newest
// first.
func (d *Database) GetOriginChanges(
ctx context.Context, prefix netip.Prefix, limit int,
) ([]routetable.OriginChange, error) {
rows, err := d.db.QueryContext(ctx, originChangesSQL,
prefix.Masked().String(), limit)
if err != nil {
return nil, fmt.Errorf("failed to read origin changes: %w", err)
}
defer func() { _ = rows.Close() }()
var changes []routetable.OriginChange
for rows.Next() {
var (
change routetable.OriginChange
prefixText string
timeSec int64
)
err := rows.Scan(&prefixText, &change.OriginASN, &change.Announced,
&change.PeerCount, &timeSec)
if err != nil {
return nil, fmt.Errorf("failed to read an origin change: %w", err)
}
change.Prefix, err = netip.ParsePrefix(prefixText)
if err != nil {
return nil, fmt.Errorf("failed to read origin change %s: %w",
prefixText, err)
}
change.Time = time.Unix(timeSec, 0).UTC()
changes = append(changes, change)
}
err = rows.Err()
if err != nil {
return nil, fmt.Errorf("failed to read origin changes: %w", err)
}
return changes, nil
}
// PruneOriginChanges deletes, for each prefix with more than
// minOriginChangesPerPrefix rows, the rows older than originChangesRetention
// that are not among its newest minOriginChangesPerPrefix. It finds those
// prefixes on a reading connection and deletes one prefix per write, so no
// write holds the lock for long.
func (d *Database) PruneOriginChanges(ctx context.Context) error {
rows, err := d.db.QueryContext(ctx, prunePrefixesSQL,
minOriginChangesPerPrefix)
if err != nil {
return fmt.Errorf("failed to find prefixes to prune: %w", err)
}
defer func() { _ = rows.Close() }()
var prefixes []string
for rows.Next() {
var prefix string
err := rows.Scan(&prefix)
if err != nil {
return fmt.Errorf("failed to read a prefix to prune: %w", err)
}
prefixes = append(prefixes, prefix)
}
err = rows.Err()
if err != nil {
return fmt.Errorf("failed to find prefixes to prune: %w", err)
}
cutoff := time.Now().Add(-originChangesRetention).Unix()
for _, prefix := range prefixes {
d.lock("PruneOriginChanges")
_, err := d.writer.ExecContext(ctx, pruneOriginChangesSQL,
prefix, cutoff, prefix, minOriginChangesPerPrefix-1)
d.unlock()
if err != nil {
return fmt.Errorf("failed to prune origin changes of %s: %w",
prefix, err)
}
}
return nil
}
internal/database/originchanges_internal_test.go
+217
View File
@@ -0,0 +1,217 @@
package database
import (
"net/netip"
"reflect"
"testing"
"time"
"git.eeqj.de/sneak/routewatch/internal/routetable"
)
// TestOriginChangesWriteThenRead writes three origin changes and reads them
// back newest first, honouring the limit.
func TestOriginChangesWriteThenRead(t *testing.T) {
t.Parallel()
db := newRoutesTestDatabase(t)
prefix := netip.MustParsePrefix(tablePrefixV4)
changes := []routetable.OriginChange{
{Prefix: prefix, OriginASN: asA, Announced: true, PeerCount: 1,
Time: tableTime(10)},
{Prefix: prefix, OriginASN: asA, Announced: false, PeerCount: 0,
Time: tableTime(20)},
{Prefix: prefix, OriginASN: asB, Announced: true, PeerCount: 1,
Time: tableTime(30)},
}
err := db.WriteOriginChanges(changes)
if err != nil {
t.Fatalf("WriteOriginChanges: %v", err)
}
got, err := db.GetOriginChanges(t.Context(), prefix, 2)
if err != nil {
t.Fatalf("GetOriginChanges: %v", err)
}
want := []routetable.OriginChange{
{Prefix: prefix, OriginASN: asB, Announced: true, PeerCount: 1,
Time: tableTime(30)},
{Prefix: prefix, OriginASN: asA, Announced: false, PeerCount: 0,
Time: tableTime(20)},
}
if !reflect.DeepEqual(got, want) {
t.Errorf("GetOriginChanges = %+v, want %+v", got, want)
}
}
// TestOriginChangesPrune checks that the prune keeps, for a prefix with more
// than 500 rows, its newest 500 rows and every row newer than 72 hours, and
// deletes the rest. It checks which rows survive by their times, not only how
// many.
func TestOriginChangesPrune(t *testing.T) {
t.Parallel()
db := newRoutesTestDatabase(t)
oldPrefix := netip.MustParsePrefix(tablePrefixV4)
straddling := netip.MustParsePrefix(tablePrefixShortV4)
busy := netip.MustParsePrefix(tablePrefixBusyV4)
other := netip.MustParsePrefix("10.20.0.0/16")
// Whole seconds, so the stored times round-trip exactly.
now := time.Now().Truncate(time.Second)
// 600 rows for oldPrefix, all older than 72 hours, oldest first. The
// prune keeps the newest 500 and deletes the oldest 100.
changes := rows(oldPrefix, now.Add(-100*time.Hour), 600)
// 600 rows for straddling: 400 older than 72 hours, then 200 newer. The
// prune keeps all 200 newer and the newest 300 of the 400 older.
changes = append(changes, rows(straddling, now.Add(-100*time.Hour), 400)...)
changes = append(changes, rows(straddling, now.Add(-71*time.Hour), 200)...)
// 100 rows older than 72 hours and minOriginChangesPerPrefix+100 newer
// rows for busy. The prune keeps all the newer rows and none of the older,
// because the newer rows alone are more than minOriginChangesPerPrefix.
changes = append(changes, rows(busy, now.Add(-100*time.Hour), 100)...)
changes = append(changes, rows(busy, now.Add(-71*time.Hour),
minOriginChangesPerPrefix+100)...)
// One row for other, which the prune leaves alone.
changes = append(changes, rows(other, now.Add(-100*time.Hour), 1)...)
err := db.WriteOriginChanges(changes)
if err != nil {
t.Fatalf("WriteOriginChanges: %v", err)
}
err = db.PruneOriginChanges(t.Context())
if err != nil {
t.Fatalf("PruneOriginChanges: %v", err)
}
// The newest row survives, and the oldest survivor is the 100th oldest,
// so a prune that kept the oldest 500 instead would fail.
checkSurvivors(t, db, oldPrefix, 500,
now.Add(-100*time.Hour).Add(599*time.Minute),
now.Add(-100*time.Hour).Add(100*time.Minute))
// The newest of the newer-than-72-hours rows survives, and the oldest
// survivor is the 100th oldest of the older-than-72-hours rows.
checkSurvivors(t, db, straddling, 500,
now.Add(-71*time.Hour).Add(199*time.Minute),
now.Add(-100*time.Hour).Add(100*time.Minute))
// Every newer-than-72-hours row survives, so the oldest survivor is the
// first of them and the newest is minOriginChangesPerPrefix+99 minutes
// after it.
checkSurvivors(t, db, busy, minOriginChangesPerPrefix+100,
now.Add(-71*time.Hour).
Add(time.Duration(minOriginChangesPerPrefix+99)*time.Minute),
now.Add(-71*time.Hour))
gotOther, err := db.GetOriginChanges(t.Context(), other, 10)
if err != nil {
t.Fatalf("GetOriginChanges: %v", err)
}
if len(gotOther) != 1 {
t.Errorf("GetOriginChanges(other) = %d rows, want 1", len(gotOther))
}
}
// rows returns n origin changes for prefix, at times from plus one minute per
// step, oldest first.
func rows(prefix netip.Prefix, from time.Time, n int) []routetable.OriginChange {
changes := make([]routetable.OriginChange, 0, n)
for i := range n {
changes = append(changes, routetable.OriginChange{
Prefix: prefix, OriginASN: asA, Announced: true, PeerCount: 1,
Time: from.Add(time.Duration(i) * time.Minute),
})
}
return changes
}
// survivorTimes returns the times of prefix's rows after the prune, newest
// first.
func survivorTimes(
t *testing.T, db *Database, prefix netip.Prefix, limit int,
) []time.Time {
t.Helper()
rows, err := db.GetOriginChanges(t.Context(), prefix, limit)
if err != nil {
t.Fatalf("GetOriginChanges: %v", err)
}
times := make([]time.Time, len(rows))
for i, row := range rows {
times[i] = row.Time
}
return times
}
// checkSurvivors checks that prefix kept exactly wantCount rows, with the
// newest survivor at wantNewest and the oldest at wantOldest.
func checkSurvivors(
t *testing.T, db *Database, prefix netip.Prefix,
wantCount int, wantNewest, wantOldest time.Time,
) {
t.Helper()
times := survivorTimes(t, db, prefix, wantCount+1)
if len(times) != wantCount {
t.Errorf("GetOriginChanges(%s) = %d rows, want %d",
prefix, len(times), wantCount)
return
}
if !times[0].Equal(wantNewest) {
t.Errorf("the newest surviving row's time = %v, want %v",
times[0], wantNewest)
}
if !times[wantCount-1].Equal(wantOldest) {
t.Errorf("the oldest surviving row's time = %v, want %v",
times[wantCount-1], wantOldest)
}
}
// TestOriginChangesSurviveRouteDeletion checks that deleting a routes row
// leaves the prefix's origin_changes rows.
func TestOriginChangesSurviveRouteDeletion(t *testing.T) {
t.Parallel()
db := newRoutesTestDatabase(t)
prefix := netip.MustParsePrefix(tablePrefixV4)
err := db.WriteOriginChanges([]routetable.OriginChange{{
Prefix: prefix, OriginASN: asA, Announced: true, PeerCount: 1,
Time: tableTime(10),
}})
if err != nil {
t.Fatalf("WriteOriginChanges: %v", err)
}
// Write a route, then delete it.
table := routetable.New(routetable.Params{})
announceTo(table, tablePrefixV4, asA, peerA, 10)
writeTableChanges(t, db, table)
table.Withdraw(prefix, peerA)
writeTableChanges(t, db, table)
got, err := db.GetOriginChanges(t.Context(), prefix, 10)
if err != nil {
t.Fatalf("GetOriginChanges: %v", err)
}
if len(got) != 1 {
t.Errorf("GetOriginChanges = %d rows, want 1", len(got))
}
}
internal/database/routes_internal_test.go
+3 -2
View File
@@ -34,6 +34,7 @@ const (
tablePrefixV4 = "10.1.2.0/24" tablePrefixV4 = "10.1.2.0/24"
tablePrefixShortV4 = "10.9.0.0/16" tablePrefixShortV4 = "10.9.0.0/16"
tablePrefixBusyV4 = "10.10.0.0/16"
tablePrefixV6 = "2001:db8:1::/48" tablePrefixV6 = "2001:db8:1::/48"
) )
@@ -107,7 +108,7 @@ func TestReadRouteTableGivesBackWhatWasWritten(t *testing.T) {
// A peer moves to another origin, one goes down and a new one comes. // A peer moves to another origin, one goes down and a new one comes.
announceTo(source, tablePrefixV4, asB, peerA, 60) announceTo(source, tablePrefixV4, asB, peerA, 60)
source.PeerDown(peerC) source.PeersDown([]string{peerC})
announceTo(source, tablePrefixV6, asB, peerE, 70) announceTo(source, tablePrefixV6, asB, peerE, 70)
writeTableChanges(t, db, source) writeTableChanges(t, db, source)
@@ -133,7 +134,7 @@ func TestReadRouteTableGivesATableThatTakesLaterUpdates(t *testing.T) {
// another one goes down, and a new peer comes. // another one goes down, and a new peer comes.
for _, table := range []*routetable.Table{source, read} { for _, table := range []*routetable.Table{source, read} {
table.Withdraw(netip.MustParsePrefix(tablePrefixV4), peerA) table.Withdraw(netip.MustParsePrefix(tablePrefixV4), peerA)
table.PeerDown(peerB) table.PeersDown([]string{peerB})
announceTo(table, tablePrefixShortV4, asB, peerD, 50) announceTo(table, tablePrefixShortV4, asB, peerD, 50)
} }
internal/database/schema.sql
+20 -1
View File
@@ -83,6 +83,9 @@ CREATE INDEX IF NOT EXISTS idx_peerings_lookup ON peerings(as_a, as_b);
-- Indexes for asns table -- Indexes for asns table
CREATE INDEX IF NOT EXISTS idx_asns_asn ON asns(asn); CREATE INDEX IF NOT EXISTS idx_asns_asn ON asns(asn);
CREATE INDEX IF NOT EXISTS idx_asns_whois_updated_at ON asns(whois_updated_at); CREATE INDEX IF NOT EXISTS idx_asns_whois_updated_at ON asns(whois_updated_at);
-- Finds the AS last seen most recently and the one last seen longest ago, for
-- the home page.
CREATE INDEX IF NOT EXISTS idx_asns_last_seen ON asns(last_seen);
-- Indexes for bgp_peers table -- Indexes for bgp_peers table
CREATE INDEX IF NOT EXISTS idx_bgp_peers_asn ON bgp_peers(peer_asn); CREATE INDEX IF NOT EXISTS idx_bgp_peers_asn ON bgp_peers(peer_asn);
@@ -116,4 +119,20 @@ CREATE TABLE IF NOT EXISTS routes (
CREATE TABLE IF NOT EXISTS route_peers ( CREATE TABLE IF NOT EXISTS route_peers (
number INTEGER PRIMARY KEY, number INTEGER PRIMARY KEY,
address TEXT NOT NULL UNIQUE address TEXT NOT NULL UNIQUE
); );
-- The origin changes of the routing table: each time a prefix and origin AS
-- gained its first peer or lost its last. The prefix handler writes them, and
-- the database maintainer prunes each prefix to its newest 500 rows or its
-- rows from the last 72 hours, whichever keeps more. time is whole seconds
-- since 1970, UTC.
CREATE TABLE IF NOT EXISTS origin_changes (
id INTEGER PRIMARY KEY,
prefix TEXT NOT NULL,
origin_asn INTEGER NOT NULL,
announced BOOLEAN NOT NULL,
peer_count INTEGER NOT NULL,
time INTEGER NOT NULL
);
CREATE INDEX IF NOT EXISTS idx_origin_changes_prefix ON origin_changes(prefix);
internal/geo/cache.go
+253
View File
@@ -0,0 +1,253 @@
package geo
import (
"context"
"database/sql"
"errors"
"fmt"
"maps"
"time"
)
const (
// entryLifetime is how long a geojs answer is kept after its fetch.
entryLifetime = 7 * 24 * time.Hour
// flushInterval is how often new answers are written to cache.db.
flushInterval = 5 * time.Second
// sweepInterval is how often expired answers are deleted.
sweepInterval = 10 * time.Minute
// rowColumns are the columns of the geolocations table in the order
// scanRow reads them.
rowColumns = "address, country_code, country, continent_code, region, " +
"city, latitude, longitude, accuracy_radius_km, time_zone, fetched_at"
)
// rowScanner is the Scan method of *sql.Row and *sql.Rows.
type rowScanner interface {
Scan(dest ...any) error
}
// cached returns the current answer held for address, from memory, then from
// the answers waiting to be written, then from cache.db. It returns nil when
// there is none.
func (l *Locator) cached(ctx context.Context, address string) *Location {
found, ok := l.entries.Get(address)
if ok {
if !l.expired(found) {
return found
}
l.entries.Remove(address)
}
l.pendingMu.Lock()
waiting := l.pending[address]
l.pendingMu.Unlock()
if waiting != nil && !l.expired(waiting) {
l.entries.Add(address, waiting)
return waiting
}
stored, err := l.readRow(ctx, address)
if err != nil {
l.logger.Warn("Failed to read a geolocation cache row",
"address", address, "error", err)
return nil
}
if stored != nil {
l.entries.Add(address, stored)
}
return stored
}
// expired says whether the answer is at the end of its lifetime.
func (l *Locator) expired(answer *Location) bool {
return !l.now().Before(answer.Updated.Add(entryLifetime))
}
// cutoff returns the fetch time at or before which an answer has expired.
func (l *Locator) cutoff() int64 {
return l.now().Add(-entryLifetime).Unix()
}
// store keeps an answer in memory and queues it for cache.db. While cache.db
// cannot be written, the queue stops growing at maxEntries answers.
func (l *Locator) store(address string, answer *Location) {
l.entries.Add(address, answer)
l.pendingMu.Lock()
defer l.pendingMu.Unlock()
if len(l.pending) < l.maxEntries {
l.pending[address] = answer
}
}
// keepCache writes new answers and deletes expired ones until ctx ends.
func (l *Locator) keepCache(ctx context.Context) {
flushes := time.NewTicker(flushInterval)
defer flushes.Stop()
sweeps := time.NewTicker(sweepInterval)
defer sweeps.Stop()
for {
select {
case <-ctx.Done():
l.flush(context.WithoutCancel(ctx))
return
case <-flushes.C:
l.flush(ctx)
case <-sweeps.C:
l.sweep(ctx)
}
}
}
// load reads the answers that have not expired into memory, at most maxEntries
// of them, the newest last so that they are the last to be dropped.
func (l *Locator) load(ctx context.Context) error {
rows, err := l.db.QueryContext(ctx,
"SELECT "+rowColumns+" FROM (SELECT "+rowColumns+" FROM geolocations "+
"WHERE fetched_at > ? ORDER BY fetched_at DESC LIMIT ?) "+
"ORDER BY fetched_at",
l.cutoff(), l.maxEntries)
if err != nil {
return fmt.Errorf("reading the geolocation cache: %w", err)
}
defer func() { _ = rows.Close() }()
for rows.Next() {
address, answer, err := scanRow(rows)
if err != nil {
return fmt.Errorf("reading a geolocation cache row: %w", err)
}
l.entries.Add(address, answer)
}
err = rows.Err()
if err != nil {
return fmt.Errorf("reading the geolocation cache: %w", err)
}
return nil
}
// readRow returns the current answer for address in cache.db, or nil when it
// has none.
func (l *Locator) readRow(
ctx context.Context, address string,
) (*Location, error) {
row := l.db.QueryRowContext(ctx,
"SELECT "+rowColumns+" FROM geolocations "+
"WHERE address = ? AND fetched_at > ?",
address, l.cutoff())
_, answer, err := scanRow(row)
if errors.Is(err, sql.ErrNoRows) {
return nil, nil //nolint:nilnil // no row is not a failure
}
return answer, err
}
// scanRow reads one row of the geolocations table.
func scanRow(row rowScanner) (string, *Location, error) {
var (
address string
fetched int64
answer Location
)
err := row.Scan(&address, &answer.CountryCode, &answer.Country,
&answer.ContinentCode, &answer.Region, &answer.City, &answer.Latitude,
&answer.Longitude, &answer.AccuracyRadiusKm, &answer.TimeZone, &fetched)
if err != nil {
return "", nil, err
}
answer.Source = sourceGeoJS
answer.Updated = time.Unix(fetched, 0).UTC()
return address, &answer, nil
}
// flush writes the pending answers to cache.db. Those it cannot write stay
// pending, unless a newer answer for the address has arrived meanwhile.
func (l *Locator) flush(ctx context.Context) {
l.pendingMu.Lock()
batch := l.pending
l.pending = make(map[string]*Location)
l.pendingMu.Unlock()
if len(batch) == 0 {
return
}
err := l.writeRows(ctx, batch)
if err == nil {
return
}
l.logger.Error("Failed to write the geolocation cache", "error", err)
l.pendingMu.Lock()
defer l.pendingMu.Unlock()
maps.Insert(batch, maps.All(l.pending))
l.pending = batch
}
// writeRows writes batch to cache.db in one transaction.
func (l *Locator) writeRows(
ctx context.Context, batch map[string]*Location,
) error {
tx, err := l.db.BeginTx(ctx, nil)
if err != nil {
return err
}
defer func() { _ = tx.Rollback() }()
for address, answer := range batch {
_, err = tx.ExecContext(ctx,
"INSERT OR REPLACE INTO geolocations ("+rowColumns+") "+
"VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)",
address, answer.CountryCode, answer.Country, answer.ContinentCode,
answer.Region, answer.City, answer.Latitude, answer.Longitude,
answer.AccuracyRadiusKm, answer.TimeZone, answer.Updated.Unix())
if err != nil {
return err
}
}
return tx.Commit()
}
// sweep deletes the expired answers from memory and cache.db.
func (l *Locator) sweep(ctx context.Context) {
for _, address := range l.entries.Keys() {
answer, ok := l.entries.Peek(address)
if ok && l.expired(answer) {
l.entries.Remove(address)
}
}
_, err := l.db.ExecContext(ctx,
"DELETE FROM geolocations WHERE fetched_at <= ?", l.cutoff())
if err != nil {
l.logger.Error("Failed to delete expired geolocation cache rows",
"error", err)
}
}
internal/geo/database.go
+349
View File
@@ -0,0 +1,349 @@
package geo
import (
"compress/gzip"
"context"
"errors"
"fmt"
"io"
"io/fs"
"net/http"
"net/netip"
"os"
"path/filepath"
"time"
"github.com/oschwald/maxminddb-golang/v2"
)
const (
// DatabaseDownloadFormat is the URL of DB-IP's City Lite database, with %s
// for the year and month.
DatabaseDownloadFormat = "https://download.db-ip.com/free/" +
"dbip-city-lite-%s.mmdb.gz"
// databaseMonthFormat is the year and month in the URL.
databaseMonthFormat = "2006-01"
// databaseFileName is the copy of the database in the state directory.
databaseFileName = "dbip-city-lite.mmdb"
// databaseDownloadSuffix ends the name of the file a download is written
// to, until it has opened.
databaseDownloadSuffix = ".download"
// maxDatabaseSize is the largest database accepted once unpacked, in
// bytes.
maxDatabaseSize = 200 << 20
// databaseDownloadTimeout limits one download.
databaseDownloadTimeout = 10 * time.Minute
// databaseCheckInterval is how often RouteWatch checks whether a new
// month's database is due. A new month's file appears some time on the
// first of the month, so a failed download is tried again this much later.
databaseCheckInterval = time.Hour
)
var (
errDatabaseStatus = errors.New("unexpected HTTP status from DB-IP")
errDatabaseTooLong = errors.New("database is over the size limit")
)
// dbipName is the part of a database record that holds an English name.
type dbipName struct {
Names struct {
English string `maxminddb:"en"`
} `maxminddb:"names"`
}
// dbipRecord is the part of a database record RouteWatch reads.
type dbipRecord struct {
City dbipName `maxminddb:"city"`
Continent struct {
Code string `maxminddb:"code"`
} `maxminddb:"continent"`
Country struct {
dbipName
ISOCode string `maxminddb:"iso_code"`
} `maxminddb:"country"`
Location struct {
Latitude *float64 `maxminddb:"latitude"`
Longitude *float64 `maxminddb:"longitude"`
} `maxminddb:"location"`
Subdivisions []dbipName `maxminddb:"subdivisions"`
}
// location returns the record as a Location fetched at the time given. The
// first subdivision is the region. The database has no accuracy radius and no
// time zone.
func (r *dbipRecord) location(fetched time.Time) *Location {
found := &Location{
CountryCode: nilIfEmpty(r.Country.ISOCode),
Country: nilIfEmpty(r.Country.Names.English),
ContinentCode: nilIfEmpty(r.Continent.Code),
City: nilIfEmpty(r.City.Names.English),
Latitude: r.Location.Latitude,
Longitude: r.Location.Longitude,
Source: sourceDBIP,
Updated: fetched,
}
if len(r.Subdivisions) > 0 {
found.Region = nilIfEmpty(r.Subdivisions[0].Names.English)
}
return found
}
// nilIfEmpty returns a pointer to text, or nil when text is empty.
func nilIfEmpty(text string) *string {
if text == "" {
return nil
}
return &text
}
// fromDatabase returns where the copy of the database places addr. It returns
// nil when there is no copy yet or the copy has no record for addr. It also
// returns nil, and logs the error, when reading the copy fails.
func (l *Locator) fromDatabase(addr netip.Addr) *Location {
l.databaseMu.RLock()
defer l.databaseMu.RUnlock()
if l.database == nil {
return nil
}
result := l.database.Lookup(addr)
err := result.Err()
if err != nil {
l.logger.Error("Failed to look up an address in the database",
"address", addr, "error", err)
return nil
}
if !result.Found() {
return nil
}
var record dbipRecord
err = result.Decode(&record)
if err != nil {
l.logger.Error("Failed to read a database record",
"address", addr, "error", err)
return nil
}
return record.location(l.databaseFetched)
}
// keepDatabaseCurrent downloads the database when it is due, at once and then
// every databaseCheckInterval, until ctx ends.
func (l *Locator) keepDatabaseCurrent(ctx context.Context) {
l.downloadDatabaseIfDue(ctx)
checks := time.NewTicker(databaseCheckInterval)
defer checks.Stop()
for {
select {
case <-ctx.Done():
return
case <-checks.C:
l.downloadDatabaseIfDue(ctx)
}
}
}
// downloadDatabaseIfDue downloads this month's database, unless the copy in
// use was downloaded this month. A failure leaves the copy as it is.
func (l *Locator) downloadDatabaseIfDue(ctx context.Context) {
now := l.now().UTC()
if !l.databaseDue(now) {
return
}
err := l.downloadDatabase(ctx, now)
if err != nil && ctx.Err() == nil {
l.logger.Error("Database download failed; keeping the previous copy",
"error", err)
}
}
// databaseDue says whether there is no open copy or it is from an earlier
// month than now.
func (l *Locator) databaseDue(now time.Time) bool {
l.databaseMu.RLock()
defer l.databaseMu.RUnlock()
return l.database == nil ||
l.databaseFetched.Format(databaseMonthFormat) !=
now.Format(databaseMonthFormat)
}
// downloadDatabase fetches the database of now's month. The file replaces the
// copy, on disk and in use, only once it has opened.
func (l *Locator) downloadDatabase(ctx context.Context, now time.Time) error {
ctx, cancel := context.WithTimeout(ctx, databaseDownloadTimeout)
defer cancel()
url := fmt.Sprintf(l.databaseURLFormat, now.Format(databaseMonthFormat))
request, err := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)
if err != nil {
return err
}
request.Header.Set(userAgentHeader, userAgent)
response, err := l.client.Do(request)
if err != nil {
return err
}
defer func() { _ = response.Body.Close() }()
if response.StatusCode != http.StatusOK {
return fmt.Errorf("%w: %s", errDatabaseStatus, response.Status)
}
return l.replaceDatabase(response.Body, now)
}
// replaceDatabase unpacks the gzip stream body beside the copy, then makes the
// result the copy once it has opened. Whatever fails, the file it wrote is
// removed and the copy stays.
func (l *Locator) replaceDatabase(body io.Reader, now time.Time) error {
root, err := os.OpenRoot(l.dir)
if err != nil {
return err
}
defer func() { _ = root.Close() }()
downloadName := databaseFileName + databaseDownloadSuffix
err = unpackDatabase(root, downloadName, body, l.maxDatabaseBytes)
if err != nil {
_ = root.Remove(downloadName)
return err
}
opened, err := maxminddb.Open(filepath.Join(l.dir, downloadName))
if err != nil {
_ = root.Remove(downloadName)
return fmt.Errorf("opening the downloaded database: %w", err)
}
err = root.Rename(downloadName, databaseFileName)
if err != nil {
_ = opened.Close()
_ = root.Remove(downloadName)
return err
}
l.useDatabase(opened, now.Truncate(time.Second))
l.logger.Info("Downloaded a new copy of the database")
return nil
}
// unpackDatabase writes the gzip stream body to the file name in root, up to
// limit bytes once unpacked.
func unpackDatabase(
root *os.Root, name string, body io.Reader, limit int64,
) error {
unpacked, err := gzip.NewReader(body)
if err != nil {
return fmt.Errorf("unpacking the database: %w", err)
}
f, err := root.Create(name)
if err != nil {
return err
}
defer func() { _ = f.Close() }()
written, err := io.Copy(f, io.LimitReader(unpacked, limit+1))
if err != nil {
return fmt.Errorf("unpacking the database: %w", err)
}
if written > limit {
return errDatabaseTooLong
}
return nil
}
// openDatabaseCopy opens the copy left by an earlier run, if there is one. A
// copy that does not open is treated as no copy, so it is downloaded again.
func (l *Locator) openDatabaseCopy() {
path := filepath.Join(l.dir, databaseFileName)
info, err := os.Stat(path)
if errors.Is(err, fs.ErrNotExist) {
return
}
if err != nil {
l.logger.Error("Failed to read the database copy", "error", err)
return
}
opened, err := maxminddb.Open(path)
if err != nil {
l.logger.Error("Failed to open the database copy", "error", err)
return
}
l.useDatabase(opened, info.ModTime().UTC().Truncate(time.Second))
}
// useDatabase makes opened the copy in use and closes the one it replaces.
func (l *Locator) useDatabase(opened *maxminddb.Reader, fetched time.Time) {
l.databaseMu.Lock()
defer l.databaseMu.Unlock()
if l.database != nil {
err := l.database.Close()
if err != nil {
l.logger.Error("Failed to close the old database copy", "error", err)
}
}
l.database = opened
l.databaseFetched = fetched
}
// closeDatabase closes the copy in use, after which no source can answer from
// it.
func (l *Locator) closeDatabase() {
l.databaseMu.Lock()
defer l.databaseMu.Unlock()
if l.database == nil {
return
}
err := l.database.Close()
if err != nil {
l.logger.Error("Failed to close the database copy", "error", err)
}
l.database = nil
}
internal/geo/geojs.go
+151
View File
@@ -0,0 +1,151 @@
package geo
import (
"context"
"encoding/json"
"errors"
"fmt"
"io"
"math"
"net/http"
"net/netip"
"strconv"
"strings"
"time"
)
const (
// GeoJSEndpoint is the URL of the geojs geo endpoint.
GeoJSEndpoint = "https://get.geojs.io/v1/ip/geo.json"
// geojsTimeLimit limits one request to geojs.
geojsTimeLimit = time.Second
// geojsAddressSeparator separates the addresses of one request.
geojsAddressSeparator = ","
// geojsUnknown is what geojs sends for a value it does not know.
geojsUnknown = "nil"
// maxGeoJSAnswerBytes is far more than an answer for the most addresses
// an IP lookup can ask about.
maxGeoJSAnswerBytes = 1 << 20
)
var errGeoJSStatus = errors.New("unexpected HTTP status from geojs")
// geojsAnswer is one address's entry in an answer from geojs.
//
//nolint:tagliatelle // the keys geojs sends
type geojsAnswer struct {
IP string `json:"ip"`
CountryCode string `json:"country_code"`
Country string `json:"country"`
ContinentCode string `json:"continent_code"`
Region string `json:"region"`
City string `json:"city"`
Latitude string `json:"latitude"`
Longitude string `json:"longitude"`
Accuracy *int `json:"accuracy"`
TimeZone string `json:"timezone"`
}
// askGeoJS asks geojs about addresses in one request, and returns its answers
// by address. An address geojs left out, or gave no country, city or
// coordinates for, has no entry.
func (l *Locator) askGeoJS(
ctx context.Context, addresses []string,
) (map[string]*Location, error) {
ctx, cancel := context.WithTimeout(ctx, l.timeLimit)
defer cancel()
// A comma and a colon are legal in a query, and the escaped forms are
// not what geojs documents.
url := l.geojsURL + "?ip=" + strings.Join(addresses, geojsAddressSeparator)
request, err := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)
if err != nil {
return nil, err
}
request.Header.Set(userAgentHeader, userAgent)
response, err := l.client.Do(request)
if err != nil {
return nil, err
}
defer func() { _ = response.Body.Close() }()
if response.StatusCode != http.StatusOK {
return nil, fmt.Errorf("%w: %d", errGeoJSStatus, response.StatusCode)
}
var parsed []geojsAnswer
err = json.NewDecoder(io.LimitReader(response.Body, maxGeoJSAnswerBytes)).
Decode(&parsed)
if err != nil {
return nil, fmt.Errorf("reading the geojs answer: %w", err)
}
fetched := l.now().UTC().Truncate(time.Second)
answers := make(map[string]*Location, len(parsed))
for _, answer := range parsed {
addr, err := netip.ParseAddr(answer.IP)
if err != nil {
continue
}
location := answer.location(fetched)
if hasLocation(location) {
answers[plainAddress(addr)] = location
}
}
return answers, nil
}
// hasLocation says whether found has a country, a city or a coordinate.
func hasLocation(found *Location) bool {
return found.CountryCode != nil || found.Country != nil ||
found.City != nil || found.Latitude != nil || found.Longitude != nil
}
// location returns the answer as a Location fetched at the time given.
func (a geojsAnswer) location(fetched time.Time) *Location {
return &Location{
CountryCode: knownText(a.CountryCode),
Country: knownText(a.Country),
ContinentCode: knownText(a.ContinentCode),
Region: knownText(a.Region),
City: knownText(a.City),
Latitude: knownNumber(a.Latitude),
Longitude: knownNumber(a.Longitude),
AccuracyRadiusKm: a.Accuracy,
TimeZone: knownText(a.TimeZone),
Source: sourceGeoJS,
Updated: fetched,
}
}
// knownText returns a pointer to text, or nil when geojs does not know it.
func knownText(text string) *string {
if text == "" || text == geojsUnknown {
return nil
}
return &text
}
// knownNumber returns text as a number, or nil when geojs does not know it. NaN
// and infinity parse, but JSON cannot carry them.
func knownNumber(text string) *float64 {
number, err := strconv.ParseFloat(text, 64)
if err != nil || math.IsNaN(number) || math.IsInf(number, 0) {
return nil
}
return &number
}
internal/geo/locator.go
+232
View File
@@ -0,0 +1,232 @@
// Package geo finds where IP addresses are. It asks geojs.io, and keeps those
// answers in memory and in cache.db. When geojs.io gives no location for an
// address, it reads a copy of DB-IP's City Lite database, which it downloads
// once a month.
package geo
import (
"context"
"database/sql"
"fmt"
"log/slog"
"net/http"
"net/netip"
"sync"
"time"
lru "github.com/hashicorp/golang-lru/v2"
"github.com/oschwald/maxminddb-golang/v2"
)
// The values of Location.Source.
const (
sourceGeoJS = "geojs"
sourceDBIP = "dbip"
)
const (
// maxEntries limits how many geojs answers are held in memory.
maxEntries = 250_000
// userAgentHeader and userAgent name routewatch to geojs and DB-IP.
userAgentHeader = "User-Agent"
userAgent = "routewatch (+https://git.eeqj.de/sneak/routewatch)"
)
// Params is what New needs.
type Params struct {
// DB is the open cache.db.
DB *sql.DB
// Dir is the directory that holds the copy of the database.
Dir string
// GeoJSURL is the URL of the geojs geo endpoint, GeoJSEndpoint in use.
GeoJSURL string
// DatabaseURLFormat is the URL of the database with %s for the year and
// month, DatabaseDownloadFormat in use.
DatabaseURLFormat string
Logger *slog.Logger
}
// Location is where an address is. A part the source does not know is nil.
//
//nolint:tagliatelle // snake_case keys, as the Go style guide asks
type Location struct {
CountryCode *string `json:"country_code"`
Country *string `json:"country"`
ContinentCode *string `json:"continent_code"`
Region *string `json:"region"`
City *string `json:"city"`
Latitude *float64 `json:"latitude"`
Longitude *float64 `json:"longitude"`
AccuracyRadiusKm *int `json:"accuracy_radius_km"`
TimeZone *string `json:"time_zone"`
// Source is geojs or dbip.
Source string `json:"source"`
// Updated is when the value was fetched: the geojs answer, or the copy of
// the database.
Updated time.Time `json:"updated"`
}
// Locator answers where addresses are. Start loads its cache and starts its
// goroutines.
type Locator struct {
db *sql.DB
dir string
geojsURL string
databaseURLFormat string
timeLimit time.Duration
maxEntries int
maxDatabaseBytes int64
logger *slog.Logger
client *http.Client
now func() time.Time
// entries holds geojs answers by address, and drops the least recently
// used first.
entries *lru.Cache[string, *Location]
// pending holds the answers that cache.db does not have yet.
pendingMu sync.Mutex
pending map[string]*Location
// database is the open copy, nil until one has opened, and databaseFetched
// is when that copy was downloaded. A lookup holds the read lock, so that
// a new copy never closes the old one under it.
databaseMu sync.RWMutex
database *maxminddb.Reader
databaseFetched time.Time
// stop ends the goroutines Start runs, and done is closed when they have
// returned.
stop context.CancelFunc
done chan struct{}
}
// New returns a Locator with an empty cache. Start loads it.
func New(params Params) (*Locator, error) {
entries, err := lru.New[string, *Location](maxEntries)
if err != nil {
return nil, fmt.Errorf("creating the geolocation cache: %w", err)
}
return &Locator{
db: params.DB,
dir: params.Dir,
geojsURL: params.GeoJSURL,
databaseURLFormat: params.DatabaseURLFormat,
timeLimit: geojsTimeLimit,
maxEntries: maxEntries,
maxDatabaseBytes: maxDatabaseSize,
logger: params.Logger.With("component", "geo"),
client: &http.Client{},
now: time.Now,
entries: entries,
pending: make(map[string]*Location),
done: make(chan struct{}),
}, nil
}
// Lookup returns where each of addrs is, in the same order. The entry for an
// address neither source answers for is nil. Addresses with no current cached
// answer go to geojs in one request. The returned Locations are shared with
// the cache and must not be changed.
func (l *Locator) Lookup(ctx context.Context, addrs []netip.Addr) []*Location {
locations := make([]*Location, len(addrs))
var unanswered []string
for i, addr := range addrs {
address := plainAddress(addr)
locations[i] = l.cached(ctx, address)
if locations[i] == nil {
unanswered = append(unanswered, address)
}
}
if len(unanswered) == 0 {
return locations
}
answers, err := l.askGeoJS(ctx, unanswered)
if err != nil {
l.logger.Warn("geojs lookup failed; using the database", "error", err)
}
for i, addr := range addrs {
if locations[i] != nil {
continue
}
address := plainAddress(addr)
answer, ok := answers[address]
if ok {
l.store(address, answer)
locations[i] = answer
continue
}
locations[i] = l.fromDatabase(addr)
}
return locations
}
// plainAddress returns addr as the requests to geojs and the cache name it: an
// IPv4 address mapped into IPv6 as plain IPv4, and with no zone. A client
// chooses the zone, so it must not reach the request.
func plainAddress(addr netip.Addr) string {
return addr.Unmap().WithZone("").String()
}
// Start loads the cached answers that have not expired and opens the copy of
// the database, if there is one. It then starts the goroutines that write new
// answers, delete expired ones and download the database. They run until Stop:
// the end of ctx does not stop them.
func (l *Locator) Start(ctx context.Context) error {
err := l.load(ctx)
if err != nil {
return err
}
l.logger.Info("Geolocation cache loaded", "entries", l.entries.Len())
l.openDatabaseCopy()
ctx, l.stop = context.WithCancel(context.WithoutCancel(ctx))
go func() {
defer close(l.done)
defer l.closeDatabase()
var workers sync.WaitGroup
workers.Go(func() { l.keepCache(ctx) })
workers.Go(func() { l.keepDatabaseCurrent(ctx) })
workers.Wait()
}()
return nil
}
// Stop cancels a download in progress, writes the answers cache.db does not
// have yet, and waits until the goroutines have returned or ctx ends.
func (l *Locator) Stop(ctx context.Context) {
l.stop()
select {
case <-l.done:
l.logger.Info("Geolocation stopped")
case <-ctx.Done():
l.logger.Warn("Stop deadline passed before the geolocation cache " +
"was written")
}
}
internal/geo/locator_internal_test.go
+1009
View File
File diff suppressed because it is too large. Load diff
internal/blocklist/download.go → internal/iplist/download.go
+19 -19
View File
@@ -1,4 +1,4 @@
package blocklist package iplist
import ( import (
"context" "context"
@@ -21,8 +21,8 @@ const (
downloadTimeout = time.Minute downloadTimeout = time.Minute
// maxDownloadSize is the size of the largest list file accepted, in // maxDownloadSize is the size of the largest list file accepted, in
// bytes. The largest list, FireHOL abusers, is about 2.5 MiB. // bytes. The largest list, iCloud Private Relay, is about 12 MiB.
maxDownloadSize = 16 << 20 maxDownloadSize = 200 << 20
) )
// The request headers a download sets. // The request headers a download sets.
@@ -78,10 +78,10 @@ var (
// downloads each list once its copy is older than its Interval, and a list // downloads each list once its copy is older than its Interval, and a list
// with no copy at once. The goroutine runs until Stop: the end of ctx does // with no copy at once. The goroutine runs until Stop: the end of ctx does
// not stop it. // not stop it.
func (b *Blocklists) Start(ctx context.Context) { func (b *IPLists) Start(ctx context.Context) {
err := os.MkdirAll(b.dir, dirPermissions) err := os.MkdirAll(b.dir, dirPermissions)
if err != nil { if err != nil {
b.logger.Error("Failed to create the blocklists directory", b.logger.Error("Failed to create the IP lists directory",
"dir", b.dir, "error", err) "dir", b.dir, "error", err)
} }
@@ -90,7 +90,7 @@ func (b *Blocklists) Start(ctx context.Context) {
for i, list := range b.lists { for i, list := range b.lists {
loadErr := b.loadCopy(list) loadErr := b.loadCopy(list)
if loadErr != nil && !errors.Is(loadErr, fs.ErrNotExist) { if loadErr != nil && !errors.Is(loadErr, fs.ErrNotExist) {
b.logger.Error("Failed to load a blocklist copy", b.logger.Error("Failed to load an IP list copy",
"list", list.Name, "error", loadErr) "list", list.Name, "error", loadErr)
} }
@@ -104,20 +104,20 @@ func (b *Blocklists) Start(ctx context.Context) {
b.run(ctx, nextDownload) b.run(ctx, nextDownload)
}() }()
b.logger.Info("Blocklist downloads started", "dir", b.dir) b.logger.Info("IP list downloads started", "dir", b.dir)
} }
// Stop stops the downloads, cancelling one in progress, and waits until the // Stop stops the downloads, cancelling one in progress, and waits until the
// goroutine has returned or ctx ends. The copies in memory stay, so Lookup // goroutine has returned or ctx ends. The copies in memory stay, so Lookup
// still answers. // still answers.
func (b *Blocklists) Stop(ctx context.Context) { func (b *IPLists) Stop(ctx context.Context) {
b.stop() b.stop()
select { select {
case <-b.done: case <-b.done:
b.logger.Info("Blocklist downloads stopped") b.logger.Info("IP list downloads stopped")
case <-ctx.Done(): case <-ctx.Done():
b.logger.Warn("Stop deadline passed before the blocklist downloads " + b.logger.Warn("Stop deadline passed before the IP list downloads " +
"stopped") "stopped")
} }
} }
@@ -125,7 +125,7 @@ func (b *Blocklists) Stop(ctx context.Context) {
// run downloads each list when nextDownload says, until ctx ends. After each // run downloads each list when nextDownload says, until ctx ends. After each
// try, whether it worked or not, the list's next download is an Interval // try, whether it worked or not, the list's next download is an Interval
// later. // later.
func (b *Blocklists) run(ctx context.Context, nextDownload []time.Time) { func (b *IPLists) run(ctx context.Context, nextDownload []time.Time) {
defer close(b.done) defer close(b.done)
if len(nextDownload) == 0 { if len(nextDownload) == 0 {
@@ -155,7 +155,7 @@ func (b *Blocklists) run(ctx context.Context, nextDownload []time.Time) {
} }
if err != nil { if err != nil {
b.logger.Error("Blocklist download failed; keeping the "+ b.logger.Error("IP list download failed; keeping the "+
"previous copy", "list", list.Name, "error", err) "previous copy", "list", list.Name, "error", err)
} }
@@ -169,7 +169,7 @@ func (b *Blocklists) run(ctx context.Context, nextDownload []time.Time) {
// on disk and in memory. An answer that the copy is still current marks the // on disk and in memory. An answer that the copy is still current marks the
// copy as updated now. Anything else leaves the copy as it is and returns an // copy as updated now. Anything else leaves the copy as it is and returns an
// error. // error.
func (b *Blocklists) download(ctx context.Context, list List) error { func (b *IPLists) download(ctx context.Context, list List) error {
ctx, cancel := context.WithTimeout(ctx, downloadTimeout) ctx, cancel := context.WithTimeout(ctx, downloadTimeout)
defer cancel() defer cancel()
@@ -212,7 +212,7 @@ func (b *Blocklists) download(ctx context.Context, list List) error {
// replaceCopy writes a new version of list, read from body, beside the list's // replaceCopy writes a new version of list, read from body, beside the list's
// copy. Only when it parses does it replace the copy, on disk and in memory. // copy. Only when it parses does it replace the copy, on disk and in memory.
// sent are the validators the publisher sent with the new version. // sent are the validators the publisher sent with the new version.
func (b *Blocklists) replaceCopy(list List, body io.Reader, sent validators) error { func (b *IPLists) replaceCopy(list List, body io.Reader, sent validators) error {
root, err := os.OpenRoot(b.dir) root, err := os.OpenRoot(b.dir)
if err != nil { if err != nil {
return err return err
@@ -244,13 +244,13 @@ func (b *Blocklists) replaceCopy(list List, body io.Reader, sent validators) err
b.setCopy(list.Name, listCopy{ b.setCopy(list.Name, listCopy{
addresses: addresses, updated: time.Now().UTC(), validators: sent, addresses: addresses, updated: time.Now().UTC(), validators: sent,
}) })
b.logger.Info("Downloaded a new version of a blocklist", "list", list.Name) b.logger.Info("Downloaded a new version of an IP list", "list", list.Name)
// Without this file, the first download after a restart asks for the // Without this file, the first download after a restart asks for the
// whole list. // whole list.
err = writeValidators(root, list.Name, sent) err = writeValidators(root, list.Name, sent)
if err != nil { if err != nil {
b.logger.Error("Failed to keep the validators of a blocklist copy", b.logger.Error("Failed to keep the validators of an IP list copy",
"list", list.Name, "error", err) "list", list.Name, "error", err)
} }
@@ -288,7 +288,7 @@ func writeAndParse(
// markCurrent records that the publisher says the list's copy is still // markCurrent records that the publisher says the list's copy is still
// current: the copy, on disk and in memory, is marked as updated now. // current: the copy, on disk and in memory, is marked as updated now.
func (b *Blocklists) markCurrent(list List) error { func (b *IPLists) markCurrent(list List) error {
root, err := os.OpenRoot(b.dir) root, err := os.OpenRoot(b.dir)
if err != nil { if err != nil {
return err return err
@@ -304,7 +304,7 @@ func (b *Blocklists) markCurrent(list List) error {
} }
b.setUpdated(list.Name, now) b.setUpdated(list.Name, now)
b.logger.Debug("Blocklist copy is still current", "list", list.Name) b.logger.Debug("IP list copy is still current", "list", list.Name)
return nil return nil
} }
@@ -312,7 +312,7 @@ func (b *Blocklists) markCurrent(list List) error {
// loadCopy makes the list's copy on disk, with the validators kept beside it, // loadCopy makes the list's copy on disk, with the validators kept beside it,
// its copy in memory. The file's modification time is when the copy was // its copy in memory. The file's modification time is when the copy was
// updated. // updated.
func (b *Blocklists) loadCopy(list List) error { func (b *IPLists) loadCopy(list List) error {
root, err := os.OpenRoot(b.dir) root, err := os.OpenRoot(b.dir)
if err != nil { if err != nil {
return err return err
internal/blocklist/blocklist.go → internal/iplist/iplist.go
+57 -17
View File
@@ -1,7 +1,7 @@
// Package blocklist downloads public IP blocklists on a schedule, keeps the // Package iplist downloads public IP lists on a schedule, keeps the last good
// last good copy of each on disk and in memory, and answers which lists // copy of each on disk and in memory, and answers which lists contain an
// contain an address. // address.
package blocklist package iplist
import ( import (
"context" "context"
@@ -29,9 +29,41 @@ const (
// start with the network's first and last address. Lines that start // start with the network's first and last address. Lines that start
// with # are comments. // with # are comments.
FormatDShield FormatDShield
// FormatOnionooJSON is one Onionoo details document. Its relays have
// addresses in two fields: exit_addresses, which has IPv4 only, and
// or_addresses, which has IPv4 and IPv6, each with a port.
FormatOnionooJSON
// FormatMullvadJSON is Mullvad's JSON list of relays. A relay's addresses
// are in ipv4_addr_in, ipv6_addr_in and ipv4_v2ray.
FormatMullvadJSON
// FormatNordVPNJSON is NordVPN's JSON list of servers. A server's
// addresses are in station and ipv6_station.
FormatNordVPNJSON
// FormatPIAJSON is Private Internet Access's JSON server list, then a
// blank line and a signature. Each region's servers has lists of servers
// by protocol, and each server has its address in ip.
FormatPIAJSON
// FormatIVPNJSON is IVPN's JSON server list. The hosts of its wireguard
// and openvpn gateways have their addresses in host and v2ray.
FormatIVPNJSON
// FormatProtonVPN has one address or network per line, with comment lines
// that start with #. Unlike FormatLines, a file with no addresses or
// networks fails.
FormatProtonVPN
// FormatICloudPrivateRelayCSV is Apple's CSV file of iCloud Private Relay
// networks. Each line starts with a network, followed by its country,
// region and city.
FormatICloudPrivateRelayCSV
) )
// List is one public blocklist. // List is one public IP list.
type List struct { type List struct {
// Name names the list in lookup answers, and names its copy on disk. // Name names the list in lookup answers, and names its copy on disk.
Name string Name string
@@ -48,6 +80,9 @@ type List struct {
// Format is how the list's file is written. // Format is how the list's file is written.
Format Format Format Format
// VPN says that the list holds servers of VPN services.
VPN bool
} }
// Listing says that a list contains an address. // Listing says that a list contains an address.
@@ -58,6 +93,10 @@ type Listing struct {
// Updated is when routewatch last downloaded the list, or last heard from // Updated is when routewatch last downloaded the list, or last heard from
// its publisher that its copy was still current. // its publisher that its copy was still current.
Updated time.Time `json:"updated"` Updated time.Time `json:"updated"`
// VPN says that the list holds servers of VPN services. A lookup answer
// reports it through is_vpn and vpn_providers.
VPN bool `json:"-"`
} }
// listCopy is a list's last good copy in memory. // listCopy is a list's last good copy in memory.
@@ -80,9 +119,9 @@ type Params struct {
Logger *slog.Logger Logger *slog.Logger
} }
// Blocklists keeps a copy of each list and answers which lists contain an // IPLists keeps a copy of each list and answers which lists contain an
// address. Start loads the copies from disk and starts downloading the lists. // address. Start loads the copies from disk and starts downloading the lists.
type Blocklists struct { type IPLists struct {
dir string dir string
lists []List lists []List
logger *slog.Logger logger *slog.Logger
@@ -97,12 +136,12 @@ type Blocklists struct {
done chan struct{} done chan struct{}
} }
// New returns a Blocklists with no copies. Start loads them. // New returns an IPLists with no copies. Start loads them.
func New(params Params) *Blocklists { func New(params Params) *IPLists {
return &Blocklists{ return &IPLists{
dir: params.Dir, dir: params.Dir,
lists: params.Lists, lists: params.Lists,
logger: params.Logger.With("component", "blocklists"), logger: params.Logger.With("component", "iplists"),
copies: make(map[string]listCopy), copies: make(map[string]listCopy),
done: make(chan struct{}), done: make(chan struct{}),
} }
@@ -111,7 +150,7 @@ func New(params Params) *Blocklists {
// Lookup returns a Listing for each list whose copy contains addr, in the // Lookup returns a Listing for each list whose copy contains addr, in the
// order of the lists given to New. It makes no outside request. When no list // order of the lists given to New. It makes no outside request. When no list
// contains addr, it returns an empty list, not nil. // contains addr, it returns an empty list, not nil.
func (b *Blocklists) Lookup(addr netip.Addr) []Listing { func (b *IPLists) Lookup(addr netip.Addr) []Listing {
b.mu.RLock() b.mu.RLock()
defer b.mu.RUnlock() defer b.mu.RUnlock()
@@ -124,6 +163,7 @@ func (b *Blocklists) Lookup(addr netip.Addr) []Listing {
Name: list.Name, Name: list.Name,
Description: list.Description, Description: list.Description,
Updated: c.updated, Updated: c.updated,
VPN: list.VPN,
}) })
} }
} }
@@ -133,7 +173,7 @@ func (b *Blocklists) Lookup(addr netip.Addr) []Listing {
// ShortestInterval returns the shortest Interval of the lists. That is the // ShortestInterval returns the shortest Interval of the lists. That is the
// soonest a copy can change, and so how long a lookup answer stays current. // soonest a copy can change, and so how long a lookup answer stays current.
func (b *Blocklists) ShortestInterval() time.Duration { func (b *IPLists) ShortestInterval() time.Duration {
var shortest time.Duration var shortest time.Duration
for i, list := range b.lists { for i, list := range b.lists {
@@ -147,7 +187,7 @@ func (b *Blocklists) ShortestInterval() time.Duration {
// updated returns when the named list's copy was last downloaded or found // updated returns when the named list's copy was last downloaded or found
// current, or the zero time when the list has no copy. // current, or the zero time when the list has no copy.
func (b *Blocklists) updated(name string) time.Time { func (b *IPLists) updated(name string) time.Time {
b.mu.RLock() b.mu.RLock()
defer b.mu.RUnlock() defer b.mu.RUnlock()
@@ -156,7 +196,7 @@ func (b *Blocklists) updated(name string) time.Time {
// copyValidators returns the validators of the named list's copy. They are // copyValidators returns the validators of the named list's copy. They are
// empty when the list has no copy. // empty when the list has no copy.
func (b *Blocklists) copyValidators(name string) validators { func (b *IPLists) copyValidators(name string) validators {
b.mu.RLock() b.mu.RLock()
defer b.mu.RUnlock() defer b.mu.RUnlock()
@@ -164,7 +204,7 @@ func (b *Blocklists) copyValidators(name string) validators {
} }
// setCopy makes c the named list's copy. // setCopy makes c the named list's copy.
func (b *Blocklists) setCopy(name string, c listCopy) { func (b *IPLists) setCopy(name string, c listCopy) {
b.mu.Lock() b.mu.Lock()
defer b.mu.Unlock() defer b.mu.Unlock()
@@ -172,7 +212,7 @@ func (b *Blocklists) setCopy(name string, c listCopy) {
} }
// setUpdated records that the named list's copy was found current at t. // setUpdated records that the named list's copy was found current at t.
func (b *Blocklists) setUpdated(name string, t time.Time) { func (b *IPLists) setUpdated(name string, t time.Time) {
b.mu.Lock() b.mu.Lock()
defer b.mu.Unlock() defer b.mu.Unlock()
internal/iplist/iplist_internal_test.go
+992
View File
@@ -0,0 +1,992 @@
package iplist
import (
"context"
"errors"
"io"
"io/fs"
"log/slog"
"net/http"
"net/http/httptest"
"net/netip"
"os"
"path/filepath"
"slices"
"strings"
"sync"
"testing"
"time"
)
// The test list's name and description, the address its good version lists,
// and the address a newer version lists instead.
const (
testListName = "test_list"
testListDescription = "On the test list"
listedAddr = "192.0.2.1"
goodListBody = "# A test list\n" + listedAddr + "\n"
newListedAddr = "192.0.2.2"
newListBody = "# A test list\n" + newListedAddr + "\n"
)
// A small Onionoo details document: a relay with an exit address and IPv4 and
// IPv6 relay addresses, one without exit addresses, and one with a list of
// ports.
const (
onionooExitAddr = "192.0.2.10"
onionooIPv6ExitAddr = "2001:db8::1"
onionooBody = `{"version":"8.0","relays":[
{"exit_addresses":["` + onionooExitAddr + `"],
"or_addresses":["192.0.2.11:443","[` + onionooIPv6ExitAddr + `]:9001"]},
{"or_addresses":["192.0.2.20:443"]},
{"or_addresses":["192.0.2.30:80,443"]}
],"bridges":[]}`
)
// Small documents in the VPN services' formats. PIA's and IVPN's have no
// public IPv6 addresses, and IVPN's holds addresses that are not its servers,
// which must not be read.
const (
mullvadBody = `[
{"hostname":"a-wg-001","ipv4_addr_in":"192.0.2.40","ipv6_addr_in":"2001:db8::40"},
{"hostname":"a-br-001","ipv4_addr_in":"192.0.2.41","ipv6_addr_in":null,
"ipv4_v2ray":"192.0.2.42"}
]`
nordVPNBody = `[
{"hostname":"a1.example.com","station":"192.0.2.50","ipv6_station":""},
{"hostname":"a2.example.com","station":"192.0.2.51","ipv6_station":"2001:db8::51"}
]`
piaBody = `{"groups":{"wg":[{"name":"wireguard","ports":[1337]}]},"regions":[
{"id":"a","servers":{
"wg":[{"ip":"192.0.2.60","cn":"a1"}],
"ikev2":[{"ip":"192.0.2.61","cn":"a1"}]}},
{"id":"b","servers":{"meta":[{"ip":"192.0.2.62","cn":"b1","van":true}]}}
]}` + "\n\nc2lnbmF0dXJl\nbGluZSB0d28=\n"
ivpnBody = `{"wireguard":[{"gateway":"a.wg.example.com","hosts":[
{"hostname":"a1","host":"192.0.2.70","v2ray":"192.0.2.71",
"ipv6":{"local_ip":"2001:db8::70/96"}}]}],
"openvpn":[{"gateway":"a.gw.example.com","hosts":[
{"hostname":"a1","host":"192.0.2.72"}]}],
"config":{"api":{"ips":["192.0.2.73"]}}}`
)
// protonVPNBody is a small file in the format of the ProtonVPN-IPs list.
const protonVPNBody = "#\n# protonvpn_ip_ranges.txt\n" +
"# https://github.com/tn3w/ProtonVPN-IPs\n#\n" +
"# The /24 block of every advertised IPv4.\n#\n" +
"192.0.2.0/24\n198.51.100.0/24\n"
// protonVPNEntryBody is a small file in the format of the ProtonVPN-IPs list
// of server addresses.
const protonVPNEntryBody = "#\n# protonvpn_entry_ips.txt\n" +
"# https://github.com/tn3w/ProtonVPN-IPs\n#\n" +
"# Entry IPs clients connect to, resolved from ProtonVPN hostnames.\n#\n" +
"192.0.2.80\n2001:db8::80\n"
// iCloudPrivateRelayAddr is an address on iCloudPrivateRelayBody.
const iCloudPrivateRelayAddr = "2001:db8:1::5"
// iCloudPrivateRelayBody is a small file in the format of Apple's iCloud
// Private Relay file.
const iCloudPrivateRelayBody = "192.0.2.0/31,GB,GB-EN,London,\n" +
"198.51.100.32/27,US,US-CA,Los Angeles,\n" +
"2001:db8:1::/64,US,US-AK,Anchorage,\n"
// emptyFileCase names the case of a wrong document that is an empty file.
const emptyFileCase = "an empty file"
// errorPage is a file that is no list, as a publisher's error page is.
const errorPage = "<!DOCTYPE html>\n<html></html>\n"
// testETag is the ETag a publisher sends with a version of the test list.
const testETag = `"v1"`
// maxWait is how long a test waits for the download goroutine.
const maxWait = 10 * time.Second
// publisher stands in for a list's publisher. It answers every request with
// its status and body, and keeps the headers of each request. A 200 answer
// carries lastModified and etag, when set, as Last-Modified and ETag. As
// from a real publisher, a request whose If-None-Match or If-Modified-Since
// matches them is answered "not modified".
type publisher struct {
mu sync.Mutex
status int
body string
lastModified time.Time
etag string
headers []http.Header
}
// newPublisher starts a publisher that answers 200 with body, and returns it
// and its URL.
func newPublisher(t *testing.T, body string) (*publisher, string) {
t.Helper()
p := &publisher{status: http.StatusOK, body: body}
srv := httptest.NewServer(p)
t.Cleanup(srv.Close)
return p, srv.URL
}
func (p *publisher) ServeHTTP(w http.ResponseWriter, r *http.Request) {
p.mu.Lock()
defer p.mu.Unlock()
p.headers = append(p.headers, r.Header.Clone())
if p.status != http.StatusOK {
w.WriteHeader(p.status)
_, _ = io.WriteString(w, p.body)
return
}
if p.etag != "" {
w.Header().Set(etagHeader, p.etag)
}
// ServeContent sends Last-Modified unless lastModified is zero, and
// answers "not modified" when the request's conditions match.
http.ServeContent(w, r, testListName, p.lastModified,
strings.NewReader(p.body))
}
// answer makes the publisher answer later requests with status and body.
func (p *publisher) answer(status int, body string) {
p.mu.Lock()
defer p.mu.Unlock()
p.status, p.body = status, body
}
// publish makes the publisher answer later requests with a version of the
// list: body, with lastModified and etag. A zero lastModified or an empty
// etag is not sent.
func (p *publisher) publish(body string, lastModified time.Time, etag string) {
p.mu.Lock()
defer p.mu.Unlock()
p.status, p.body = http.StatusOK, body
p.lastModified, p.etag = lastModified, etag
}
// requests returns the headers of the requests the publisher has had.
func (p *publisher) requests() []http.Header {
p.mu.Lock()
defer p.mu.Unlock()
return append([]http.Header(nil), p.headers...)
}
// testList returns a list served at url, written in format.
func testList(url string, format Format) List {
return List{
Name: testListName,
Description: testListDescription,
URL: url,
Interval: time.Hour,
Format: format,
}
}
func newTestIPLists(dir string, list List) *IPLists {
return New(Params{
Dir: dir,
Lists: []List{list},
Logger: slog.New(slog.DiscardHandler),
})
}
// lookup looks addr up in b.
func lookup(t *testing.T, b *IPLists, addr string) []Listing {
t.Helper()
return b.Lookup(netip.MustParseAddr(addr))
}
// TestLookupFindsListedAddresses downloads a list in each format and looks
// up addresses on it, inside its networks, and off it, in IPv4 and IPv6.
// A listed address has one listing that names the list; any other has an
// empty list of listings.
func TestLookupFindsListedAddresses(t *testing.T) {
t.Parallel()
runLookupCases(t, []lookupCase{
{
name: "single addresses",
format: FormatLines,
body: "# comment\n192.0.2.1\n\n2001:db8::1\n",
listed: []string{"192.0.2.1", "::ffff:192.0.2.1", "2001:db8::1"},
unlisted: []string{"192.0.2.2", "2001:db8::2"},
},
{
name: "networks",
format: FormatLines,
body: "# comment\n198.51.100.0/24\n2001:db8:1::/48\n",
listed: []string{"198.51.100.0", "198.51.100.255", "2001:db8:1::5"},
unlisted: []string{"198.51.101.0", "2001:db8:2::1"},
},
{
name: "Spamhaus networks",
format: FormatSpamhausJSON,
body: `{"cidr":"203.0.113.0/25","sblid":"SBL1","rir":"arin"}` + "\n" +
`{"cidr":"2001:db8:3::/48","sblid":"SBL2","rir":"ripencc"}` + "\n" +
`{"type":"metadata","timestamp":1793074442,"records":2}` + "\n",
listed: []string{"203.0.113.1", "2001:db8:3::1"},
unlisted: []string{"203.0.113.200", "2001:db8:4::1"},
},
{
name: "DShield networks",
format: FormatDShield,
body: "# DShield.org Recommended Block List\n" +
"192.0.2.0\t192.0.2.255\t24\t327\tEXAMPLE\tUS\tNone\n",
listed: []string{"192.0.2.0", "192.0.2.77"},
unlisted: []string{"192.0.3.1", "2001:db8::1"},
},
{
name: "Onionoo relays",
format: FormatOnionooJSON,
body: onionooBody,
listed: []string{
onionooExitAddr, "192.0.2.11", "192.0.2.20", "192.0.2.30",
onionooIPv6ExitAddr,
},
unlisted: []string{"192.0.2.12", "2001:db8::2"},
},
{
name: "iCloud Private Relay networks",
format: FormatICloudPrivateRelayCSV,
body: iCloudPrivateRelayBody,
listed: []string{
"192.0.2.1", "198.51.100.63", iCloudPrivateRelayAddr,
},
unlisted: []string{"192.0.2.2", "198.51.100.64", "2001:db8:2::1"},
},
})
}
// TestLookupFindsVPNServers downloads a list in each VPN service's format and
// looks up addresses on it and off it.
func TestLookupFindsVPNServers(t *testing.T) {
t.Parallel()
runLookupCases(t, []lookupCase{
{
name: "Mullvad relays",
format: FormatMullvadJSON,
body: mullvadBody,
listed: []string{"192.0.2.40", "192.0.2.41", "192.0.2.42", "2001:db8::40"},
unlisted: []string{"192.0.2.43", "2001:db8::41"},
},
{
name: "NordVPN servers",
format: FormatNordVPNJSON,
body: nordVPNBody,
listed: []string{"192.0.2.50", "192.0.2.51", "2001:db8::51"},
unlisted: []string{"192.0.2.52", "2001:db8::50"},
},
{
name: "PIA servers, with the signature after the JSON",
format: FormatPIAJSON,
body: piaBody,
listed: []string{"192.0.2.60", "192.0.2.61", "192.0.2.62"},
unlisted: []string{"192.0.2.63", "2001:db8::60"},
},
{
name: "IVPN hosts",
format: FormatIVPNJSON,
body: ivpnBody,
listed: []string{"192.0.2.70", "192.0.2.71", "192.0.2.72"},
unlisted: []string{"192.0.2.73", "2001:db8::70"},
},
{
name: "ProtonVPN networks",
format: FormatProtonVPN,
body: protonVPNBody,
listed: []string{"192.0.2.0", "192.0.2.255", "198.51.100.7"},
unlisted: []string{"192.0.3.1", "2001:db8::90"},
},
{
name: "ProtonVPN server addresses",
format: FormatProtonVPN,
body: protonVPNEntryBody,
listed: []string{"192.0.2.80", "2001:db8::80"},
unlisted: []string{"192.0.2.81", "2001:db8::81"},
},
})
}
// lookupCase is a list file, the addresses it holds and some it does not.
type lookupCase struct {
name string
format Format
body string
listed []string
unlisted []string
}
// runLookupCases downloads each case's list file and checks its addresses.
func runLookupCases(t *testing.T, cases []lookupCase) {
t.Helper()
for _, tt := range cases {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
_, url := newPublisher(t, tt.body)
b := newTestIPLists(t.TempDir(), testList(url, tt.format))
err := b.download(t.Context(), b.lists[0])
if err != nil {
t.Fatalf("download: %v", err)
}
checkLookups(t, b, tt.listed, tt.unlisted)
})
}
}
// checkLookups checks that each of listed has one listing that names the test
// list, and each of unlisted has an empty list of listings.
func checkLookups(t *testing.T, b *IPLists, listed, unlisted []string) {
t.Helper()
for _, addr := range listed {
listings := lookup(t, b, addr)
if len(listings) != 1 || listings[0].Name != testListName ||
listings[0].Description != testListDescription ||
listings[0].Updated.IsZero() {
t.Errorf("%s: listings %+v, want one for %s", addr,
listings, testListName)
}
}
for _, addr := range unlisted {
listings := lookup(t, b, addr)
if listings == nil || len(listings) != 0 {
t.Errorf("%s: listings %#v, want an empty list", addr, listings)
}
}
}
// TestFailedDownloadKeepsThePreviousCopy downloads a good version of a list,
// then one that fails. The good copy stays in memory and on disk, and no
// part of the failed download is left beside it.
func TestFailedDownloadKeepsThePreviousCopy(t *testing.T) {
t.Parallel()
tests := []struct {
name string
status int
body string
}{
{"server error", http.StatusInternalServerError, "unavailable"},
{"not a list", http.StatusOK, errorPage},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
dir := t.TempDir()
p, url := newPublisher(t, goodListBody)
b := newTestIPLists(dir, testList(url, FormatLines))
err := b.download(t.Context(), b.lists[0])
if err != nil {
t.Fatalf("first download: %v", err)
}
before := lookup(t, b, listedAddr)
p.answer(tt.status, tt.body)
err = b.download(t.Context(), b.lists[0])
if err == nil {
t.Fatal("second download returned no error")
}
after := lookup(t, b, listedAddr)
if len(after) != 1 || len(before) != 1 ||
!after[0].Updated.Equal(before[0].Updated) {
t.Errorf("listings %+v after the failure, want %+v", after, before)
}
checkGoodCopyOnDisk(t, dir)
})
}
}
// TestFileThatIsNotAnOnionooDocumentKeepsThePreviousCopy downloads a good
// Onionoo document, then files that are not one. Each fails the parse, and
// the good copy stays.
func TestFileThatIsNotAnOnionooDocumentKeepsThePreviousCopy(t *testing.T) {
t.Parallel()
tests := []struct {
name string
body string
}{
{"not JSON", errorPage},
{"other JSON", `{"status":"ok","data":{"relays_count":1}}`},
{"JSON array", `[{"or_addresses":["192.0.2.1:443"]}]`},
{"no relays", `{"relays":[],"bridges":[]}`},
{"relays without addresses", `{"relays":[{"nickname":"example"}]}`},
{"relay address without a port", `{"relays":[{"or_addresses":["192.0.2.1"]}]}`},
{"exit address that is not one", `{"relays":[{"exit_addresses":["example"]}]}`},
{"text after the document", `{"relays":[{"or_addresses":["192.0.2.1:1"]}]} x`},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
dir := t.TempDir()
p, url := newPublisher(t, onionooBody)
b := newTestIPLists(dir, testList(url, FormatOnionooJSON))
err := b.download(t.Context(), b.lists[0])
if err != nil {
t.Fatalf("first download: %v", err)
}
p.answer(http.StatusOK, tt.body)
err = b.download(t.Context(), b.lists[0])
if err == nil {
t.Fatal("second download returned no error")
}
if len(lookup(t, b, onionooExitAddr)) != 1 {
t.Errorf("%s is no longer listed", onionooExitAddr)
}
onDisk, err := fs.ReadFile(os.DirFS(dir), testListName)
if err != nil || string(onDisk) != onionooBody {
t.Errorf("copy on disk %q (%v), want the good version", onDisk, err)
}
})
}
}
// TestWrongVPNDocumentFailsToParse parses documents that are not a VPN
// service's list. Each fails, so none can replace a good copy.
func TestWrongVPNDocumentFailsToParse(t *testing.T) {
t.Parallel()
formats := []struct {
name string
format Format
good string
empty string
badAddress string
}{
{
"Mullvad", FormatMullvadJSON, mullvadBody,
`[{"hostname":"a"}]`, `[{"ipv4_addr_in":"example"}]`,
},
{
"NordVPN", FormatNordVPNJSON, nordVPNBody,
`[{"hostname":"a","station":"","ipv6_station":""}]`,
`[{"station":"example"}]`,
},
{
"PIA", FormatPIAJSON, piaBody,
`{"regions":[{"id":"a","servers":{}}]}`,
`{"regions":[{"servers":{"wg":[{"ip":"example"}]}}]}`,
},
{
"IVPN", FormatIVPNJSON, ivpnBody,
`{"wireguard":[{"hosts":[]}],"openvpn":[]}`,
`{"wireguard":[{"hosts":[{"host":"example"}]}]}`,
},
}
for _, f := range formats {
bodies := map[string]string{
"not JSON": errorPage,
"other JSON": `{"status":"ok","data":{"count":1}}`,
"no addresses": f.empty,
"bad address": f.badAddress,
"cut off": f.good[:len(f.good)/2],
emptyFileCase: "",
}
for name, body := range bodies {
t.Run(f.name+" "+name, func(t *testing.T) {
t.Parallel()
addresses, err := parse(strings.NewReader(body), f.format)
if err == nil {
t.Errorf("parse returned %v and no error", addresses.Ranges())
}
})
}
}
}
// TestWrongProtonVPNDocumentFailsToParse parses documents that are not a
// ProtonVPN-IPs list. Each fails, so none can replace a good copy.
func TestWrongProtonVPNDocumentFailsToParse(t *testing.T) {
t.Parallel()
bodies := map[string]string{
"error page": errorPage,
"JSON": `{"status":"ok"}`,
"comments only": "#\n# protonvpn_ip_ranges.txt\n#\n",
"bad network": "192.0.2.0/24\nexample\n",
emptyFileCase: "",
}
for name, body := range bodies {
t.Run(name, func(t *testing.T) {
t.Parallel()
addresses, err := parse(strings.NewReader(body), FormatProtonVPN)
if err == nil {
t.Errorf("parse returned %v and no error", addresses.Ranges())
}
})
}
}
// TestWrongICloudPrivateRelayDocumentFailsToParse parses documents that are
// not Apple's iCloud Private Relay file. Each fails, so none can replace a
// good copy.
func TestWrongICloudPrivateRelayDocumentFailsToParse(t *testing.T) {
t.Parallel()
bodies := map[string]string{
"error page": errorPage,
"JSON": `{"status":"ok","count":1}`,
"no other field": "192.0.2.0/24\n",
"bad network": "192.0.2.0/24,GB,GB-EN,London,\nexample,GB,GB-EN,London,\n",
"an address": "192.0.2.1,GB,GB-EN,London,\n",
emptyFileCase: "",
}
for name, body := range bodies {
t.Run(name, func(t *testing.T) {
t.Parallel()
addresses, err := parse(strings.NewReader(body),
FormatICloudPrivateRelayCSV)
if err == nil {
t.Errorf("parse returned %v and no error", addresses.Ranges())
}
})
}
}
// TestLookupMarksVPNLists looks up an address on a VPN list and on another
// list. Only the VPN list's listing says it is one.
func TestLookupMarksVPNLists(t *testing.T) {
t.Parallel()
_, url := newPublisher(t, goodListBody)
vpnList := testList(url, FormatLines)
vpnList.Name = "test_vpn_list"
vpnList.VPN = true
otherList := testList(url, FormatLines)
b := New(Params{
Dir: t.TempDir(),
Lists: []List{vpnList, otherList},
Logger: slog.New(slog.DiscardHandler),
})
for _, list := range b.lists {
err := b.download(t.Context(), list)
if err != nil {
t.Fatalf("download of %s: %v", list.Name, err)
}
}
listings := lookup(t, b, listedAddr)
if len(listings) != 2 || !listings[0].VPN || listings[1].VPN {
t.Errorf("listings %+v, want the first of two marked as a VPN list",
listings)
}
}
// TestPublicListsMarkTheVPNLists checks which public lists are VPN lists,
// since their names are what vpn_providers reports.
func TestPublicListsMarkTheVPNLists(t *testing.T) {
t.Parallel()
var got []string
for _, list := range Lists() {
if list.VPN {
got = append(got, list.Name)
}
}
want := []string{
"ivpn", "mullvad", "nordvpn", "pia", "protonvpn", "protonvpn_entry",
"x4bnet", "x4bnet_v6",
}
if !slices.Equal(got, want) {
t.Errorf("VPN lists %v, want %v", got, want)
}
}
// checkGoodCopyOnDisk checks that dir holds the good version of the test list
// and no part of a failed download.
func checkGoodCopyOnDisk(t *testing.T, dir string) {
t.Helper()
copies := os.DirFS(dir)
onDisk, err := fs.ReadFile(copies, testListName)
if err != nil || string(onDisk) != goodListBody {
t.Errorf("copy on disk %q (%v), want %q", onDisk, err, goodListBody)
}
_, err = fs.Stat(copies, testListName+downloadSuffix)
if !errors.Is(err, fs.ErrNotExist) {
t.Errorf("the failed download's file is still there (%v)", err)
}
}
// commentLines is an endless io.Reader of comment lines. It lets a test send
// a large list file without holding the file in memory.
type commentLines struct {
offset int
}
func (c *commentLines) Read(p []byte) (int, error) {
const line = "# a comment line that pads a large list file\n"
for filled := 0; filled < len(p); {
copied := copy(p[filled:], line[c.offset:])
filled += copied
c.offset = (c.offset + copied) % len(line)
}
return len(p), nil
}
// largeListFile returns a reader of a list file of size bytes: comment lines,
// then newListedAddr on the last line.
func largeListFile(size int64) io.Reader {
lastLine := "\n" + newListedAddr + "\n"
return io.MultiReader(
io.LimitReader(&commentLines{}, size-int64(len(lastLine))),
strings.NewReader(lastLine),
)
}
// TestLargeFileUnderTheSizeLimitIsAccepted replaces a list with a 199 MiB
// file. The address on its last line is listed, so the whole file was read.
func TestLargeFileUnderTheSizeLimitIsAccepted(t *testing.T) {
t.Parallel()
const size = 199 << 20
b := newTestIPLists(t.TempDir(), testList("", FormatLines))
err := b.replaceCopy(b.lists[0], largeListFile(size), validators{})
if err != nil {
t.Fatalf("replaceCopy: %v", err)
}
if listings := lookup(t, b, newListedAddr); len(listings) != 1 {
t.Errorf("listings %+v, want one", listings)
}
}
// TestFileOverTheSizeLimitKeepsThePreviousCopy downloads a good version of a
// list, then replaces it with a file one byte over the limit. The attempt
// fails, and the good copy stays in memory and on disk.
func TestFileOverTheSizeLimitKeepsThePreviousCopy(t *testing.T) {
t.Parallel()
dir := t.TempDir()
_, url := newPublisher(t, goodListBody)
b := newTestIPLists(dir, testList(url, FormatLines))
err := b.download(t.Context(), b.lists[0])
if err != nil {
t.Fatalf("download: %v", err)
}
err = b.replaceCopy(b.lists[0], largeListFile(maxDownloadSize+1), validators{})
if !errors.Is(err, errTooLarge) {
t.Fatalf("replaceCopy: %v, want %v", err, errTooLarge)
}
if listings := lookup(t, b, listedAddr); len(listings) != 1 {
t.Errorf("listings of %s %+v, want one", listedAddr, listings)
}
checkGoodCopyOnDisk(t, dir)
}
// TestRestartLoadsCopiesFromDisk downloads a list, then starts a new
// IPLists on the same directory, as a restart does. The new one answers
// from the copy on disk at once, and does not download the list again while
// the copy is younger than the list's interval.
func TestRestartLoadsCopiesFromDisk(t *testing.T) {
t.Parallel()
dir := t.TempDir()
p, url := newPublisher(t, goodListBody)
list := testList(url, FormatLines)
first := newTestIPLists(dir, list)
err := first.download(t.Context(), list)
if err != nil {
t.Fatalf("download: %v", err)
}
downloaded := lookup(t, first, listedAddr)[0].Updated
second := newTestIPLists(dir, list)
second.Start(t.Context())
second.Stop(t.Context())
// The download takes its time after writing the file, and the restart
// reads the file's time. A busy host can put seconds between the two.
const maxUpdatedDifference = 15 * time.Second
listings := lookup(t, second, listedAddr)
if len(listings) != 1 ||
listings[0].Updated.Sub(downloaded).Abs() > maxUpdatedDifference {
t.Errorf("after the restart, listings %+v, want one updated at %s",
listings, downloaded)
}
if got := len(p.requests()); got != 1 {
t.Errorf("the publisher had %d requests, want 1", got)
}
}
// TestStartRefreshesAnOldCopy starts on a copy older than its list's
// interval. The list is downloaded at once, with routewatch's User-Agent and
// the Last-Modified and ETag the publisher sent with the copy, kept on disk.
// The publisher answers that the copy is still current, so the copy is kept
// and marked as updated now.
func TestStartRefreshesAnOldCopy(t *testing.T) {
t.Parallel()
dir := t.TempDir()
p, url := newPublisher(t, goodListBody)
list := testList(url, FormatLines)
lastModified := time.Now().Add(-3 * list.Interval).UTC().Truncate(time.Second)
p.publish(goodListBody, lastModified, testETag)
err := newTestIPLists(dir, list).download(t.Context(), list)
if err != nil {
t.Fatalf("download: %v", err)
}
old := time.Now().Add(-2 * list.Interval).UTC().Truncate(time.Second)
err = os.Chtimes(filepath.Join(dir, testListName), old, old)
if err != nil {
t.Fatalf("Chtimes: %v", err)
}
b := newTestIPLists(dir, list)
b.Start(t.Context())
deadline := time.Now().Add(maxWait)
for !lookup(t, b, listedAddr)[0].Updated.After(old) {
if time.Now().After(deadline) {
t.Fatalf("the copy was not marked updated within %s", maxWait)
}
time.Sleep(time.Millisecond)
}
b.Stop(t.Context())
requests := p.requests()
last := requests[len(requests)-1]
want := lastModified.Format(http.TimeFormat)
if got := last.Get(ifModifiedSinceHeader); got != want {
t.Errorf("If-Modified-Since %q, want %q", got, want)
}
if got := last.Get(ifNoneMatchHeader); got != testETag {
t.Errorf("If-None-Match %q, want %q", got, testETag)
}
if got := last.Get(userAgentHeader); got != userAgent {
t.Errorf("User-Agent %q, want %q", got, userAgent)
}
}
// TestNewVersionOlderThanTheLastDownloadReplacesTheCopy downloads a list.
// The publisher then puts out a new version whose Last-Modified is earlier
// than that download, as when a cache in front of the publisher passes the
// version on late. The next download sends the Last-Modified of the copy,
// not the time of the download, so it gets the new version.
func TestNewVersionOlderThanTheLastDownloadReplacesTheCopy(t *testing.T) {
t.Parallel()
p, url := newPublisher(t, goodListBody)
list := testList(url, FormatLines)
b := newTestIPLists(t.TempDir(), list)
firstVersion := time.Now().Add(-2 * list.Interval).UTC().Truncate(time.Second)
p.publish(goodListBody, firstVersion, "")
err := b.download(t.Context(), list)
if err != nil {
t.Fatalf("first download: %v", err)
}
p.publish(newListBody, firstVersion.Add(list.Interval), "")
err = b.download(t.Context(), list)
if err != nil {
t.Fatalf("second download: %v", err)
}
if listings := lookup(t, b, newListedAddr); len(listings) != 1 {
t.Errorf("%s: listings %+v, want one from the new version",
newListedAddr, listings)
}
want := firstVersion.Format(http.TimeFormat)
if got := p.requests()[1].Get(ifModifiedSinceHeader); got != want {
t.Errorf("If-Modified-Since %q, want %q", got, want)
}
}
// TestDownloadWithoutLastModifiedOrETagSendsNoCondition downloads a list
// twice from a publisher that sends neither Last-Modified nor ETag. Neither
// request carries If-Modified-Since or If-None-Match, so the second download
// gets the whole list again.
func TestDownloadWithoutLastModifiedOrETagSendsNoCondition(t *testing.T) {
t.Parallel()
p, url := newPublisher(t, goodListBody)
list := testList(url, FormatLines)
b := newTestIPLists(t.TempDir(), list)
err := b.download(t.Context(), list)
if err != nil {
t.Fatalf("first download: %v", err)
}
err = b.download(t.Context(), list)
if err != nil {
t.Fatalf("second download: %v", err)
}
for i, request := range p.requests() {
if request.Get(ifModifiedSinceHeader) != "" ||
request.Get(ifNoneMatchHeader) != "" {
t.Errorf("request %d has a condition: %v", i, request)
}
}
}
// TestStopCancelsADownloadInProgress stops while the publisher has not
// answered. Stop cancels the download and returns once the download
// goroutine has stopped.
func TestStopCancelsADownloadInProgress(t *testing.T) {
t.Parallel()
arrived := make(chan struct{})
var once sync.Once
srv := httptest.NewServer(http.HandlerFunc(
func(_ http.ResponseWriter, r *http.Request) {
once.Do(func() { close(arrived) })
<-r.Context().Done()
}))
t.Cleanup(srv.Close)
b := newTestIPLists(t.TempDir(), testList(srv.URL, FormatLines))
b.Start(t.Context())
select {
case <-arrived:
case <-time.After(maxWait):
t.Fatalf("no download began within %s", maxWait)
}
ctx, cancel := context.WithTimeout(t.Context(), maxWait)
defer cancel()
b.Stop(ctx)
select {
case <-b.done:
default:
t.Error("Stop returned before the download goroutine stopped")
}
}
// TestTorExitsListHoldsIPv6Exits downloads an Onionoo document as the public
// Tor exit list, which is what an IPv6 address's is_tor answer comes from.
func TestTorExitsListHoldsIPv6Exits(t *testing.T) {
t.Parallel()
checkPublicListHolds(t, TorExitsList, onionooBody, onionooIPv6ExitAddr)
}
// TestICloudPrivateRelayListHoldsItsNetworks downloads a file in Apple's
// format as the public iCloud Private Relay list, which is what an address's
// is_relay answer comes from.
func TestICloudPrivateRelayListHoldsItsNetworks(t *testing.T) {
t.Parallel()
checkPublicListHolds(t, ICloudPrivateRelayList, iCloudPrivateRelayBody,
iCloudPrivateRelayAddr)
}
// checkPublicListHolds downloads body as the public list called name and
// checks that addr has one listing, which names that list.
func checkPublicListHolds(t *testing.T, name, body, addr string) {
t.Helper()
index := slices.IndexFunc(Lists(), func(list List) bool {
return list.Name == name
})
if index < 0 {
t.Fatalf("no list named %s", name)
}
list := Lists()[index]
_, list.URL = newPublisher(t, body)
b := newTestIPLists(t.TempDir(), list)
err := b.download(t.Context(), list)
if err != nil {
t.Fatalf("download: %v", err)
}
listings := lookup(t, b, addr)
if len(listings) != 1 || listings[0].Name != name {
t.Errorf("listings %+v, want one for %s", listings, name)
}
}
// TestPublicListsAreComplete checks that every public list has what a
// download and a lookup answer need, and a unique name.
func TestPublicListsAreComplete(t *testing.T) {
t.Parallel()
names := make(map[string]bool)
for _, list := range Lists() {
if list.Name == "" || list.Description == "" || list.URL == "" ||
list.Interval <= 0 || names[list.Name] {
t.Errorf("list %+v is incomplete or has a name used before", list)
}
names[list.Name] = true
}
}
internal/iplist/lists.go
+209
View File
@@ -0,0 +1,209 @@
package iplist
import (
"slices"
"time"
)
// TorExitsList is the name of the list of Tor exit nodes.
const TorExitsList = "tor_exits"
// ICloudPrivateRelayList is the name of the list of iCloud Private Relay's
// networks.
const ICloudPrivateRelayList = "icloud_private_relay"
// protonVPNIPsURL is where the ProtonVPN-IPs mirror publishes its files.
const protonVPNIPsURL = "https://raw.githubusercontent.com/tn3w/ProtonVPN-IPs/master/"
// How often each list is downloaded. No list is downloaded more often than
// its publisher updates it or allows.
const (
// DShield asks that its feeds be downloaded at most once an hour:
// https://isc.sans.edu/feeds_doc.html
dshieldInterval = time.Hour
// abuse.ch makes the list every 5 minutes and recommends a download at
// least every 15: https://feodotracker.abuse.ch/blocklist/
feodoTrackerInterval = 15 * time.Minute
// FireHOL's page for each list gives how often the list changes on
// average: about every 5 hours for abusers and every 3 hours for level
// 3. FireHOL sets no download limit.
// https://iplists.firehol.org/?ipset=firehol_abusers_30d
// https://iplists.firehol.org/?ipset=firehol_level3
fireHOLAbusersInterval = 5 * time.Hour
fireHOLLevel3Interval = 3 * time.Hour
// Apple's iCloud Private Relay file is 12 MB, so once a day.
iCloudPrivateRelayInterval = 24 * time.Hour
// Spamhaus asks that DROP be downloaded at most once a day:
// https://www.spamhaus.org/blocklists/do-not-route-or-peer/
spamhausDROPInterval = 24 * time.Hour
// Onionoo's relay data follows Tor's hourly network consensus, and
// Onionoo sets no download limit:
// https://metrics.torproject.org/onionoo.html
torExitsInterval = time.Hour
// A VPN service's servers change slowly, so once a day is enough.
vpnListInterval = 24 * time.Hour
)
// Lists returns the public IP lists routewatch downloads. Each can be
// downloaded whole without an account or a key. Spamhaus merged its EDROP
// list into DROP, so DROP covers both.
func Lists() []List {
return slices.Concat(nonVPNLists(), vpnLists())
}
// nonVPNLists returns the public lists that are not lists of VPN servers.
func nonVPNLists() []List {
return []List{
{
Name: "dshield",
Description: "In one of the 20 networks that DShield saw scan " +
"the most targets in the last three days",
URL: "https://feeds.dshield.org/block.txt",
Interval: dshieldInterval,
Format: FormatDShield,
},
{
Name: "feodo_tracker",
Description: "A botnet command-and-control server",
URL: "https://feodotracker.abuse.ch/downloads/ipblocklist.txt",
Interval: feodoTrackerInterval,
Format: FormatLines,
},
{
Name: "firehol_abusers_30d",
Description: "Reported for comment, form or forum spam in the " +
"last 30 days",
URL: "https://iplists.firehol.org/files/firehol_abusers_30d.netset",
Interval: fireHOLAbusersInterval,
Format: FormatLines,
},
{
Name: "firehol_level3",
Description: "Reported for attacks, spyware or viruses in the " +
"last 30 days",
URL: "https://iplists.firehol.org/files/firehol_level3.netset",
Interval: fireHOLLevel3Interval,
Format: FormatLines,
},
{
Name: ICloudPrivateRelayList,
Description: "In a network where iCloud Private Relay traffic leaves",
URL: "https://mask-api.icloud.com/egress-ip-ranges.csv",
Interval: iCloudPrivateRelayInterval,
Format: FormatICloudPrivateRelayCSV,
},
{
Name: "spamhaus_drop",
Description: "In an IPv4 network that Spamhaus says spammers " +
"or cyber criminals have hijacked or lease",
URL: "https://www.spamhaus.org/drop/drop_v4.json",
Interval: spamhausDROPInterval,
Format: FormatSpamhausJSON,
},
{
Name: "spamhaus_dropv6",
Description: "In an IPv6 network that Spamhaus says spammers " +
"or cyber criminals have hijacked or lease",
URL: "https://www.spamhaus.org/drop/drop_v6.json",
Interval: spamhausDROPInterval,
Format: FormatSpamhausJSON,
},
{
Name: TorExitsList,
Description: "A Tor exit node, where traffic from the Tor network leaves",
URL: "https://onionoo.torproject.org/details?" +
"flag=Exit&running=true&fields=exit_addresses,or_addresses",
Interval: torExitsInterval,
Format: FormatOnionooJSON,
},
}
}
// vpnLists returns the public lists of VPN servers. Their names are what
// vpn_providers reports.
func vpnLists() []List {
return []List{
{
Name: "ivpn",
Description: "A server of the IVPN service",
URL: "https://api.ivpn.net/v5/servers.json",
Interval: vpnListInterval,
Format: FormatIVPNJSON,
VPN: true,
},
{
Name: "mullvad",
Description: "A server of the Mullvad VPN service",
URL: "https://api.mullvad.net/www/relays/all/",
Interval: vpnListInterval,
Format: FormatMullvadJSON,
VPN: true,
},
{
Name: "nordvpn",
Description: "A server of the NordVPN service",
URL: "https://api.nordvpn.com/v1/servers?limit=0" +
"&fields[servers.station]&fields[servers.ipv6_station]" +
"&fields[servers.hostname]",
Interval: vpnListInterval,
Format: FormatNordVPNJSON,
VPN: true,
},
{
Name: "pia",
Description: "A server of the Private Internet Access VPN service",
URL: "https://serverlist.piaservers.net/vpninfo/servers/v6",
Interval: vpnListInterval,
Format: FormatPIAJSON,
VPN: true,
},
{
// Proton's own server list needs a logged-in session, so this is
// the public ProtonVPN-IPs mirror of it. Proton publishes only
// the addresses clients connect to. The mirror's README says
// traffic leaves from others in the same /24, so this file of
// /24 networks is the one it says to use for detecting exits.
Name: "protonvpn",
Description: "In a /24 network that holds a server of the " +
"ProtonVPN service",
URL: protonVPNIPsURL + "protonvpn_ip_ranges.txt",
Interval: vpnListInterval,
Format: FormatProtonVPN,
VPN: true,
},
{
Name: "protonvpn_entry",
Description: "A server of the ProtonVPN service",
URL: protonVPNIPsURL + "protonvpn_entry_ips.txt",
Interval: vpnListInterval,
Format: FormatProtonVPN,
VPN: true,
},
{
Name: "x4bnet",
Description: "In an IPv4 network of a VPN service, according to " +
"X4BNet's community list",
URL: "https://raw.githubusercontent.com/X4BNet/lists_vpn/main/" +
"output/vpn/ipv4.txt",
Interval: vpnListInterval,
Format: FormatLines,
VPN: true,
},
{
Name: "x4bnet_v6",
Description: "In an IPv6 network of a VPN service, according to " +
"X4BNet's community list",
URL: "https://raw.githubusercontent.com/X4BNet/lists_vpn/main/" +
"output/vpn/ipv6.txt",
Interval: vpnListInterval,
Format: FormatLines,
VPN: true,
},
}
}
internal/iplist/parse.go
+435
View File
@@ -0,0 +1,435 @@
package iplist
import (
"bufio"
"encoding/json"
"errors"
"fmt"
"io"
"net"
"net/netip"
"slices"
"strings"
"go4.org/netipx"
)
const (
// commentPrefix starts a comment line in a list file.
commentPrefix = "#"
// networkSeparator separates the address and the mask length of a
// network, as in 192.0.2.0/24.
networkSeparator = "/"
// dshieldFieldSeparator separates the fields of a DShield line.
dshieldFieldSeparator = "\t"
// iCloudPrivateRelayFieldSeparator separates the fields of a line of
// Apple's iCloud Private Relay file.
iCloudPrivateRelayFieldSeparator = ","
// spamhausMetadataType is the type of the line that ends a Spamhaus
// file. That line holds the file's metadata and no network.
spamhausMetadataType = "metadata"
)
var (
errUnknownFormat = errors.New("unknown list format")
errNoNetwork = errors.New("no network on the line")
errBadRange = errors.New("first and last address make no range")
errNoAddresses = errors.New("no addresses in the document")
)
// parse reads a list file written in format and returns the addresses it
// holds. Anything it cannot read fails the whole file, so a file that is not
// the list, such as an error page, never replaces a good copy.
func parse(r io.Reader, format Format) (*netipx.IPSet, error) {
switch format {
case FormatLines:
return parseLines(r, addAddressOrNetwork)
case FormatSpamhausJSON:
return parseLines(r, addSpamhausNetwork)
case FormatDShield:
return parseLines(r, addDShieldNetwork)
case FormatOnionooJSON:
return parseOnionoo(r)
case FormatMullvadJSON:
return parseMullvad(r)
case FormatNordVPNJSON:
return parseNordVPN(r)
case FormatPIAJSON:
return parsePIA(r)
case FormatIVPNJSON:
return parseIVPN(r)
case FormatProtonVPN:
return parseLinesNotEmpty(r, addAddressOrNetwork)
case FormatICloudPrivateRelayCSV:
return parseLinesNotEmpty(r, addICloudPrivateRelayNetwork)
default:
return nil, errUnknownFormat
}
}
// parseLines reads a list file line by line, skipping blank lines and
// comments, and calls addLine with each other line.
func parseLines(
r io.Reader, addLine func(*netipx.IPSetBuilder, string) error,
) (*netipx.IPSet, error) {
var builder netipx.IPSetBuilder
scanner := bufio.NewScanner(r)
for lineNumber := 1; scanner.Scan(); lineNumber++ {
line := strings.TrimSpace(scanner.Text())
if line == "" || strings.HasPrefix(line, commentPrefix) {
continue
}
err := addLine(&builder, line)
if err != nil {
return nil, fmt.Errorf("line %d: %w", lineNumber, err)
}
}
err := scanner.Err()
if err != nil {
return nil, err
}
return builder.IPSet()
}
// addAddressOrNetwork adds an address, such as 192.0.2.1, or a network, such
// as 192.0.2.0/24, to builder.
func addAddressOrNetwork(builder *netipx.IPSetBuilder, text string) error {
if strings.Contains(text, networkSeparator) {
network, err := netip.ParsePrefix(text)
if err != nil {
return err
}
builder.AddPrefix(network)
return nil
}
addr, err := netip.ParseAddr(text)
if err != nil {
return err
}
builder.Add(addr)
return nil
}
// addSpamhausNetwork adds the network on a line of a Spamhaus file to
// builder. The metadata line adds nothing.
func addSpamhausNetwork(builder *netipx.IPSetBuilder, line string) error {
var entry struct {
CIDR string `json:"cidr"`
Type string `json:"type"`
}
err := json.Unmarshal([]byte(line), &entry)
if err != nil {
return err
}
if entry.Type == spamhausMetadataType {
return nil
}
network, err := netip.ParsePrefix(entry.CIDR)
if err != nil {
return err
}
builder.AddPrefix(network)
return nil
}
// addDShieldNetwork adds the network on a line of a DShield file to builder.
// The line's first two fields are the network's first and last address.
func addDShieldNetwork(builder *netipx.IPSetBuilder, line string) error {
firstField, rest, found := strings.Cut(line, dshieldFieldSeparator)
if !found {
return errNoNetwork
}
lastField, _, _ := strings.Cut(rest, dshieldFieldSeparator)
first, err := netip.ParseAddr(firstField)
if err != nil {
return err
}
last, err := netip.ParseAddr(lastField)
if err != nil {
return err
}
network := netipx.IPRangeFrom(first, last)
if !network.IsValid() {
return errBadRange
}
builder.AddRange(network)
return nil
}
// parseOnionoo returns every address in the exit_addresses and or_addresses
// fields of the relays in an Onionoo details document. A document with no
// addresses fails, because the Tor network always has relays.
func parseOnionoo(r io.Reader) (*netipx.IPSet, error) {
//nolint:tagliatelle // Onionoo's own field names
var details struct {
Relays []struct {
ExitAddresses []string `json:"exit_addresses"`
ORAddresses []string `json:"or_addresses"`
} `json:"relays"`
}
err := readJSON(r, &details)
if err != nil {
return nil, err
}
var builder netipx.IPSetBuilder
for _, relay := range details.Relays {
for _, text := range relay.ExitAddresses {
err = addAddress(&builder, text)
if err != nil {
return nil, err
}
}
for _, text := range relay.ORAddresses {
err = addAddressWithPort(&builder, text)
if err != nil {
return nil, err
}
}
}
addresses, err := builder.IPSet()
if err != nil {
return nil, err
}
if len(addresses.Ranges()) == 0 {
return nil, errNoAddresses
}
return addresses, nil
}
// parseMullvad returns the addresses of the relays in a Mullvad document. A
// relay with no IPv6 address has null for it, and only bridges have
// ipv4_v2ray.
func parseMullvad(r io.Reader) (*netipx.IPSet, error) {
//nolint:tagliatelle // Mullvad's own field names
var relays []struct {
IPv4 string `json:"ipv4_addr_in"`
IPv6 string `json:"ipv6_addr_in"`
IPv4V2Ray string `json:"ipv4_v2ray"`
}
err := readJSON(r, &relays)
if err != nil {
return nil, err
}
var texts []string
for _, relay := range relays {
texts = append(texts, relay.IPv4, relay.IPv6, relay.IPv4V2Ray)
}
return addressSet(texts)
}
// parseNordVPN returns the addresses of the servers in a NordVPN document. A
// server with no IPv6 address has an empty ipv6_station.
func parseNordVPN(r io.Reader) (*netipx.IPSet, error) {
//nolint:tagliatelle // NordVPN's own field names
var servers []struct {
Station string `json:"station"`
IPv6Station string `json:"ipv6_station"`
}
err := readJSON(r, &servers)
if err != nil {
return nil, err
}
var texts []string
for _, server := range servers {
texts = append(texts, server.Station, server.IPv6Station)
}
return addressSet(texts)
}
// parsePIA returns the addresses of the servers in a Private Internet Access
// document. json.Decoder stops at the end of the JSON, so the signature after
// it is not read.
func parsePIA(r io.Reader) (*netipx.IPSet, error) {
var list struct {
Regions []struct {
Servers map[string][]struct {
IP string `json:"ip"`
} `json:"servers"`
} `json:"regions"`
}
err := json.NewDecoder(r).Decode(&list)
if err != nil {
return nil, err
}
var texts []string
for _, region := range list.Regions {
for _, servers := range region.Servers {
for _, server := range servers {
texts = append(texts, server.IP)
}
}
}
return addressSet(texts)
}
// parseIVPN returns the addresses of the hosts in an IVPN document. A host's
// ipv6 object holds only an address inside the VPN, so it is not read.
func parseIVPN(r io.Reader) (*netipx.IPSet, error) {
type gateway struct {
Hosts []struct {
Host string `json:"host"`
V2Ray string `json:"v2ray"`
} `json:"hosts"`
}
var list struct {
WireGuard []gateway `json:"wireguard"`
OpenVPN []gateway `json:"openvpn"`
}
err := readJSON(r, &list)
if err != nil {
return nil, err
}
var texts []string
for _, gw := range slices.Concat(list.WireGuard, list.OpenVPN) {
for _, host := range gw.Hosts {
texts = append(texts, host.Host, host.V2Ray)
}
}
return addressSet(texts)
}
// parseLinesNotEmpty is parseLines for a list that always holds addresses, so
// a file with none fails.
func parseLinesNotEmpty(
r io.Reader, addLine func(*netipx.IPSetBuilder, string) error,
) (*netipx.IPSet, error) {
addresses, err := parseLines(r, addLine)
if err != nil {
return nil, err
}
if len(addresses.Ranges()) == 0 {
return nil, errNoAddresses
}
return addresses, nil
}
// addICloudPrivateRelayNetwork adds the network at the start of a line of
// Apple's iCloud Private Relay file to builder.
func addICloudPrivateRelayNetwork(builder *netipx.IPSetBuilder, line string) error {
field, _, found := strings.Cut(line, iCloudPrivateRelayFieldSeparator)
if !found {
return errNoNetwork
}
network, err := netip.ParsePrefix(field)
if err != nil {
return err
}
builder.AddPrefix(network)
return nil
}
// readJSON reads r to its end and decodes it, as one JSON document, into v.
func readJSON(r io.Reader, v any) error {
data, err := io.ReadAll(r)
if err != nil {
return err
}
return json.Unmarshal(data, v)
}
// addressSet returns the set of the addresses in texts, skipping empty ones.
// A list with no addresses fails, because every VPN service has servers.
func addressSet(texts []string) (*netipx.IPSet, error) {
var builder netipx.IPSetBuilder
for _, text := range texts {
if text == "" {
continue
}
err := addAddress(&builder, text)
if err != nil {
return nil, err
}
}
addresses, err := builder.IPSet()
if err != nil {
return nil, err
}
if len(addresses.Ranges()) == 0 {
return nil, errNoAddresses
}
return addresses, nil
}
// addAddress adds an address, such as 192.0.2.1, to builder.
func addAddress(builder *netipx.IPSetBuilder, text string) error {
addr, err := netip.ParseAddr(text)
if err != nil {
return err
}
builder.Add(addr)
return nil
}
// addAddressWithPort adds the address of text, such as 192.0.2.1:443 or
// [2001:db8::1]:443, to builder. Onionoo allows a list of ports after the
// address, so the part after the address is not read.
func addAddressWithPort(builder *netipx.IPSetBuilder, text string) error {
host, _, err := net.SplitHostPort(text)
if err != nil {
return err
}
return addAddress(builder, host)
}
internal/ptr/cache.go
+324
View File
@@ -0,0 +1,324 @@
// Package ptr looks up the PTR names of addresses over DNS-over-HTTPS. It
// keeps answers in memory for as long as DNS allows, and in cache.db so that
// the answers survive a restart.
package ptr
import (
"context"
"database/sql"
"fmt"
"log/slog"
"maps"
"net/http"
"net/netip"
"slices"
"strings"
"sync"
"time"
"git.eeqj.de/sneak/routewatch/internal/bogon"
"github.com/miekg/dns"
)
const (
// flushInterval is how often new answers are written to cache.db.
flushInterval = 5 * time.Second
// sweepInterval is how often expired answers are deleted.
sweepInterval = 10 * time.Minute
// nameSeparator separates the names in a row of the hostnames table.
nameSeparator = " "
// maxAddresses limits how many addresses the cache holds, so that a public
// lookup cannot grow memory and cache.db without bound.
maxAddresses = 250_000
)
// Params is what New needs.
type Params struct {
// DB is the open cache.db.
DB *sql.DB
// Resolvers are the URLs of the DNS-over-HTTPS resolvers to ask, in order.
Resolvers []string
Logger *slog.Logger
}
// entry is one address's cached answer.
type entry struct {
// names are the address's PTR names, nil when it has none.
names []string
expires time.Time
}
// Cache answers PTR lookups from memory, and asks the resolvers for an address
// it holds no current answer for. Start loads it from cache.db.
type Cache struct {
db *sql.DB
resolvers []string
timeLimit time.Duration
maxEntries int
logger *slog.Logger
client *http.Client
now func() time.Time
// entries holds the kept answers by address, at most maxEntries of them.
// pending holds those that cache.db does not have yet.
mu sync.RWMutex
entries map[string]entry
pending map[string]entry
// stop ends the goroutine Start runs, and done is closed when it returns.
stop context.CancelFunc
done chan struct{}
}
// New returns an empty Cache. Start loads it.
func New(params Params) *Cache {
return &Cache{
db: params.DB,
resolvers: params.Resolvers,
timeLimit: LookupTimeout,
maxEntries: maxAddresses,
logger: params.Logger.With("component", "ptr"),
client: &http.Client{},
now: time.Now,
entries: make(map[string]entry),
pending: make(map[string]entry),
done: make(chan struct{}),
}
}
// LookupAddr returns the PTR names of addr, fully qualified, or none when it
// has none. A reserved address has none, and is not sent to the resolvers. A
// lookup takes at most LookupTimeout. A cached answer makes no outside request.
// It returns an error when no resolver answered, and nothing is cached then.
func (c *Cache) LookupAddr(ctx context.Context, addr string) ([]string, error) {
parsed, err := netip.ParseAddr(addr)
if err != nil {
return nil, fmt.Errorf("parsing the address: %w", err)
}
_, reserved := bogon.Addr(parsed)
if reserved {
return []string{}, nil
}
address := parsed.Unmap().String()
cached, ok := c.current(address)
if ok {
return slices.Clone(cached.names), nil
}
reverseName, err := dns.ReverseAddr(address)
if err != nil {
return nil, fmt.Errorf("building the reverse name: %w", err)
}
result, err := c.lookup(ctx, reverseName)
if err != nil {
return nil, err
}
if result.ttl > 0 {
c.store(address, entry{names: result.names, expires: c.now().Add(result.ttl)})
}
return slices.Clone(result.names), nil
}
// Start loads the answers that have not expired from cache.db. It then starts
// the goroutine that writes new answers there and deletes expired ones. The
// goroutine runs until Stop: the end of ctx does not stop it.
func (c *Cache) Start(ctx context.Context) error {
err := c.load(ctx)
if err != nil {
return err
}
c.logger.Info("PTR cache loaded", "entries", len(c.entries))
ctx, c.stop = context.WithCancel(context.WithoutCancel(ctx))
go c.run(ctx)
return nil
}
// Stop ends the goroutine, which first writes the answers cache.db does not
// have yet, and waits until it has returned or ctx ends.
func (c *Cache) Stop(ctx context.Context) {
c.stop()
select {
case <-c.done:
c.logger.Info("PTR cache stopped")
case <-ctx.Done():
c.logger.Warn("Stop deadline passed before the PTR cache was written")
}
}
// current returns the answer held for address, unless it has expired.
func (c *Cache) current(address string) (entry, bool) {
c.mu.RLock()
defer c.mu.RUnlock()
found, ok := c.entries[address]
if !ok || !c.now().Before(found.expires) {
return entry{}, false
}
return found, true
}
// store keeps an answer in memory and queues it for cache.db. Once entries
// holds maxEntries addresses it keeps no new address. It still replaces the
// answer of an address already held.
func (c *Cache) store(address string, answer entry) {
c.mu.Lock()
defer c.mu.Unlock()
_, held := c.entries[address]
if !held && len(c.entries) >= c.maxEntries {
return
}
c.entries[address] = answer
c.pending[address] = answer
}
// run writes new answers and deletes expired ones until ctx ends.
func (c *Cache) run(ctx context.Context) {
defer close(c.done)
flushes := time.NewTicker(flushInterval)
defer flushes.Stop()
sweeps := time.NewTicker(sweepInterval)
defer sweeps.Stop()
for {
select {
case <-ctx.Done():
c.flush(context.WithoutCancel(ctx))
return
case <-flushes.C:
c.flush(ctx)
case <-sweeps.C:
c.sweep(ctx)
}
}
}
// load reads the rows that have not expired into memory.
func (c *Cache) load(ctx context.Context) error {
rows, err := c.db.QueryContext(ctx,
"SELECT address, names, expires_at FROM hostnames WHERE expires_at > ?",
c.now().Unix())
if err != nil {
return fmt.Errorf("reading the PTR cache: %w", err)
}
defer func() { _ = rows.Close() }()
for rows.Next() {
var (
address, names string
expires int64
)
err = rows.Scan(&address, &names, &expires)
if err != nil {
return fmt.Errorf("reading a PTR cache row: %w", err)
}
c.entries[address] = entry{
names: strings.Fields(names),
expires: time.Unix(expires, 0).UTC(),
}
}
err = rows.Err()
if err != nil {
return fmt.Errorf("reading the PTR cache: %w", err)
}
return nil
}
// flush writes the pending answers to cache.db. Those it cannot write stay
// pending, unless a newer answer for the address has arrived meanwhile.
func (c *Cache) flush(ctx context.Context) {
c.mu.Lock()
batch := c.pending
c.pending = make(map[string]entry)
c.mu.Unlock()
if len(batch) == 0 {
return
}
err := c.writeRows(ctx, batch)
if err == nil {
return
}
c.logger.Error("Failed to write the PTR cache", "error", err)
c.mu.Lock()
defer c.mu.Unlock()
for address, answer := range batch {
_, newer := c.pending[address]
if !newer {
c.pending[address] = answer
}
}
}
// writeRows writes batch to cache.db in one transaction.
func (c *Cache) writeRows(ctx context.Context, batch map[string]entry) error {
tx, err := c.db.BeginTx(ctx, nil)
if err != nil {
return err
}
defer func() { _ = tx.Rollback() }()
for address, answer := range batch {
_, err = tx.ExecContext(ctx,
"INSERT OR REPLACE INTO hostnames (address, names, expires_at) "+
"VALUES (?, ?, ?)",
address,
strings.Join(answer.names, nameSeparator),
answer.expires.Unix())
if err != nil {
return err
}
}
return tx.Commit()
}
// sweep deletes the expired answers from memory and cache.db.
func (c *Cache) sweep(ctx context.Context) {
now := c.now()
expired := func(_ string, answer entry) bool {
return !now.Before(answer.expires)
}
c.mu.Lock()
maps.DeleteFunc(c.entries, expired)
maps.DeleteFunc(c.pending, expired)
c.mu.Unlock()
_, err := c.db.ExecContext(ctx,
"DELETE FROM hostnames WHERE expires_at <= ?", now.Unix())
if err != nil {
c.logger.Error("Failed to delete expired PTR cache rows", "error", err)
}
}
internal/ptr/cache_internal_test.go
+951
View File
@@ -0,0 +1,951 @@
package ptr
import (
"context"
"database/sql"
"errors"
"io"
"log/slog"
"net/http"
"net/http/httptest"
"slices"
"strconv"
"sync"
"testing"
"testing/synctest"
"time"
"git.eeqj.de/sneak/routewatch/internal/cachedb"
"github.com/miekg/dns"
)
// These addresses are public, because a reserved address is not sent to the
// resolvers. That rules out the documentation ranges.
const (
testAddress = "8.8.4.4"
testReverse = "4.4.8.8.in-addr.arpa."
mappedAddress = "::ffff:" + testAddress
otherAddress = "8.8.8.8"
testV6Address = "2606:4700:4700::1111"
testV6Reverse = "1.1.1.1.0.0.0.0.0.0.0.0.0.0.0.0." +
"0.0.0.0.0.0.7.4.0.0.7.4.6.0.6.2.ip6.arpa."
)
const (
testName = "host.example.com."
otherName = "other.example.com."
// testTimeLimit replaces LookupTimeout in the tests that use a real
// server. A stall on a busy host cannot use it up, and no test waits for
// it.
testTimeLimit = 2 * time.Minute
)
// classlessOwner is the name that holds the PTR records of a CNAME chain.
const classlessOwner = "4.0-25.4.8.8.in-addr.arpa."
// fixedTime returns the time a test's clock starts at.
func fixedTime() time.Time {
return time.Date(2026, time.January, 2, 3, 4, 5, 0, time.UTC)
}
// fakeResolver is a DNS-over-HTTPS server. It answers each query with reply's
// result, and counts its requests.
type fakeResolver struct {
server *httptest.Server
mu sync.Mutex
requests int
reply func(http.ResponseWriter, *http.Request, *dns.Msg)
}
// newFakeResolver starts a fake resolver that answers with reply.
func newFakeResolver(
t *testing.T,
reply func(http.ResponseWriter, *http.Request, *dns.Msg),
) *fakeResolver {
t.Helper()
resolver := &fakeResolver{reply: reply}
resolver.server = httptest.NewServer(http.HandlerFunc(resolver.serve))
t.Cleanup(resolver.server.Close)
return resolver
}
// serve checks that the request is RFC 8484 wire format and passes the
// question on to the current reply.
func (f *fakeResolver) serve(w http.ResponseWriter, r *http.Request) {
f.mu.Lock()
f.requests++
reply := f.reply
f.mu.Unlock()
body, err := io.ReadAll(r.Body)
if err != nil {
http.Error(w, err.Error(), http.StatusBadRequest)
return
}
var query dns.Msg
err = query.Unpack(body)
if err != nil || r.Header.Get("Content-Type") != dnsMessageType ||
r.Header.Get("Accept") != dnsMessageType || r.Method != http.MethodPost {
http.Error(w, "not an RFC 8484 request", http.StatusBadRequest)
return
}
reply(w, r, &query)
}
func (f *fakeResolver) setReply(
reply func(http.ResponseWriter, *http.Request, *dns.Msg),
) {
f.mu.Lock()
defer f.mu.Unlock()
f.reply = reply
}
func (f *fakeResolver) requestCount() int {
f.mu.Lock()
defer f.mu.Unlock()
return f.requests
}
// writeReply packs reply and writes it as the answer to query.
func writeReply(w http.ResponseWriter, query, reply *dns.Msg) {
reply.SetReply(query)
wire, err := reply.Pack()
if err != nil {
http.Error(w, err.Error(), http.StatusInternalServerError)
return
}
w.Header().Set("Content-Type", dnsMessageType)
_, _ = w.Write(wire)
}
// ptrReply answers with one PTR record for each name, each with the TTL ttl.
func ptrReply(
ttl uint32, names ...string,
) func(http.ResponseWriter, *http.Request, *dns.Msg) {
return func(w http.ResponseWriter, _ *http.Request, query *dns.Msg) {
reply := new(dns.Msg)
for _, name := range names {
reply.Answer = append(reply.Answer, &dns.PTR{
Hdr: dns.RR_Header{
Name: query.Question[0].Name, Rrtype: dns.TypePTR,
Class: dns.ClassINET, Ttl: ttl,
},
Ptr: name,
})
}
writeReply(w, query, reply)
}
}
// rcodeReply answers with the response code and nothing else.
func rcodeReply(rcode int) func(http.ResponseWriter, *http.Request, *dns.Msg) {
return func(w http.ResponseWriter, _ *http.Request, query *dns.Msg) {
reply := new(dns.Msg)
reply.SetRcode(query, rcode)
wire, err := reply.Pack()
if err != nil {
http.Error(w, err.Error(), http.StatusInternalServerError)
return
}
_, _ = w.Write(wire)
}
}
// soaReply answers with the response code and a SOA record with these TTLs.
func soaReply(
rcode int, soaTTL, minimum uint32,
) func(http.ResponseWriter, *http.Request, *dns.Msg) {
return func(w http.ResponseWriter, _ *http.Request, query *dns.Msg) {
reply := new(dns.Msg)
reply.SetRcode(query, rcode)
reply.Ns = []dns.RR{&dns.SOA{
Hdr: dns.RR_Header{
Name: "arpa.", Rrtype: dns.TypeSOA, Class: dns.ClassINET, Ttl: soaTTL,
},
Ns: "ns.example.com.", Mbox: "hostmaster.example.com.", Minttl: minimum,
}}
wire, err := reply.Pack()
if err != nil {
http.Error(w, err.Error(), http.StatusInternalServerError)
return
}
_, _ = w.Write(wire)
}
}
// hangingReply never answers: it waits until the client gives up.
func hangingReply(_ http.ResponseWriter, r *http.Request, _ *dns.Msg) {
<-r.Context().Done()
}
// statusReply answers with an HTTP status.
func statusReply(status int) func(http.ResponseWriter, *http.Request, *dns.Msg) {
return func(w http.ResponseWriter, _ *http.Request, _ *dns.Msg) {
w.WriteHeader(status)
}
}
// openTestDB opens a cache.db in dir.
func openTestDB(t *testing.T, dir string) *sql.DB {
t.Helper()
db, err := cachedb.Open(t.Context(), dir)
if err != nil {
t.Fatalf("opening the cache database: %v", err)
}
t.Cleanup(func() { _ = db.Close() })
return db
}
// testClock is a clock a test moves by hand.
type testClock struct {
mu sync.Mutex
now time.Time
}
func (c *testClock) time() time.Time {
c.mu.Lock()
defer c.mu.Unlock()
return c.now
}
func (c *testClock) advance(d time.Duration) {
c.mu.Lock()
defer c.mu.Unlock()
c.now = c.now.Add(d)
}
// newTestCache returns a Cache that asks the resolvers in order, reads the
// time from a clock the test holds, has testTimeLimit, and is not started.
func newTestCache(
t *testing.T, db *sql.DB, resolvers ...*fakeResolver,
) (*Cache, *testClock) {
t.Helper()
urls := make([]string, 0, len(resolvers))
for _, resolver := range resolvers {
urls = append(urls, resolver.server.URL)
}
cache := New(Params{DB: db, Resolvers: urls, Logger: slog.Default()})
clock := &testClock{now: fixedTime()}
cache.now = clock.time
cache.timeLimit = testTimeLimit
return cache, clock
}
// handlerTransport hands each request to the fake resolver for its host, with
// no network between them. A test in a synctest bubble needs this: the bubble's
// clock stands still while one of its goroutines waits on a real connection. As
// over a network, a request whose time is up is not sent.
type handlerTransport map[string]*fakeResolver
func (h handlerTransport) RoundTrip(r *http.Request) (*http.Response, error) {
recorder := httptest.NewRecorder()
if r.Context().Err() == nil {
h[r.URL.Host].serve(recorder, r)
}
err := r.Context().Err()
if err != nil {
return nil, err
}
return recorder.Result(), nil
}
// newBubbleCache returns a Cache with the real time limit, for a test in a
// synctest bubble. It has one fake resolver for each reply, in order, reached
// through a handlerTransport.
func newBubbleCache(
replies ...func(http.ResponseWriter, *http.Request, *dns.Msg),
) (*Cache, []*fakeResolver) {
transport := make(handlerTransport, len(replies))
resolvers := make([]*fakeResolver, 0, len(replies))
urls := make([]string, 0, len(replies))
for i, reply := range replies {
host := "resolver" + strconv.Itoa(i) + ".example.com"
resolver := &fakeResolver{reply: reply}
transport[host] = resolver
resolvers = append(resolvers, resolver)
urls = append(urls, "https://"+host+"/dns-query")
}
cache := New(Params{Resolvers: urls, Logger: slog.Default()})
cache.client = &http.Client{Transport: transport}
return cache, resolvers
}
// lookupOK looks up address and fails the test on an error.
func lookupOK(t *testing.T, cache *Cache, address string) []string {
t.Helper()
names, err := cache.LookupAddr(t.Context(), address)
if err != nil {
t.Fatalf("LookupAddr(%s): %v", address, err)
}
return names
}
func countRows(t *testing.T, db *sql.DB) int {
t.Helper()
var rows int
err := db.QueryRowContext(t.Context(),
"SELECT COUNT(*) FROM hostnames").Scan(&rows)
if err != nil {
t.Fatalf("counting rows: %v", err)
}
return rows
}
func TestLookupAsksForTheReverseName(t *testing.T) {
t.Parallel()
tests := []struct {
address string
want string
}{
{testAddress, testReverse},
{mappedAddress, testReverse},
{testV6Address, testV6Reverse},
}
for _, tt := range tests {
var asked string
resolver := newFakeResolver(t,
func(w http.ResponseWriter, r *http.Request, query *dns.Msg) {
asked = query.Question[0].Name
if query.Question[0].Qtype != dns.TypePTR {
t.Errorf("query type %d, want PTR", query.Question[0].Qtype)
}
ptrReply(300, testName)(w, r, query)
})
cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
names := lookupOK(t, cache, tt.address)
if !slices.Equal(names, []string{testName}) {
t.Errorf("%s: names %v, want %s", tt.address, names, testName)
}
if asked != tt.want {
t.Errorf("%s: asked for %s, want %s", tt.address, asked, tt.want)
}
}
}
// TestOnlyPublicAddressesAreSentToTheResolvers gives every resolver an answer
// to send, which a reserved address must not get.
func TestOnlyPublicAddressesAreSentToTheResolvers(t *testing.T) {
t.Parallel()
tests := []struct {
name string
address string
want []string
requests int
}{
{"private IPv4", "10.0.0.1", []string{}, 0},
{"documentation IPv4", "192.0.2.1", []string{}, 0},
{"private IPv4 in IPv6 form", "::ffff:10.0.0.1", []string{}, 0},
{"unique-local IPv6", "fd00::1", []string{}, 0},
{"documentation IPv6", "2001:db8::1", []string{}, 0},
{"public IPv4", testAddress, []string{testName}, 1},
{"public IPv4 in IPv6 form", mappedAddress, []string{testName}, 1},
{"public IPv6", testV6Address, []string{testName}, 1},
}
for _, tt := range tests {
resolver := newFakeResolver(t, ptrReply(300, testName))
cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
names := lookupOK(t, cache, tt.address)
if names == nil || !slices.Equal(names, tt.want) {
t.Errorf("%s: names %#v, want %#v", tt.name, names, tt.want)
}
if got := resolver.requestCount(); got != tt.requests {
t.Errorf("%s: %d requests, want %d", tt.name, got, tt.requests)
}
}
}
// TestResolversAreTriedInOrderUntilOneAnswers has the first two resolvers fail,
// in different ways, and the third answer. The fourth is not asked.
func TestResolversAreTriedInOrderUntilOneAnswers(t *testing.T) {
t.Parallel()
var (
mu sync.Mutex
order []int
)
asked := func(
index int, reply func(http.ResponseWriter, *http.Request, *dns.Msg),
) func(http.ResponseWriter, *http.Request, *dns.Msg) {
return func(w http.ResponseWriter, r *http.Request, query *dns.Msg) {
mu.Lock()
order = append(order, index)
mu.Unlock()
reply(w, r, query)
}
}
resolvers := []*fakeResolver{
newFakeResolver(t, asked(0, statusReply(http.StatusServiceUnavailable))),
newFakeResolver(t, asked(1, rcodeReply(dns.RcodeServerFailure))),
newFakeResolver(t, asked(2, ptrReply(300, testName))),
newFakeResolver(t, asked(3, ptrReply(300, otherName))),
}
cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), resolvers...)
names := lookupOK(t, cache, testAddress)
if !slices.Equal(names, []string{testName}) {
t.Errorf("names %v, want %s", names, testName)
}
if !slices.Equal(order, []int{0, 1, 2}) {
t.Errorf("resolvers asked %v, want [0 1 2]", order)
}
}
// TestResolverThatNeverAnswersLeavesTimeForTheNext would fail if the first
// resolver could take the whole time limit. The first gets half of it, the
// share of one resolver in two. The test runs in a synctest bubble, whose clock
// is fake, so a stall on the host uses none of the limit.
func TestResolverThatNeverAnswersLeavesTimeForTheNext(t *testing.T) {
t.Parallel()
synctest.Test(t, func(t *testing.T) {
cache, _ := newBubbleCache(hangingReply, ptrReply(300, testName))
start := time.Now()
names := lookupOK(t, cache, testAddress)
elapsed := time.Since(start)
if !slices.Equal(names, []string{testName}) {
t.Errorf("names %v, want %s", names, testName)
}
if elapsed != time.Second {
t.Errorf("took %s, want 1s", elapsed)
}
})
}
// TestLookupStopsAtTheTimeLimit has no resolver answer. The lookup fails when
// 2 seconds have passed, having asked every resolver. The test runs in a
// synctest bubble, whose clock is fake, so a stall on the host uses none of the
// limit.
func TestLookupStopsAtTheTimeLimit(t *testing.T) {
t.Parallel()
synctest.Test(t, func(t *testing.T) {
cache, resolvers := newBubbleCache(
hangingReply, hangingReply, hangingReply, hangingReply)
start := time.Now()
_, err := cache.LookupAddr(t.Context(), testAddress)
elapsed := time.Since(start)
if !errors.Is(err, context.DeadlineExceeded) {
t.Errorf("error %v, want %v", err, context.DeadlineExceeded)
}
if elapsed != 2*time.Second {
t.Errorf("took %s, want 2s", elapsed)
}
for i, resolver := range resolvers {
if resolver.requestCount() != 1 {
t.Errorf("resolver %d asked %d times, want once",
i, resolver.requestCount())
}
}
})
}
// TestAnswerIsServedFromMemoryUntilItExpires makes a second lookup within the
// TTL, which asks nobody, and a third after it, which asks again.
func TestAnswerIsServedFromMemoryUntilItExpires(t *testing.T) {
t.Parallel()
resolver := newFakeResolver(t, ptrReply(300, testName))
cache, clock := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
lookupOK(t, cache, testAddress)
names := lookupOK(t, cache, testAddress)
if !slices.Equal(names, []string{testName}) {
t.Errorf("cached names %v, want %s", names, testName)
}
if got := resolver.requestCount(); got != 1 {
t.Errorf("%d requests after the second lookup, want 1", got)
}
clock.advance(300 * time.Second)
lookupOK(t, cache, testAddress)
if got := resolver.requestCount(); got != 2 {
t.Errorf("%d requests after the TTL passed, want 2", got)
}
}
// TestAnAddressHasOneCacheEntryHoweverItIsWritten looks up an IPv4 address in
// its IPv4-mapped IPv6 form, then in its usual form.
func TestAnAddressHasOneCacheEntryHoweverItIsWritten(t *testing.T) {
t.Parallel()
resolver := newFakeResolver(t, ptrReply(300, testName))
cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
lookupOK(t, cache, mappedAddress)
lookupOK(t, cache, testAddress)
if got := resolver.requestCount(); got != 1 {
t.Errorf("%d requests, want 1", got)
}
}
// TestCallerCannotChangeACachedAnswer changes the list each lookup returned, as
// the server does when it removes the trailing dots. The second lookup is the
// first answered from the cache. The third shows that the cached list did not
// change with the list the second returned.
func TestCallerCannotChangeACachedAnswer(t *testing.T) {
t.Parallel()
resolver := newFakeResolver(t, ptrReply(300, testName))
cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
for range 3 {
names := lookupOK(t, cache, testAddress)
if !slices.Equal(names, []string{testName}) {
t.Errorf("names %v, want %s", names, testName)
}
names[0] = "changed"
}
}
func TestTTLIsClamped(t *testing.T) {
t.Parallel()
tests := []struct {
name string
ttl uint32
want time.Duration
}{
{"below the minimum", 1, time.Minute},
{"zero", 0, time.Minute},
{"at the minimum", 60, time.Minute},
{"in range", 300, 300 * time.Second},
{"at the maximum", 86400, 24 * time.Hour},
{"above the maximum", 604800, 24 * time.Hour},
}
for _, tt := range tests {
resolver := newFakeResolver(t, ptrReply(tt.ttl, testName))
cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
lookupOK(t, cache, testAddress)
got := cache.entries[testAddress].expires.Sub(fixedTime())
if got != tt.want {
t.Errorf("%s: kept for %s, want %s", tt.name, got, tt.want)
}
}
}
// TestSmallestTTLOfTheChainCounts answers with a CNAME record and two PTR
// records, whose TTLs all differ.
func TestSmallestTTLOfTheChainCounts(t *testing.T) {
t.Parallel()
reply := func(w http.ResponseWriter, _ *http.Request, query *dns.Msg) {
owner := query.Question[0].Name
answer := new(dns.Msg)
answer.Answer = []dns.RR{
&dns.CNAME{
Hdr: dns.RR_Header{
Name: owner, Rrtype: dns.TypeCNAME, Class: dns.ClassINET, Ttl: 200,
},
Target: classlessOwner,
},
&dns.PTR{
Hdr: dns.RR_Header{
Name: classlessOwner, Rrtype: dns.TypePTR,
Class: dns.ClassINET, Ttl: 900,
},
Ptr: testName,
},
&dns.PTR{
Hdr: dns.RR_Header{
Name: classlessOwner, Rrtype: dns.TypePTR,
Class: dns.ClassINET, Ttl: 600,
},
Ptr: otherName,
},
}
writeReply(w, query, answer)
}
cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), newFakeResolver(t, reply))
names := lookupOK(t, cache, testAddress)
if !slices.Equal(names, []string{testName, otherName}) {
t.Errorf("names %v, want both PTR names", names)
}
got := cache.entries[testAddress].expires.Sub(fixedTime())
if got != 200*time.Second {
t.Errorf("kept for %s, want 200s", got)
}
}
func TestNegativeTTL(t *testing.T) {
t.Parallel()
tests := []struct {
name string
rcode int
soaTTL uint32
minimum uint32
want time.Duration
}{
{"name does not exist", dns.RcodeNameError, 3600, 300, 300 * time.Second},
{"no PTR record", dns.RcodeSuccess, 3600, 300, 300 * time.Second},
{"limited to an hour", dns.RcodeNameError, 86400, 7200, time.Hour},
{"SOA's own TTL is smaller", dns.RcodeNameError, 100, 300, 100 * time.Second},
}
for _, tt := range tests {
resolver := newFakeResolver(t, soaReply(tt.rcode, tt.soaTTL, tt.minimum))
cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
names := lookupOK(t, cache, testAddress)
if len(names) != 0 {
t.Errorf("%s: names %v, want none", tt.name, names)
}
got := cache.entries[testAddress].expires.Sub(fixedTime())
if got != tt.want {
t.Errorf("%s: kept for %s, want %s", tt.name, got, tt.want)
}
lookupOK(t, cache, testAddress)
if count := resolver.requestCount(); count != 1 {
t.Errorf("%s: %d requests, want 1", tt.name, count)
}
}
}
// TestAnswerWithoutNamesOrSOAIsNotCached has nothing to say how long the
// answer may be kept.
func TestAnswerWithoutNamesOrSOAIsNotCached(t *testing.T) {
t.Parallel()
resolver := newFakeResolver(t, rcodeReply(dns.RcodeNameError))
cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
lookupOK(t, cache, testAddress)
lookupOK(t, cache, testAddress)
if got := resolver.requestCount(); got != 2 {
t.Errorf("%d requests, want 2", got)
}
}
// TestFailedQueryIsNotCached has the only resolver fail, and then recover.
func TestFailedQueryIsNotCached(t *testing.T) {
t.Parallel()
resolver := newFakeResolver(t, rcodeReply(dns.RcodeServerFailure))
cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
_, err := cache.LookupAddr(t.Context(), testAddress)
if !errors.Is(err, errBadResponse) {
t.Fatalf("error %v, want %v", err, errBadResponse)
}
if len(cache.entries)+len(cache.pending) != 0 {
t.Error("a failed query left an entry in the cache")
}
resolver.setReply(ptrReply(300, testName))
names := lookupOK(t, cache, testAddress)
if !slices.Equal(names, []string{testName}) {
t.Errorf("names %v, want %s", names, testName)
}
}
// TestNamesThatAreNotHostNamesAreDropped answers with a name that holds markup
// beside a good one, as a PTR record can.
func TestNamesThatAreNotHostNamesAreDropped(t *testing.T) {
t.Parallel()
resolver := newFakeResolver(t,
ptrReply(300, "bad<script>.example.com.", testName, "."))
cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
names := lookupOK(t, cache, testAddress)
if !slices.Equal(names, []string{testName}) {
t.Errorf("names %v, want only %s", names, testName)
}
}
// TestCacheSurvivesARestart stops a cache that holds a positive and a negative
// answer, and starts a new one on the reopened file. It makes no request.
func TestCacheSurvivesARestart(t *testing.T) {
t.Parallel()
dir := t.TempDir()
db := openTestDB(t, dir)
resolver := newFakeResolver(t,
func(w http.ResponseWriter, r *http.Request, query *dns.Msg) {
if query.Question[0].Name == testReverse {
ptrReply(300, testName, otherName)(w, r, query)
return
}
soaReply(dns.RcodeNameError, 3600, 300)(w, r, query)
})
cache, _ := newTestCache(t, db, resolver)
err := cache.Start(t.Context())
if err != nil {
t.Fatalf("Start: %v", err)
}
lookupOK(t, cache, testAddress)
lookupOK(t, cache, otherAddress)
cache.Stop(t.Context())
err = db.Close()
if err != nil {
t.Fatalf("closing the database: %v", err)
}
restarted, _ := newTestCache(t, openTestDB(t, dir), resolver)
err = restarted.Start(t.Context())
if err != nil {
t.Fatalf("Start after the restart: %v", err)
}
defer restarted.Stop(t.Context())
requestsBefore := resolver.requestCount()
names := lookupOK(t, restarted, testAddress)
if !slices.Equal(names, []string{testName, otherName}) {
t.Errorf("names after restart %v", names)
}
if names := lookupOK(t, restarted, otherAddress); len(names) != 0 {
t.Errorf("names of the address with none after restart: %v", names)
}
if got := resolver.requestCount(); got != requestsBefore {
t.Errorf("%d requests after the restart, want none",
got-requestsBefore)
}
}
// TestSweepDeletesExpiredRows also checks that a restart does not load a row
// that has expired since it was written.
func TestSweepDeletesExpiredRows(t *testing.T) {
t.Parallel()
db := openTestDB(t, t.TempDir())
resolver := newFakeResolver(t,
func(w http.ResponseWriter, r *http.Request, query *dns.Msg) {
ttl := uint32(300)
if query.Question[0].Name == testReverse {
ttl = 60
}
ptrReply(ttl, testName)(w, r, query)
})
cache, clock := newTestCache(t, db, resolver)
lookupOK(t, cache, testAddress)
lookupOK(t, cache, otherAddress)
cache.flush(t.Context())
if got := countRows(t, db); got != 2 {
t.Fatalf("%d rows before the sweep, want 2", got)
}
clock.advance(90 * time.Second)
loaded, loadedClock := newTestCache(t, db, resolver)
loadedClock.advance(90 * time.Second)
err := loaded.load(t.Context())
if err != nil {
t.Fatalf("load: %v", err)
}
if len(loaded.entries) != 1 {
t.Errorf("loaded %d entries, want the 1 not expired", len(loaded.entries))
}
cache.sweep(t.Context())
if got := countRows(t, db); got != 1 {
t.Errorf("%d rows after the sweep, want 1", got)
}
if len(cache.entries) != 1 {
t.Errorf("%d entries in memory after the sweep, want 1", len(cache.entries))
}
}
// TestFlushKeepsAnswersItCouldNotWrite makes one write fail by hiding the
// table. The next write, once the table is back, stores the answer.
func TestFlushKeepsAnswersItCouldNotWrite(t *testing.T) {
t.Parallel()
db := openTestDB(t, t.TempDir())
resolver := newFakeResolver(t, ptrReply(300, testName))
cache, _ := newTestCache(t, db, resolver)
lookupOK(t, cache, testAddress)
_, err := db.ExecContext(t.Context(), "ALTER TABLE hostnames RENAME TO hidden")
if err != nil {
t.Fatalf("renaming the table: %v", err)
}
cache.flush(t.Context())
_, err = db.ExecContext(t.Context(), "ALTER TABLE hidden RENAME TO hostnames")
if err != nil {
t.Fatalf("renaming the table back: %v", err)
}
if got := countRows(t, db); got != 0 {
t.Fatalf("%d rows after the failed write, want 0", got)
}
cache.flush(t.Context())
if got := countRows(t, db); got != 1 {
t.Errorf("%d rows after the second write, want 1", got)
}
}
// TestNewAddressIsNotKeptAtTheLimit fills a cache that holds one address. A
// lookup of a second address still returns its answer, and the cache keeps
// nothing for it until the sweep has deleted the first address's expired
// answer.
func TestNewAddressIsNotKeptAtTheLimit(t *testing.T) {
t.Parallel()
db := openTestDB(t, t.TempDir())
resolver := newFakeResolver(t, ptrReply(300, testName))
cache, clock := newTestCache(t, db, resolver)
cache.maxEntries = 1
lookupOK(t, cache, testAddress)
names := lookupOK(t, cache, otherAddress)
if !slices.Equal(names, []string{testName}) {
t.Errorf("names %v at the limit, want %s", names, testName)
}
_, inEntries := cache.entries[otherAddress]
_, inPending := cache.pending[otherAddress]
if inEntries || inPending {
t.Errorf("a new address was kept at the limit: in entries %t, in pending %t",
inEntries, inPending)
}
cache.flush(t.Context())
if got := countRows(t, db); got != 1 {
t.Errorf("%d rows at the limit, want 1", got)
}
clock.advance(300 * time.Second)
cache.sweep(t.Context())
lookupOK(t, cache, otherAddress)
_, inEntries = cache.entries[otherAddress]
if !inEntries {
t.Error("a new address was not kept after the sweep made room")
}
}
// TestHeldAddressIsReplacedAtTheLimit lets the answer of the only address a
// cache holds expire. The new answer replaces it in memory and is queued for
// cache.db.
func TestHeldAddressIsReplacedAtTheLimit(t *testing.T) {
t.Parallel()
resolver := newFakeResolver(t, ptrReply(300, testName))
cache, clock := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
cache.maxEntries = 1
lookupOK(t, cache, testAddress)
clock.advance(300 * time.Second)
resolver.setReply(ptrReply(300, otherName))
lookupOK(t, cache, testAddress)
want := []string{otherName}
if got := cache.entries[testAddress].names; !slices.Equal(got, want) {
t.Errorf("entries holds %v, want %v", got, want)
}
if got := cache.pending[testAddress].names; !slices.Equal(got, want) {
t.Errorf("pending holds %v, want %v", got, want)
}
}
internal/ptr/doh.go
+200
View File
@@ -0,0 +1,200 @@
package ptr
import (
"bytes"
"context"
"errors"
"fmt"
"io"
"math"
"net/http"
"strings"
"time"
"github.com/miekg/dns"
)
const (
// LookupTimeout limits one address's lookup, every resolver included.
LookupTimeout = 2 * time.Second
// minTTL and maxTTL limit how long PTR names are kept.
minTTL = time.Minute
maxTTL = 24 * time.Hour
// maxNegativeTTL limits how long an address with no PTR names is
// remembered as having none.
maxNegativeTTL = time.Hour
// dnsMessageType is the content type of RFC 8484 requests and answers.
dnsMessageType = "application/dns-message"
// maxMessageBytes is the largest possible DNS message.
maxMessageBytes = 65535
)
var (
errBadStatus = errors.New("unexpected HTTP status")
errBadResponse = errors.New("resolver reported an error")
)
// Resolvers returns the URLs of the public DNS-over-HTTPS resolvers, in the
// order they are tried.
func Resolvers() []string {
return []string{
"https://dns.google/dns-query",
"https://cloudflare-dns.com/dns-query",
"https://unfiltered.adguard-dns.com/dns-query",
"https://dns.quad9.net/dns-query",
}
}
// answer is a resolver's answer for one address.
type answer struct {
// names are the address's PTR names, nil when it has none.
names []string
// ttl is how long the answer may be kept. Zero means it is not kept.
ttl time.Duration
}
// lookup asks the resolvers in turn for the PTR names of the reverse name
// until one answers. It fails when none has answered within the time limit.
func (c *Cache) lookup(ctx context.Context, reverseName string) (answer, error) {
ctx, cancel := context.WithTimeout(ctx, c.timeLimit)
defer cancel()
query := new(dns.Msg).SetQuestion(reverseName, dns.TypePTR)
query.Id = 0 // RFC 8484 asks for 0, so that equal queries can be cached.
wire, err := query.Pack()
if err != nil {
return answer{}, fmt.Errorf("packing the query: %w", err)
}
var failures []error
for i, resolver := range c.resolvers {
// Each resolver gets an equal share of the time left, so that one
// that never answers leaves time for the next.
deadline, _ := ctx.Deadline()
share := time.Until(deadline) / time.Duration(len(c.resolvers)-i)
result, err := c.ask(ctx, resolver, wire, share)
if err == nil {
return result, nil
}
failures = append(failures, fmt.Errorf("%s: %w", resolver, err))
}
return answer{}, errors.Join(failures...)
}
// ask sends the query to one resolver and waits at most timeout for its answer.
func (c *Cache) ask(
ctx context.Context, resolver string, query []byte, timeout time.Duration,
) (answer, error) {
ctx, cancel := context.WithTimeout(ctx, timeout)
defer cancel()
request, err := http.NewRequestWithContext(
ctx, http.MethodPost, resolver, bytes.NewReader(query))
if err != nil {
return answer{}, err
}
request.Header.Set("Content-Type", dnsMessageType)
request.Header.Set("Accept", dnsMessageType)
response, err := c.client.Do(request)
if err != nil {
return answer{}, err
}
defer func() { _ = response.Body.Close() }()
if response.StatusCode != http.StatusOK {
return answer{}, fmt.Errorf("%w: %d", errBadStatus, response.StatusCode)
}
body, err := io.ReadAll(io.LimitReader(response.Body, maxMessageBytes))
if err != nil {
return answer{}, err
}
var reply dns.Msg
err = reply.Unpack(body)
if err != nil {
return answer{}, err
}
return answerFrom(&reply)
}
// answerFrom reads a resolver's reply. A name that does not exist and a name
// with no PTR records are answers. Every other response code is a failure.
func answerFrom(reply *dns.Msg) (answer, error) {
if reply.Rcode != dns.RcodeSuccess && reply.Rcode != dns.RcodeNameError {
return answer{}, fmt.Errorf("%w: %s",
errBadResponse, dns.RcodeToString[reply.Rcode])
}
var names []string
seconds := uint32(math.MaxUint32)
for _, record := range reply.Answer {
// The chain to a PTR record can hold CNAME records, and the answer
// is good only as long as every record in it.
seconds = min(seconds, record.Header().Ttl)
ptr, ok := record.(*dns.PTR)
if ok && isHostName(ptr.Ptr) {
names = append(names, ptr.Ptr)
}
}
if len(names) == 0 {
return answer{ttl: negativeTTL(reply.Ns)}, nil
}
ttl := time.Duration(seconds) * time.Second
return answer{names: names, ttl: min(max(ttl, minTTL), maxTTL)}, nil
}
// negativeTTL returns how long a reply with no PTR names may be kept: the
// smaller of the SOA record's own TTL and its minimum field (RFC 2308), at most
// maxNegativeTTL. Without a SOA record it is zero.
func negativeTTL(authority []dns.RR) time.Duration {
for _, record := range authority {
soa, ok := record.(*dns.SOA)
if ok {
ttl := time.Duration(min(soa.Hdr.Ttl, soa.Minttl)) * time.Second
return min(ttl, maxNegativeTTL)
}
}
return 0
}
// isHostName reports whether name is a host name. A PTR record can hold any
// bytes, and the names go into web pages, so anything else is dropped, as
// net.Resolver.LookupAddr drops it. The root name is not a host name.
func isHostName(name string) bool {
_, ok := dns.IsDomainName(name)
return ok && name != "." && !strings.ContainsFunc(name, notInHostName)
}
// notInHostName reports whether r cannot be part of a host name.
func notInHostName(r rune) bool {
return !strings.ContainsRune(hostNameCharacters, r)
}
// hostNameCharacters are the characters of a host name, in presentation format.
const hostNameCharacters = "abcdefghijklmnopqrstuvwxyz" +
"ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_."
internal/routetable/originchanges.go
+103
View File
@@ -0,0 +1,103 @@
package routetable
import (
"net/netip"
"slices"
"time"
)
// MaxWaitingOriginChanges is the most origin changes the table keeps waiting
// for the prefix handler to write. The oldest change past it is dropped and
// counted.
const MaxWaitingOriginChanges = 100000
// OriginChange is one change of a prefix and origin AS pair: the origin AS
// gained its first peer, or lost its last.
type OriginChange struct {
Prefix netip.Prefix
OriginASN int
// Announced says the origin AS gained its first peer. When false, it
// lost its last peer.
Announced bool
// PeerCount is how many peers carry the prefix just after the change,
// counting every origin AS.
PeerCount int
// Time is when RouteWatch applied the change.
Time time.Time
}
// recordOriginChange records that the pair of prefix and asn gained its first
// peer, when announced, or lost its last, when not. The caller holds the lock.
// peerCount is how many peers carry the prefix just after the change.
func (t *Table) recordOriginChange(
prefix netip.Prefix, asn int, announced bool, peerCount int,
) {
change := OriginChange{
Prefix: prefix,
OriginASN: asn,
Announced: announced,
PeerCount: peerCount,
Time: t.now(),
}
t.originChanges = append(t.originChanges, change)
t.trimOriginChanges()
}
// TakeOriginChanges returns at most limit of the origin changes that wait to
// be written, oldest first, and how many were dropped since the last call. It
// then forgets what it returned.
func (t *Table) TakeOriginChanges(limit int) ([]OriginChange, int) {
t.mu.Lock()
defer t.mu.Unlock()
n := min(limit, len(t.originChanges))
changes := slices.Clone(t.originChanges[:n])
t.originChanges = t.originChanges[n:]
dropped := t.originChangesDropped
t.originChangesDropped = 0
return changes, dropped
}
// PutBackOriginChanges records again what one TakeOriginChanges call returned,
// for a caller that could not write it. The next TakeOriginChanges returns
// those changes first, before the ones that arrived since. The oldest changes
// past the cap are dropped and counted.
func (t *Table) PutBackOriginChanges(changes []OriginChange) {
t.mu.Lock()
defer t.mu.Unlock()
t.originChanges = append(changes, t.originChanges...)
t.trimOriginChanges()
}
// trimOriginChanges drops the oldest origin changes past the cap and counts
// them. The caller holds the lock.
func (t *Table) trimOriginChanges() {
if extra := len(t.originChanges) - MaxWaitingOriginChanges; extra > 0 {
t.originChangesDropped += extra
t.originChanges = t.originChanges[extra:]
}
}
// OriginChangeCount returns how many origin changes wait for TakeOriginChanges.
func (t *Table) OriginChangeCount() int {
t.mu.RLock()
defer t.mu.RUnlock()
return len(t.originChanges)
}
// prefixPeerCount returns how many peers carry prefix, counting every origin
// AS. The caller holds the lock.
func (t *Table) prefixPeerCount(prefix netip.Prefix) int {
count := 0
for _, o := range t.origins(prefix) {
count += int(o.peers.Count())
}
return count
}
internal/routetable/originchanges_test.go
+302
View File
@@ -0,0 +1,302 @@
package routetable_test
import (
"math"
"net/netip"
"reflect"
"testing"
"time"
"github.com/bits-and-blooms/bitset"
"git.eeqj.de/sneak/routewatch/internal/routetable"
)
// originChange returns the origin change the table records for prefix and asn
// at the clock's time, announced or withdrawn, with peerCount peers.
func originChange(
prefix netip.Prefix, asn int, announced bool, peerCount int, at time.Time,
) routetable.OriginChange {
return routetable.OriginChange{
Prefix: prefix,
OriginASN: asn,
Announced: announced,
PeerCount: peerCount,
Time: at,
}
}
// TestOriginChangesRecordAnnouncedAndWithdrawn checks that a prefix and origin
// AS pair records an announced row when it gains its first peer, nothing for a
// second peer, and a withdrawn row when it loses its last peer.
func TestOriginChangesRecordAnnouncedAndWithdrawn(t *testing.T) {
t.Parallel()
now := at(0)
table := routetable.New(routetable.Params{
Now: func() time.Time { return now },
})
prefix := netip.MustParsePrefix(prefixV4)
table.Announce(prefix, asA, routeOf(peerA, asA, 10))
table.Announce(prefix, asA, routeOf(peerB, asA, 20))
checkOriginChanges(t, table, []routetable.OriginChange{
originChange(prefix, asA, true, 1, now),
})
table.Withdraw(prefix, peerA)
table.Withdraw(prefix, peerB)
checkOriginChanges(t, table, []routetable.OriginChange{
originChange(prefix, asA, false, 0, now),
})
}
// TestOriginChangesRecordAPeerMovingOrigin checks that a peer moving from one
// origin AS to another records a withdrawn row for the old one and an
// announced row for the new one.
func TestOriginChangesRecordAPeerMovingOrigin(t *testing.T) {
t.Parallel()
now := at(0)
table := routetable.New(routetable.Params{
Now: func() time.Time { return now },
})
prefix := netip.MustParsePrefix(prefixV4)
table.Announce(prefix, asA, routeOf(peerA, asA, 10))
table.Announce(prefix, asB, routeOf(peerA, asB, 20))
checkOriginChanges(t, table, []routetable.OriginChange{
originChange(prefix, asA, true, 1, now),
originChange(prefix, asA, false, 0, now),
originChange(prefix, asB, true, 1, now),
})
}
// TestOriginChangesRecordPeersDown checks that PeersDown records a withdrawn
// row for each prefix and origin AS pair it empties.
func TestOriginChangesRecordPeersDown(t *testing.T) {
t.Parallel()
now := at(0)
table := routetable.New(routetable.Params{
Now: func() time.Time { return now },
})
v4 := netip.MustParsePrefix(prefixV4)
v6 := netip.MustParsePrefix(prefixV6)
table.Announce(v4, asA, routeOf(peerA, asA, 10))
table.Announce(v6, asA, routeOf(peerA, asA, 10))
table.Announce(v4, asB, routeOf(peerB, asB, 20))
table.PeersDown([]string{peerA})
// peerA carried v4 and v6 with asA; both pairs are emptied. peerB still
// carries v4 with asB, so that pair is not.
checkOriginChanges(t, table, []routetable.OriginChange{
originChange(v4, asA, true, 1, now),
originChange(v6, asA, true, 1, now),
originChange(v4, asB, true, 2, now),
originChange(v4, asA, false, 1, now),
originChange(v6, asA, false, 0, now),
})
}
// TestOriginChangesLoadRecordsNothing checks that Load records no origin
// change.
func TestOriginChangesLoadRecordsNothing(t *testing.T) {
t.Parallel()
table := routetable.New(routetable.Params{
PeerNumbers: map[string]uint{peerA: 0},
})
prefix := netip.MustParsePrefix(prefixV4)
peers := new(bitset.BitSet)
peers.Set(0)
table.Load(routetable.Change{
Prefix: prefix,
OriginASN: asA,
Peers: peers,
Routes: []routetable.Route{routeOf(peerA, asA, 10)},
})
changes, dropped := table.TakeOriginChanges(math.MaxInt)
if dropped != 0 || len(changes) != 0 {
t.Errorf("TakeOriginChanges = %+v, %d; want none", changes, dropped)
}
}
// TestOriginChangesTakeReturnsOldestFirst checks that TakeOriginChanges
// returns the changes oldest first and at most max.
func TestOriginChangesTakeReturnsOldestFirst(t *testing.T) {
t.Parallel()
table := routetable.New(routetable.Params{})
prefix := netip.MustParsePrefix(prefixV4)
table.Announce(prefix, asA, routeOf(peerA, asA, 10))
table.Announce(prefix, asB, routeOf(peerB, asB, 20))
table.Announce(prefix, asC, routeOf(peerC, asC, 30))
first, dropped := table.TakeOriginChanges(2)
if dropped != 0 {
t.Errorf("dropped = %d, want 0", dropped)
}
if len(first) != 2 || first[0].OriginASN != asA || first[1].OriginASN != asB {
t.Errorf("first TakeOriginChanges = %+v, want the first two", first)
}
second, _ := table.TakeOriginChanges(math.MaxInt)
if len(second) != 1 || second[0].OriginASN != asC {
t.Errorf("second TakeOriginChanges = %+v, want the third", second)
}
}
// TestOriginChangesPutBackPutsRowsInFront checks that PutBackOriginChanges
// puts rows back in front, so the next TakeOriginChanges returns them first.
func TestOriginChangesPutBackPutsRowsInFront(t *testing.T) {
t.Parallel()
table := routetable.New(routetable.Params{})
prefix := netip.MustParsePrefix(prefixV4)
table.Announce(prefix, asA, routeOf(peerA, asA, 10))
table.Announce(prefix, asB, routeOf(peerB, asB, 20))
taken, _ := table.TakeOriginChanges(math.MaxInt)
table.Announce(prefix, asC, routeOf(peerC, asC, 30))
table.PutBackOriginChanges(taken)
changes, _ := table.TakeOriginChanges(math.MaxInt)
if len(changes) != 3 || changes[0].OriginASN != asA ||
changes[1].OriginASN != asB || changes[2].OriginASN != asC {
t.Errorf("TakeOriginChanges = %+v, want the put-back rows first", changes)
}
}
// TestOriginChangesDropPastTheLimit checks that a change past 100,000 waiting
// rows is dropped and counted.
func TestOriginChangesDropPastTheLimit(t *testing.T) {
t.Parallel()
table := routetable.New(routetable.Params{})
addr := netip.MustParseAddr("10.0.0.0")
for range routetable.MaxWaitingOriginChanges + 1 {
prefix := netip.PrefixFrom(addr, 32)
table.Announce(prefix, asA, routeOf(peerA, asA, 10))
addr = addr.Next()
}
changes, dropped := table.TakeOriginChanges(routetable.MaxWaitingOriginChanges)
if dropped != 1 {
t.Errorf("dropped = %d, want 1", dropped)
}
if len(changes) != routetable.MaxWaitingOriginChanges {
t.Errorf("len(changes) = %d, want %d", len(changes),
routetable.MaxWaitingOriginChanges)
}
}
// TestOriginChangesTakeResetsTheDroppedCount checks that a TakeOriginChanges
// that reports dropped rows leaves the next one reporting none, so each drop
// is logged once, not on every later write.
func TestOriginChangesTakeResetsTheDroppedCount(t *testing.T) {
t.Parallel()
table := routetable.New(routetable.Params{})
addr := netip.MustParseAddr("10.0.0.0")
for range routetable.MaxWaitingOriginChanges + 1 {
table.Announce(netip.PrefixFrom(addr, 32), asA, routeOf(peerA, asA, 10))
addr = addr.Next()
}
_, dropped := table.TakeOriginChanges(routetable.MaxWaitingOriginChanges)
if dropped != 1 {
t.Fatalf("dropped = %d, want 1", dropped)
}
_, dropped = table.TakeOriginChanges(0)
if dropped != 0 {
t.Errorf("the next take's dropped = %d, want 0", dropped)
}
}
// TestOriginChangesPutBackTrimsToTheLimit checks that putting back what a
// failed write took, after new changes filled the table again, drops the
// oldest changes past the cap and counts them, so the cap still holds. The
// clock advances one second per change, so a change's time says its age.
func TestOriginChangesPutBackTrimsToTheLimit(t *testing.T) {
t.Parallel()
const (
taken = 20000
added = 20000
)
now := time.Unix(0, 0)
table := routetable.New(routetable.Params{
Now: func() time.Time {
now = now.Add(time.Second)
return now
},
})
addr := netip.MustParseAddr("10.0.0.0")
announce := func(n int) {
for range n {
table.Announce(netip.PrefixFrom(addr, 32), asA, routeOf(peerA, asA, 10))
addr = addr.Next()
}
}
announce(routetable.MaxWaitingOriginChanges)
takenChanges, _ := table.TakeOriginChanges(taken)
announce(added)
table.PutBackOriginChanges(takenChanges)
changes, dropped := table.TakeOriginChanges(math.MaxInt)
if dropped != added {
t.Errorf("dropped = %d, want %d", dropped, added)
}
if len(changes) != routetable.MaxWaitingOriginChanges {
t.Errorf("len(changes) = %d, want %d", len(changes),
routetable.MaxWaitingOriginChanges)
}
// The put-back rows are the oldest, so they are the ones dropped. The
// first remaining change is the one that followed them.
if want := time.Unix(int64(added+1), 0); !changes[0].Time.Equal(want) {
t.Errorf("first change's time = %v, want %v", changes[0].Time, want)
}
}
// checkOriginChanges checks that TakeOriginChanges, taking every change,
// returns want.
func checkOriginChanges(
t *testing.T, table *routetable.Table, want []routetable.OriginChange,
) {
t.Helper()
changes, dropped := table.TakeOriginChanges(math.MaxInt)
if dropped != 0 {
t.Errorf("dropped = %d, want 0", dropped)
}
if !reflect.DeepEqual(changes, want) {
t.Errorf("TakeOriginChanges = %+v, want %+v", changes, want)
}
}
internal/routetable/overview.go
+264
View File
@@ -0,0 +1,264 @@
package routetable
import (
"cmp"
"net/netip"
"slices"
"time"
"git.eeqj.de/sneak/routewatch/internal/bogon"
"git.eeqj.de/sneak/routewatch/internal/ristypes"
)
// Overview holds figures about the whole table. Working them out takes a walk
// over every prefix, so a caller asks for them now and then and keeps them.
type Overview struct {
// NewestRoute and OldestRoute are the newest and the oldest kept routes,
// or nil when the table keeps none. Of several with the same time, it is
// any one of them.
NewestRoute *PrefixRoute
OldestRoute *PrefixRoute
// MostPrefixesASN is the AS that originates the most prefixes, and
// MostPrefixes is how many it originates. Of several with as many, it is
// the lowest AS number. AS 0, no known origin, counts neither here nor
// in the single-prefix figures.
MostPrefixesASN int
MostPrefixes int
// SinglePrefixASes counts the ASes that originate one prefix.
SinglePrefixASes int
// NewestSinglePrefix is the newest kept route of those ASes, or nil when
// they keep none.
NewestSinglePrefix *PrefixRoute
// Bogons are the bogon announcements, in prefix order: at most the
// number Overview is asked for. BogonCount counts them all.
Bogons []Bogon
BogonCount int
// MultipleOrigins are the prefixes that peers carry with more than one
// origin AS, in prefix order: at most the number Overview is asked for.
// MultipleOriginCount counts them all.
MultipleOrigins []MultipleOriginPrefix
MultipleOriginCount int
}
// PrefixRoute is the time of a kept route, with its prefix and origin AS.
type PrefixRoute struct {
Prefix netip.Prefix
OriginASN int
Time time.Time
}
// Bogon is a bogon announcement: a prefix and origin AS pair whose prefix or
// origin AS is reserved, as package bogon tells.
type Bogon struct {
Prefix netip.Prefix
OriginASN int
// Peers is how many peers carry the prefix with this origin AS.
Peers int
// Reasons say why the prefix, the origin AS or both are reserved.
Reasons []string
}
// MultipleOriginPrefix is a prefix that peers carry with more than one origin
// AS.
type MultipleOriginPrefix struct {
Prefix netip.Prefix
// Origins are its origin ASes, in AS number order.
Origins []OriginPeers
}
// OriginPeers is one origin AS of a prefix, and how many peers carry the prefix
// with it.
type OriginPeers struct {
ASN int
Peers int
}
// Overview works out the table's overview. It lists at most maxListed bogon
// announcements and at most maxListed prefixes with more than one origin AS:
// the first in prefix order. It visits every prefix in the table, in batches
// of walkBatch. After each batch, it lets the table's lock go for as long as
// it held the lock for the batch.
func (t *Table) Overview(maxListed int) Overview {
var overview Overview
t.walkPrefixes(func(prefix netip.Prefix, origins []*origin) {
overview.noteKeptRoutes(prefix, origins)
overview.noteBogons(prefix, origins)
overview.noteMultipleOrigins(prefix, origins)
})
t.countPrefixesPerOrigin(&overview)
slices.SortFunc(overview.Bogons, func(a, b Bogon) int {
return cmp.Or(a.Prefix.Compare(b.Prefix),
cmp.Compare(a.OriginASN, b.OriginASN))
})
overview.BogonCount = len(overview.Bogons)
overview.Bogons = overview.Bogons[:min(maxListed, overview.BogonCount)]
slices.SortFunc(overview.MultipleOrigins, func(a, b MultipleOriginPrefix) int {
return a.Prefix.Compare(b.Prefix)
})
overview.MultipleOriginCount = len(overview.MultipleOrigins)
overview.MultipleOrigins =
overview.MultipleOrigins[:min(maxListed, overview.MultipleOriginCount)]
return overview
}
// walkPrefixes calls visit with every prefix of the table and its origins. It
// holds the read lock for walkBatch prefixes at a time. After each batch, it
// lets the table's lock go for as long as it held the lock for the batch.
// During a walk over many batches, updates can then take the lock about half
// of the time. The walk may or may not visit a prefix that is added or removed
// while the lock is let go. Go allows this in a range over a map that changes.
// visit must not keep origins once it returns.
func (t *Table) walkPrefixes(visit func(prefix netip.Prefix, origins []*origin)) {
t.mu.RLock()
defer t.mu.RUnlock()
visited := 0
batchStart := time.Now()
for _, f := range []*family{&t.ipv4, &t.ipv6} {
for _, prefixes := range f.byLength {
for prefix, origins := range prefixes {
visit(prefix, origins)
visited++
if visited%walkBatch == 0 {
held := time.Since(batchStart)
t.mu.RUnlock()
time.Sleep(held)
t.mu.RLock()
batchStart = time.Now()
}
}
}
}
}
// countPrefixesPerOrigin works out the overview's figures of how many prefixes
// each AS originates. It holds the read lock once, for one look at each origin
// AS, of which there are far fewer than prefixes.
func (t *Table) countPrefixesPerOrigin(overview *Overview) {
t.mu.RLock()
defer t.mu.RUnlock()
for asn, prefixes := range t.byOrigin {
if asn == ristypes.NoOrigin {
continue
}
count := len(prefixes)
if count > overview.MostPrefixes ||
(count == overview.MostPrefixes && asn < overview.MostPrefixesASN) {
overview.MostPrefixesASN = asn
overview.MostPrefixes = count
}
if count == 1 {
overview.SinglePrefixASes++
overview.noteSinglePrefix(asn, prefixes)
}
}
}
// noteSinglePrefix makes the newest kept route of asn, whose one prefix is in
// prefixes, the overview's newest single-prefix route when it is newer.
func (overview *Overview) noteSinglePrefix(
asn int, prefixes map[netip.Prefix]*origin,
) {
for prefix, o := range prefixes {
newest := o.newestTime()
if newest == nil {
continue
}
if overview.NewestSinglePrefix == nil ||
newest.After(overview.NewestSinglePrefix.Time) {
overview.NewestSinglePrefix = &PrefixRoute{
Prefix: prefix, OriginASN: asn, Time: *newest,
}
}
}
}
// noteKeptRoutes makes the newest and the oldest kept routes of prefix's
// origins the overview's newest and oldest routes when they are newer or older.
func (overview *Overview) noteKeptRoutes(prefix netip.Prefix, origins []*origin) {
for _, o := range origins {
if len(o.routes) == 0 {
continue
}
newest := o.routes[0].time
if overview.NewestRoute == nil || newest.After(overview.NewestRoute.Time) {
overview.NewestRoute = &PrefixRoute{
Prefix: prefix, OriginASN: o.asn, Time: newest,
}
}
oldest := o.routes[len(o.routes)-1].time
if overview.OldestRoute == nil || oldest.Before(overview.OldestRoute.Time) {
overview.OldestRoute = &PrefixRoute{
Prefix: prefix, OriginASN: o.asn, Time: oldest,
}
}
}
}
// noteBogons adds each origin of prefix to the overview's bogon announcements
// when the prefix or the origin AS is reserved.
func (overview *Overview) noteBogons(prefix netip.Prefix, origins []*origin) {
prefixReason, prefixReserved := bogon.Prefix(prefix)
for _, o := range origins {
asnReason, asnReserved := bogon.ASN(o.asn)
if !prefixReserved && !asnReserved {
continue
}
announcement := Bogon{
Prefix: prefix, OriginASN: o.asn, Peers: int(o.peers.Count()),
}
if prefixReserved {
announcement.Reasons = append(announcement.Reasons, prefixReason)
}
if asnReserved {
announcement.Reasons = append(announcement.Reasons, asnReason)
}
overview.Bogons = append(overview.Bogons, announcement)
}
}
// noteMultipleOrigins adds prefix to the overview's prefixes with more than one
// origin AS when it has more than one.
func (overview *Overview) noteMultipleOrigins(
prefix netip.Prefix, origins []*origin,
) {
if len(origins) <= 1 {
return
}
entry := MultipleOriginPrefix{
Prefix: prefix,
Origins: make([]OriginPeers, 0, len(origins)),
}
for _, o := range origins {
entry.Origins = append(entry.Origins,
OriginPeers{ASN: o.asn, Peers: int(o.peers.Count())})
}
overview.MultipleOrigins = append(overview.MultipleOrigins, entry)
}
internal/routetable/overview_internal_test.go
+191
View File
@@ -0,0 +1,191 @@
package routetable
import (
"net/netip"
"runtime"
"testing"
"time"
)
// TestWalkPrefixesVisitsEveryPrefix walks a table with more prefixes than two
// of the walk's batches, while another goroutine keeps adding and removing
// other prefixes of the same mask length. The walk lets the lock go between
// batches, so those updates get in while it runs. Every prefix that was in
// the table all along must be visited once.
func TestWalkPrefixesVisitsEveryPrefix(t *testing.T) {
t.Parallel()
const (
asn = 1000
peer = "192.0.2.1"
// prefixCount is more prefixes than two of the walk's batches.
prefixCount = 2*walkBatch + 1
)
routeTime := time.Date(2026, 1, 2, 3, 4, 5, 0, time.UTC)
table := New(Params{})
prefixes := make([]netip.Prefix, 0, prefixCount)
addr := netip.MustParseAddr("1.0.0.0")
for range prefixCount {
prefix := netip.PrefixFrom(addr, addr.BitLen())
table.Announce(prefix, asn, Route{Peer: peer, Time: routeTime})
prefixes = append(prefixes, prefix)
addr = addr.Next()
}
stop := make(chan struct{})
updated := make(chan struct{})
go func() {
defer close(updated)
other := netip.MustParseAddr("2.0.0.0")
for {
select {
case <-stop:
return
default:
}
prefix := netip.PrefixFrom(other, other.BitLen())
table.Announce(prefix, asn, Route{Peer: peer, Time: routeTime})
table.Withdraw(prefix, peer)
other = other.Next()
}
}()
visits := make(map[netip.Prefix]int)
table.walkPrefixes(func(prefix netip.Prefix, _ []*origin) {
visits[prefix]++
})
close(stop)
<-updated
for _, prefix := range prefixes {
if visits[prefix] != 1 {
t.Fatalf("the walk visited %s %d times, want once", prefix,
visits[prefix])
}
}
}
// TestWalkPrefixesLetsUpdatesIn starts an update during the walk's first
// batch. The update must have been made by the time the walk visits the first
// prefix of its second batch, because the walk lets the lock go in between.
func TestWalkPrefixesLetsUpdatesIn(t *testing.T) {
t.Parallel()
const (
asn = 1000
peer = "192.0.2.1"
)
routeTime := time.Date(2026, 1, 2, 3, 4, 5, 0, time.UTC)
table := New(Params{})
addr := netip.MustParseAddr("1.0.0.0")
for range walkBatch + 1 {
prefix := netip.PrefixFrom(addr, addr.BitLen())
table.Announce(prefix, asn, Route{Peer: peer, Time: routeTime})
addr = addr.Next()
}
updatePrefix := netip.MustParsePrefix("2.0.0.0/8")
updateDone := make(chan struct{})
visited := 0
madeBeforeSecondBatch := false
table.walkPrefixes(func(netip.Prefix, []*origin) {
visited++
switch visited {
case 1:
go func() {
defer close(updateDone)
table.Announce(updatePrefix, asn, Route{Peer: peer, Time: routeTime})
}()
// Wait until the update waits for the lock. TryRLock fails
// once a writer waits.
for table.mu.TryRLock() {
table.mu.RUnlock()
runtime.Gosched()
}
case walkBatch + 1:
// The walk holds the read lock, so the table can be read.
madeBeforeSecondBatch = table.origins(updatePrefix) != nil
}
})
<-updateDone
if !madeBeforeSecondBatch {
t.Fatal("an update started during the walk's first batch was not made " +
"before its second batch")
}
}
// TestOverviewLetsUpdatesIn applies another peer's 1,000 announcements while
// Overview walks a table with more prefixes than five of the walk's batches.
// After each batch, the walk lets the lock go for as long as it held the lock.
// So all 1,000 announcements must be applied before Overview returns. A walk
// that takes the lock back at once lets in about one update per batch.
func TestOverviewLetsUpdatesIn(t *testing.T) {
t.Parallel()
const (
asn = 1000
peer = "192.0.2.1"
otherPeer = "192.0.2.2"
// prefixCount is more prefixes than five of the walk's batches.
prefixCount = 5*walkBatch + 1
announcements = 1000
)
routeTime := time.Date(2026, 1, 2, 3, 4, 5, 0, time.UTC)
table := New(Params{})
prefixes := make([]netip.Prefix, 0, prefixCount)
addr := netip.MustParseAddr("1.0.0.0")
for range prefixCount {
prefix := netip.PrefixFrom(addr, addr.BitLen())
table.Announce(prefix, asn, Route{Peer: peer, Time: routeTime})
prefixes = append(prefixes, prefix)
addr = addr.Next()
}
overviewDone := make(chan struct{})
go func() {
defer close(overviewDone)
table.Overview(0)
}()
// Wait until Overview holds the read lock. TryLock fails while a reader
// holds it.
for table.mu.TryLock() {
table.mu.Unlock()
runtime.Gosched()
}
for _, prefix := range prefixes[:announcements] {
table.Announce(prefix, asn, Route{Peer: otherPeer, Time: routeTime})
}
select {
case <-overviewDone:
t.Fatal("Overview returned before another peer's 1,000 announcements " +
"were applied")
default:
}
<-overviewDone
}
internal/routetable/overview_test.go
+231
View File
@@ -0,0 +1,231 @@
package routetable_test
import (
"net/netip"
"reflect"
"testing"
"git.eeqj.de/sneak/routewatch/internal/routetable"
)
// Origin ASes that are not reserved, unlike asA, asB and asC, which are
// documentation AS numbers and so make bogon announcements.
const (
asOne = 1000
asTwo = 2000
asThree = 3000
asFour = 4000
asFive = 5000
// noKnownOrigin is the origin AS of a route whose path ends in an AS
// set.
noKnownOrigin = 0
// privateUseAS and asTrans are reserved AS numbers.
privateUseAS = 64512
asTrans = 23456
// maxListed is how many bogon announcements and prefixes with more than
// one origin AS the tests ask Overview for.
maxListed = 10
)
// prefixRoute returns the PrefixRoute of prefix with origin AS asn, second
// seconds after the start.
func prefixRoute(prefix string, asn, second int) *routetable.PrefixRoute {
return &routetable.PrefixRoute{
Prefix: netip.MustParsePrefix(prefix), OriginASN: asn, Time: at(second),
}
}
func TestOverviewOfAnEmptyTable(t *testing.T) {
t.Parallel()
got := routetable.New(routetable.Params{}).Overview(maxListed)
if !reflect.DeepEqual(got, routetable.Overview{}) {
t.Errorf("Overview() = %+v, want no figures", got)
}
}
// TestOverviewNewestAndOldestRoutes checks that the newest and the oldest kept
// routes are found among every origin's kept routes, and that withdrawn routes
// no longer count.
func TestOverviewNewestAndOldestRoutes(t *testing.T) {
t.Parallel()
table := routetable.New(routetable.Params{})
announceAll(table, "1.0.0.0/24", asOne, 20, peerA, peerB)
// The oldest is the older of this origin's two kept routes.
announceAll(table, "2.0.0.0/24", asTwo, 10, peerA, peerB)
announceAll(table, "2001:4860::/32", asThree, 40, peerC)
// Withdrawn routes, newer and older than every other.
announceAll(table, "3.0.0.0/24", asOne, 50, peerA)
announceAll(table, "4.0.0.0/24", asOne, 5, peerB)
table.Withdraw(netip.MustParsePrefix("3.0.0.0/24"), peerA)
table.Withdraw(netip.MustParsePrefix("4.0.0.0/24"), peerB)
got := table.Overview(maxListed)
want := prefixRoute("2001:4860::/32", asThree, 40)
if !reflect.DeepEqual(got.NewestRoute, want) {
t.Errorf("NewestRoute = %+v, want %+v", got.NewestRoute, want)
}
want = prefixRoute("2.0.0.0/24", asTwo, 10)
if !reflect.DeepEqual(got.OldestRoute, want) {
t.Errorf("OldestRoute = %+v, want %+v", got.OldestRoute, want)
}
}
// TestOverviewPrefixesPerOrigin checks the AS that originates the most
// prefixes and the ASes that originate one.
func TestOverviewPrefixesPerOrigin(t *testing.T) {
t.Parallel()
table := routetable.New(routetable.Params{})
// asOne and asTwo originate two prefixes each; the lower AS number counts.
announceAll(table, "1.0.0.0/24", asTwo, 10, peerA)
announceAll(table, "1.0.1.0/24", asTwo, 10, peerA)
announceAll(table, "2.0.0.0/24", asOne, 10, peerA)
announceAll(table, "2.0.1.0/24", asOne, 10, peerB)
// Three ASes originate one prefix. asThree's route is the newest, and
// asFive's origin keeps no route: peers B and C withdrew theirs.
announceAll(table, "3.0.0.0/24", asThree, 30, peerA)
announceAll(table, "4.0.0.0/24", asFour, 20, peerA)
announceAll(table, "5.0.0.0/24", asFive, 40, peerA, peerB, peerC)
table.Withdraw(netip.MustParsePrefix("5.0.0.0/24"), peerB)
table.Withdraw(netip.MustParsePrefix("5.0.0.0/24"), peerC)
got := table.Overview(maxListed)
if got.MostPrefixesASN != asOne || got.MostPrefixes != 2 {
t.Errorf("most prefixes: AS%d with %d, want AS%d with 2",
got.MostPrefixesASN, got.MostPrefixes, asOne)
}
if got.SinglePrefixASes != 3 {
t.Errorf("SinglePrefixASes = %d, want 3", got.SinglePrefixASes)
}
want := prefixRoute("3.0.0.0/24", asThree, 30)
if !reflect.DeepEqual(got.NewestSinglePrefix, want) {
t.Errorf("NewestSinglePrefix = %+v, want %+v", got.NewestSinglePrefix, want)
}
}
// TestOverviewLeavesOutNoKnownOrigin checks that AS 0, which stands for no
// known origin, counts in neither the most nor the single-prefix figures. It
// originates one prefix, with a route newer than asOne's, and asOne would lose
// the tie for the most prefixes to it.
func TestOverviewLeavesOutNoKnownOrigin(t *testing.T) {
t.Parallel()
table := routetable.New(routetable.Params{})
announceAll(table, "1.0.0.0/24", asOne, 10, peerA)
announceAll(table, "2.0.0.0/24", noKnownOrigin, 20, peerA)
got := table.Overview(maxListed)
if got.MostPrefixesASN != asOne || got.SinglePrefixASes != 1 {
t.Errorf("most prefixes AS%d, %d single-prefix ASes; want AS%d, 1",
got.MostPrefixesASN, got.SinglePrefixASes, asOne)
}
want := prefixRoute("1.0.0.0/24", asOne, 10)
if !reflect.DeepEqual(got.NewestSinglePrefix, want) {
t.Errorf("NewestSinglePrefix = %+v, want %+v", got.NewestSinglePrefix, want)
}
}
// TestOverviewBogons checks which routes are bogon announcements and why, in
// prefix order, and that a smaller maxListed lists fewer but counts them all.
func TestOverviewBogons(t *testing.T) {
t.Parallel()
table := routetable.New(routetable.Params{})
// A reserved prefix, carried by two peers.
announceAll(table, "192.168.0.0/16", asOne, 10, peerA, peerB)
// A reserved origin AS.
announceAll(table, "1.0.0.0/24", privateUseAS, 10, peerA)
// Both.
announceAll(table, "10.0.0.0/8", asTrans, 10, peerA)
// Neither: a normal route, and a block that may be announced although it
// lies inside a reserved one.
announceAll(table, "1.0.1.0/24", asOne, 10, peerA)
announceAll(table, "2001:4:112::/48", asTwo, 10, peerA)
want := []routetable.Bogon{
{
Prefix: netip.MustParsePrefix("1.0.0.0/24"), OriginASN: privateUseAS,
Peers: 1, Reasons: []string{"Private-Use (AS64512-AS65534)"},
},
{
Prefix: netip.MustParsePrefix("10.0.0.0/8"), OriginASN: asTrans,
Peers: 1,
Reasons: []string{
"Private-Use (10.0.0.0/8)", "AS_TRANS (AS23456)",
},
},
{
Prefix: netip.MustParsePrefix("192.168.0.0/16"), OriginASN: asOne,
Peers: 2, Reasons: []string{"Private-Use (192.168.0.0/16)"},
},
}
got := table.Overview(maxListed)
if !reflect.DeepEqual(got.Bogons, want) || got.BogonCount != len(want) {
t.Errorf("Overview(%d): %d bogons %+v, want %d %+v", maxListed,
got.BogonCount, got.Bogons, len(want), want)
}
const fewer = 2
got = table.Overview(fewer)
if !reflect.DeepEqual(got.Bogons, want[:fewer]) || got.BogonCount != len(want) {
t.Errorf("Overview(%d): %d bogons %+v, want %d %+v", fewer,
got.BogonCount, got.Bogons, len(want), want[:fewer])
}
}
// TestOverviewMultipleOrigins checks the prefixes with more than one origin
// AS, in prefix order, and that a smaller maxListed lists fewer but counts them
// all.
func TestOverviewMultipleOrigins(t *testing.T) {
t.Parallel()
table := routetable.New(routetable.Params{})
announceAll(table, "2001:4860::/32", asThree, 10, peerA)
announceAll(table, "2001:4860::/32", asTwo, 10, peerB)
announceAll(table, "1.0.0.0/24", asOne, 10, peerA, peerB)
announceAll(table, "1.0.0.0/24", asTwo, 30, peerC)
// One origin only.
announceAll(table, "2.0.0.0/24", asOne, 10, peerA, peerB)
want := []routetable.MultipleOriginPrefix{
{
Prefix: netip.MustParsePrefix("1.0.0.0/24"),
Origins: []routetable.OriginPeers{
{ASN: asOne, Peers: 2}, {ASN: asTwo, Peers: 1},
},
},
{
Prefix: netip.MustParsePrefix("2001:4860::/32"),
Origins: []routetable.OriginPeers{
{ASN: asTwo, Peers: 1}, {ASN: asThree, Peers: 1},
},
},
}
got := table.Overview(maxListed)
if !reflect.DeepEqual(got.MultipleOrigins, want) ||
got.MultipleOriginCount != len(want) {
t.Errorf("Overview(%d): %d prefixes %+v, want %d %+v", maxListed,
got.MultipleOriginCount, got.MultipleOrigins, len(want), want)
}
got = table.Overview(1)
if !reflect.DeepEqual(got.MultipleOrigins, want[:1]) ||
got.MultipleOriginCount != len(want) {
t.Errorf("Overview(1): %d prefixes %+v, want %d %+v",
got.MultipleOriginCount, got.MultipleOrigins, len(want), want[:1])
}
}
internal/routetable/reads.go
+6 -1
View File
@@ -14,6 +14,9 @@ type PrefixSummary struct {
// OriginASN is the origin AS that the most peers carry the prefix with. // OriginASN is the origin AS that the most peers carry the prefix with.
// When several have as many peers, it is the lowest AS number. // When several have as many peers, it is the lowest AS number.
OriginASN int OriginASN int
// OriginASNs are all the origin ASes that peers carry the prefix with, in
// AS number order.
OriginASNs []int
// Peers is how many peers carry the prefix. // Peers is how many peers carry the prefix.
Peers int Peers int
// Newest is the time of the newest kept route of the prefix, or nil when // Newest is the time of the newest kept route of the prefix, or nil when
@@ -211,10 +214,12 @@ func (t *Table) addresses(peers *bitset.BitSet) []string {
// summarize returns the summary of prefix, whose origins are in AS number // summarize returns the summary of prefix, whose origins are in AS number
// order. // order.
func summarize(prefix netip.Prefix, origins []*origin) PrefixSummary { func summarize(prefix netip.Prefix, origins []*origin) PrefixSummary {
summary := PrefixSummary{Prefix: prefix} summary := PrefixSummary{Prefix: prefix, OriginASNs: make([]int, 0, len(origins))}
mostPeers := 0 mostPeers := 0
for _, o := range origins { for _, o := range origins {
summary.OriginASNs = append(summary.OriginASNs, o.asn)
peers := int(o.peers.Count()) peers := int(o.peers.Count())
summary.Peers += peers summary.Peers += peers
internal/routetable/reads_test.go
+22 -19
View File
@@ -46,21 +46,22 @@ func TestLookup(t *testing.T) {
tests := []struct { tests := []struct {
addr string addr string
// want is the summary's prefix, or empty when none is found. // want is the summary's prefix, or empty when none is found.
want string want string
originASN int originASN int
peers int originASNs []int
newest int // in seconds after the start; 0 for none peers int
newest int // in seconds after the start; 0 for none
}{ }{
{"10.1.2.3", prefixV4, asA, 2, 20}, {"10.1.2.3", prefixV4, asA, []int{asA, asB}, 2, 20},
{"::ffff:10.1.2.3", prefixV4, asA, 2, 20}, {"::ffff:10.1.2.3", prefixV4, asA, []int{asA, asB}, 2, 20},
{"10.1.3.4", "10.1.0.0/16", asB, 3, 30}, {"10.1.3.4", "10.1.0.0/16", asB, []int{asA, asB}, 3, 30},
{"10.2.0.1", "10.0.0.0/8", asA, 1, 10}, {"10.2.0.1", "10.0.0.0/8", asA, []int{asA}, 1, 10},
{"10.9.0.1", "10.9.0.0/16", asA, 1, 0}, {"10.9.0.1", "10.9.0.0/16", asA, []int{asA}, 1, 0},
{"192.0.2.1", "", 0, 0, 0}, {"192.0.2.1", "", 0, nil, 0, 0},
{"2001:db8:1::5", prefixV6, asB, 1, 20}, {"2001:db8:1::5", prefixV6, asB, []int{asB}, 1, 20},
{"2001:db8:2::1", "2001:db8::/32", asA, 1, 10}, {"2001:db8:2::1", "2001:db8::/32", asA, []int{asA}, 1, 10},
{"3000::1", "3000::/16", asA, 1, 10}, {"3000::1", "3000::/16", asA, []int{asA}, 1, 10},
{"2001:db9::1", "", 0, 0, 0}, {"2001:db9::1", "", 0, nil, 0, 0},
} }
for _, tc := range tests { for _, tc := range tests {
@@ -77,9 +78,10 @@ func TestLookup(t *testing.T) {
} }
want := routetable.PrefixSummary{ want := routetable.PrefixSummary{
Prefix: netip.MustParsePrefix(tc.want), Prefix: netip.MustParsePrefix(tc.want),
OriginASN: tc.originASN, OriginASN: tc.originASN,
Peers: tc.peers, OriginASNs: tc.originASNs,
Peers: tc.peers,
} }
if tc.newest != 0 { if tc.newest != 0 {
want.Newest = timeAt(tc.newest) want.Newest = timeAt(tc.newest)
@@ -166,7 +168,8 @@ func TestSamplePrefixes(t *testing.T) {
for _, got := range sample { for _, got := range sample {
want := routetable.PrefixSummary{ want := routetable.PrefixSummary{
Prefix: got.Prefix, OriginASN: asA, Peers: 1, Newest: timeAt(10), Prefix: got.Prefix, OriginASN: asA, OriginASNs: []int{asA},
Peers: 1, Newest: timeAt(10),
} }
if seen[got.Prefix] || got.Prefix.Bits() != tc.maskLength || if seen[got.Prefix] || got.Prefix.Bits() != tc.maskLength ||
!reflect.DeepEqual(got, want) { !reflect.DeepEqual(got, want) {
@@ -224,7 +227,7 @@ func TestCounts(t *testing.T) {
}) })
// peerC was the last peer of the IPv6 prefix. It keeps its number. // peerC was the last peer of the IPv6 prefix. It keeps its number.
table.PeerDown(peerC) table.PeersDown([]string{peerC})
checkCounts(t, table, routetable.Counts{ checkCounts(t, table, routetable.Counts{
Pairs: 2, Pairs: 2,
Peers: 3, Peers: 3,
internal/routetable/routetable.go
+83 -13
View File
@@ -2,7 +2,9 @@
// and origin AS, it keeps the peers whose current route to the prefix has that // and origin AS, it keeps the peers whose current route to the prefix has that
// origin AS. It also keeps the two newest of those routes in full. It applies // origin AS. It also keeps the two newest of those routes in full. It applies
// announcements, withdrawals and peers' sessions going down. It answers the // announcements, withdrawals and peers' sessions going down. It answers the
// route reads that the pages and the API need. // route reads that the pages and the API need. It also records each prefix and
// origin AS pair's origin changes: when it gains its first peer and when it
// loses its last.
package routetable package routetable
import ( import (
@@ -27,6 +29,11 @@ const (
// kept routes in order: each of its nodes holds up to 63 times. // kept routes in order: each of its nodes holds up to 63 times.
keptTimesDegree = 32 keptTimesDegree = 32
// walkBatch is how many prefixes a walk over the whole table visits in
// one hold of the lock. Overview and PeersDown each walk the whole table.
// Callers waiting for the lock get it between batches.
walkBatch = 10000
ipv4Bits = 32 ipv4Bits = 32
ipv6Bits = 128 ipv6Bits = 128
@@ -86,6 +93,9 @@ type Params struct {
// peer not in it gets the next number above all of them the first time it // peer not in it gets the next number above all of them the first time it
// announces a route. // announces a route.
PeerNumbers map[string]uint PeerNumbers map[string]uint
// Now returns the time RouteWatch applies a change at. It is time.Now
// unless a test gives one.
Now func() time.Time
} }
// Table is the routing table. Its methods are safe for concurrent use. // Table is the routing table. Its methods are safe for concurrent use.
@@ -121,11 +131,24 @@ type Table struct {
// originsWithoutKeptRoute counts the origins that peers carry but that // originsWithoutKeptRoute counts the origins that peers carry but that
// keep no route. // keep no route.
originsWithoutKeptRoute int originsWithoutKeptRoute int
// now returns the time RouteWatch applies a change at.
now func() time.Time
// originChanges holds the origin changes that wait to be written, oldest
// first. originChangesDropped counts those dropped since the last
// TakeOriginChanges.
originChanges []OriginChange
originChangesDropped int
} }
// New returns an empty table that numbers new peers on from // New returns an empty table that numbers new peers on from
// params.PeerNumbers. // params.PeerNumbers.
func New(params Params) *Table { func New(params Params) *Table {
now := params.Now
if now == nil {
now = time.Now
}
t := &Table{ t := &Table{
ipv4: newFamily(ipv4Bits, minLookupMaskLengthV4), ipv4: newFamily(ipv4Bits, minLookupMaskLengthV4),
ipv6: newFamily(ipv6Bits, minLookupMaskLengthV6), ipv6: newFamily(ipv6Bits, minLookupMaskLengthV6),
@@ -134,6 +157,7 @@ func New(params Params) *Table {
peerAddresses: make(map[uint]string, len(params.PeerNumbers)), peerAddresses: make(map[uint]string, len(params.PeerNumbers)),
newPeers: make(map[string]uint), newPeers: make(map[string]uint),
changed: make(map[pair]struct{}), changed: make(map[pair]struct{}),
now: now,
keptTimes: btree.NewG(keptTimesDegree, func(a, b keptTime) bool { keptTimes: btree.NewG(keptTimesDegree, func(a, b keptTime) bool {
return a.time.Before(b.time) return a.time.Before(b.time)
}), }),
@@ -200,24 +224,60 @@ func (t *Table) Withdraw(prefix netip.Prefix, peer string) {
} }
} }
// PeerDown applies a peer's session going down: the peer leaves every peer // PeersDown applies the sessions of peers going down: each of the peers leaves
// set, and every route of it is dropped. When the peer carries any prefix, it // every peer set, and every route of each is dropped. When any of them carries
// visits every prefix in the table. // a prefix, PeersDown visits every prefix in the table once, in batches of
func (t *Table) PeerDown(peer string) { // walkBatch. After each batch, it lets the table's lock go for as long as it
// held the lock for the batch. During a walk over many batches, reads and
// updates can then take the lock about half of the time. An announcement by
// one of the peers applied during the walk may be dropped too. So the caller
// applies those peers' later updates only once PeersDown has returned.
func (t *Table) PeersDown(peers []string) {
t.mu.Lock() t.mu.Lock()
defer t.mu.Unlock() defer t.mu.Unlock()
number, known := t.peerNumbers[peer] // numbers holds the number of each of the peers that carries a prefix.
if !known || t.peerPrefixes[number] == 0 { numbers := make([]uint, 0, len(peers))
for _, peer := range peers {
number, known := t.peerNumbers[peer]
if known && t.peerPrefixes[number] > 0 {
numbers = append(numbers, number)
}
}
if len(numbers) == 0 {
return return
} }
visited := 0
batchStart := time.Now()
for _, f := range []*family{&t.ipv4, &t.ipv6} { for _, f := range []*family{&t.ipv4, &t.ipv6} {
for _, prefixes := range f.byLength { for _, prefixes := range f.byLength {
for prefix, origins := range prefixes { for prefix, origins := range prefixes {
o := originWithPeer(origins, number) for _, number := range numbers {
if o != nil { o := originWithPeer(origins, number)
t.leave(prefix, o, number) if o != nil {
t.leave(prefix, o, number)
// leave may have removed an origin of the
// prefix, or the prefix itself.
origins = prefixes[prefix]
}
}
// Go allows the map to change before the next step of
// the range over it.
visited++
if visited%walkBatch == 0 {
held := time.Since(batchStart)
t.mu.Unlock()
time.Sleep(held)
t.mu.Lock()
batchStart = time.Now()
} }
} }
} }
@@ -227,8 +287,9 @@ func (t *Table) PeerDown(peer string) {
// Load puts one prefix and origin AS pair that the database holds into the // Load puts one prefix and origin AS pair that the database holds into the
// table, as startup does with each row it reads. The change's peers join the // table, as startup does with each row it reads. The change's peers join the
// pair's peer set, and its routes are kept as an announcement's would be. // pair's peer set, and its routes are kept as an announcement's would be.
// Unlike an update, Load records no change, so TakeChanges does not hand the // Unlike an update, Load records no change and no origin change, so
// pair back to be written again. Loading a pair twice changes nothing. // TakeChanges does not hand the pair back to be written again. Loading a pair
// twice changes nothing.
// //
// The caller makes sure that every peer change names, in its peer set or in // The caller makes sure that every peer change names, in its peer set or in
// its routes, has a number in Params.PeerNumbers. // its routes, has a number in Params.PeerNumbers.
@@ -419,6 +480,7 @@ func (t *Table) removeOrigin(prefix netip.Prefix, o *origin) {
// r in full when it is one of the two newest routes of o. The peer's earlier // r in full when it is one of the two newest routes of o. The peer's earlier
// route, if o keeps one, is replaced: it is no longer the peer's current route. // route, if o keeps one, is replaced: it is no longer the peer's current route.
// The pair is recorded as changed only when its peer set or kept routes change. // The pair is recorded as changed only when its peer set or kept routes change.
// When r is the origin's first peer, an announced origin change is recorded.
func (t *Table) join(prefix netip.Prefix, o *origin, r route) { func (t *Table) join(prefix netip.Prefix, o *origin, r route) {
if slices.ContainsFunc(o.routes, r.equal) { if slices.ContainsFunc(o.routes, r.equal) {
// The peer announced its kept route again. // The peer announced its kept route again.
@@ -428,6 +490,8 @@ func (t *Table) join(prefix netip.Prefix, o *origin, r route) {
wasWithoutKeptRoute := o.withoutKeptRoute() wasWithoutKeptRoute := o.withoutKeptRoute()
joined := !o.peers.Test(r.peer) joined := !o.peers.Test(r.peer)
firstPeer := joined && o.peers.None()
if joined { if joined {
o.peers.Set(r.peer) o.peers.Set(r.peer)
@@ -441,6 +505,10 @@ func (t *Table) join(prefix netip.Prefix, o *origin, r route) {
if joined || dropped || kept { if joined || dropped || kept {
t.recordChange(prefix, o, wasWithoutKeptRoute) t.recordChange(prefix, o, wasWithoutKeptRoute)
} }
if firstPeer {
t.recordOriginChange(prefix, o.asn, true, t.prefixPeerCount(prefix))
}
} }
// leave takes peer out of the peer set of o, an origin of prefix, and drops // leave takes peer out of the peer set of o, an origin of prefix, and drops
@@ -499,7 +567,8 @@ func (t *Table) dropKeptRoute(o *origin, peer uint) bool {
// recordChange records that the pair of prefix and the AS of o changed, and // recordChange records that the pair of prefix and the AS of o changed, and
// brings the count of origins without a kept route up to date. // brings the count of origins without a kept route up to date.
// wasWithoutKeptRoute says whether o was such an origin before the change. An // wasWithoutKeptRoute says whether o was such an origin before the change. An
// origin that no peer carries any more is removed. // origin that no peer carries any more is removed, and a withdrawn origin
// change is recorded.
func (t *Table) recordChange( func (t *Table) recordChange(
prefix netip.Prefix, o *origin, wasWithoutKeptRoute bool, prefix netip.Prefix, o *origin, wasWithoutKeptRoute bool,
) { ) {
@@ -508,6 +577,7 @@ func (t *Table) recordChange(
t.countOriginWithoutKeptRoute(o, wasWithoutKeptRoute) t.countOriginWithoutKeptRoute(o, wasWithoutKeptRoute)
if o.peers.None() { if o.peers.None() {
t.recordOriginChange(prefix, o.asn, false, t.prefixPeerCount(prefix))
t.removeOrigin(prefix, o) t.removeOrigin(prefix, o)
} }
} }
internal/routetable/routetable_internal_test.go
+69
View File
@@ -0,0 +1,69 @@
package routetable
import (
"net/netip"
"runtime"
"testing"
"time"
)
// TestPeersDownLetsReadsIn reads the table's counts again and again while a
// peer that carries more than two batches of prefixes goes down. PeersDown lets
// the lock go after every walkBatch prefixes, so a read must get in while the
// peer still carries some of its prefixes but no longer all.
func TestPeersDownLetsReadsIn(t *testing.T) {
t.Parallel()
const (
asn = 1000
peer = "192.0.2.1"
// prefixCount is more prefixes than two of walkBatch.
prefixCount = 2*walkBatch + 1
)
routeTime := time.Date(2026, 1, 2, 3, 4, 5, 0, time.UTC)
table := New(Params{})
addr := netip.MustParseAddr("1.0.0.0")
for range prefixCount {
prefix := netip.PrefixFrom(addr, addr.BitLen())
table.Announce(prefix, asn, Route{Peer: peer, Time: routeTime})
addr = addr.Next()
}
// Hold a read lock until PeersDown waits for the lock, so that the first
// read below starts once PeersDown holds it. TryRLock fails once a writer
// waits.
table.mu.RLock()
peerDownDone := make(chan struct{})
go func() {
defer close(peerDownDone)
table.PeersDown([]string{peer})
}()
for table.mu.TryRLock() {
table.mu.RUnlock()
runtime.Gosched()
}
table.mu.RUnlock()
for {
routes := table.Counts().IPv4Routes
if routes > 0 && routes < prefixCount {
break
}
select {
case <-peerDownDone:
t.Fatal("no read got in while PeersDown ran")
default:
}
}
<-peerDownDone
}
internal/routetable/routetable_test.go
+45 -11
View File
@@ -69,10 +69,10 @@ func withdraw(peer string) step {
} }
} }
// peerDown is the step of peer's session going down. // peersDown is the step of the sessions of peers going down.
func peerDown(peer string) step { func peersDown(peers ...string) step {
return func(table *routetable.Table, _ netip.Prefix) { return func(table *routetable.Table, _ netip.Prefix) {
table.PeerDown(peer) table.PeersDown(peers)
} }
} }
@@ -272,21 +272,28 @@ func TestWithdrawalsAndPeerDowns(t *testing.T) {
{ {
name: "a peer going down leaves the prefix", name: "a peer going down leaves the prefix",
steps: []step{announce(peerA, asA, 10), announce(peerB, asA, 20), steps: []step{announce(peerA, asA, 10), announce(peerB, asA, 20),
peerDown(peerB)}, peersDown(peerB)},
want: []routetable.Origin{{ASN: asA, Peers: []string{peerA}, want: []routetable.Origin{{ASN: asA, Peers: []string{peerA},
Routes: []routetable.Route{routeOf(peerA, asA, 10)}}}, Routes: []routetable.Route{routeOf(peerA, asA, 10)}}},
}, },
{ {
name: "a peer going down after it withdrew changes nothing", name: "a peer going down after it withdrew changes nothing",
steps: []step{announce(peerA, asA, 10), announce(peerB, asA, 20), steps: []step{announce(peerA, asA, 10), announce(peerB, asA, 20),
withdraw(peerB), peerDown(peerB)}, withdraw(peerB), peersDown(peerB)},
want: []routetable.Origin{{ASN: asA, Peers: []string{peerA}, want: []routetable.Origin{{ASN: asA, Peers: []string{peerA},
Routes: []routetable.Route{routeOf(peerA, asA, 10)}}}, Routes: []routetable.Route{routeOf(peerA, asA, 10)}}},
}, },
{
name: "peers going down together each leave the prefix",
steps: []step{announce(peerA, asA, 10), announce(peerB, asB, 20),
announce(peerC, asB, 30), peersDown(peerA, peerB)},
want: []routetable.Origin{{ASN: asB, Peers: []string{peerC},
Routes: []routetable.Route{routeOf(peerC, asB, 30)}}},
},
}) })
} }
func TestPeerDownLeavesEveryPrefix(t *testing.T) { func TestPeersDownLeavesEveryPrefix(t *testing.T) {
t.Parallel() t.Parallel()
table := routetable.New(routetable.Params{}) table := routetable.New(routetable.Params{})
@@ -303,7 +310,7 @@ func TestPeerDownLeavesEveryPrefix(t *testing.T) {
} }
table.Announce(prefixes[0], asB, routeOf(peerB, asB, 20)) table.Announce(prefixes[0], asB, routeOf(peerB, asB, 20))
table.PeerDown(peerA) table.PeersDown([]string{peerA})
want := []routetable.Origin{{ASN: asB, Peers: []string{peerB}, want := []routetable.Origin{{ASN: asB, Peers: []string{peerB},
Routes: []routetable.Route{routeOf(peerB, asB, 20)}}} Routes: []routetable.Route{routeOf(peerB, asB, 20)}}}
@@ -333,6 +340,32 @@ func TestPeerDownLeavesEveryPrefix(t *testing.T) {
} }
} }
// TestPeersDownTakesOutPeersOfDifferentPrefixes takes peerA and peerB out in
// one PeersDown. peerA carries only prefixV4, and peerB only prefixV6. So
// peerA's leaving removes prefixV4 before PeersDown looks for peerB there. Both
// prefixes must then be gone.
func TestPeersDownTakesOutPeersOfDifferentPrefixes(t *testing.T) {
t.Parallel()
table := routetable.New(routetable.Params{})
prefixes := []netip.Prefix{
netip.MustParsePrefix(prefixV4),
netip.MustParsePrefix(prefixV6),
}
table.Announce(prefixes[0], asA, routeOf(peerA, asA, 10))
table.Announce(prefixes[1], asB, routeOf(peerB, asB, 20))
table.PeersDown([]string{peerA, peerB})
for _, prefix := range prefixes {
got := table.Origins(prefix)
if got != nil {
t.Errorf("Origins(%s) = %+v after its only peer went down, want nil",
prefix, got)
}
}
}
func TestCountsOriginsWithoutKeptRoute(t *testing.T) { func TestCountsOriginsWithoutKeptRoute(t *testing.T) {
t.Parallel() t.Parallel()
@@ -358,7 +391,7 @@ func TestCountsOriginsWithoutKeptRoute(t *testing.T) {
{announce(peerC, asA, 30), 0}, {announce(peerC, asA, 30), 0},
{withdraw(peerB), 0}, {withdraw(peerB), 0},
{withdraw(peerC), 1}, {withdraw(peerC), 1},
{peerDown(peerA), 0}, {peersDown(peerA), 0},
} }
for i, s := range steps { for i, s := range steps {
@@ -464,7 +497,7 @@ func TestTakeChangesHoldsOnlyPairsThatChanged(t *testing.T) {
checkChanges(t, table, []change{}, map[string]uint{}) checkChanges(t, table, []change{}, map[string]uint{})
// peerA going down changes v4, the one prefix it carries. // peerA going down changes v4, the one prefix it carries.
table.PeerDown(peerA) table.PeersDown([]string{peerA})
checkChanges(t, table, []change{ checkChanges(t, table, []change{
{Prefix: prefixV4, OriginASN: asA, Peers: []uint{1, 2}, {Prefix: prefixV4, OriginASN: asA, Peers: []uint{1, 2},
Routes: []routetable.Route{ Routes: []routetable.Route{
@@ -473,7 +506,7 @@ func TestTakeChangesHoldsOnlyPairsThatChanged(t *testing.T) {
}, map[string]uint{}) }, map[string]uint{})
// peerA, which carries nothing now, goes down again. // peerA, which carries nothing now, goes down again.
table.PeerDown(peerA) table.PeersDown([]string{peerA})
checkChanges(t, table, []change{}, map[string]uint{}) checkChanges(t, table, []change{}, map[string]uint{})
} }
@@ -617,7 +650,7 @@ func TestConcurrentUse(t *testing.T) {
func(round int) { table.Announce(prefix, asA, routeOf(peerA, asA, round)) }, func(round int) { table.Announce(prefix, asA, routeOf(peerA, asA, round)) },
func(round int) { table.Announce(prefix, asB, routeOf(peerB, asB, round)) }, func(round int) { table.Announce(prefix, asB, routeOf(peerB, asB, round)) },
func(int) { table.Withdraw(prefix, peerA) }, func(int) { table.Withdraw(prefix, peerA) },
func(int) { table.PeerDown(peerB) }, func(int) { table.PeersDown([]string{peerB}) },
func(int) { table.PutBackChanges(table.TakeChanges(math.MaxInt)) }, func(int) { table.PutBackChanges(table.TakeChanges(math.MaxInt)) },
func(int) { table.ChangeCount() }, func(int) { table.ChangeCount() },
func(int) { table.Lookup(prefix.Addr()) }, func(int) { table.Lookup(prefix.Addr()) },
@@ -625,6 +658,7 @@ func TestConcurrentUse(t *testing.T) {
func(int) { table.OriginatedPrefixes(asA) }, func(int) { table.OriginatedPrefixes(asA) },
func(int) { table.SamplePrefixes(ipVersion, prefix.Bits(), sampleSize) }, func(int) { table.SamplePrefixes(ipVersion, prefix.Bits(), sampleSize) },
func(int) { table.Counts() }, func(int) { table.Counts() },
func(int) { table.Overview(sampleSize) },
} }
var wg sync.WaitGroup var wg sync.WaitGroup
internal/routewatch/app.go
+116 -17
View File
@@ -9,17 +9,21 @@ package routewatch
import ( import (
"context" "context"
"database/sql"
"errors" "errors"
"fmt" "fmt"
"path/filepath" "path/filepath"
"sync" "sync"
"time" "time"
"git.eeqj.de/sneak/routewatch/internal/blocklist" "git.eeqj.de/sneak/routewatch/internal/cachedb"
"git.eeqj.de/sneak/routewatch/internal/config" "git.eeqj.de/sneak/routewatch/internal/config"
"git.eeqj.de/sneak/routewatch/internal/database" "git.eeqj.de/sneak/routewatch/internal/database"
"git.eeqj.de/sneak/routewatch/internal/geo"
"git.eeqj.de/sneak/routewatch/internal/iplist"
"git.eeqj.de/sneak/routewatch/internal/logger" "git.eeqj.de/sneak/routewatch/internal/logger"
"git.eeqj.de/sneak/routewatch/internal/metrics" "git.eeqj.de/sneak/routewatch/internal/metrics"
"git.eeqj.de/sneak/routewatch/internal/ptr"
"git.eeqj.de/sneak/routewatch/internal/routetable" "git.eeqj.de/sneak/routewatch/internal/routetable"
"git.eeqj.de/sneak/routewatch/internal/server" "git.eeqj.de/sneak/routewatch/internal/server"
"git.eeqj.de/sneak/routewatch/internal/streamer" "git.eeqj.de/sneak/routewatch/internal/streamer"
@@ -61,12 +65,15 @@ type RouteWatch struct {
peeringHandler *PeeringHandler peeringHandler *PeeringHandler
asnFetcher *ASNFetcher asnFetcher *ASNFetcher
dbMaintainer *DBMaintainer dbMaintainer *DBMaintainer
blocklists *blocklist.Blocklists ipLists *iplist.IPLists
cacheDB *sql.DB
ptrCache *ptr.Cache
geoLocator *geo.Locator
} }
// blocklistsDirName is the directory in the state directory that holds the // ipListsDirName is the directory in the state directory that holds the IP
// blocklist copies. // list copies.
const blocklistsDirName = "blocklists" const ipListsDirName = "iplists"
// New creates a new RouteWatch instance // New creates a new RouteWatch instance
func New(deps Dependencies) *RouteWatch { func New(deps Dependencies) *RouteWatch {
@@ -138,17 +145,27 @@ func (rw *RouteWatch) Run(ctx context.Context) error {
rw.asnFetcher.Start(ctx) rw.asnFetcher.Start(ctx)
rw.server.SetASNFetcher(rw.asnFetcher) rw.server.SetASNFetcher(rw.asnFetcher)
// Load the blocklist copies from disk and start downloading the lists. // Load the IP list copies from disk and start downloading the lists.
// The HTTP handlers read the server's blocklists without a lock, so they // The HTTP handlers read the server's IP lists without a lock, so they
// are set before the handlers run. // are set before the handlers run.
blocklists := blocklist.New(blocklist.Params{ ipLists := iplist.New(iplist.Params{
Dir: filepath.Join(rw.config.StateDir, blocklistsDirName), Dir: filepath.Join(rw.config.StateDir, ipListsDirName),
Lists: blocklist.Lists(), Lists: iplist.Lists(),
Logger: rw.logger.Logger, Logger: rw.logger.Logger,
}) })
blocklists.Start(ctx) ipLists.Start(ctx)
rw.blocklists = blocklists rw.ipLists = ipLists
rw.server.SetBlocklists(blocklists) rw.server.SetIPLists(ipLists)
err = rw.startPTRCache(ctx)
if err != nil {
return err
}
err = rw.startGeoLocator(ctx)
if err != nil {
return err
}
// Start HTTP server // Start HTTP server
err = rw.server.Start(ctx) err = rw.server.Start(ctx)
@@ -168,8 +185,9 @@ func (rw *RouteWatch) Run(ctx context.Context) error {
// Shutdown stops all services in order: the streamer, the handlers, which // Shutdown stops all services in order: the streamer, the handlers, which
// write what they hold, the WHOIS fetcher, the database maintainer, the // write what they hold, the WHOIS fetcher, the database maintainer, the
// blocklist downloads and the HTTP server, and last the database, which it // IP list downloads, the HTTP server, the geolocation cache and the PTR cache,
// checkpoints and closes. Each stage waits at most until ctx ends, so // and last the database, which it checkpoints and closes. Each stage waits at
// most until ctx ends, so
// Shutdown returns soon after: a handler logs what it could not write by // Shutdown returns soon after: a handler logs what it could not write by
// then, and the HTTP server closes the connections of requests still // then, and the HTTP server closes the connections of requests still
// running. // running.
@@ -219,8 +237,8 @@ func (rw *RouteWatch) Shutdown(ctx context.Context) {
rw.dbMaintainer.Stop(ctx) rw.dbMaintainer.Stop(ctx)
} }
if rw.blocklists != nil { if rw.ipLists != nil {
rw.blocklists.Stop(ctx) rw.ipLists.Stop(ctx)
} }
err := rw.server.Stop(ctx) err := rw.server.Stop(ctx)
@@ -229,6 +247,12 @@ func (rw *RouteWatch) Shutdown(ctx context.Context) {
"error", err) "error", err)
} }
if rw.geoLocator != nil {
rw.geoLocator.Stop(ctx)
}
rw.stopPTRCache(ctx)
rw.closeDatabase(ctx) rw.closeDatabase(ctx)
// Log final metrics // Log final metrics
@@ -242,6 +266,81 @@ func (rw *RouteWatch) Shutdown(ctx context.Context) {
) )
} }
// startPTRCache opens cache.db, loads the PTR cache from it and gives the
// server the cache. The HTTP handlers read it without a lock, so it is set
// before they run.
func (rw *RouteWatch) startPTRCache(ctx context.Context) error {
cacheDB, err := cachedb.Open(ctx, rw.config.StateDir)
if err != nil {
return err
}
ptrCache := ptr.New(ptr.Params{
DB: cacheDB,
Resolvers: ptr.Resolvers(),
Logger: rw.logger.Logger,
})
err = ptrCache.Start(ctx)
if err != nil {
_ = cacheDB.Close()
return err
}
rw.cacheDB = cacheDB
rw.ptrCache = ptrCache
rw.server.SetPTRResolver(ptrCache)
return nil
}
// startGeoLocator loads the geolocation cache from cache.db, which
// startPTRCache has opened, and gives the server the locator. The HTTP handlers
// read it without a lock, so it is set before they run.
func (rw *RouteWatch) startGeoLocator(ctx context.Context) error {
locator, err := geo.New(geo.Params{
DB: rw.cacheDB,
Dir: rw.config.StateDir,
GeoJSURL: geo.GeoJSEndpoint,
DatabaseURLFormat: geo.DatabaseDownloadFormat,
Logger: rw.logger.Logger,
})
if err != nil {
return err
}
err = locator.Start(ctx)
if err != nil {
return err
}
rw.geoLocator = locator
rw.server.SetGeoLocator(locator)
return nil
}
// stopPTRCache stops the PTR cache, which writes the answers cache.db does not
// have yet, and closes cache.db, unless ctx has ended and a write may still be
// running.
func (rw *RouteWatch) stopPTRCache(ctx context.Context) {
if rw.ptrCache == nil {
return
}
rw.ptrCache.Stop(ctx)
if ctx.Err() != nil {
return
}
err := rw.cacheDB.Close()
if err != nil {
rw.logger.Error("Failed to close the cache database", "error", err)
}
}
// closeDatabase checkpoints and closes the database, unless ctx has ended: a // closeDatabase checkpoints and closes the database, unless ctx has ended: a
// write may then still be running, and both would wait for it. SQLite rolls // write may then still be running, and both would wait for it. SQLite rolls
// back a write cut off by the exit when the database next opens. // back a write cut off by the exit when the database next opens.
internal/routewatch/app_integration_internal_test.go
+141 -29
View File
@@ -8,6 +8,8 @@ import (
"net/http" "net/http"
"net/http/httptest" "net/http/httptest"
"net/netip" "net/netip"
"os"
"path/filepath"
"slices" "slices"
"strconv" "strconv"
"strings" "strings"
@@ -223,6 +225,35 @@ func (m *mockStore) GetAS(_ context.Context, asn int) (*database.ASN, bool, erro
return &database.ASN{ASN: asn}, false, nil return &database.ASN{ASN: asn}, false, nil
} }
// GetLastSeenASes returns copies of the stored ASes last seen most recently
// and longest ago, or neither when none is stored.
func (m *mockStore) GetLastSeenASes(
_ context.Context,
) (*database.ASN, *database.ASN, error) {
m.mu.Lock()
defer m.mu.Unlock()
var newest, oldest *database.ASN
for _, asn := range m.ASNs {
if newest == nil || asn.LastSeen.After(newest.LastSeen) {
newest = asn
}
if oldest == nil || asn.LastSeen.Before(oldest.LastSeen) {
oldest = asn
}
}
if newest == nil {
return nil, nil, nil
}
newestCopy, oldestCopy := *newest, *oldest
return &newestCopy, &oldestCopy, nil
}
// GetASWHOIS returns the stored AS, or only its number when none is stored. // GetASWHOIS returns the stored AS, or only its number when none is stored.
func (m *mockStore) GetASWHOIS(ctx context.Context, asn int) (*database.ASN, error) { func (m *mockStore) GetASWHOIS(ctx context.Context, asn int) (*database.ASN, error) {
asnInfo, _, err := m.GetAS(ctx, asn) asnInfo, _, err := m.GetAS(ctx, asn)
@@ -301,6 +332,23 @@ func (m *mockStore) ReadRouteTable(_ context.Context) (*routetable.Table, error)
return routetable.New(routetable.Params{}), nil return routetable.New(routetable.Params{}), nil
} }
// WriteOriginChanges records nothing: the mock keeps no origin changes.
func (m *mockStore) WriteOriginChanges(_ []routetable.OriginChange) error {
return nil
}
// GetOriginChanges returns no origin changes.
func (m *mockStore) GetOriginChanges(
_ context.Context, _ netip.Prefix, _ int,
) ([]routetable.OriginChange, error) {
return nil, nil
}
// PruneOriginChanges does nothing.
func (m *mockStore) PruneOriginChanges(_ context.Context) error {
return nil
}
// GetOrCreateASNBatch mock implementation // GetOrCreateASNBatch mock implementation
func (m *mockStore) GetOrCreateASNBatch(asns map[int]database.SeenTimes) error { func (m *mockStore) GetOrCreateASNBatch(asns map[int]database.SeenTimes) error {
m.mu.Lock() m.mu.Lock()
@@ -372,7 +420,7 @@ func TestRouteWatchLiveFeed(t *testing.T) {
// Create streamer // Create streamer
s := streamer.New(logger, metricsTracker) s := streamer.New(logger, metricsTracker)
// The state directory holds the blocklist copies Run downloads. // The state directory holds the IP list copies Run downloads.
cfg := &config.Config{ cfg := &config.Config{
StateDir: t.TempDir(), StateDir: t.TempDir(),
MaxRuntime: 5 * time.Second, MaxRuntime: 5 * time.Second,
@@ -480,8 +528,6 @@ func announcementFeed(prefixes []string) string {
func TestShutdownWritesTheUpdatesQueuedInTheStreamer(t *testing.T) { func TestShutdownWritesTheUpdatesQueuedInTheStreamer(t *testing.T) {
t.Parallel() t.Parallel()
const maxWait = 10 * time.Second
prefixes := []string{"192.0.2.0/24", "198.51.100.0/24", "203.0.113.0/24"} prefixes := []string{"192.0.2.0/24", "198.51.100.0/24", "203.0.113.0/24"}
feed := announcementFeed(prefixes) feed := announcementFeed(prefixes)
@@ -527,9 +573,9 @@ func TestShutdownWritesTheUpdatesQueuedInTheStreamer(t *testing.T) {
for range cap(linesSeen) { for range cap(linesSeen) {
select { select {
case <-linesSeen: case <-linesSeen:
case <-time.After(maxWait): case <-time.After(stepTimeout):
t.Fatalf("the streamer did not read %d lines within %s", t.Fatalf("the streamer did not read %d lines within %s",
cap(linesSeen), maxWait) cap(linesSeen), stepTimeout)
} }
} }
@@ -542,8 +588,8 @@ func TestShutdownWritesTheUpdatesQueuedInTheStreamer(t *testing.T) {
select { select {
case <-shutDown: case <-shutDown:
case <-time.After(maxWait): case <-time.After(stepTimeout):
t.Fatalf("Shutdown did not return within %s", maxWait) t.Fatalf("Shutdown did not return within %s", stepTimeout)
} }
store.mu.Lock() store.mu.Lock()
@@ -580,21 +626,16 @@ func freePort(t *testing.T) int {
return addr.Port return addr.Port
} }
// TestShutdownReturnsByItsDeadlineWhileAWriteIsBlocked starts the HTTP server // TestShutdownDoesNotWaitForABlockedWrite starts the HTTP server and has the
// and has the AS handler start a write that the store holds until the test // AS handler start a write that the store holds until the test ends, past
// ends, past Shutdown's deadline. Shutdown must return within its deadline // Shutdown's deadline. Shutdown must return without waiting for the write, with
// plus a small margin, with the HTTP server stopped, and must neither // the HTTP server stopped, and must neither checkpoint nor close the database:
// checkpoint nor close the database: the real one would wait for the write. // the real one would wait for the write.
// Before the fix Shutdown waited for the write. // Before the fix Shutdown waited for the write.
func TestShutdownReturnsByItsDeadlineWhileAWriteIsBlocked(t *testing.T) { func TestShutdownDoesNotWaitForABlockedWrite(t *testing.T) {
t.Parallel() t.Parallel()
const ( const deadline = 100 * time.Millisecond
deadline = 100 * time.Millisecond
// margin is how long Shutdown may take after its deadline, to stop
// the HTTP server.
margin = 2 * time.Second
)
blocking := newBlockingStore() blocking := newBlockingStore()
defer blocking.releaseWrites() defer blocking.releaseWrites()
@@ -605,12 +646,15 @@ func TestShutdownReturnsByItsDeadlineWhileAWriteIsBlocked(t *testing.T) {
cfg := &config.Config{Port: port} cfg := &config.Config{Port: port}
s := streamer.New(log, metrics.New()) s := streamer.New(log, metrics.New())
// A started server reads its routing table in the background, so it
// needs one.
rw := New(Dependencies{ rw := New(Dependencies{
DB: store, DB: store,
Streamer: s, Streamer: s,
Server: server.New(store, nil, s, log, cfg), Server: server.New(store, routetable.New(routetable.Params{}), s, log,
Logger: log, cfg),
Config: cfg, Logger: log,
Config: cfg,
}) })
err := rw.server.Start(t.Context()) err := rw.server.Start(t.Context())
@@ -619,9 +663,8 @@ func TestShutdownReturnsByItsDeadlineWhileAWriteIsBlocked(t *testing.T) {
} }
rw.dbHandler = NewASHandler(store, log) rw.dbHandler = NewASHandler(store, log)
fill := ristypes.ASPath{Sequence: slices.Repeat([]int{testASNA}, asnBatchSize)}
startBlockedWrite(t, blocking, rw.dbHandler, startBlockedWrite(t, blocking, rw.dbHandler,
[]*ristypes.RISMessage{{Path: fill}}) []*ristypes.RISMessage{{Path: pathOfASes(asnBatchSize)}})
ctx, cancel := context.WithTimeout(t.Context(), deadline) ctx, cancel := context.WithTimeout(t.Context(), deadline)
defer cancel() defer cancel()
@@ -635,9 +678,9 @@ func TestShutdownReturnsByItsDeadlineWhileAWriteIsBlocked(t *testing.T) {
select { select {
case <-shutDown: case <-shutDown:
case <-time.After(deadline + margin): case <-time.After(deadline + stepTimeout):
t.Fatalf("Shutdown did not return within %s of its deadline while "+ t.Fatalf("Shutdown did not return within %s of its deadline while "+
"a write was blocked", margin) "a write was blocked", stepTimeout)
} }
var dialer net.Dialer var dialer net.Dialer
@@ -712,8 +755,6 @@ func (s *closeOrderStore) record(call string) {
func TestShutdownCheckpointsAndClosesTheDatabaseLast(t *testing.T) { func TestShutdownCheckpointsAndClosesTheDatabaseLast(t *testing.T) {
t.Parallel() t.Parallel()
const deadline = 10 * time.Second
store := &closeOrderStore{Store: newMockStore()} store := &closeOrderStore{Store: newMockStore()}
log := logger.New() log := logger.New()
cfg := &config.Config{} cfg := &config.Config{}
@@ -731,7 +772,7 @@ func TestShutdownCheckpointsAndClosesTheDatabaseLast(t *testing.T) {
Path: ristypes.ASPath{Sequence: []int{testASNA}}, Path: ristypes.ASPath{Sequence: []int{testASNA}},
}) })
ctx, cancel := context.WithTimeout(t.Context(), deadline) ctx, cancel := context.WithTimeout(t.Context(), stepTimeout)
defer cancel() defer cancel()
rw.Shutdown(ctx) rw.Shutdown(ctx)
@@ -744,3 +785,74 @@ func TestShutdownCheckpointsAndClosesTheDatabaseLast(t *testing.T) {
t.Errorf("Shutdown made the calls %q, want %q", store.calls, want) t.Errorf("Shutdown made the calls %q, want %q", store.calls, want)
} }
} }
// TestPTRCacheAnswersTheIPLookup starts the PTR cache and the HTTP server as
// Run does, and looks up a reserved address, which asks no resolver. Without
// the PTR cache the server has no PTR resolver, and every IP lookup answers
// 500.
func TestPTRCacheAnswersTheIPLookup(t *testing.T) {
t.Parallel()
store := newMockStore()
log := logger.New()
port := freePort(t)
cfg := &config.Config{Port: port, StateDir: t.TempDir()}
s := streamer.New(log, metrics.New())
// A started server reads its routing table in the background, so it
// needs one.
rw := New(Dependencies{
DB: store,
Streamer: s,
Server: server.New(store, routetable.New(routetable.Params{}), s, log,
cfg),
Logger: log,
Config: cfg,
})
err := rw.startPTRCache(t.Context())
if err != nil {
t.Fatalf("failed to start the PTR cache: %v", err)
}
defer rw.stopPTRCache(t.Context())
err = rw.server.Start(t.Context())
if err != nil {
t.Fatalf("failed to start the HTTP server: %v", err)
}
defer func() { _ = rw.server.Stop(t.Context()) }()
req, err := http.NewRequestWithContext(t.Context(), http.MethodGet,
"http://"+net.JoinHostPort("127.0.0.1", strconv.Itoa(port))+
"/api/v1/ip/10.0.0.1", nil)
if err != nil {
t.Fatalf("failed to build the request: %v", err)
}
resp, err := http.DefaultClient.Do(req)
if err != nil {
t.Fatalf("the IP lookup failed: %v", err)
}
defer func() { _ = resp.Body.Close() }()
body, err := io.ReadAll(resp.Body)
if err != nil {
t.Fatalf("failed to read the answer: %v", err)
}
if resp.StatusCode != http.StatusOK {
t.Fatalf("status %d, want %d; body %s", resp.StatusCode, http.StatusOK, body)
}
if !strings.Contains(string(body), `"ptr":[]`) {
t.Errorf("answer %s, want an empty ptr", body)
}
_, err = os.Stat(filepath.Join(cfg.StateDir, "cache.db"))
if err != nil {
t.Errorf("cache.db is not in the state directory: %v", err)
}
}
internal/routewatch/ashandler.go
+42 -87
View File
@@ -18,39 +18,34 @@ const (
// (asnBatchTimeout), so a queue smaller than asnBatchSize is fine. // (asnBatchTimeout), so a queue smaller than asnBatchSize is fine.
asHandlerQueueSize = 20000 asHandlerQueueSize = 20000
// asnBatchSize is the number of ASN operations to batch together // asnBatchSize is the number of ASes in a full batch, which wakes the
// flush goroutine to write it.
asnBatchSize = 30000 asnBatchSize = 30000
// asnBatchMaxSize is the most ASN operations the batch holds while the
// flush goroutine writes the previous one: ten batches, about 10 MiB
// (README "Memory"). At this size HandleMessage waits until the flush
// goroutine takes the batch.
asnBatchMaxSize = 300000
// asnBatchTimeout is the maximum time to wait before flushing a batch // asnBatchTimeout is the maximum time to wait before flushing a batch
// DO NOT reduce this timeout - larger batches are more efficient // DO NOT reduce this timeout - larger batches are more efficient
asnBatchTimeout = 2 * time.Second asnBatchTimeout = 2 * time.Second
) )
// ASHandler processes Autonomous System Number (ASN) information extracted from // ASHandler records every AS in the AS paths of BGP UPDATE messages. Its batch
// BGP UPDATE messages. It uses batched database operations to efficiently store // holds the earliest and the latest time of each AS's updates. The flush
// ASN data, collecting operations into batches that are flushed either when the // goroutine writes the batch to the database when it holds asnBatchSize ASes,
// batch reaches a size threshold or after a timeout period. // and every asnBatchTimeout.
type ASHandler struct { type ASHandler struct {
db database.Store db database.Store
logger *logger.Logger logger *logger.Logger
// Batching. mu guards batch and writing only: the flush goroutine takes // Batching. mu guards batch and writing only. The flush goroutine takes
// the batch under mu and writes it after releasing mu, so HandleMessage // the batch under mu and writes it after releasing mu. So HandleMessage
// waits for a database write only while batch is at asnBatchMaxSize. // never waits for a database write.
mu sync.Mutex mu sync.Mutex
batch []asnOp // batch holds the earliest and the latest time of the updates for each AS
// writing is how many operations the flush goroutine took from batch // since the flush goroutine last took it. It holds one entry per AS,
// and has not finished writing. // however many updates arrive.
writing int batch map[int]database.SeenTimes
// batchTaken is signalled when the flush goroutine takes batch; its L is // writing is how many ASes the flush goroutine took from batch and has
// &mu. // not finished writing.
batchTaken sync.Cond writing int
batchFullCh chan struct{} // wakes the flush goroutine when batch is full batchFullCh chan struct{} // wakes the flush goroutine when batch is full
// stopCh hands Stop's context to the flush goroutine. It holds one, so // stopCh hands Stop's context to the flush goroutine. It holds one, so
// Stop does not wait for a write in progress to hand it over. // Stop does not wait for a write in progress to hand it over.
@@ -58,16 +53,10 @@ type ASHandler struct {
done chan struct{} // closed when the flush goroutine returns done chan struct{} // closed when the flush goroutine returns
} }
type asnOp struct {
number int
timestamp time.Time
}
// NewASHandler creates and returns a new ASHandler instance. It initializes // NewASHandler creates and returns a new ASHandler instance. It initializes
// the batching system and starts a background goroutine that periodically // the batching system and starts a background goroutine that periodically
// flushes accumulated ASN operations to the database. The caller must call // writes the collected ASes to the database. The caller must call Stop when
// Stop when finished to ensure all pending operations are flushed and the // finished, to write the pending ASes and end the background goroutine.
// background goroutine is terminated.
func NewASHandler(db database.Store, logger *logger.Logger) *ASHandler { func NewASHandler(db database.Store, logger *logger.Logger) *ASHandler {
return newASHandler(db, logger, asnBatchTimeout) return newASHandler(db, logger, asnBatchTimeout)
} }
@@ -81,12 +70,11 @@ func newASHandler(
h := &ASHandler{ h := &ASHandler{
db: db, db: db,
logger: logger, logger: logger,
batch: make([]asnOp, 0, asnBatchSize), batch: make(map[int]database.SeenTimes),
batchFullCh: make(chan struct{}, 1), batchFullCh: make(chan struct{}, 1),
stopCh: make(chan context.Context, 1), stopCh: make(chan context.Context, 1),
done: make(chan struct{}), done: make(chan struct{}),
} }
h.batchTaken.L = &h.mu
// Start the flush timer goroutine // Start the flush timer goroutine
go flushLoop(batchTimeout, h.batchFullCh, h.stopCh, h.done, h.flushBatch) go flushLoop(batchTimeout, h.batchFullCh, h.stopCh, h.done, h.flushBatch)
@@ -110,48 +98,25 @@ func (h *ASHandler) QueueCapacity() int {
return asHandlerQueueSize return asHandlerQueueSize
} }
// HandleMessage processes a RIS Live BGP message by extracting all ASNs from // HandleMessage adds the time of msg to the batch entry of each AS in its AS
// the AS path and queuing them for batch insertion into the database. The // path, the origin AS and the members of an AS set included. When the batch
// origin ASN and all transit ASNs are recorded with their associated // holds asnBatchSize ASes, HandleMessage wakes the flush goroutine to write it.
// timestamps. When the batch reaches the configured size threshold, the flush
// goroutine is woken to write it.
func (h *ASHandler) HandleMessage(msg *ristypes.RISMessage) { func (h *ASHandler) HandleMessage(msg *ristypes.RISMessage) {
// Use the pre-parsed timestamp
timestamp := msg.ParsedTimestamp
originASN := msg.Path.Origin()
h.mu.Lock() h.mu.Lock()
defer h.mu.Unlock() defer h.mu.Unlock()
// While the batch is at its maximum size, wait until the flush goroutine // The origin AS is the last AS of the sequence, so the loop adds it too.
// takes it. Meanwhile the handler takes nothing off its queue, which
// fills, and the streamer drops messages for it.
for len(h.batch) >= asnBatchMaxSize {
h.batchTaken.Wait()
}
// Queue origin ASN operation
if originASN > 0 {
h.batch = append(h.batch, asnOp{
number: originASN,
timestamp: timestamp,
})
}
// Also track all ASNs in the path, the members of an AS set included
for _, asn := range slices.Concat(msg.Path.Sequence, msg.Path.Set) { for _, asn := range slices.Concat(msg.Path.Sequence, msg.Path.Set) {
if asn > 0 { if asn > 0 {
h.batch = append(h.batch, asnOp{ seen := h.batch[asn]
number: asn, seen.Add(msg.ParsedTimestamp)
timestamp: timestamp, h.batch[asn] = seen
})
} }
} }
// A full batch wakes the flush goroutine. If it is writing, the wake-up // A full batch wakes the flush goroutine. If it is writing, the wake-up
// waits in batchFullCh and the batch keeps growing until the write ends // waits in batchFullCh and the batch keeps taking updates until the write
// or the batch reaches asnBatchMaxSize. // ends.
if len(h.batch) >= asnBatchSize { if len(h.batch) >= asnBatchSize {
select { select {
case h.batchFullCh <- struct{}{}: case h.batchFullCh <- struct{}{}:
@@ -160,10 +125,11 @@ func (h *ASHandler) HandleMessage(msg *ristypes.RISMessage) {
} }
} }
// Stop stops the flush goroutine, which writes the operations the handler holds // Stop stops the flush goroutine and waits for it until ctx ends. The flush
// before it returns, and waits for it until ctx ends. Once ctx has ended the // goroutine writes the batch before it returns, unless ctx has ended. A write
// flush goroutine skips that last write, and a write still running is lost // still running when the process exits is lost. Stop logs how many entries are
// when the process exits, so Stop logs how many operations are not written. // not written, in the batch being written and in the next batch. An AS in both
// batches counts twice.
func (h *ASHandler) Stop(ctx context.Context) { func (h *ASHandler) Stop(ctx context.Context) {
h.stopCh <- ctx h.stopCh <- ctx
@@ -178,14 +144,14 @@ func (h *ASHandler) Stop(ctx context.Context) {
if unwritten > 0 { if unwritten > 0 {
h.logger.Error("Stop deadline passed before the AS handler wrote "+ h.logger.Error("Stop deadline passed before the AS handler wrote "+
"its updates", "updates", unwritten) "its batches", "batch_entries", unwritten)
} }
} }
// takeBatch returns the pending operations and leaves an empty batch in their // takeBatch returns the pending ASes and leaves an empty batch in their place
// place for HandleMessage to fill. They count in writing until flushBatch has // for HandleMessage to fill. They count in writing until flushBatch has written
// written them. // them.
func (h *ASHandler) takeBatch() []asnOp { func (h *ASHandler) takeBatch() map[int]database.SeenTimes {
h.mu.Lock() h.mu.Lock()
defer h.mu.Unlock() defer h.mu.Unlock()
@@ -195,8 +161,7 @@ func (h *ASHandler) takeBatch() []asnOp {
batch := h.batch batch := h.batch
h.writing = len(batch) h.writing = len(batch)
h.batch = make([]asnOp, 0, asnBatchSize) h.batch = make(map[int]database.SeenTimes)
h.batchTaken.Broadcast()
return batch return batch
} }
@@ -209,21 +174,11 @@ func (h *ASHandler) flushBatch() {
return return
} }
// The earliest and the latest time the batch saw each AS. The batch holds
// several updates for an AS, from many peers, so a new AS is stored first
// seen at the earliest of them and last seen at the latest.
asns := make(map[int]database.SeenTimes)
for _, op := range batch {
seen := asns[op.number]
seen.Add(op.timestamp)
asns[op.number] = seen
}
// Process all ASNs in a single batch transaction // Process all ASNs in a single batch transaction
err := h.db.GetOrCreateASNBatch(asns) err := h.db.GetOrCreateASNBatch(batch)
if err != nil { if err != nil {
h.logger.Error("Failed to process ASN batch", h.logger.Error("Failed to process ASN batch",
"error", err, "count", len(asns)) "error", err, "count", len(batch))
} }
h.mu.Lock() h.mu.Lock()
internal/routewatch/ashandler_internal_test.go
+24 -7
View File
@@ -5,28 +5,43 @@ import (
"slices" "slices"
"testing" "testing"
"git.eeqj.de/sneak/routewatch/internal/database"
"git.eeqj.de/sneak/routewatch/internal/logger" "git.eeqj.de/sneak/routewatch/internal/logger"
"git.eeqj.de/sneak/routewatch/internal/ristypes"
) )
// pathOfASes returns an AS path of n different ASes: AS 1 to AS n. With n up to
// asnBatchSize, none of them is testASNA to testASND.
func pathOfASes(n int) ristypes.ASPath {
sequence := make([]int, n)
for i := range sequence {
sequence[i] = i + 1
}
return ristypes.ASPath{Sequence: sequence}
}
// TestASHandlerStoresTheEarliestAndLatestTimesOfANewAS handles two updates // TestASHandlerStoresTheEarliestAndLatestTimesOfANewAS handles two updates
// whose path carries an AS the database does not hold yet, the second 5 // whose path carries an AS the database does not hold yet, in one batch into a
// seconds after the first, in one batch into a real database. The AS is stored // real database. The second is 5 seconds after the first, and the handler gets
// first seen at the time of the first update and last seen at the time of the // it first. The AS is stored first seen at the time of the first update and
// second. // last seen at the time of the second.
func TestASHandlerStoresTheEarliestAndLatestTimesOfANewAS(t *testing.T) { func TestASHandlerStoresTheEarliestAndLatestTimesOfANewAS(t *testing.T) {
t.Parallel() t.Parallel()
db := newTestDatabase(t) db := newTestDatabase(t)
// Built without NewASHandler's flush goroutine, so the test flushes itself. // Built without NewASHandler's flush goroutine, so the test flushes itself.
h := &ASHandler{db: db, logger: logger.New()} h := &ASHandler{
db: db, logger: logger.New(), batch: make(map[int]database.SeenTimes),
}
first := peerAnnouncement(testPeerIP, testV4Prefix) first := peerAnnouncement(testPeerIP, testV4Prefix)
second := peerAnnouncement(testPeerIP, testV4Prefix) second := peerAnnouncement(testPeerIP, testV4Prefix)
second.ParsedTimestamp = first.ParsedTimestamp.Add(secondUpdateAfter) second.ParsedTimestamp = first.ParsedTimestamp.Add(secondUpdateAfter)
h.HandleMessage(first)
h.HandleMessage(second) h.HandleMessage(second)
h.HandleMessage(first)
h.flushBatch() h.flushBatch()
asn, _, err := db.GetAS(t.Context(), testASNA) asn, _, err := db.GetAS(t.Context(), testASNA)
@@ -54,7 +69,9 @@ func TestASHandlerRecordsNothingFromAPathWithASZero(t *testing.T) {
store := newMockStore() store := newMockStore()
// Built without NewASHandler's flush goroutine, so the test flushes itself. // Built without NewASHandler's flush goroutine, so the test flushes itself.
h := &ASHandler{db: store, logger: logger.New()} h := &ASHandler{
db: store, logger: logger.New(), batch: make(map[int]database.SeenTimes),
}
msg := peerAnnouncement(testPeerIP, testV4Prefix) msg := peerAnnouncement(testPeerIP, testV4Prefix)
msg.Path = decodePath(t, testASNA, 0, testASNB) msg.Path = decodePath(t, testASNA, 0, testASNB)
internal/routewatch/asnfetcher.go
+31 -5
View File
@@ -187,25 +187,33 @@ func (f *ASNFetcher) recordSuccess() {
f.statsMu.Unlock() f.statsMu.Unlock()
} }
// recordFailure increases the interval on failed fetch using exponential backoff. // lengthenInterval makes the interval 1.5 times as long, up to maxInterval.
func (f *ASNFetcher) recordFailure() { // A failed lookup and a skipped one both lengthen it.
func (f *ASNFetcher) lengthenInterval() {
f.intervalMu.Lock() f.intervalMu.Lock()
f.consecutiveFails++ defer f.intervalMu.Unlock()
// Exponential backoff: multiply by 1.5, capped at max
newInterval := min( newInterval := min(
f.currentInterval*backoffNumerator/backoffDenominator, maxInterval) f.currentInterval*backoffNumerator/backoffDenominator, maxInterval)
if newInterval != f.currentInterval { if newInterval != f.currentInterval {
f.logger.Debug("Increased fetch interval due to failure", f.logger.Debug("Increased fetch interval",
"old_interval", f.currentInterval, "old_interval", f.currentInterval,
"new_interval", newInterval, "new_interval", newInterval,
"consecutive_failures", f.consecutiveFails, "consecutive_failures", f.consecutiveFails,
) )
f.currentInterval = newInterval f.currentInterval = newInterval
} }
}
// recordFailure counts a failed fetch and lengthens the interval.
func (f *ASNFetcher) recordFailure() {
f.intervalMu.Lock()
f.consecutiveFails++
f.intervalMu.Unlock() f.intervalMu.Unlock()
f.lengthenInterval()
// Record error time for stats, dropping those older than statsWindow // Record error time for stats, dropping those older than statsWindow
f.statsMu.Lock() f.statsMu.Lock()
now := f.now() now := f.now()
@@ -287,6 +295,16 @@ func (f *ASNFetcher) fetchNextStale(ctx context.Context) {
// so the AS stays stale. An AS IANA refers to no RIR is stored with no // so the AS stays stale. An AS IANA refers to no RIR is stored with no
// WHOIS data, so it is not looked up again until it is stale; that counts // WHOIS data, so it is not looked up again until it is stale; that counts
// as neither a success nor a failure. // as neither a success nor a failure.
//
// The WHOIS client pauses an RIR's or NIC.br's server for whois.PauseTime
// after the server refuses a query. Lookups at the other servers go on. IANA
// is never paused, so a refusal by IANA is an ordinary failure. A lookup
// whose RIR is paused fails with whois.ErrPaused and is skipped. A skipped
// lookup leaves the AS stale and is not counted as a failure. Like a
// failure, a skipped lookup lengthens the interval. Each lookup asks IANA
// before it finds its RIR paused, so with a one-second interval the fetcher
// would ask IANA every second. The lookups that QueueImmediate asks for also
// run through fetchAndUpdate.
func (f *ASNFetcher) fetchAndUpdate(ctx context.Context, asn int) bool { func (f *ASNFetcher) fetchAndUpdate(ctx context.Context, asn int) bool {
ctx, cancel := context.WithTimeout(ctx, time.Minute) ctx, cancel := context.WithTimeout(ctx, time.Minute)
defer cancel() defer cancel()
@@ -307,6 +325,14 @@ func (f *ASNFetcher) fetchAndUpdate(ctx context.Context, asn int) bool {
return false return false
} }
if errors.Is(err, whois.ErrPaused) {
f.logger.Info("Skipped WHOIS lookup, the RIR's server is paused",
"asn", asn, "error", err)
f.lengthenInterval()
return false
}
if err != nil { if err != nil {
f.logger.Error("WHOIS lookup failed", "asn", asn, "error", err) f.logger.Error("WHOIS lookup failed", "asn", asn, "error", err)
f.recordFailure() f.recordFailure()
internal/routewatch/asnfetcher_internal_test.go
+150 -4
View File
@@ -13,6 +13,7 @@ import (
"git.eeqj.de/sneak/routewatch/internal/database" "git.eeqj.de/sneak/routewatch/internal/database"
"git.eeqj.de/sneak/routewatch/internal/logger" "git.eeqj.de/sneak/routewatch/internal/logger"
"git.eeqj.de/sneak/routewatch/internal/whois"
) )
// The WHOIS servers a lookup asks: IANA first, then the RIR IANA refers it // The WHOIS servers a lookup asks: IANA first, then the RIR IANA refers it
@@ -131,6 +132,151 @@ func TestFetchAndUpdateKeepsTheRowWhenTheLookupFails(t *testing.T) {
} }
} }
// TestFetchAndUpdateWaitsOutAPause looks up an AS at RIPE while RIPE refuses
// the query. The test sets the WHOIS client's clock. The next lookup comes a
// second before whois.PauseTime has passed. It sends RIPE nothing and leaves
// the AS never looked up. It counts as neither a success nor a failure. A
// lookup at whois.PauseTime asks RIPE again.
func TestFetchAndUpdateWaitsOutAPause(t *testing.T) {
t.Parallel()
f, db := newFetcherWithWHOISAnswers(t, map[string]string{
ianaWHOISServer: ianaRefersToRIPE,
ripeWHOISServer: ripeAccessDenied,
})
ripeAsks := 0
dial := f.whoisClient.DialContext
f.whoisClient.DialContext = func(
ctx context.Context, network, address string,
) (net.Conn, error) {
if address == ripeWHOISServer {
ripeAsks++
}
return dial(ctx, network, address)
}
start := time.Date(2026, 11, 2, 0, 0, 0, 0, time.UTC)
now := start
f.whoisClient.Now = func() time.Time { return now }
f.fetchAndUpdate(t.Context(), testASNA)
now = start.Add(whois.PauseTime - time.Second)
f.fetchAndUpdate(t.Context(), testASNA)
if ripeAsks != 1 {
t.Errorf("RIPE was asked %d times during its pause, want 1", ripeAsks)
}
stats, err := db.GetWHOISStats(t.Context(), whoisStaleThreshold)
if err != nil {
t.Fatalf("GetWHOISStats: %v", err)
}
if stats.NeverFetched != 1 {
t.Errorf("never looked up = %d, want 1", stats.NeverFetched)
}
got := f.GetStats()
if got.ConsecutiveFails != 1 || got.ErrorsLastHour != 1 ||
got.SuccessesLastHour != 0 {
t.Errorf("%d failures in a row, %d errors, %d successes; want 1, 1, 0",
got.ConsecutiveFails, got.ErrorsLastHour, got.SuccessesLastHour)
}
now = start.Add(whois.PauseTime)
f.fetchAndUpdate(t.Context(), testASNA)
if ripeAsks != 2 {
t.Errorf("RIPE was asked %d times after its pause, want 2", ripeAsks)
}
}
// TestFetchAndUpdateBacksOffDuringAPause looks up an AS at RIPE while RIPE
// refuses the query. The refusal pauses RIPE for an hour, so every later
// lookup in the test is skipped. The test sets the WHOIS client's clock and
// looks the AS up again each time the interval has passed. Like a failure,
// each skip must make the interval 1.5 times as long, up to one minute. The
// skips must not count as failures.
func TestFetchAndUpdateBacksOffDuringAPause(t *testing.T) {
t.Parallel()
f, _ := newFetcherWithWHOISAnswers(t, map[string]string{
ianaWHOISServer: ianaRefersToRIPE,
ripeWHOISServer: ripeAccessDenied,
})
now := time.Date(2026, 11, 2, 0, 0, 0, 0, time.UTC)
f.whoisClient.Now = func() time.Time { return now }
f.fetchAndUpdate(t.Context(), testASNA)
for i, want := range []time.Duration{
33750 * time.Millisecond,
50625 * time.Millisecond,
time.Minute,
time.Minute,
} {
now = now.Add(f.getInterval())
f.fetchAndUpdate(t.Context(), testASNA)
if got := f.getInterval(); got != want {
t.Errorf("interval after %d skipped lookups = %v, want %v",
i+1, got, want)
}
}
got := f.GetStats()
if got.ConsecutiveFails != 1 || got.ErrorsLastHour != 1 {
t.Errorf("%d failures in a row and %d errors, want 1 and 1",
got.ConsecutiveFails, got.ErrorsLastHour)
}
}
// TestFetchAndUpdateKeepsAskingIANA looks up an AS while IANA's server
// refuses the connection. The test sets the WHOIS client's clock. The next
// lookup comes a second before whois.PauseTime has passed. IANA is never
// paused, so that lookup asks IANA again. Each refusal counts as a failure.
func TestFetchAndUpdateKeepsAskingIANA(t *testing.T) {
t.Parallel()
// With no answers, every server refuses the connection.
f, _ := newFetcherWithWHOISAnswers(t, map[string]string{})
ianaAsks := 0
dial := f.whoisClient.DialContext
f.whoisClient.DialContext = func(
ctx context.Context, network, address string,
) (net.Conn, error) {
if address == ianaWHOISServer {
ianaAsks++
}
return dial(ctx, network, address)
}
start := time.Date(2026, 11, 2, 0, 0, 0, 0, time.UTC)
now := start
f.whoisClient.Now = func() time.Time { return now }
f.fetchAndUpdate(t.Context(), testASNA)
now = start.Add(whois.PauseTime - time.Second)
f.fetchAndUpdate(t.Context(), testASNA)
got := f.GetStats()
if ianaAsks != 2 || got.ConsecutiveFails != 2 {
t.Errorf("IANA was asked %d times, with %d failures in a row; "+
"want 2 and 2", ianaAsks, got.ConsecutiveFails)
}
}
// TestRecordStepsTheInterval has the fetcher fail from its base interval of // TestRecordStepsTheInterval has the fetcher fail from its base interval of
// 15 seconds, then succeed. Each failure makes the interval 1.5 times as // 15 seconds, then succeed. Each failure makes the interval 1.5 times as
// long, up to one minute, and each success halves it, down to one second. // long, up to one minute, and each success halves it, down to one second.
@@ -224,7 +370,7 @@ func TestASNFetcherStopReturnsByItsDeadline(t *testing.T) {
select { select {
case <-lookupStarted: case <-lookupStarted:
case <-time.After(handleMessageTimeout): case <-time.After(stepTimeout):
t.Fatal("the fetcher did not start the lookup") t.Fatal("the fetcher did not start the lookup")
} }
@@ -240,22 +386,22 @@ func TestASNFetcherStopReturnsByItsDeadline(t *testing.T) {
select { select {
case <-f.done: case <-f.done:
case <-time.After(handleMessageTimeout): case <-time.After(stepTimeout):
t.Fatal("the fetcher goroutine did not return after the lookup ended") t.Fatal("the fetcher goroutine did not return after the lookup ended")
} }
} }
// TestRecordKeepsOnlyTheStatsWindow records a success and a failure every // TestRecordKeepsOnlyTheStatsWindow records a success and a failure every
// second, by a clock the test sets, far longer than statsWindow, and never // second, by a clock the test sets, for three times statsWindow, and never
// asks for the stats. The fetcher must keep only the times within the last // asks for the stats. The fetcher must keep only the times within the last
// statsWindow. // statsWindow.
func TestRecordKeepsOnlyTheStatsWindow(t *testing.T) { func TestRecordKeepsOnlyTheStatsWindow(t *testing.T) {
t.Parallel() t.Parallel()
const ( const (
records = 100_000
step = time.Second step = time.Second
want = int(statsWindow / step) want = int(statsWindow / step)
records = 3 * want
) )
clock := time.Now() clock := time.Now()
internal/routewatch/batchwrite_internal_test.go
+211 -69
View File
@@ -5,6 +5,7 @@ import (
"context" "context"
"encoding/json" "encoding/json"
"fmt" "fmt"
"io"
"log/slog" "log/slog"
"slices" "slices"
"sync" "sync"
@@ -19,9 +20,15 @@ import (
) )
const ( const (
// handleMessageTimeout is how long a test waits for HandleMessage to // stepTimeout is how long a test waits for a step it expects, such as
// return, or for a write to start, before it fails. // HandleMessage returning, a write starting or Shutdown returning, before
handleMessageTimeout = 2 * time.Second // it fails. Only a step that never comes should reach it. On a loaded
// host, under the race detector, HandleMessage takes seconds to apply a
// full prefix batch. The helpers below bound every wait with it, Stop
// included. A test that hangs in one of them waits out at most two of
// these bounds, its step's and Stop's, and then fails with its own
// message. That leaves time before go test's 90-second timeout.
stepTimeout = 15 * time.Second
// stillWaitingAfter is how long a test watches a HandleMessage that must // stillWaitingAfter is how long a test watches a HandleMessage that must
// wait. One that does not wait returns well within it. // wait. One that does not wait returns well within it.
@@ -168,15 +175,18 @@ func (s *blockingStore) releaseWrites() {
// //
//nolint:tagliatelle // field names are the keys the handlers log //nolint:tagliatelle // field names are the keys the handlers log
type stopLog struct { type stopLog struct {
Msg string `json:"msg"` Msg string `json:"msg"`
Updates int `json:"updates"` Updates int `json:"updates"`
TableChanges int `json:"table_changes"` TableChanges int `json:"table_changes"`
Paths int `json:"paths"` HeldMessages int `json:"held_messages"`
OriginChanges int `json:"origin_changes"`
Paths int `json:"paths"`
BatchEntries int `json:"batch_entries"`
} }
// newErrorLogger returns a logger that writes only errors, as JSON lines, to // newErrorLogger returns a logger that writes only errors, as JSON lines, to
// logs. // logs.
func newErrorLogger(logs *bytes.Buffer) *logger.Logger { func newErrorLogger(logs io.Writer) *logger.Logger {
return &logger.Logger{Logger: slog.New(slog.NewJSONHandler(logs, return &logger.Logger{Logger: slog.New(slog.NewJSONHandler(logs,
&slog.HandlerOptions{Level: slog.LevelError}))} &slog.HandlerOptions{Level: slog.LevelError}))}
} }
@@ -198,7 +208,7 @@ func lastLogged(t *testing.T, logs *bytes.Buffer) stopLog {
return logged return logged
} }
// returnsInTime reports whether f returns within handleMessageTimeout. // returnsInTime reports whether f returns within stepTimeout.
func returnsInTime(f func()) bool { func returnsInTime(f func()) bool {
done := make(chan struct{}) done := make(chan struct{})
@@ -210,11 +220,22 @@ func returnsInTime(f func()) bool {
select { select {
case <-done: case <-done:
return true return true
case <-time.After(handleMessageTimeout): case <-time.After(stepTimeout):
return false return false
} }
} }
// stopInTime stops h, with no deadline, and fails the test if Stop does not
// return within stepTimeout. It only marks the test failed, so it can be
// deferred.
func stopInTime(t *testing.T, h interface{ Stop(ctx context.Context) }) {
t.Helper()
if !returnsInTime(func() { h.Stop(t.Context()) }) {
t.Errorf("Stop did not return within %s", stepTimeout)
}
}
// startBlockedWrite hands h the messages in fill and waits until h starts to // startBlockedWrite hands h the messages in fill and waits until h starts to
// write them to store. The prefix, AS and peer handlers start when fill fills // write them to store. The prefix, AS and peer handlers start when fill fills
// their batch, and the peering handler on its timer. store holds the write // their batch, and the peering handler on its timer. store holds the write
@@ -240,7 +261,7 @@ func startBlockedWrite(
select { select {
case <-store.writeStarted: case <-store.writeStarted:
case <-time.After(handleMessageTimeout): case <-time.After(stepTimeout):
t.Fatal("the handler did not start to write the messages") t.Fatal("the handler did not start to write the messages")
} }
} }
@@ -261,7 +282,7 @@ func handleWhileAWriteIsBlocked(
) { ) {
t.Helper() t.Helper()
defer h.Stop(t.Context()) defer stopInTime(t, h)
defer store.releaseWrites() defer store.releaseWrites()
startBlockedWrite(t, store, h, fill) startBlockedWrite(t, store, h, fill)
@@ -275,7 +296,9 @@ func handleWhileAWriteIsBlocked(
// while store holds the write, hands h the messages in toMax, which bring its // while store holds the write, hands h the messages in toMax, which bring its
// next batch to its maximum size, and the message extra. HandleMessage for // next batch to its maximum size, and the message extra. HandleMessage for
// extra must wait until the test lets the write finish, and return after. Then // extra must wait until the test lets the write finish, and return after. Then
// it stops h, which writes what it holds. // it stops h, which writes what it holds. The tests lower h's maximum batch
// size to one batch, so toMax is one batch: the real maximum of ten batches is
// slow to reach under the race detector.
func handleAtMaxBatchSize( func handleAtMaxBatchSize(
t *testing.T, t *testing.T,
store *blockingStore, store *blockingStore,
@@ -288,13 +311,18 @@ func handleAtMaxBatchSize(
) { ) {
t.Helper() t.Helper()
defer h.Stop(t.Context()) defer stopInTime(t, h)
defer store.releaseWrites() defer store.releaseWrites()
startBlockedWrite(t, store, h, fill) startBlockedWrite(t, store, h, fill)
for _, msg := range toMax { if !returnsInTime(func() {
h.HandleMessage(msg) for _, msg := range toMax {
h.HandleMessage(msg)
}
}) {
t.Fatal("HandleMessage did not return while the batch grew to its " +
"maximum size")
} }
returned := make(chan struct{}) returned := make(chan struct{})
@@ -315,7 +343,7 @@ func handleAtMaxBatchSize(
select { select {
case <-returned: case <-returned:
case <-time.After(handleMessageTimeout): case <-time.After(stepTimeout):
t.Fatal("HandleMessage did not return after the database write finished") t.Fatal("HandleMessage did not return after the database write finished")
} }
} }
@@ -345,8 +373,12 @@ func stopWhileAWriteIsBlocked(
startBlockedWrite(t, store, h, fill) startBlockedWrite(t, store, h, fill)
for _, msg := range extra { if !returnsInTime(func() {
h.HandleMessage(msg) for _, msg := range extra {
h.HandleMessage(msg)
}
}) {
t.Fatal("HandleMessage did not return while a database write was blocked")
} }
ctx, cancel := context.WithTimeout(t.Context(), stopDeadline) ctx, cancel := context.WithTimeout(t.Context(), stopDeadline)
@@ -361,7 +393,7 @@ func stopWhileAWriteIsBlocked(
select { select {
case <-done: case <-done:
case <-time.After(handleMessageTimeout): case <-time.After(stepTimeout):
t.Fatal("the flush goroutine did not return after the write finished") t.Fatal("the flush goroutine did not return after the write finished")
} }
} }
@@ -380,7 +412,8 @@ func TestPrefixHandlerSkipsItsLastWriteAfterTheStopDeadline(t *testing.T) {
store := newBlockingStore() store := newBlockingStore()
h := newPrefixHandler(store, newErrorLogger(&logs), h := newPrefixHandler(store, newErrorLogger(&logs),
routetable.New(routetable.Params{}), longerThanAnyTest) routetable.New(routetable.Params{}), longerThanAnyTest,
maxTableChangesPerWrite)
fill := slices.Repeat([]string{testV4Prefix}, prefixBatchSize) fill := slices.Repeat([]string{testV4Prefix}, prefixBatchSize)
stopWhileAWriteIsBlocked(t, store, h, h.done, stopWhileAWriteIsBlocked(t, store, h, h.done,
[]*ristypes.RISMessage{prefixAnnouncement(fill)}, []*ristypes.RISMessage{prefixAnnouncement(fill)},
@@ -440,6 +473,42 @@ func (s tableWriteBlockingStore) WriteRouteChanges(
return s.mockStore.WriteRouteChanges(changes, newPeers) return s.mockStore.WriteRouteChanges(changes, newPeers)
} }
// stopPrefixHandlerWithBlockedWrite stops the prefix handler, whose store
// holds the write that fill starts, after handing it the message extra, and
// returns what Stop logged. blocking is the store the write waits on; store is
// a blockingStore wrapped for the routing table's changes or the origin
// changes.
func stopPrefixHandlerWithBlockedWrite(
t *testing.T,
blocking *blockingStore,
store database.Store,
logs *bytes.Buffer,
fill, extra *ristypes.RISMessage,
) stopLog {
t.Helper()
h := NewPrefixHandler(store, newErrorLogger(logs),
routetable.New(routetable.Params{}))
stopWhileAWriteIsBlocked(t, blocking, h, h.done,
[]*ristypes.RISMessage{fill}, extra)
return lastLogged(t, logs)
}
// originChangesBlockingStore is a blockingStore whose writes of the origin
// changes also wait until the test calls releaseWrites.
type originChangesBlockingStore struct {
*blockingStore
}
func (s originChangesBlockingStore) WriteOriginChanges(
changes []routetable.OriginChange,
) error {
s.waitForRelease()
return s.mockStore.WriteOriginChanges(changes)
}
// TestPrefixHandlerStopCountsTheTableChangesOfAWriteInProgress holds the write // TestPrefixHandlerStopCountsTheTableChangesOfAWriteInProgress holds the write
// of the routing table's changes that a full batch starts, then hands the // of the routing table's changes that a full batch starts, then hands the
// prefix handler one more prefix and stops it with a deadline that passes // prefix handler one more prefix and stops it with a deadline that passes
@@ -453,33 +522,81 @@ func TestPrefixHandlerStopCountsTheTableChangesOfAWriteInProgress(t *testing.T)
var logs bytes.Buffer var logs bytes.Buffer
blocking := newBlockingStore() blocking := newBlockingStore()
h := NewPrefixHandler(tableWriteBlockingStore{blockingStore: blocking},
newErrorLogger(&logs), routetable.New(routetable.Params{}))
fill := slices.Repeat([]string{testV4Prefix}, prefixBatchSize) fill := slices.Repeat([]string{testV4Prefix}, prefixBatchSize)
stopWhileAWriteIsBlocked(t, blocking, h, h.done, logged := stopPrefixHandlerWithBlockedWrite(t, blocking,
[]*ristypes.RISMessage{prefixAnnouncement(fill)}, tableWriteBlockingStore{blockingStore: blocking}, &logs,
prefixAnnouncement([]string{extraPrefix})) prefixAnnouncement(fill), prefixAnnouncement([]string{extraPrefix}))
if logged := lastLogged(t, &logs); logged.TableChanges != 2 { if logged.TableChanges != 2 {
t.Errorf("Stop logged %d table changes not written, want 2", t.Errorf("Stop logged %d table changes not written, want 2",
logged.TableChanges) logged.TableChanges)
} }
} }
// TestPrefixHandlerStopCountsTheOriginChangesOfAWriteInProgress holds the
// write of the origin changes that a full batch starts, then hands the prefix
// handler one more prefix and stops it with a deadline that passes meanwhile.
// Stop must log as not written both the change the held write took and the one
// since.
func TestPrefixHandlerStopCountsTheOriginChangesOfAWriteInProgress(t *testing.T) {
t.Parallel()
const extraPrefix = "198.51.100.0/24"
var logs bytes.Buffer
blocking := newBlockingStore()
fill := slices.Repeat([]string{testV4Prefix}, prefixBatchSize)
logged := stopPrefixHandlerWithBlockedWrite(t, blocking,
originChangesBlockingStore{blockingStore: blocking}, &logs,
prefixAnnouncement(fill), prefixAnnouncement([]string{extraPrefix}))
if logged.OriginChanges != 2 {
t.Errorf("Stop logged %d origin changes not written, want 2",
logged.OriginChanges)
}
}
// TestPrefixHandlerStopCountsTheWaitingOriginChanges stops the prefix handler
// with a deadline that has already passed, so the flush goroutine skips its
// last write. The origin changes still waiting in the routing table are then
// not written, and Stop must log them.
func TestPrefixHandlerStopCountsTheWaitingOriginChanges(t *testing.T) {
t.Parallel()
var logs bytes.Buffer
store := newMockStore()
h := newPrefixHandler(store, newErrorLogger(&logs),
routetable.New(routetable.Params{}), longerThanAnyTest,
maxTableChangesPerWrite)
h.HandleMessage(peerAnnouncement(testPeerIP, testV4Prefix, testV6Prefix))
ctx, cancel := context.WithCancel(t.Context())
cancel()
h.Stop(ctx)
if logged := lastLogged(t, &logs); logged.OriginChanges != 2 {
t.Errorf("Stop logged %d origin changes not written, want 2",
logged.OriginChanges)
}
}
// TestASHandlerSkipsItsLastWriteAfterTheStopDeadline also checks what Stop
// logs: the asnBatchSize entries of the held write and the entry for testASNB,
// handled since, are not written.
func TestASHandlerSkipsItsLastWriteAfterTheStopDeadline(t *testing.T) { func TestASHandlerSkipsItsLastWriteAfterTheStopDeadline(t *testing.T) {
t.Parallel() t.Parallel()
// Each message gives an update for its origin AS and one for each AS const wantEntries = asnBatchSize + 1
// in its path: fill asnBatchSize+1, extra 2.
const wantUpdates = asnBatchSize + 1 + 2
var logs bytes.Buffer var logs bytes.Buffer
store := newBlockingStore() store := newBlockingStore()
h := newASHandler(store, newErrorLogger(&logs), longerThanAnyTest) h := newASHandler(store, newErrorLogger(&logs), longerThanAnyTest)
fill := ristypes.ASPath{Sequence: slices.Repeat([]int{testASNA}, asnBatchSize)}
stopWhileAWriteIsBlocked(t, store, h, h.done, stopWhileAWriteIsBlocked(t, store, h, h.done,
[]*ristypes.RISMessage{{Path: fill}}, []*ristypes.RISMessage{{Path: pathOfASes(asnBatchSize)}},
&ristypes.RISMessage{Path: ristypes.ASPath{Sequence: []int{testASNB}}}) &ristypes.RISMessage{Path: ristypes.ASPath{Sequence: []int{testASNB}}})
store.mu.Lock() store.mu.Lock()
@@ -489,26 +606,27 @@ func TestASHandlerSkipsItsLastWriteAfterTheStopDeadline(t *testing.T) {
t.Errorf("AS%d was written after the stop deadline", testASNB) t.Errorf("AS%d was written after the stop deadline", testASNB)
} }
if logged := lastLogged(t, &logs); logged.Updates != wantUpdates { if logged := lastLogged(t, &logs); logged.BatchEntries != wantEntries {
t.Errorf("Stop logged %d updates not written, want %d", t.Errorf("Stop logged %d batch entries not written, want %d",
logged.Updates, wantUpdates) logged.BatchEntries, wantEntries)
} }
} }
// TestASHandlerSkipsAFullBatchAfterTheStopDeadline hands the AS handler a full // TestASHandlerSkipsAFullBatchAfterTheStopDeadline hands the AS handler a full
// batch while a write is held, so the batch's wake-up of the flush goroutine // batch while a write is held, so the batch's wake-up of the flush goroutine
// waits. The stop deadline passes meanwhile. When the write ends, the flush // waits. The full batch holds the fill's ASes again, and testASNB. The stop
// goroutine must stop instead of writing the batch. // deadline passes meanwhile. When the write ends, the flush goroutine must stop
// instead of writing the batch.
func TestASHandlerSkipsAFullBatchAfterTheStopDeadline(t *testing.T) { func TestASHandlerSkipsAFullBatchAfterTheStopDeadline(t *testing.T) {
t.Parallel() t.Parallel()
store := newBlockingStore() store := newBlockingStore()
h := newASHandler(store, logger.New(), longerThanAnyTest) h := newASHandler(store, logger.New(), longerThanAnyTest)
fill := ristypes.ASPath{Sequence: slices.Repeat([]int{testASNA}, asnBatchSize)} fill := &ristypes.RISMessage{Path: pathOfASes(asnBatchSize)}
full := ristypes.ASPath{Sequence: slices.Repeat([]int{testASNB}, asnBatchSize)}
stopWhileAWriteIsBlocked(t, store, h, h.done, stopWhileAWriteIsBlocked(t, store, h, h.done,
[]*ristypes.RISMessage{{Path: fill}}, []*ristypes.RISMessage{fill},
&ristypes.RISMessage{Path: full}) fill,
&ristypes.RISMessage{Path: ristypes.ASPath{Sequence: []int{testASNB}}})
store.mu.Lock() store.mu.Lock()
defer store.mu.Unlock() defer store.mu.Unlock()
@@ -597,7 +715,7 @@ func TestPeeringHandlerStopCountsTheWriteInProgress(t *testing.T) {
select { select {
case <-h.done: case <-h.done:
case <-time.After(handleMessageTimeout): case <-time.After(stepTimeout):
t.Fatal("the processing goroutine did not return after the write " + t.Fatal("the processing goroutine did not return after the write " +
"finished") "finished")
} }
@@ -618,7 +736,7 @@ func TestPeeringHandlerStartsNoWriteAfterTheStopDeadline(t *testing.T) {
const processInterval = 10 * time.Millisecond const processInterval = 10 * time.Millisecond
store := newBlockingStore() store := newBlockingStore()
h := newPeeringHandler(store, logger.New(), processInterval) h := newPeeringHandler(store, logger.New(), processInterval, maxTrackedPaths)
stopWhileAWriteIsBlocked(t, store, h, h.done, stopWhileAWriteIsBlocked(t, store, h, h.done,
[]*ristypes.RISMessage{ []*ristypes.RISMessage{
{Path: ristypes.ASPath{Sequence: []int{testASNA, testASNB}}}, {Path: ristypes.ASPath{Sequence: []int{testASNA, testASNB}}},
@@ -674,9 +792,8 @@ func TestASHandlerHandlesMessagesWhileAWriteIsBlocked(t *testing.T) {
store := newBlockingStore() store := newBlockingStore()
h := newASHandler(store, logger.New(), longerThanAnyTest) h := newASHandler(store, logger.New(), longerThanAnyTest)
fill := ristypes.ASPath{Sequence: slices.Repeat([]int{testASNA}, asnBatchSize)}
handleWhileAWriteIsBlocked(t, store, h, handleWhileAWriteIsBlocked(t, store, h,
[]*ristypes.RISMessage{{Path: fill}}, []*ristypes.RISMessage{{Path: pathOfASes(asnBatchSize)}},
&ristypes.RISMessage{Path: ristypes.ASPath{Sequence: []int{testASNB}}}) &ristypes.RISMessage{Path: ristypes.ASPath{Sequence: []int{testASNB}}})
store.mu.Lock() store.mu.Lock()
@@ -714,9 +831,11 @@ func TestPrefixHandlerWaitsAtTheMaximumBatchSize(t *testing.T) {
const extraPrefix = "198.51.100.0/24" const extraPrefix = "198.51.100.0/24"
store := newBlockingStore() store := newBlockingStore()
h := NewPrefixHandler(store, logger.New(), routetable.New(routetable.Params{})) h := newPrefixHandler(store, logger.New(), routetable.New(routetable.Params{}),
longerThanAnyTest, maxTableChangesPerWrite)
h.batchMaxSize = prefixBatchSize
fill := slices.Repeat([]string{testV4Prefix}, prefixBatchSize) fill := slices.Repeat([]string{testV4Prefix}, prefixBatchSize)
toMax := slices.Repeat([]string{testV4Prefix}, prefixBatchMaxSize) toMax := slices.Repeat([]string{testV4Prefix}, prefixBatchSize)
handleAtMaxBatchSize(t, store, h, handleAtMaxBatchSize(t, store, h,
[]*ristypes.RISMessage{prefixAnnouncement(fill)}, []*ristypes.RISMessage{prefixAnnouncement(fill)},
[]*ristypes.RISMessage{prefixAnnouncement(toMax)}, []*ristypes.RISMessage{prefixAnnouncement(toMax)},
@@ -731,31 +850,48 @@ func TestPrefixHandlerWaitsAtTheMaximumBatchSize(t *testing.T) {
} }
} }
func TestASHandlerWaitsAtTheMaximumBatchSize(t *testing.T) { // TestASHandlerNeverWaitsForAWrite starts a write that the store holds. Then it
// hands the AS handler twenty messages whose paths each hold one AS
// asnBatchSize times. HandleMessage must return each time, and the batch must
// hold one entry, for that AS.
func TestASHandlerNeverWaitsForAWrite(t *testing.T) {
t.Parallel() t.Parallel()
const messages = 20
store := newBlockingStore() store := newBlockingStore()
h := newASHandler(store, logger.New(), longerThanAnyTest) h := newASHandler(store, logger.New(), longerThanAnyTest)
fill := ristypes.ASPath{Sequence: slices.Repeat([]int{testASNA}, asnBatchSize)}
toMax := ristypes.ASPath{Sequence: slices.Repeat([]int{testASNA}, asnBatchMaxSize)}
handleAtMaxBatchSize(t, store, h,
[]*ristypes.RISMessage{{Path: fill}},
[]*ristypes.RISMessage{{Path: toMax}},
&ristypes.RISMessage{Path: ristypes.ASPath{Sequence: []int{testASNB}}})
store.mu.Lock() defer stopInTime(t, h)
defer store.mu.Unlock() defer store.releaseWrites()
if !store.asns[testASNB] { startBlockedWrite(t, store, h,
t.Errorf("Stop did not write AS%d, handled after the batch reached its "+ []*ristypes.RISMessage{{Path: pathOfASes(asnBatchSize)}})
"maximum size", testASNB)
oneAS := &ristypes.RISMessage{
Path: ristypes.ASPath{Sequence: slices.Repeat([]int{testASNB}, asnBatchSize)},
}
if !returnsInTime(func() {
for range messages {
h.HandleMessage(oneAS)
}
}) {
t.Fatal("HandleMessage did not return while a database write was blocked")
}
h.mu.Lock()
defer h.mu.Unlock()
if len(h.batch) != 1 {
t.Errorf("the batch holds %d entries for one AS, want 1", len(h.batch))
} }
} }
// TestPeerHandlerWaitsAtTheMaximumBatchSize must not have its flush timer fire. // TestPeerHandlerWaitsAtTheMaximumBatchSize must not have its flush timer fire.
// A timer flush during the fill would take only part of it. The batch would // A timer flush during the fill would take only part of it. The batch would
// then reach its maximum size before the test's last message, and the test // then reach its maximum size before the test's last message, and the test
// would hang. // would fail.
func TestPeerHandlerWaitsAtTheMaximumBatchSize(t *testing.T) { func TestPeerHandlerWaitsAtTheMaximumBatchSize(t *testing.T) {
t.Parallel() t.Parallel()
@@ -763,10 +899,11 @@ func TestPeerHandlerWaitsAtTheMaximumBatchSize(t *testing.T) {
store := newBlockingStore() store := newBlockingStore()
h := newPeerHandler(store, logger.New(), longerThanAnyTest) h := newPeerHandler(store, logger.New(), longerThanAnyTest)
h.batchMaxSize = peerBatchSize
message := []*ristypes.RISMessage{{Peer: testPeerIP}} message := []*ristypes.RISMessage{{Peer: testPeerIP}}
handleAtMaxBatchSize(t, store, h, handleAtMaxBatchSize(t, store, h,
slices.Repeat(message, peerBatchSize), slices.Repeat(message, peerBatchSize),
slices.Repeat(message, peerBatchMaxSize), slices.Repeat(message, peerBatchSize),
&ristypes.RISMessage{Peer: otherPeerIP}) &ristypes.RISMessage{Peer: otherPeerIP})
store.mu.Lock() store.mu.Lock()
@@ -796,8 +933,9 @@ func TestHandlersWakeTheFlushGoroutineWhenTheBatchIsFull(t *testing.T) {
batchSize: prefixBatchSize, batchSize: prefixBatchSize,
handle: func(n int) chan struct{} { handle: func(n int) chan struct{} {
h := &PrefixHandler{ h := &PrefixHandler{
batchFullCh: make(chan struct{}, 1), batchMaxSize: prefixBatchMaxSize,
table: routetable.New(routetable.Params{}), batchFullCh: make(chan struct{}, 1),
table: routetable.New(routetable.Params{}),
} }
h.HandleMessage(prefixAnnouncement( h.HandleMessage(prefixAnnouncement(
slices.Repeat([]string{testV4Prefix}, n))) slices.Repeat([]string{testV4Prefix}, n)))
@@ -809,11 +947,12 @@ func TestHandlersWakeTheFlushGoroutineWhenTheBatchIsFull(t *testing.T) {
name: "AS", name: "AS",
batchSize: asnBatchSize, batchSize: asnBatchSize,
handle: func(n int) chan struct{} { handle: func(n int) chan struct{} {
h := &ASHandler{batchFullCh: make(chan struct{}, 1)} h := &ASHandler{
// The origin AS and each AS in the path are one update each. batch: make(map[int]database.SeenTimes),
h.HandleMessage(&ristypes.RISMessage{ batchFullCh: make(chan struct{}, 1),
Path: ristypes.ASPath{Sequence: slices.Repeat([]int{testASNA}, n-1)}, }
}) // Each of the path's n ASes is one entry of the batch.
h.HandleMessage(&ristypes.RISMessage{Path: pathOfASes(n)})
return h.batchFullCh return h.batchFullCh
}, },
@@ -822,7 +961,10 @@ func TestHandlersWakeTheFlushGoroutineWhenTheBatchIsFull(t *testing.T) {
name: "peer", name: "peer",
batchSize: peerBatchSize, batchSize: peerBatchSize,
handle: func(n int) chan struct{} { handle: func(n int) chan struct{} {
h := &PeerHandler{batchFullCh: make(chan struct{}, 1)} h := &PeerHandler{
batchMaxSize: peerBatchMaxSize,
batchFullCh: make(chan struct{}, 1),
}
for range n { for range n {
h.HandleMessage(&ristypes.RISMessage{Peer: testPeerIP}) h.HandleMessage(&ristypes.RISMessage{Peer: testPeerIP})
} }
internal/routewatch/dbmaintainer.go
+27
View File
@@ -25,6 +25,10 @@ const (
// analyzeInterval is how often to run ANALYZE. // analyzeInterval is how often to run ANALYZE.
analyzeInterval = 1 * time.Hour analyzeInterval = 1 * time.Hour
// originChangesPruneInterval is how often to prune the origin_changes
// table.
originChangesPruneInterval = 1 * time.Hour
// checkpointTimeout is the max time for WAL checkpoint. // checkpointTimeout is the max time for WAL checkpoint.
checkpointTimeout = 10 * time.Second checkpointTimeout = 10 * time.Second
@@ -33,6 +37,9 @@ const (
// analyzeTimeout is the max time for ANALYZE. // analyzeTimeout is the max time for ANALYZE.
analyzeTimeout = 5 * time.Minute analyzeTimeout = 5 * time.Minute
// originChangesPruneTimeout is the max time for the origin changes prune.
originChangesPruneTimeout = 5 * time.Minute
) )
// checkpointIncompleteMessage is logged, at debug level like a completed // checkpointIncompleteMessage is logged, at debug level like a completed
@@ -80,6 +87,7 @@ func (m *DBMaintainer) Start(ctx context.Context) {
"checkpoint_interval", checkpointInterval, "checkpoint_interval", checkpointInterval,
"vacuum_interval", vacuumInterval, "vacuum_interval", vacuumInterval,
"analyze_interval", analyzeInterval, "analyze_interval", analyzeInterval,
"origin_changes_prune_interval", originChangesPruneInterval,
) )
} }
@@ -111,6 +119,9 @@ func (m *DBMaintainer) run(ctx context.Context) {
analyzeTimer := time.NewTimer(analyzeInterval) analyzeTimer := time.NewTimer(analyzeInterval)
defer analyzeTimer.Stop() defer analyzeTimer.Stop()
pruneTimer := time.NewTimer(originChangesPruneInterval)
defer pruneTimer.Stop()
for { for {
select { select {
case <-m.stopCh: case <-m.stopCh:
@@ -127,6 +138,10 @@ func (m *DBMaintainer) run(ctx context.Context) {
case <-analyzeTimer.C: case <-analyzeTimer.C:
m.runAnalyze(ctx) m.runAnalyze(ctx)
analyzeTimer.Reset(analyzeInterval) analyzeTimer.Reset(analyzeInterval)
case <-pruneTimer.C:
m.runPruneOriginChanges(ctx)
pruneTimer.Reset(originChangesPruneInterval)
} }
} }
} }
@@ -175,6 +190,18 @@ func (m *DBMaintainer) runAnalyze(ctx context.Context) {
} }
} }
// runPruneOriginChanges prunes the origin_changes table.
func (m *DBMaintainer) runPruneOriginChanges(ctx context.Context) {
duration, err := runWithTimeout(ctx, originChangesPruneTimeout,
m.db.PruneOriginChanges)
if err != nil {
m.logger.Error("Origin changes prune failed", "error", err,
"duration", duration)
} else {
m.logger.Debug("Origin changes pruned", "duration", duration)
}
}
// runWithTimeout runs operation with a context that ends after timeout and // runWithTimeout runs operation with a context that ends after timeout and
// returns how long it took and its error. // returns how long it took and its error.
func runWithTimeout( func runWithTimeout(
internal/routewatch/dbmaintainer_internal_test.go
+2 -2
View File
@@ -97,7 +97,7 @@ func TestDBMaintainerStopReturnsByItsDeadline(t *testing.T) {
select { select {
case <-store.started: case <-store.started:
case <-time.After(handleMessageTimeout): case <-time.After(stepTimeout):
t.Fatal("the maintainer did not start the checkpoint") t.Fatal("the maintainer did not start the checkpoint")
} }
@@ -113,7 +113,7 @@ func TestDBMaintainerStopReturnsByItsDeadline(t *testing.T) {
select { select {
case <-m.done: case <-m.done:
case <-time.After(handleMessageTimeout): case <-time.After(stepTimeout):
t.Fatal("the maintenance goroutine did not return after the " + t.Fatal("the maintenance goroutine did not return after the " +
"checkpoint ended") "checkpoint ended")
} }
internal/routewatch/peerhandler.go
+14 -9
View File
@@ -43,10 +43,14 @@ type PeerHandler struct {
db database.Store db database.Store
logger *logger.Logger logger *logger.Logger
// batchMaxSize is peerBatchMaxSize. Only HandleMessage reads it, so a test
// may lower it before it hands the handler a message.
batchMaxSize int
// Batching. mu guards peerBatch and writing only: the flush goroutine // Batching. mu guards peerBatch and writing only: the flush goroutine
// takes the batch under mu and writes it after releasing mu, so // takes the batch under mu and writes it after releasing mu, so
// HandleMessage waits for a database write only while peerBatch is at // HandleMessage waits for a database write only while peerBatch is at
// peerBatchMaxSize. // batchMaxSize.
mu sync.Mutex mu sync.Mutex
peerBatch []peerUpdate peerBatch []peerUpdate
// writing is how many updates the flush goroutine took from peerBatch // writing is how many updates the flush goroutine took from peerBatch
@@ -84,12 +88,13 @@ func newPeerHandler(
db database.Store, logger *logger.Logger, batchTimeout time.Duration, db database.Store, logger *logger.Logger, batchTimeout time.Duration,
) *PeerHandler { ) *PeerHandler {
h := &PeerHandler{ h := &PeerHandler{
db: db, db: db,
logger: logger, logger: logger,
peerBatch: make([]peerUpdate, 0, peerBatchSize), batchMaxSize: peerBatchMaxSize,
batchFullCh: make(chan struct{}, 1), peerBatch: make([]peerUpdate, 0, peerBatchSize),
stopCh: make(chan context.Context, 1), batchFullCh: make(chan struct{}, 1),
done: make(chan struct{}), stopCh: make(chan context.Context, 1),
done: make(chan struct{}),
} }
h.batchTaken.L = &h.mu h.batchTaken.L = &h.mu
@@ -135,7 +140,7 @@ func (h *PeerHandler) HandleMessage(msg *ristypes.RISMessage) {
// While the batch is at its maximum size, wait until the flush goroutine // While the batch is at its maximum size, wait until the flush goroutine
// takes it. Meanwhile the handler takes nothing off its queue, which // takes it. Meanwhile the handler takes nothing off its queue, which
// fills, and the streamer drops messages for it. // fills, and the streamer drops messages for it.
for len(h.peerBatch) >= peerBatchMaxSize { for len(h.peerBatch) >= h.batchMaxSize {
h.batchTaken.Wait() h.batchTaken.Wait()
} }
@@ -149,7 +154,7 @@ func (h *PeerHandler) HandleMessage(msg *ristypes.RISMessage) {
// A full batch wakes the flush goroutine. If it is writing, the wake-up // A full batch wakes the flush goroutine. If it is writing, the wake-up
// waits in batchFullCh and the batch keeps growing until the write ends // waits in batchFullCh and the batch keeps growing until the write ends
// or the batch reaches peerBatchMaxSize. // or the batch reaches batchMaxSize.
if len(h.peerBatch) >= peerBatchSize { if len(h.peerBatch) >= peerBatchSize {
select { select {
case h.batchFullCh <- struct{}{}: case h.batchFullCh <- struct{}{}:
internal/routewatch/peerhandler_internal_test.go
+1 -1
View File
@@ -35,7 +35,7 @@ func TestPeerHandlerWritesTheEarliestAndLatestTimesOfANewPeer(t *testing.T) {
// Built without NewPeerHandler's flush goroutine, so the test flushes // Built without NewPeerHandler's flush goroutine, so the test flushes
// itself. // itself.
h := &PeerHandler{db: store, logger: logger.New()} h := &PeerHandler{db: store, logger: logger.New(), batchMaxSize: peerBatchMaxSize}
first := peerAnnouncement(testPeerIP, testV4Prefix) first := peerAnnouncement(testPeerIP, testV4Prefix)
second := peerAnnouncement(testPeerIP, testV4Prefix) second := peerAnnouncement(testPeerIP, testV4Prefix)
internal/routewatch/peeringhandler.go
+16 -9
View File
@@ -42,6 +42,10 @@ type PeeringHandler struct {
db database.Store db database.Store
logger *logger.Logger logger *logger.Logger
// maxPaths is the most paths asPaths holds: maxTrackedPaths, except in
// tests that give a smaller one.
maxPaths int
// In-memory AS path tracking: each path, JSON-encoded, with the earliest // In-memory AS path tracking: each path, JSON-encoded, with the earliest
// and the latest time an update carried it. // and the latest time an update carried it.
mu sync.Mutex mu sync.Mutex
@@ -62,21 +66,24 @@ type PeeringHandler struct {
// periodically processes accumulated AS paths into peering records. The // periodically processes accumulated AS paths into peering records. The
// handler begins processing immediately upon creation. // handler begins processing immediately upon creation.
func NewPeeringHandler(db database.Store, logger *logger.Logger) *PeeringHandler { func NewPeeringHandler(db database.Store, logger *logger.Logger) *PeeringHandler {
return newPeeringHandler(db, logger, peeringProcessInterval) return newPeeringHandler(db, logger, peeringProcessInterval, maxTrackedPaths)
} }
// newPeeringHandler is NewPeeringHandler with the processing timer's interval, // newPeeringHandler is NewPeeringHandler with the processing timer's interval,
// processInterval, in place of peeringProcessInterval. A test gives a short // processInterval, in place of peeringProcessInterval, and the most paths it
// one to have the timer start a write. // holds, maxPaths, in place of maxTrackedPaths. A test gives a short interval to
// have the timer start a write, and a small maxPaths to fill the map quickly.
func newPeeringHandler( func newPeeringHandler(
db database.Store, logger *logger.Logger, processInterval time.Duration, db database.Store, logger *logger.Logger, processInterval time.Duration,
maxPaths int,
) *PeeringHandler { ) *PeeringHandler {
h := &PeeringHandler{ h := &PeeringHandler{
db: db, db: db,
logger: logger, logger: logger,
asPaths: make(map[string]database.SeenTimes), asPaths: make(map[string]database.SeenTimes),
stopCh: make(chan context.Context, 1), maxPaths: maxPaths,
done: make(chan struct{}), stopCh: make(chan context.Context, 1),
done: make(chan struct{}),
} }
// Start the periodic processing goroutine // Start the periodic processing goroutine
@@ -131,7 +138,7 @@ func (h *PeeringHandler) HandleMessage(msg *ristypes.RISMessage) {
defer h.mu.Unlock() defer h.mu.Unlock()
seen, exists := h.asPaths[key] seen, exists := h.asPaths[key]
if !exists && len(h.asPaths) >= maxTrackedPaths { if !exists && len(h.asPaths) >= h.maxPaths {
// Map is full; drop this new path and count it. // Map is full; drop this new path and count it.
h.droppedPaths++ h.droppedPaths++
internal/routewatch/peeringhandler_internal_test.go
+31 -18
View File
@@ -5,7 +5,6 @@ import (
"fmt" "fmt"
"maps" "maps"
"slices" "slices"
"strconv"
"sync" "sync"
"testing" "testing"
"time" "time"
@@ -20,6 +19,10 @@ const (
testASNB = 64501 testASNB = 64501
testASNC = 64502 testASNC = 64502
testASND = 64503 testASND = 64503
// testMaxTrackedPaths is a limit of the path map that a test fills
// quickly, in place of maxTrackedPaths.
testMaxTrackedPaths = 10
) )
// recordingStore wraps mockStore to count every RecordPeering call, so a // recordingStore wraps mockStore to count every RecordPeering call, so a
@@ -52,9 +55,10 @@ func (r *recordingStore) callCount() int {
// processing goroutine, so tests drive processing explicitly. // processing goroutine, so tests drive processing explicitly.
func newTestHandler(db database.Store) *PeeringHandler { func newTestHandler(db database.Store) *PeeringHandler {
return &PeeringHandler{ return &PeeringHandler{
db: db, db: db,
logger: logger.New(), logger: logger.New(),
asPaths: make(map[string]database.SeenTimes), asPaths: make(map[string]database.SeenTimes),
maxPaths: maxTrackedPaths,
} }
} }
@@ -244,25 +248,28 @@ func TestPeeringHandlerStopWritesTheRemainingPaths(t *testing.T) {
// TestPeeringHandlerCapDropsAndCounts verifies that a full map drops new paths // TestPeeringHandlerCapDropsAndCounts verifies that a full map drops new paths
// and counts them, while a path already tracked is refreshed rather than // and counts them, while a path already tracked is refreshed rather than
// dropped. // dropped. The handler's limit is small, and its timer does not fire.
func TestPeeringHandlerCapDropsAndCounts(t *testing.T) { func TestPeeringHandlerCapDropsAndCounts(t *testing.T) {
t.Parallel() t.Parallel()
store := &recordingStore{mockStore: newMockStore()} store := &recordingStore{mockStore: newMockStore()}
h := newTestHandler(store) h := newPeeringHandler(store, logger.New(), longerThanAnyTest,
testMaxTrackedPaths)
defer stopInTime(t, h)
now := time.Now().UTC() now := time.Now().UTC()
// Fill the map to exactly maxTrackedPaths, including one real path key so // Fill the map to exactly its limit, including one real path key so the
// the "already tracked" branch can be exercised. The filler keys are never // "already tracked" branch can be exercised. The other paths are of one
// processed in this test, so their contents do not matter. // AS, so they carry no peering.
existing := pathKey(t, testASNA, testASNB) existing := pathKey(t, testASNA, testASNB)
h.mu.Lock() h.mu.Lock()
h.asPaths[existing] = database.SeenTimes{First: now, Last: now} h.asPaths[existing] = database.SeenTimes{First: now, Last: now}
for i := 0; len(h.asPaths) < maxTrackedPaths; i++ { for asn := 1; len(h.asPaths) < testMaxTrackedPaths; asn++ {
h.asPaths[strconv.Itoa(i)] = database.SeenTimes{First: now, Last: now} h.asPaths[pathKey(t, asn)] = database.SeenTimes{First: now, Last: now}
} }
h.mu.Unlock() h.mu.Unlock()
@@ -270,8 +277,9 @@ func TestPeeringHandlerCapDropsAndCounts(t *testing.T) {
handle(h, now.Add(time.Second), testASNA, testASNC) handle(h, now.Add(time.Second), testASNA, testASNC)
tracked, dropped := snapshot(h) tracked, dropped := snapshot(h)
if tracked != maxTrackedPaths { if tracked != testMaxTrackedPaths {
t.Fatalf("want map size %d after drop, got %d", maxTrackedPaths, tracked) t.Fatalf("want map size %d after drop, got %d", testMaxTrackedPaths,
tracked)
} }
if dropped != 1 { if dropped != 1 {
@@ -283,8 +291,9 @@ func TestPeeringHandlerCapDropsAndCounts(t *testing.T) {
handle(h, refreshed, testASNA, testASNB) handle(h, refreshed, testASNA, testASNB)
tracked, dropped = snapshot(h) tracked, dropped = snapshot(h)
if tracked != maxTrackedPaths { if tracked != testMaxTrackedPaths {
t.Fatalf("want map size %d after refresh, got %d", maxTrackedPaths, tracked) t.Fatalf("want map size %d after refresh, got %d", testMaxTrackedPaths,
tracked)
} }
if dropped != 1 { if dropped != 1 {
@@ -303,17 +312,21 @@ func TestPeeringHandlerCapDropsAndCounts(t *testing.T) {
// TestPeeringHandlerRunResetsTheDroppedCount fills the map, has the handler // TestPeeringHandlerRunResetsTheDroppedCount fills the map, has the handler
// drop one path, and runs the processing. The count of dropped paths is the // drop one path, and runs the processing. The count of dropped paths is the
// run's own, so it is 0 again after the run. // run's own, so it is 0 again after the run. The handler's limit is small, and
// its timer does not fire.
func TestPeeringHandlerRunResetsTheDroppedCount(t *testing.T) { func TestPeeringHandlerRunResetsTheDroppedCount(t *testing.T) {
t.Parallel() t.Parallel()
h := newTestHandler(newMockStore()) h := newPeeringHandler(newMockStore(), logger.New(), longerThanAnyTest,
testMaxTrackedPaths)
defer stopInTime(t, h)
now := time.Now().UTC() now := time.Now().UTC()
// Paths of one AS carry no peering, so the run records nothing. // Paths of one AS carry no peering, so the run records nothing.
h.mu.Lock() h.mu.Lock()
for asn := 1; len(h.asPaths) < maxTrackedPaths; asn++ { for asn := 1; len(h.asPaths) < testMaxTrackedPaths; asn++ {
h.asPaths[pathKey(t, asn)] = database.SeenTimes{First: now, Last: now} h.asPaths[pathKey(t, asn)] = database.SeenTimes{First: now, Last: now}
} }
h.mu.Unlock() h.mu.Unlock()
internal/routewatch/prefixhandler.go
+307 -61
View File
@@ -15,12 +15,15 @@ import (
) )
const ( const (
// prefixHandlerQueueSize is the queue capacity for prefix tracking // prefixHandlerQueueSize is the most messages the handler's queue holds.
// operations, about 4 seconds of feed at peak. The streamer drops updates // While the routing table's Overview or PeersDown walks every prefix, it
// rather than blocks when a queue is full (a STATE message is held until // holds the table's lock about half of the time. The handler then applies
// there is room), so this bounds memory. Batches still flush on a timer // updates more slowly. When the feed pauses for some seconds and then
// (prefixBatchTimeout). // catches up, its backlog can arrive faster than that, and the queue
prefixHandlerQueueSize = 20000 // holds the backlog. The streamer drops an update that finds the queue
// full. A message takes about 1 KiB, so a full queue takes about 100 MiB
// (README "Memory").
prefixHandlerQueueSize = 100000
// prefixBatchSize is the number of prefix updates to batch together // prefixBatchSize is the number of prefix updates to batch together
prefixBatchSize = 25000 prefixBatchSize = 25000
@@ -44,6 +47,25 @@ const (
// most one pair. So the million pairs that a full-table peer's session // most one pair. So the million pairs that a full-table peer's session
// going down changes are written in about a minute. // going down changes are written in about a minute.
maxTableChangesPerWrite = 20000 maxTableChangesPerWrite = 20000
// maxOriginChangesPerWrite is the most origin changes of the routing
// table that one flush writes; the rest wait for the next flushes.
maxOriginChangesPerWrite = 20000
// maxHeldBackMessages is the most messages the handler holds back from
// peers whose session went down. A peer's messages are held back from
// the moment its session goes down until peerDown has applied them. If
// peerDown is running at that moment, the peer waits for the rest of
// peerDown's current PeersDown call. The peer also waits while peerDown
// applies the messages held back from that call's peers, those that
// arrive meanwhile included. The next PeersDown call takes the peer out.
// Once that call returns, peerDown applies the messages held back from
// that call's peers, one peer after another, in the order the call lists
// them. A held-back message that says the peer's session went down again
// makes the peer's later messages wait for the next call. A message takes
// about 1 KiB, so 150,000 take about 150 MiB (README "Memory"). At this
// number HandleMessage waits until one of them is applied.
maxHeldBackMessages = 150000
) )
// PrefixHandler keeps the routing table in memory current from the feed. It // PrefixHandler keeps the routing table in memory current from the feed. It
@@ -52,18 +74,39 @@ const (
// does an announcement whose AS path is empty or holds AS 0 anywhere. A peer // does an announcement whose AS path is empty or holds AS 0 anywhere. A peer
// whose BGP session goes down leaves every prefix. // whose BGP session goes down leaves every prefix.
// //
// Each flush writes the table's changes to the database. It also stores each // The table's PeersDown applies sessions going down. It visits every prefix,
// prefix the updates name with the time it was first seen. // which takes seconds on a full table. So the handler runs PeersDown on a
// separate goroutine and goes on taking messages meanwhile. One PeersDown runs
// at a time. The next one takes every peer whose session went down since the
// previous one began. PeersDown lets the table's lock go about half of the
// time, so the handler applies other peers' messages while PeersDown runs. The
// handler holds back a down peer's later messages until peerDown applies them,
// as the doc of maxHeldBackMessages describes. It applies them in order, one at
// a time, and takes new messages in between. It holds back at most
// maxHeldBackMessages messages.
//
// Each flush writes the table's changes and origin changes to the database.
// It also stores each prefix the updates name with the time it was first seen.
type PrefixHandler struct { type PrefixHandler struct {
db database.Store db database.Store
logger *logger.Logger logger *logger.Logger
metrics *metrics.Tracker metrics *metrics.Tracker
table *routetable.Table table *routetable.Table
// Batching. mu guards batch, writing and writingTableChanges only: the // batchMaxSize is prefixBatchMaxSize. Only HandleMessage reads it, so a
// flush goroutine takes them under mu and writes them after releasing // test may lower it before it hands the handler a message.
// mu, so HandleMessage waits for a database write only while batch is at batchMaxSize int
// prefixBatchMaxSize. // tableChangesPerWrite is maxTableChangesPerWrite, except in tests that
// give a smaller one.
tableChangesPerWrite int
// originChangesPerWrite is maxOriginChangesPerWrite, except in tests that
// give a smaller one.
originChangesPerWrite int
// Batching. mu guards batch, writing, writingTableChanges and
// writingOriginChanges: the flush goroutine takes them under mu and
// writes them after releasing mu, so HandleMessage waits for a database
// write only while batch is at batchMaxSize.
mu sync.Mutex mu sync.Mutex
batch []seenPrefix batch []seenPrefix
// writing is how many updates the flush goroutine took and has not // writing is how many updates the flush goroutine took and has not
@@ -72,6 +115,9 @@ type PrefixHandler struct {
// writingTableChanges is how many changes the flush goroutine took from // writingTableChanges is how many changes the flush goroutine took from
// the routing table and has not finished writing. // the routing table and has not finished writing.
writingTableChanges int writingTableChanges int
// writingOriginChanges is how many origin changes the flush goroutine
// took from the routing table and has not finished writing.
writingOriginChanges int
// batchTaken is signalled when the flush goroutine takes batch; its L is // batchTaken is signalled when the flush goroutine takes batch; its L is
// &mu. // &mu.
batchTaken sync.Cond batchTaken sync.Cond
@@ -80,6 +126,26 @@ type PrefixHandler struct {
// Stop does not wait for a write in progress to hand it over. // Stop does not wait for a write in progress to hand it over.
stopCh chan context.Context stopCh chan context.Context
done chan struct{} // closed when the flush goroutine returns done chan struct{} // closed when the flush goroutine returns
// Peers whose session went down. heldBack, under mu, holds each such
// peer's later messages, in order, until the peer has left every prefix
// and they are applied. A peer with no such messages yet has an empty
// entry. heldCount, under mu, is how many messages heldBack holds.
// heldTaken is signalled each time a held-back message is taken out to
// be applied; its L is &mu.
heldBack map[string][]*ristypes.RISMessage
heldCount int
heldTaken sync.Cond
// downPeers, under mu, lists the peers whose session went down and that
// the next PeersDown takes. peerDownRunning, under mu, says whether
// peerDown is running. peerDowns counts the peerDown goroutines that have
// not returned.
downPeers []string
peerDownRunning bool
peerDowns sync.WaitGroup
// tablePeersDown is the table's PeersDown. Only peerDown calls it, so a
// test may replace it before it hands the handler a message.
tablePeersDown func(peers []string)
} }
// seenPrefix is what the batch keeps of an update: the prefix it names and its // seenPrefix is what the batch keeps of an update: the prefix it names and its
@@ -119,26 +185,36 @@ func (u prefixUpdate) announcesRoute() bool {
func NewPrefixHandler( func NewPrefixHandler(
db database.Store, logger *logger.Logger, table *routetable.Table, db database.Store, logger *logger.Logger, table *routetable.Table,
) *PrefixHandler { ) *PrefixHandler {
return newPrefixHandler(db, logger, table, prefixBatchTimeout) return newPrefixHandler(db, logger, table, prefixBatchTimeout,
maxTableChangesPerWrite)
} }
// newPrefixHandler is NewPrefixHandler with the flush timer's interval, // newPrefixHandler is NewPrefixHandler with the flush timer's interval,
// batchTimeout, in place of prefixBatchTimeout. A test that the timer must not // batchTimeout, in place of prefixBatchTimeout, and tableChangesPerWrite in
// disturb gives an interval longer than the test runs. // place of maxTableChangesPerWrite. A test that the timer must not disturb
// gives an interval longer than the test runs. A test of writes split over
// several flushes gives a small tableChangesPerWrite, so that it exceeds it
// with few changes.
func newPrefixHandler( func newPrefixHandler(
db database.Store, logger *logger.Logger, table *routetable.Table, db database.Store, logger *logger.Logger, table *routetable.Table,
batchTimeout time.Duration, batchTimeout time.Duration, tableChangesPerWrite int,
) *PrefixHandler { ) *PrefixHandler {
h := &PrefixHandler{ h := &PrefixHandler{
db: db, db: db,
logger: logger, logger: logger,
table: table, table: table,
batch: make([]seenPrefix, 0, prefixBatchSize), batch: make([]seenPrefix, 0, prefixBatchSize),
batchFullCh: make(chan struct{}, 1), batchMaxSize: prefixBatchMaxSize,
stopCh: make(chan context.Context, 1), tableChangesPerWrite: tableChangesPerWrite,
done: make(chan struct{}), originChangesPerWrite: maxOriginChangesPerWrite,
batchFullCh: make(chan struct{}, 1),
stopCh: make(chan context.Context, 1),
done: make(chan struct{}),
heldBack: make(map[string][]*ristypes.RISMessage),
tablePeersDown: table.PeersDown,
} }
h.batchTaken.L = &h.mu h.batchTaken.L = &h.mu
h.heldTaken.L = &h.mu
// Start the flush timer goroutine // Start the flush timer goroutine
go flushLoop(batchTimeout, h.batchFullCh, h.stopCh, h.done, h.flushBatch) go flushLoop(batchTimeout, h.batchFullCh, h.stopCh, h.done, h.flushBatch)
@@ -166,11 +242,102 @@ func (h *PrefixHandler) QueueCapacity() int {
return prefixHandlerQueueSize return prefixHandlerQueueSize
} }
// HandleMessage processes a message to track prefix information // HandleMessage processes a message to track prefix information. A message
// from a peer whose session went down is held back until peerDown applies it.
func (h *PrefixHandler) HandleMessage(msg *ristypes.RISMessage) { func (h *PrefixHandler) HandleMessage(msg *ristypes.RISMessage) {
h.mu.Lock()
defer h.mu.Unlock()
// While maxHeldBackMessages messages are held back, wait until one of them
// is taken out to be applied. Meanwhile the handler takes nothing off its
// queue, as at batchMaxSize.
for h.heldCount >= maxHeldBackMessages {
h.heldTaken.Wait()
}
held, goingDown := h.heldBack[msg.Peer]
if goingDown {
h.heldBack[msg.Peer] = append(held, msg)
h.heldCount++
return
}
h.applyMessage(msg)
}
// HeldBackCount returns how many messages the handler holds back from peers
// whose session went down. The status page shows it.
func (h *PrefixHandler) HeldBackCount() int {
h.mu.Lock()
defer h.mu.Unlock()
return h.heldCount
}
// Stop waits for every PeersDown the handler started and for the messages held
// back meanwhile to be applied. It gives up this wait once ctx ends. Then Stop
// stops the flush goroutine and waits for it until ctx ends. The flush
// goroutine makes one last flush before it returns. That flush writes at most
// tableChangesPerWrite of the routing table's changes, originChangesPerWrite of
// its origin changes, and the prefixes of the updates the handler holds. Once
// ctx has ended the flush goroutine skips that last flush, and a write still
// running is lost when the process exits. A failed write of the table's
// changes is not retried either. Stop logs how many updates, table changes and
// origin changes are not written. It also logs how many held-back messages are
// not applied. The caller calls Stop once its last HandleMessage has returned.
func (h *PrefixHandler) Stop(ctx context.Context) {
peerDownsDone := make(chan struct{})
go func() {
h.peerDowns.Wait()
close(peerDownsDone)
}()
select {
case <-peerDownsDone:
case <-ctx.Done():
}
h.stopCh <- ctx
select {
case <-h.done:
case <-ctx.Done():
}
h.mu.Lock()
unwritten := h.writing + len(h.batch)
tableChanges := h.writingTableChanges + h.table.ChangeCount()
heldMessages := h.heldCount
originChanges := h.writingOriginChanges + h.table.OriginChangeCount()
h.mu.Unlock()
if unwritten == 0 && tableChanges == 0 && heldMessages == 0 &&
originChanges == 0 {
return
}
if ctx.Err() != nil {
h.logger.Error("Stop deadline passed before the prefix handler wrote "+
"its updates", "updates", unwritten, "table_changes", tableChanges,
"held_messages", heldMessages, "origin_changes", originChanges)
return
}
h.logger.Error("The prefix handler stopped before it wrote everything",
"updates", unwritten, "table_changes", tableChanges,
"held_messages", heldMessages, "origin_changes", originChanges)
}
// applyMessage applies msg. The caller holds mu. A peer's session going down
// has the peer leave every prefix. An update is applied to the routing table,
// and its prefixes join the batch.
func (h *PrefixHandler) applyMessage(msg *ristypes.RISMessage) {
if msg.Type == ristypes.MessageTypeState { if msg.Type == ristypes.MessageTypeState {
if msg.State == ristypes.StateDown { if msg.State == ristypes.StateDown {
h.table.PeerDown(msg.Peer) h.startPeerDown(msg.Peer)
} }
return return
@@ -185,13 +352,10 @@ func (h *PrefixHandler) HandleMessage(msg *ristypes.RISMessage) {
// the path after the rest of it. // the path after the rest of it.
path := slices.Concat(msg.Path.Sequence, msg.Path.Set) path := slices.Concat(msg.Path.Sequence, msg.Path.Set)
h.mu.Lock()
defer h.mu.Unlock()
// While the batch is at its maximum size, wait until the flush goroutine // While the batch is at its maximum size, wait until the flush goroutine
// takes it. Meanwhile the handler takes nothing off its queue, which // takes it. Meanwhile the handler takes nothing off its queue, which
// fills, and the streamer drops messages for it. // fills, and the streamer drops messages for it.
for len(h.batch) >= prefixBatchMaxSize { for len(h.batch) >= h.batchMaxSize {
h.batchTaken.Wait() h.batchTaken.Wait()
} }
@@ -239,7 +403,7 @@ func (h *PrefixHandler) HandleMessage(msg *ristypes.RISMessage) {
// A full batch wakes the flush goroutine. If it is writing, the wake-up // A full batch wakes the flush goroutine. If it is writing, the wake-up
// waits in batchFullCh and the batch keeps growing until the write ends // waits in batchFullCh and the batch keeps growing until the write ends
// or the batch reaches prefixBatchMaxSize. // or the batch reaches batchMaxSize.
if len(h.batch) >= prefixBatchSize { if len(h.batch) >= prefixBatchSize {
select { select {
case h.batchFullCh <- struct{}{}: case h.batchFullCh <- struct{}{}:
@@ -248,39 +412,88 @@ func (h *PrefixHandler) HandleMessage(msg *ristypes.RISMessage) {
} }
} }
// Stop stops the flush goroutine, which makes one last flush before it returns, // startPeerDown adds peer to downPeers. It starts peerDown on a new goroutine
// and waits for it until ctx ends. That flush writes at most // unless peerDown is running. The caller holds mu. The peer's messages are
// maxTableChangesPerWrite of the routing table's changes, and the prefixes of // held back until peerDown has applied them. Messages held back for an earlier
// the updates the handler holds. Once ctx has ended the flush goroutine skips // session of the peer going down, and not yet applied, stay held back.
// that last flush, and a write still running is lost when the process exits. A func (h *PrefixHandler) startPeerDown(peer string) {
// failed write of the table's changes is not retried either. Stop logs how many _, goingDown := h.heldBack[peer]
// updates and how many of the table's changes are not written. if !goingDown {
func (h *PrefixHandler) Stop(ctx context.Context) { h.heldBack[peer] = []*ristypes.RISMessage{}
h.stopCh <- ctx
select {
case <-h.done:
case <-ctx.Done():
} }
h.mu.Lock() h.downPeers = append(h.downPeers, peer)
unwritten := h.writing + len(h.batch)
tableChanges := h.writingTableChanges + h.table.ChangeCount()
h.mu.Unlock()
if unwritten == 0 && tableChanges == 0 { if h.peerDownRunning {
return return
} }
if ctx.Err() != nil { h.peerDownRunning = true
h.logger.Error("Stop deadline passed before the prefix handler wrote "+ h.peerDowns.Add(1)
"its updates", "updates", unwritten, "table_changes", tableChanges)
return go h.peerDown()
}
// peerDown takes every peer in downPeers and runs the table's PeersDown for
// them. Then it applies the messages held back from each of those peers. It
// repeats this until downPeers is empty.
func (h *PrefixHandler) peerDown() {
defer h.peerDowns.Done()
for {
h.mu.Lock()
peers := h.downPeers
h.downPeers = nil
if len(peers) == 0 {
h.peerDownRunning = false
h.mu.Unlock()
return
}
h.mu.Unlock()
h.tablePeersDown(peers)
for _, peer := range peers {
h.applyHeldBack(peer)
}
} }
}
h.logger.Error("The prefix handler stopped before it wrote everything", // applyHeldBack applies the messages held back from peer, in order. It takes
"updates", unwritten, "table_changes", tableChanges) // mu for one message at a time, so HandleMessage takes new messages in
// between. The peer's new messages join the end of the held-back ones. A
// held-back message that says the peer's session went down again adds the
// peer to downPeers. The rest stay held back until the next PeersDown has
// returned.
func (h *PrefixHandler) applyHeldBack(peer string) {
for {
h.mu.Lock()
held := h.heldBack[peer]
if len(held) == 0 {
delete(h.heldBack, peer)
h.mu.Unlock()
return
}
msg := held[0]
held[0] = nil // so that the message is freed once applied
h.heldBack[peer] = held[1:]
h.heldCount--
h.heldTaken.Broadcast()
h.applyMessage(msg)
h.mu.Unlock()
if msg.Type == ristypes.MessageTypeState &&
msg.State == ristypes.StateDown {
return
}
}
} }
// takeBatch returns the pending updates and leaves an empty batch in their // takeBatch returns the pending updates and leaves an empty batch in their
@@ -302,11 +515,12 @@ func (h *PrefixHandler) takeBatch() []seenPrefix {
return batch return batch
} }
// flushBatch writes the routing table's changes, then takes the pending batch // flushBatch writes the routing table's changes and origin changes, then
// and stores the prefixes it names, without holding the mutex during the // takes the pending batch and stores the prefixes it names, without holding
// writes. // the mutex during the writes.
func (h *PrefixHandler) flushBatch() { func (h *PrefixHandler) flushBatch() {
h.writeTableChanges() h.writeTableChanges()
h.writeOriginChanges()
batch := h.takeBatch() batch := h.takeBatch()
if len(batch) == 0 { if len(batch) == 0 {
@@ -378,14 +592,13 @@ func (h *PrefixHandler) applyToTable(update prefixUpdate) {
}) })
} }
// writeTableChanges writes at most maxTableChangesPerWrite changes of the // writeTableChanges writes at most tableChangesPerWrite changes of the routing
// routing table in memory, and every peer the table numbered since the last // table in memory, and every peer the table numbered since the last write.
// write.
// When the write fails, they go back to the table, so that a later write writes // When the write fails, they go back to the table, so that a later write writes
// them again, each pair with its content then. // them again, each pair with its content then.
func (h *PrefixHandler) writeTableChanges() { func (h *PrefixHandler) writeTableChanges() {
h.mu.Lock() h.mu.Lock()
changes, newPeers := h.table.TakeChanges(maxTableChangesPerWrite) changes, newPeers := h.table.TakeChanges(h.tableChangesPerWrite)
h.writingTableChanges = len(changes) h.writingTableChanges = len(changes)
h.mu.Unlock() h.mu.Unlock()
@@ -409,6 +622,39 @@ func (h *PrefixHandler) writeTableChanges() {
} }
} }
// writeOriginChanges writes at most originChangesPerWrite of the routing
// table's origin changes. When the write fails, they go back to the table, so
// that a later write writes them again. A dropped change is logged as a
// warning.
func (h *PrefixHandler) writeOriginChanges() {
h.mu.Lock()
changes, dropped := h.table.TakeOriginChanges(h.originChangesPerWrite)
h.writingOriginChanges = len(changes)
h.mu.Unlock()
if dropped > 0 {
h.logger.Warn("Origin changes dropped", "dropped", dropped)
}
if len(changes) == 0 {
return
}
err := h.db.WriteOriginChanges(changes)
h.mu.Lock()
defer h.mu.Unlock()
h.writingOriginChanges = 0
if err != nil {
h.logger.Error("Failed to write the origin changes; the next flush "+
"retries", "changes", len(changes), "error", err)
h.table.PutBackOriginChanges(changes)
}
}
// canonicalPrefix returns prefix in the text form net/netip prints, the form // canonicalPrefix returns prefix in the text form net/netip prints, the form
// the prefix tables store and the IP lookup reads them in. The feed sends IPv6 // the prefix tables store and the IP lookup reads them in. The feed sends IPv6
// announcements compressed ("2001:db8::/32") but IPv6 withdrawals uncompressed // announcements compressed ("2001:db8::/32") but IPv6 withdrawals uncompressed
internal/routewatch/prefixhandler_internal_test.go
+104 -6
View File
@@ -237,22 +237,120 @@ func TestPrefixHandlerStopLogsNothingWhenItWroteEverything(t *testing.T) {
} }
} }
// longerThanAnyTest is a flush timer interval that no test lasts. A test whose // TestPrefixHandlerStopLogsTheMessagesHeldBack stops a prefix handler with a
// prefix, AS or peer handler must flush only when its batch is full and on Stop // deadline that has passed, while a peer's PeersDown is held up and one message
// gives it to newPrefixHandler, newASHandler or newPeerHandler. // of the peer is held back. Stop must log that message as not applied.
func TestPrefixHandlerStopLogsTheMessagesHeldBack(t *testing.T) {
t.Parallel()
var logs bytes.Buffer
h := newPrefixHandler(newMockStore(), newErrorLogger(&logs),
routetable.New(routetable.Params{}), longerThanAnyTest,
maxTableChangesPerWrite)
release := holdUpPeersDown(h)
defer close(release)
h.HandleMessage(peerAnnouncement(testPeerIP, testV4Prefix))
h.HandleMessage(sessionDown())
h.HandleMessage(peerAnnouncement(testPeerIP, testV6Prefix))
ctx, cancel := context.WithCancel(t.Context())
cancel()
h.Stop(ctx)
logged := lastLogged(t, &logs)
if logged.HeldMessages != 1 {
t.Errorf("Stop logged %d held messages not applied, want 1",
logged.HeldMessages)
}
}
// TestPrefixHandlerStopWaitsForTheMessagesHeldBack stops a prefix handler
// while a peer's PeersDown is held up and an announcement of the peer is held
// back. Stop must wait. Once the PeersDown is let go and Stop returns, the
// announcement must be in the database.
func TestPrefixHandlerStopWaitsForTheMessagesHeldBack(t *testing.T) {
t.Parallel()
db := newTestDatabase(t)
h := newPrefixHandler(db, logger.New(), routetable.New(routetable.Params{}),
longerThanAnyTest, maxTableChangesPerWrite)
release := holdUpPeersDown(h)
h.HandleMessage(sessionDown())
h.HandleMessage(peerAnnouncement(testPeerIP, testV4Prefix))
stopped := make(chan struct{})
go func() {
h.Stop(t.Context())
close(stopped)
}()
select {
case <-stopped:
t.Error("Stop returned while a PeersDown was held up")
case <-time.After(stillWaitingAfter):
}
close(release)
select {
case <-stopped:
case <-time.After(stepTimeout):
t.Fatalf("Stop did not return within %s of the PeersDown's release",
stepTimeout)
}
read, err := db.ReadRouteTable(t.Context())
if err != nil {
t.Fatalf("ReadRouteTable: %v", err)
}
checkTableOrigins(t, read, map[string]map[int][]string{
testV4Prefix: {testASNB: {testPeerIP}},
})
}
// longerThanAnyTest is a timer interval that no test lasts. A test gives it to
// newPrefixHandler, newASHandler, newPeerHandler or newPeeringHandler when the
// handler must write only when its batch is full, when the test says, or on
// Stop.
const longerThanAnyTest = time.Hour const longerThanAnyTest = time.Hour
// prefixHandlerWithoutTimer returns a prefix handler that writes to store and // prefixHandlerWithoutTimer returns a prefix handler that writes to store and
// applies the updates to an empty routing table. It is built without // applies the updates to an empty routing table. It is built without
// NewPrefixHandler's flush goroutine, so the test flushes itself. // NewPrefixHandler's flush goroutine, so the test flushes itself.
func prefixHandlerWithoutTimer(store database.Store) *PrefixHandler { func prefixHandlerWithoutTimer(store database.Store) *PrefixHandler {
table := routetable.New(routetable.Params{})
return &PrefixHandler{ return &PrefixHandler{
db: store, db: store,
logger: logger.New(), logger: logger.New(),
table: routetable.New(routetable.Params{}), table: table,
batchMaxSize: prefixBatchMaxSize,
tableChangesPerWrite: maxTableChangesPerWrite,
originChangesPerWrite: maxOriginChangesPerWrite,
heldBack: make(map[string][]*ristypes.RISMessage),
tablePeersDown: table.PeersDown,
} }
} }
// holdUpPeersDown makes each PeersDown of h wait until the returned channel is
// closed, as another peer's long PeersDown would hold it up. The test calls it
// before it hands h a message.
func holdUpPeersDown(h *PrefixHandler) chan struct{} {
release := make(chan struct{})
h.tablePeersDown = func(peers []string) {
<-release
h.table.PeersDown(peers)
}
return release
}
// newTestDatabase opens a database in a new temporary directory. It is closed // newTestDatabase opens a database in a new temporary directory. It is closed
// when the test ends. // when the test ends.
func newTestDatabase(t *testing.T) *database.Database { func newTestDatabase(t *testing.T) *database.Database {
internal/routewatch/prefixhandler_originchanges_internal_test.go
+181
View File
@@ -0,0 +1,181 @@
package routewatch
import (
"bytes"
"encoding/json"
"errors"
"log/slog"
"net/netip"
"slices"
"testing"
"git.eeqj.de/sneak/routewatch/internal/database"
"git.eeqj.de/sneak/routewatch/internal/logger"
"git.eeqj.de/sneak/routewatch/internal/routetable"
)
// TestPrefixHandlerWritesOriginChanges hands a running prefix handler an
// announcement and flushes. The flush must write the origin change to the
// database.
func TestPrefixHandlerWritesOriginChanges(t *testing.T) {
t.Parallel()
db := newTestDatabase(t)
h := prefixHandlerWithoutTimer(db)
h.HandleMessage(peerAnnouncement(testPeerIP, testV4Prefix))
h.flushBatch()
got, err := db.GetOriginChanges(t.Context(),
netip.MustParsePrefix(testV4Prefix), 10)
if err != nil {
t.Fatalf("GetOriginChanges: %v", err)
}
if len(got) != 1 || !got[0].Announced || got[0].OriginASN != testASNB {
t.Errorf("GetOriginChanges = %+v, want one announced row for AS%d",
got, testASNB)
}
}
// errTestOriginChangeWrite is the error a test store's failing write of the
// origin changes returns.
var errTestOriginChangeWrite = errors.New(
"test: the write of the origin changes failed")
// originChangesFailsStore is a real database whose first write of the origin
// changes fails, writing nothing. writes counts the writes asked for.
type originChangesFailsStore struct {
*database.Database
writes int
}
func (s *originChangesFailsStore) WriteOriginChanges(
changes []routetable.OriginChange,
) error {
s.writes++
if s.writes == 1 {
return errTestOriginChangeWrite
}
return s.Database.WriteOriginChanges(changes)
}
// TestPrefixHandlerWritesAFailedOriginChangeWriteAgain runs two flushes into a
// database whose first write of the origin changes fails. The second write must
// hold the change of the first.
func TestPrefixHandlerWritesAFailedOriginChangeWriteAgain(t *testing.T) {
t.Parallel()
db := newTestDatabase(t)
store := &originChangesFailsStore{Database: db}
h := prefixHandlerWithoutTimer(store)
h.HandleMessage(peerAnnouncement(testPeerIP, testV4Prefix))
h.flushBatch()
h.flushBatch()
got, err := db.GetOriginChanges(t.Context(),
netip.MustParsePrefix(testV4Prefix), 10)
if err != nil {
t.Fatalf("GetOriginChanges: %v", err)
}
if len(got) != 1 || !got[0].Announced || got[0].OriginASN != testASNB {
t.Errorf("GetOriginChanges = %+v, want one announced row for AS%d",
got, testASNB)
}
}
// originChangesWriteSizesStore is a real database that records how many
// changes each write of the origin changes holds.
type originChangesWriteSizesStore struct {
*database.Database
counts []int
}
func (s *originChangesWriteSizesStore) WriteOriginChanges(
changes []routetable.OriginChange,
) error {
s.counts = append(s.counts, len(changes))
return s.Database.WriteOriginChanges(changes)
}
// TestPrefixHandlerWritesManyOriginChangesOverSeveralFlushes has more origin
// changes than one write takes, then flushes three times. The first write must
// hold one write's worth, the second the rest, and the third nothing. The
// handler's limit is small.
func TestPrefixHandlerWritesManyOriginChangesOverSeveralFlushes(t *testing.T) {
t.Parallel()
const perWrite = 10
db := newTestDatabase(t)
store := &originChangesWriteSizesStore{Database: db}
h := prefixHandlerWithoutTimer(store)
h.originChangesPerWrite = perWrite
announceManyPrefixes(h.table, perWrite*3/2)
h.flushBatch()
h.flushBatch()
h.flushBatch()
want := []int{perWrite, perWrite*3/2 - perWrite}
if !slices.Equal(store.counts, want) {
t.Errorf("WriteOriginChanges held %v changes, want %v", store.counts, want)
}
}
// TestPrefixHandlerLogsTheDroppedOriginChanges fills the routing table with
// one origin change more than it keeps, then flushes. The warning the flush
// logs must carry the dropped count.
func TestPrefixHandlerLogsTheDroppedOriginChanges(t *testing.T) {
t.Parallel()
var logs bytes.Buffer
db := newTestDatabase(t)
h := prefixHandlerWithoutTimer(db)
h.logger = &logger.Logger{
Logger: slog.New(slog.NewJSONHandler(&logs,
&slog.HandlerOptions{Level: slog.LevelWarn})),
}
announceManyPrefixes(h.table, routetable.MaxWaitingOriginChanges+1)
h.flushBatch()
var warning struct {
Msg string `json:"msg"`
Dropped *int `json:"dropped"`
}
found := false
for line := range bytes.SplitSeq(bytes.TrimSpace(logs.Bytes()), []byte("\n")) {
warning.Dropped = nil
err := json.Unmarshal(line, &warning)
if err != nil {
t.Fatalf("want a JSON log line, got %q: %v", line, err)
}
if warning.Msg != "Origin changes dropped" {
continue
}
found = true
if warning.Dropped == nil || *warning.Dropped != 1 {
t.Errorf("the warning's dropped = %v, want 1", warning.Dropped)
}
}
if !found {
t.Errorf("no warning logged the dropped origin changes")
}
}
internal/routewatch/prefixhandler_table_internal_test.go
+401 -23
View File
@@ -7,8 +7,10 @@ import (
"log/slog" "log/slog"
"net/netip" "net/netip"
"reflect" "reflect"
"runtime"
"slices" "slices"
"strings" "strings"
"sync"
"testing" "testing"
"time" "time"
@@ -30,11 +32,12 @@ const (
// firstManyPrefix is the first prefix announceManyPrefixes announces. // firstManyPrefix is the first prefix announceManyPrefixes announces.
firstManyPrefix = "10.0.0.0/32" firstManyPrefix = "10.0.0.0/32"
)
// tableWriteTimeout is how long a test waits for the flush timer to write the // testMaxTableChangesPerWrite is a limit of one write of the routing
// routing table's changes: a few ticks of it. // table's changes that a test exceeds quickly, in place of
const tableWriteTimeout = 5 * prefixBatchTimeout // maxTableChangesPerWrite.
testMaxTableChangesPerWrite = 10
)
// tableCase is one test of the routing table in memory: the messages handed to // tableCase is one test of the routing table in memory: the messages handed to
// the prefix handler, and for each prefix the peers that carry it with each // the prefix handler, and for each prefix the peers that carry it with each
@@ -100,6 +103,359 @@ func TestPrefixHandlerAppliesUpdatesToTheRoutingTable(t *testing.T) {
}) })
} }
// TestPrefixHandlerTakesMessagesWhileAPeerGoesDown holds up the PeersDown of a
// peer whose session went down, as another peer's long PeersDown would. The
// handler must go on taking messages. It applies another peer's announcement
// at once. It holds back these messages of the down peer, in this order:
// - an announcement;
// - its session going down again;
// - a second announcement.
//
// HeldBackCount must count them. Once the PeersDown calls have returned, the
// down peer must carry only the prefix of the second announcement.
func TestPrefixHandlerTakesMessagesWhileAPeerGoesDown(t *testing.T) {
t.Parallel()
const heldMessages = 3
h := prefixHandlerWithoutTimer(newMockStore())
release := holdUpPeersDown(h)
h.HandleMessage(peerAnnouncement(testPeerIP, testV4Prefix))
handled := returnsInTime(func() {
for _, msg := range []*ristypes.RISMessage{
sessionDown(),
peerAnnouncement(secondPeerIP, otherV4Prefix),
peerAnnouncement(testPeerIP, testV6Prefix),
sessionDown(),
peerAnnouncement(testPeerIP, setV4Prefix),
} {
h.HandleMessage(msg)
}
})
if !handled {
t.Fatalf("the handler did not take the messages after the session "+
"went down within %s", stepTimeout)
}
checkTableOrigins(t, h.table, map[string]map[int][]string{
testV4Prefix: {testASNB: {testPeerIP}},
otherV4Prefix: {testASNB: {secondPeerIP}},
testV6Prefix: {},
setV4Prefix: {},
})
if h.HeldBackCount() != heldMessages {
t.Errorf("HeldBackCount() = %d, want %d", h.HeldBackCount(),
heldMessages)
}
close(release)
if !returnsInTime(h.peerDowns.Wait) {
t.Fatalf("the PeersDown calls did not return within %s", stepTimeout)
}
checkTableOrigins(t, h.table, map[string]map[int][]string{
testV4Prefix: {},
otherV4Prefix: {testASNB: {secondPeerIP}},
testV6Prefix: {},
setV4Prefix: {testASNB: {testPeerIP}},
})
}
// TestPrefixHandlerTakesPeersDownTogether has four peers announce testV4Prefix.
// It holds up the PeersDown of the first peer, whose session goes down.
// Meanwhile the sessions of the three others go down, and each of them
// announces otherV4Prefix. Once the first PeersDown is let go, the next one
// must take the three others together. No peer may then carry testV4Prefix,
// and the three others must carry otherV4Prefix.
func TestPrefixHandlerTakesPeersDownTogether(t *testing.T) {
t.Parallel()
others := []string{secondPeerIP, thirdPeerIP, fourthPeerIP}
h := prefixHandlerWithoutTimer(newMockStore())
// calls receives the peers of each PeersDown, with room for one call
// for each peer.
calls := make(chan []string, len(others)+1)
release := make(chan struct{})
h.tablePeersDown = func(peers []string) {
calls <- slices.Clone(peers)
<-release
h.table.PeersDown(peers)
}
for _, peer := range append([]string{testPeerIP}, others...) {
h.HandleMessage(peerAnnouncement(peer, testV4Prefix))
}
h.HandleMessage(sessionDown())
select {
case <-calls:
case <-time.After(stepTimeout):
t.Fatalf("PeersDown did not begin within %s", stepTimeout)
}
for _, peer := range others {
h.HandleMessage(sessionDownOf(peer))
h.HandleMessage(peerAnnouncement(peer, otherV4Prefix))
}
close(release)
if !returnsInTime(h.peerDowns.Wait) {
t.Fatalf("the PeersDown calls did not return within %s", stepTimeout)
}
close(calls)
later := make([][]string, 0, len(calls))
for peers := range calls {
later = append(later, peers)
}
if !reflect.DeepEqual(later, [][]string{others}) {
t.Errorf("the PeersDown calls after the first took %v, want %v "+
"together", later, others)
}
checkTableOrigins(t, h.table, map[string]map[int][]string{
testV4Prefix: {},
otherV4Prefix: {testASNB: others},
})
}
// TestPrefixHandlerAppliesMessagesWhilePeersDownRuns gives a peer 50,000
// prefixes and hands the prefix handler that peer's session going down. The
// table's PeersDown then visits the prefixes in five batches. Once PeersDown
// has begun, the handler is handed 1,000 announcements of another peer. The
// handler must apply them all before PeersDown ends, while the down peer still
// carries some of its prefixes.
func TestPrefixHandlerAppliesMessagesWhilePeersDownRuns(t *testing.T) {
t.Parallel()
const (
// downPeerPrefixes is five times the 10,000 prefixes PeersDown visits
// in one hold of the table's lock.
downPeerPrefixes = 50000
// otherPeerMessages is far more messages than the handler applies
// while PeersDown runs, if PeersDown takes the lock back at once after
// each batch. The handler then applies only a few for each batch.
otherPeerMessages = 1000
// firstOtherAddr is the address of the other peer's first prefix.
firstOtherAddr = "2001:db8:2::"
)
h := prefixHandlerWithoutTimer(newMockStore())
announceManyPrefixes(h.table, downPeerPrefixes)
h.HandleMessage(sessionDown())
// Wait until PeersDown has begun: the down peer has left some of its
// prefixes. The down peer's prefixes are IPv4 and the other peer's are
// IPv6, so the counts tell them apart.
for h.table.Counts().IPv4Routes == downPeerPrefixes {
runtime.Gosched()
}
// Each announcement names the /128 of the next address.
addr := netip.MustParseAddr(firstOtherAddr)
for range otherPeerMessages {
h.HandleMessage(peerAnnouncement(secondPeerIP,
netip.PrefixFrom(addr, addr.BitLen()).String()))
addr = addr.Next()
}
counts := h.table.Counts()
if counts.IPv6Routes != otherPeerMessages {
t.Errorf("the other peer carries %d prefixes, want %d",
counts.IPv6Routes, otherPeerMessages)
}
if counts.IPv4Routes == 0 {
t.Errorf("PeersDown ended before the handler applied the other peer's "+
"%d announcements", otherPeerMessages)
}
if !returnsInTime(h.peerDowns.Wait) {
t.Fatalf("the PeersDown did not return within %s", stepTimeout)
}
}
// TestPrefixHandlerTakesMessagesWhileAReturningPeerSendsItsTable gives a peer
// 50,000 prefixes and hands the prefix handler that peer's session going down.
// Once PeersDown has begun, the peer comes back and sends more announcements
// than the handler's queue holds, as a peer that sends its whole table again
// does. The handler must hold them back and go on taking messages. Another
// peer's announcement, handed next, must be applied before PeersDown ends.
func TestPrefixHandlerTakesMessagesWhileAReturningPeerSendsItsTable(t *testing.T) {
t.Parallel()
const (
// downPeerPrefixes is five times the 10,000 prefixes PeersDown visits
// in one hold of the table's lock.
downPeerPrefixes = 50000
returningMessages = prefixHandlerQueueSize + 1
)
table := routetable.New(routetable.Params{})
announceManyPrefixes(table, downPeerPrefixes)
h := newPrefixHandler(newMockStore(), logger.New(), table,
longerThanAnyTest, maxTableChangesPerWrite)
defer stopInTime(t, h)
h.HandleMessage(sessionDown())
// Wait until PeersDown has begun: the down peer has left some of its
// prefixes, which are all IPv4.
for h.table.Counts().IPv4Routes == downPeerPrefixes {
runtime.Gosched()
}
returning := peerAnnouncement(testPeerIP, testV6Prefix)
if !returnsInTime(func() {
for range returningMessages {
h.HandleMessage(returning)
}
h.HandleMessage(peerAnnouncement(secondPeerIP, testV6Prefix))
}) {
t.Fatalf("the handler did not take the messages within %s", stepTimeout)
}
if h.table.Counts().IPv4Routes == 0 {
t.Error("PeersDown ended before the handler took the other peer's " +
"announcement")
}
checkTableOrigins(t, h.table, map[string]map[int][]string{
testV6Prefix: {testASNB: {secondPeerIP}},
})
if !returnsInTime(h.peerDowns.Wait) {
t.Fatalf("the PeersDown did not return within %s", stepTimeout)
}
checkTableOrigins(t, h.table, map[string]map[int][]string{
testV6Prefix: {testASNB: {testPeerIP, secondPeerIP}},
})
}
// TestPrefixHandlerTakesMessagesWhileItAppliesHeldBackOnes holds back many
// messages of a peer whose session went down. Each names a prefix that does
// not parse, so applying it logs an error. Each log write takes a
// millisecond. While the handler applies the held-back messages, it must take
// another peer's announcement.
func TestPrefixHandlerTakesMessagesWhileItAppliesHeldBackOnes(t *testing.T) {
t.Parallel()
const (
// heldMessages take the handler at least a second to apply.
heldMessages = 1000
badPrefix = "not a prefix"
)
logs := &slowWriter{firstWrite: make(chan struct{})}
h := newPrefixHandler(newMockStore(), newErrorLogger(logs),
routetable.New(routetable.Params{}), longerThanAnyTest,
maxTableChangesPerWrite)
defer stopInTime(t, h)
release := holdUpPeersDown(h)
h.HandleMessage(sessionDown())
for range heldMessages {
h.HandleMessage(peerAnnouncement(testPeerIP, badPrefix))
}
close(release)
select {
case <-logs.firstWrite:
case <-time.After(stepTimeout):
t.Fatal("the handler did not start to apply the held-back messages")
}
if !returnsInTime(func() {
h.HandleMessage(peerAnnouncement(secondPeerIP, otherV4Prefix))
}) {
t.Fatalf("HandleMessage did not return within %s", stepTimeout)
}
h.mu.Lock()
left := len(h.heldBack[testPeerIP])
h.mu.Unlock()
if left == 0 {
t.Error("the handler took another peer's announcement only once it " +
"had applied every held-back message")
}
}
// TestPrefixHandlerWaitsAtTheMaximumHeldBack holds up the PeersDown of a peer
// whose session went down. It hands the handler maxHeldBackMessages messages
// of that peer. HandleMessage must then wait, even for another peer's
// message, until the PeersDown returns and a held-back message is applied.
func TestPrefixHandlerWaitsAtTheMaximumHeldBack(t *testing.T) {
t.Parallel()
h := newPrefixHandler(newMockStore(), logger.New(),
routetable.New(routetable.Params{}), longerThanAnyTest,
maxTableChangesPerWrite)
defer stopInTime(t, h)
release := holdUpPeersDown(h)
h.HandleMessage(sessionDown())
held := peerAnnouncement(testPeerIP, testV6Prefix)
for range maxHeldBackMessages {
h.HandleMessage(held)
}
returned := make(chan struct{})
go func() {
h.HandleMessage(peerAnnouncement(secondPeerIP, otherV4Prefix))
close(returned)
}()
select {
case <-returned:
t.Error("HandleMessage returned while maxHeldBackMessages messages " +
"were held back")
case <-time.After(stillWaitingAfter):
}
close(release)
select {
case <-returned:
case <-time.After(stepTimeout):
t.Fatal("HandleMessage did not return after the PeersDown returned")
}
}
// slowWriter takes a millisecond over each write and drops what it is given.
// It closes firstWrite at the first write.
type slowWriter struct {
firstWrite chan struct{}
once sync.Once
}
func (w *slowWriter) Write(p []byte) (int, error) {
w.once.Do(func() { close(w.firstWrite) })
time.Sleep(time.Millisecond)
return len(p), nil
}
// TestPrefixHandlerAppliesAPathWithoutAnOriginToTheRoutingTable hands the // TestPrefixHandlerAppliesAPathWithoutAnOriginToTheRoutingTable hands the
// prefix handler announcements whose AS path gives no origin. One whose path // prefix handler announcements whose AS path gives no origin. One whose path
// is empty or holds AS 0 removes the peer's route, as a withdrawal does; one // is empty or holds AS 0 removes the peer's route, as a withdrawal does; one
@@ -198,8 +554,9 @@ func TestPrefixHandlerKeepsThePathOfAPathEndingInASet(t *testing.T) {
} }
} }
// checkTableCases hands the messages of each case to a new prefix handler and // checkTableCases hands the messages of each case to a new prefix handler. It
// checks its routing table right after, with no flush. // checks the handler's routing table once the handler's PeersDown calls have
// returned, with no flush.
func checkTableCases(t *testing.T, tests []tableCase) { func checkTableCases(t *testing.T, tests []tableCase) {
t.Helper() t.Helper()
@@ -212,17 +569,28 @@ func checkTableCases(t *testing.T, tests []tableCase) {
h.HandleMessage(msg) h.HandleMessage(msg)
} }
for prefix, want := range tt.want { h.peerDowns.Wait()
got := tableOrigins(h.table, prefix) checkTableOrigins(t, h.table, tt.want)
if !reflect.DeepEqual(got, want) {
t.Errorf("peers of %s by origin AS = %v, want %v",
prefix, got, want)
}
}
}) })
} }
} }
// checkTableOrigins checks, for each prefix in want, the peers that carry it
// in table with each origin AS.
func checkTableOrigins(
t *testing.T, table *routetable.Table, want map[string]map[int][]string,
) {
t.Helper()
for prefix, wantOrigins := range want {
got := tableOrigins(table, prefix)
if !reflect.DeepEqual(got, wantOrigins) {
t.Errorf("peers of %s by origin AS = %v, want %v",
prefix, got, wantOrigins)
}
}
}
// tableWritesStore is a real database that hands each write of the routing // tableWritesStore is a real database that hands each write of the routing
// table's changes to written once it is made. // table's changes to written once it is made.
type tableWritesStore struct { type tableWritesStore struct {
@@ -276,9 +644,9 @@ func TestPrefixHandlerWritesTheTableChangesEachSecond(t *testing.T) {
t.Fatalf("wrote %+v, want the pair of %s and AS%d with "+ t.Fatalf("wrote %+v, want the pair of %s and AS%d with "+
"removed %t", changes, prefix, testASNB, step.wantRemoved) "removed %t", changes, prefix, testASNB, step.wantRemoved)
} }
case <-time.After(tableWriteTimeout): case <-time.After(stepTimeout):
t.Fatalf("the routing table's change was not written within %s", t.Fatalf("the routing table's change was not written within %s",
tableWriteTimeout) stepTimeout)
} }
} }
} }
@@ -375,25 +743,32 @@ func (s *tableWriteSizesStore) WriteRouteChanges(
// takes, then flushes three times. The first write must hold as many pairs as // takes, then flushes three times. The first write must hold as many pairs as
// one write takes, and the peer. The second must hold the other pairs, and the // one write takes, and the peer. The second must hold the other pairs, and the
// third flush must write nothing. The database must then hold the table in // third flush must write nothing. The database must then hold the table in
// memory. // memory. The handler's limit is small, and its timer does not fire.
func TestPrefixHandlerWritesManyTableChangesOverSeveralFlushes(t *testing.T) { func TestPrefixHandlerWritesManyTableChangesOverSeveralFlushes(t *testing.T) {
t.Parallel() t.Parallel()
const ( const (
pairs = maxTableChangesPerWrite * 3 / 2 pairs = testMaxTableChangesPerWrite * 3 / 2
flushes = 3 flushes = 3
) )
db := newTestDatabase(t) db := newTestDatabase(t)
store := &tableWriteSizesStore{Database: db} store := &tableWriteSizesStore{Database: db}
h := prefixHandlerWithoutTimer(store) table := routetable.New(routetable.Params{})
announceManyPrefixes(h.table, pairs) announceManyPrefixes(table, pairs)
h := newPrefixHandler(store, logger.New(), table, longerThanAnyTest,
testMaxTableChangesPerWrite)
defer stopInTime(t, h)
for range flushes { for range flushes {
h.flushBatch() h.flushBatch()
} }
wantChanges := []int{maxTableChangesPerWrite, pairs - maxTableChangesPerWrite} wantChanges := []int{
testMaxTableChangesPerWrite, pairs - testMaxTableChangesPerWrite,
}
wantNewPeers := []int{1, 0} wantNewPeers := []int{1, 0}
if !slices.Equal(store.changes, wantChanges) || if !slices.Equal(store.changes, wantChanges) ||
@@ -415,11 +790,11 @@ func TestPrefixHandlerWritesManyTableChangesOverSeveralFlushes(t *testing.T) {
// takes. Its last flush writes one write's worth, so Stop must log the pairs // takes. Its last flush writes one write's worth, so Stop must log the pairs
// that no write took, and must not say that the stop deadline passed. The // that no write took, and must not say that the stop deadline passed. The
// flush timer must not fire, or its writes could leave no pairs for Stop to // flush timer must not fire, or its writes could leave no pairs for Stop to
// log. // log. The handler's limit of one write is small.
func TestPrefixHandlerStopLogsTheTableChangesLeftUnwritten(t *testing.T) { func TestPrefixHandlerStopLogsTheTableChangesLeftUnwritten(t *testing.T) {
t.Parallel() t.Parallel()
const pairs = maxTableChangesPerWrite + 1 const pairs = testMaxTableChangesPerWrite + 1
var logs bytes.Buffer var logs bytes.Buffer
@@ -427,7 +802,8 @@ func TestPrefixHandlerStopLogsTheTableChangesLeftUnwritten(t *testing.T) {
table := routetable.New(routetable.Params{}) table := routetable.New(routetable.Params{})
announceManyPrefixes(table, pairs) announceManyPrefixes(table, pairs)
h := newPrefixHandler(store, newErrorLogger(&logs), table, longerThanAnyTest) h := newPrefixHandler(store, newErrorLogger(&logs), table, longerThanAnyTest,
testMaxTableChangesPerWrite)
h.Stop(t.Context()) h.Stop(t.Context())
written := 0 written := 0
@@ -489,6 +865,7 @@ func TestARestartReadsTheRoutingTableBack(t *testing.T) {
h.HandleMessage(msg) h.HandleMessage(msg)
} }
h.peerDowns.Wait()
h.flushBatch() h.flushBatch()
var logs bytes.Buffer var logs bytes.Buffer
@@ -527,6 +904,7 @@ func TestARestartReadsTheRoutingTableBack(t *testing.T) {
restarted.HandleMessage(msg) restarted.HandleMessage(msg)
} }
h.peerDowns.Wait()
restarted.Stop(t.Context()) restarted.Stop(t.Context())
read, err := db.ReadRouteTable(t.Context()) read, err := db.ReadRouteTable(t.Context())
internal/server/handlers.go
+336 -126
View File
@@ -15,15 +15,16 @@ import (
"strings" "strings"
"time" "time"
"git.eeqj.de/sneak/routewatch/internal/blocklist" "git.eeqj.de/sneak/routewatch/internal/bogon"
"git.eeqj.de/sneak/routewatch/internal/database" "git.eeqj.de/sneak/routewatch/internal/database"
"git.eeqj.de/sneak/routewatch/internal/geo"
"git.eeqj.de/sneak/routewatch/internal/iplist"
"git.eeqj.de/sneak/routewatch/internal/metrics" "git.eeqj.de/sneak/routewatch/internal/metrics"
"git.eeqj.de/sneak/routewatch/internal/ristypes" "git.eeqj.de/sneak/routewatch/internal/ristypes"
"git.eeqj.de/sneak/routewatch/internal/routetable" "git.eeqj.de/sneak/routewatch/internal/routetable"
"git.eeqj.de/sneak/routewatch/internal/streamer" "git.eeqj.de/sneak/routewatch/internal/streamer"
"git.eeqj.de/sneak/routewatch/internal/templates" "git.eeqj.de/sneak/routewatch/internal/templates"
asinfo "git.eeqj.de/sneak/routewatch/pkg/asinfo" asinfo "git.eeqj.de/sneak/routewatch/pkg/asinfo"
"github.com/dustin/go-humanize"
"github.com/go-chi/chi/v5" "github.com/go-chi/chi/v5"
) )
@@ -39,12 +40,9 @@ const (
const ( const (
// maxLookupTargets is the most addresses and host names an IP lookup may // maxLookupTargets is the most addresses and host names an IP lookup may
// list, and the most addresses it may have once the names are resolved: // list, and the most addresses it may have once the names are resolved:
// each address costs two database reads and a PTR lookup. // each address costs two database reads and a PTR lookup. Ten PTR lookups
// that run to ptr.LookupTimeout fit in the request's 30-second limit.
maxLookupTargets = 10 maxLookupTargets = 10
// ptrLookupTimeout is each PTR lookup's own time limit, so that ten
// addresses whose PTR lookups never answer fit in the 30-second limit.
ptrLookupTimeout = 2 * time.Second
) )
// The Cache-Control header of an IP lookup answer, such as // The Cache-Control header of an IP lookup answer, such as
@@ -89,6 +87,10 @@ const (
ipVersionV6 = 6 ipVersionV6 = 6
) )
// maxOriginChangesOnPage is the most origin changes the prefix page shows. A
// prefix with more shows the newest ones and says so.
const maxOriginChangesOnPage = 5000
// HealthCheckResponse represents the health check response. // HealthCheckResponse represents the health check response.
type HealthCheckResponse struct { type HealthCheckResponse struct {
Status string `json:"status"` Status string `json:"status"`
@@ -160,6 +162,7 @@ func (s *Server) handleIndex() http.HandlerFunc {
err := tmpl.Execute(w, indexPageData{ err := tmpl.Execute(w, indexPageData{
CSPNonce: cspNonce(r.Context()), CSPNonce: cspNonce(r.Context()),
ClientIP: extractClientIP(r), ClientIP: extractClientIP(r),
Cards: s.cards.Load(),
}) })
if err != nil { if err != nil {
s.logger.Error("Failed to render index template", "error", err) s.logger.Error("Failed to render index template", "error", err)
@@ -181,6 +184,9 @@ type indexPageData struct {
// ClientIP is the visitor's address, which the IP information API card // ClientIP is the visitor's address, which the IP information API card
// looks up: the address /ip/ would look up for the same request. // looks up: the address /ip/ would look up for the same request.
ClientIP string ClientIP string
// Cards is the copy of the cards that show figures of the routing table,
// or nil before the server has first worked them out.
Cards *homeCards
} }
// writeJSONError writes a standardized JSON error response with the given // writeJSONError writes a standardized JSON error response with the given
@@ -222,18 +228,23 @@ type WHOISStatsInfo struct {
NeverFetched int `json:"never_fetched"` NeverFetched int `json:"never_fetched"`
SuccessesLastHour int `json:"successes_last_hour"` SuccessesLastHour int `json:"successes_last_hour"`
ErrorsLastHour int `json:"errors_last_hour"` ErrorsLastHour int `json:"errors_last_hour"`
CurrentInterval string `json:"current_interval"`
ConsecutiveFails int `json:"consecutive_fails"` ConsecutiveFails int `json:"consecutive_fails"`
FreshPercent float64 `json:"fresh_percent"` FreshPercent float64 `json:"fresh_percent"`
// CurrentIntervalSeconds is the wait between two fetches. It can have a
// fractional part, such as 22.5.
CurrentIntervalSeconds float64 `json:"current_interval_seconds"`
} }
// Stats is the /status.json answer: uptime, message counts, database stats, // Stats is the /status.json answer: uptime, message counts, database stats,
// and the routing table's figures. OldestRoute and NewestRoute are the times // and the routing table's figures. UptimeSeconds is the time since the stream
// of the oldest and the newest kept routes. // last connected, or 0 if it has never connected. MemoryUsageBytes is the Go
// heap in use. OldestRoute and NewestRoute are the times of the oldest and the
// newest kept routes.
// //
//nolint:tagliatelle // field names are the existing JSON API //nolint:tagliatelle // field names are the existing JSON API
type Stats struct { type Stats struct {
Uptime string `json:"uptime"` UptimeSeconds int64 `json:"uptime_seconds"`
TotalMessages uint64 `json:"total_messages"` TotalMessages uint64 `json:"total_messages"`
TotalBytes uint64 `json:"total_bytes"` TotalBytes uint64 `json:"total_bytes"`
TotalWireBytes uint64 `json:"total_wire_bytes"` TotalWireBytes uint64 `json:"total_wire_bytes"`
@@ -243,7 +254,7 @@ type Stats struct {
Connected bool `json:"connected"` Connected bool `json:"connected"`
GoVersion string `json:"go_version"` GoVersion string `json:"go_version"`
Goroutines int `json:"goroutines"` Goroutines int `json:"goroutines"`
MemoryUsage string `json:"memory_usage"` MemoryUsageBytes uint64 `json:"memory_usage_bytes"`
ASNs int `json:"asns"` ASNs int `json:"asns"`
Prefixes int `json:"prefixes"` Prefixes int `json:"prefixes"`
IPv4Prefixes int `json:"ipv4_prefixes"` IPv4Prefixes int `json:"ipv4_prefixes"`
@@ -358,7 +369,7 @@ func (s *Server) statusStats(
runtime.ReadMemStats(&memStats) runtime.ReadMemStats(&memStats)
return Stats{ return Stats{
Uptime: streamUptime(streamMetrics.ConnectedSince), UptimeSeconds: uptimeSeconds(streamMetrics.ConnectedSince),
TotalMessages: streamMetrics.TotalMessages, TotalMessages: streamMetrics.TotalMessages,
TotalBytes: streamMetrics.TotalBytes, TotalBytes: streamMetrics.TotalBytes,
TotalWireBytes: streamMetrics.TotalWireBytes, TotalWireBytes: streamMetrics.TotalWireBytes,
@@ -368,7 +379,7 @@ func (s *Server) statusStats(
Connected: streamMetrics.Connected, Connected: streamMetrics.Connected,
GoVersion: runtime.Version(), GoVersion: runtime.Version(),
Goroutines: runtime.NumGoroutine(), Goroutines: runtime.NumGoroutine(),
MemoryUsage: humanize.Bytes(memStats.Alloc), MemoryUsageBytes: memStats.Alloc,
ASNs: dbStats.ASNs, ASNs: dbStats.ASNs,
Prefixes: counts.IPv4Prefixes + counts.IPv6Prefixes, Prefixes: counts.IPv4Prefixes + counts.IPv6Prefixes,
IPv4Prefixes: counts.IPv4Prefixes, IPv4Prefixes: counts.IPv4Prefixes,
@@ -435,30 +446,31 @@ func (s *Server) getWHOISStats(ctx context.Context) *WHOISStatsInfo {
NeverFetched: dbStats.NeverFetched, NeverFetched: dbStats.NeverFetched,
SuccessesLastHour: fetcherStats.SuccessesLastHour, SuccessesLastHour: fetcherStats.SuccessesLastHour,
ErrorsLastHour: fetcherStats.ErrorsLastHour, ErrorsLastHour: fetcherStats.ErrorsLastHour,
CurrentInterval: fetcherStats.CurrentInterval.String(),
ConsecutiveFails: fetcherStats.ConsecutiveFails, ConsecutiveFails: fetcherStats.ConsecutiveFails,
FreshPercent: freshPercent, FreshPercent: freshPercent,
CurrentIntervalSeconds: fetcherStats.CurrentInterval.Seconds(),
} }
} }
// streamUptime is how long the stream has been connected, to the second, or // uptimeSeconds is the number of whole seconds since the stream last
// "0s" if it has never connected. // connected, or 0 if it has never connected.
func streamUptime(connectedSince time.Time) string { func uptimeSeconds(connectedSince time.Time) int64 {
if connectedSince.IsZero() { if connectedSince.IsZero() {
return "0s" return 0
} }
return time.Since(connectedSince).Truncate(time.Second).String() return int64(time.Since(connectedSince) / time.Second)
} }
// connectionDuration is how long the stream has been connected, to the // connectionDurationSeconds is the number of whole seconds the stream has
// second, or "disconnected". // been connected, or nil while it is not connected.
func connectionDuration(connected bool, connectedSince time.Time) string { func connectionDurationSeconds(connected bool, connectedSince time.Time) *int64 {
if !connected || connectedSince.IsZero() { if !connected || connectedSince.IsZero() {
return "disconnected" return nil
} }
return time.Since(connectedSince).Truncate(time.Second).String() return new(uptimeSeconds(connectedSince))
} }
// whoisStaleThreshold matches the fetcher's threshold for consistency. // whoisStaleThreshold matches the fetcher's threshold for consistency.
@@ -477,6 +489,7 @@ type HandlerStatsInfo struct {
QueueHighWaterMark int `json:"queue_high_water_mark"` QueueHighWaterMark int `json:"queue_high_water_mark"`
ProcessedCount uint64 `json:"processed_count"` ProcessedCount uint64 `json:"processed_count"`
DroppedCount uint64 `json:"dropped_count"` DroppedCount uint64 `json:"dropped_count"`
HeldBackCount int `json:"held_back_count"`
AvgProcessTimeMs float64 `json:"avg_process_time_ms"` AvgProcessTimeMs float64 `json:"avg_process_time_ms"`
MinProcessTimeMs float64 `json:"min_process_time_ms"` MinProcessTimeMs float64 `json:"min_process_time_ms"`
MaxProcessTimeMs float64 `json:"max_process_time_ms"` MaxProcessTimeMs float64 `json:"max_process_time_ms"`
@@ -508,7 +521,7 @@ type StreamStats struct {
// //
//nolint:tagliatelle // field names are the existing JSON API //nolint:tagliatelle // field names are the existing JSON API
type StatsResponse struct { type StatsResponse struct {
Uptime string `json:"uptime"` UptimeSeconds int64 `json:"uptime_seconds"`
TotalMessages uint64 `json:"total_messages"` TotalMessages uint64 `json:"total_messages"`
TotalBytes uint64 `json:"total_bytes"` TotalBytes uint64 `json:"total_bytes"`
TotalWireBytes uint64 `json:"total_wire_bytes"` TotalWireBytes uint64 `json:"total_wire_bytes"`
@@ -516,11 +529,10 @@ type StatsResponse struct {
MbitsPerSec float64 `json:"mbits_per_sec"` MbitsPerSec float64 `json:"mbits_per_sec"`
WireMbitsPerSec float64 `json:"wire_mbits_per_sec"` WireMbitsPerSec float64 `json:"wire_mbits_per_sec"`
Connected bool `json:"connected"` Connected bool `json:"connected"`
ConnectionDuration string `json:"connection_duration"`
ReconnectCount uint64 `json:"reconnect_count"` ReconnectCount uint64 `json:"reconnect_count"`
GoVersion string `json:"go_version"` GoVersion string `json:"go_version"`
Goroutines int `json:"goroutines"` Goroutines int `json:"goroutines"`
MemoryUsage string `json:"memory_usage"` MemoryUsageBytes uint64 `json:"memory_usage_bytes"`
GC GCStats `json:"gc"` GC GCStats `json:"gc"`
Stream StreamStats `json:"stream"` Stream StreamStats `json:"stream"`
ASNs int `json:"asns"` ASNs int `json:"asns"`
@@ -542,6 +554,9 @@ type StatsResponse struct {
IPv6PrefixDistribution []PrefixDistribution `json:"ipv6_prefix_distribution"` IPv6PrefixDistribution []PrefixDistribution `json:"ipv6_prefix_distribution"`
WHOISStats *WHOISStatsInfo `json:"whois_stats,omitempty"` WHOISStats *WHOISStatsInfo `json:"whois_stats,omitempty"`
// ConnectionDurationSeconds is null while the stream is not connected.
ConnectionDurationSeconds *int64 `json:"connection_duration_seconds"`
OriginsWithoutKeptRoute int `json:"origins_without_kept_route"` OriginsWithoutKeptRoute int `json:"origins_without_kept_route"`
} }
@@ -559,6 +574,7 @@ func handlerStatsInfo(handlerStats []streamer.HandlerStats) []HandlerStatsInfo {
QueueHighWaterMark: hs.QueueHighWaterMark, QueueHighWaterMark: hs.QueueHighWaterMark,
ProcessedCount: hs.ProcessedCount, ProcessedCount: hs.ProcessedCount,
DroppedCount: hs.DroppedCount, DroppedCount: hs.DroppedCount,
HeldBackCount: hs.HeldBackCount,
AvgProcessTimeMs: float64(hs.AvgProcessTime.Microseconds()) / AvgProcessTimeMs: float64(hs.AvgProcessTime.Microseconds()) /
microsecondsPerMillisecond, microsecondsPerMillisecond,
MinProcessTimeMs: float64(hs.MinProcessTime.Microseconds()) / MinProcessTimeMs: float64(hs.MinProcessTime.Microseconds()) /
@@ -680,20 +696,18 @@ func (s *Server) statsResponse(
runtime.ReadMemStats(&memStats) runtime.ReadMemStats(&memStats)
return StatsResponse{ return StatsResponse{
Uptime: streamUptime(streamMetrics.ConnectedSince), UptimeSeconds: uptimeSeconds(streamMetrics.ConnectedSince),
TotalMessages: streamMetrics.TotalMessages, TotalMessages: streamMetrics.TotalMessages,
TotalBytes: streamMetrics.TotalBytes, TotalBytes: streamMetrics.TotalBytes,
TotalWireBytes: streamMetrics.TotalWireBytes, TotalWireBytes: streamMetrics.TotalWireBytes,
MessagesPerSec: streamMetrics.MessagesPerSec, MessagesPerSec: streamMetrics.MessagesPerSec,
MbitsPerSec: streamMetrics.BitsPerSec / bitsPerMegabit, MbitsPerSec: streamMetrics.BitsPerSec / bitsPerMegabit,
WireMbitsPerSec: streamMetrics.WireBitsPerSec / bitsPerMegabit, WireMbitsPerSec: streamMetrics.WireBitsPerSec / bitsPerMegabit,
Connected: streamMetrics.Connected, Connected: streamMetrics.Connected,
ConnectionDuration: connectionDuration(
streamMetrics.Connected, streamMetrics.ConnectedSince),
ReconnectCount: streamMetrics.ReconnectCount, ReconnectCount: streamMetrics.ReconnectCount,
GoVersion: runtime.Version(), GoVersion: runtime.Version(),
Goroutines: runtime.NumGoroutine(), Goroutines: runtime.NumGoroutine(),
MemoryUsage: humanize.Bytes(memStats.Alloc), MemoryUsageBytes: memStats.Alloc,
GC: gcStats(&memStats), GC: gcStats(&memStats),
Stream: s.streamStats(), Stream: s.streamStats(),
ASNs: dbStats.ASNs, ASNs: dbStats.ASNs,
@@ -715,6 +729,9 @@ func (s *Server) statsResponse(
IPv6PrefixDistribution: prefixDistribution(counts.IPv6PrefixesByLength), IPv6PrefixDistribution: prefixDistribution(counts.IPv6PrefixesByLength),
WHOISStats: whoisStats, WHOISStats: whoisStats,
ConnectionDurationSeconds: connectionDurationSeconds(
streamMetrics.Connected, streamMetrics.ConnectedSince),
OriginsWithoutKeptRoute: counts.OriginsWithoutKeptRoute, OriginsWithoutKeptRoute: counts.OriginsWithoutKeptRoute,
} }
} }
@@ -747,19 +764,48 @@ type IPLookupResponse struct {
Errors []string `json:"errors,omitempty"` Errors []string `json:"errors,omitempty"`
} }
// IPLookupResult is the answer for one address: its PTR names, its live route // IPLookupResult is the answer for one address: its PTR names, its flags, its
// and that route's AS, and the blocklists that list it. IPInfo is nil when // live route and that route's AS, the IP lists that contain it, and where it
// the address has no live route, and the answer then has no route or AS // is. Every result has every field. The fields of IPInfo are null when the
// fields. IP hides the IPInfo field of the same name, so that an address with // address has no live route.
// no route has it too. //
//nolint:tagliatelle // snake_case keys, as the Go style guide asks
type IPLookupResult struct { type IPLookupResult struct {
*IPInfo IPInfo
IP string `json:"ip"` IP string `json:"ip"`
PTR []string `json:"ptr,omitempty"` // PTR is empty, never nil, when the address has no PTR names.
PTR []string `json:"ptr"`
// Blocklists has one entry for each blocklist the address is on. Flags IPLookupFlags `json:"flags"`
Blocklists []blocklist.Listing `json:"blocklists"`
// VPNProviders names the VPN lists the address is on. It is empty, never
// nil, when there are none.
VPNProviders []string `json:"vpn_providers"`
// IPLists has one entry for each IP list the address is on.
IPLists []iplist.Listing `json:"ip_lists"`
// Geo is where the address is. It is nil when no source answers.
Geo *geo.Location `json:"geo"`
}
// IPLookupFlags are the yes-or-no facts about an address. Every result has
// them, whether or not the address has a live route.
//
//nolint:tagliatelle // snake_case keys, as the Go style guide asks
type IPLookupFlags struct {
// IsTor says that the address is on the Tor exit list.
IsTor bool `json:"is_tor"`
// IsVPN says that the address is on a list of VPN servers.
IsVPN bool `json:"is_vpn"`
// IsRelay says that the address is on the iCloud Private Relay list.
IsRelay bool `json:"is_relay"`
// IsBogon says that the address is reserved, as package bogon tells.
IsBogon bool `json:"is_bogon"`
} }
// handleIPInfo returns a handler that provides comprehensive IP information. // handleIPInfo returns a handler that provides comprehensive IP information.
@@ -800,6 +846,8 @@ func (s *Server) handleIPInfo() http.HandlerFunc {
return return
} }
locations := s.geoLocations(ctx, ipsToLookup)
// Track ASNs that need WHOIS refresh // Track ASNs that need WHOIS refresh
refreshASNs := make(map[int]bool) refreshASNs := make(map[int]bool)
@@ -814,8 +862,8 @@ func (s *Server) handleIPInfo() http.HandlerFunc {
switch { switch {
case errors.Is(err, ErrNoRoute): case errors.Is(err, ErrNoRoute):
// The address still gets a result, without route fields. // The address still gets a result, with every field of
ipInfo = nil // ipInfo null.
case errors.Is(err, ErrInvalidIP): case errors.Is(err, ErrInvalidIP):
response.Errors = append(response.Errors, ip+": "+err.Error()) response.Errors = append(response.Errors, ip+": "+err.Error())
@@ -835,15 +883,12 @@ func (s *Server) handleIPInfo() http.HandlerFunc {
return return
} }
response.Results = append(response.Results, IPLookupResult{ result := s.ipLookupResult(ip, ptrs, ipInfo)
IP: ip, result.Geo = locations[ip]
PTR: ptrs, response.Results = append(response.Results, result)
IPInfo: ipInfo,
Blocklists: s.blocklistListings(ip),
})
if ipInfo != nil && ipInfo.NeedsWHOISRefresh { if ipInfo.NeedsWHOISRefresh {
refreshASNs[ipInfo.ASN] = true refreshASNs[*ipInfo.ASN] = true
} }
} }
@@ -854,60 +899,72 @@ func (s *Server) handleIPInfo() http.HandlerFunc {
} }
} }
// ipInfo returns the IP lookup's answer for ip. The routing table gives the // ipInfo returns what the IP lookup knows about the route of ip. The routing
// most specific prefix that holds the address, the number of peers that carry // table gives the most specific prefix that holds the address, the number of
// it, the origin AS that most of them carry, and the time of its newest kept // peers that carry it, its origin ASes and the one that most peers carry, and
// route. The database gives the prefix's first-seen time and the AS's WHOIS // the time of its newest kept route. The database gives the prefix's
// details. It returns ErrNoRoute when no prefix holds the address, and // first-seen time and the AS's WHOIS details. It returns ErrNoRoute when no
// ErrInvalidIP when ip does not parse. // prefix holds the address, and ErrInvalidIP when ip does not parse. With an
func (s *Server) ipInfo(ctx context.Context, ip string) (*IPInfo, error) { // error, every field of the IPInfo it returns is nil.
func (s *Server) ipInfo(ctx context.Context, ip string) (IPInfo, error) {
addr, err := netip.ParseAddr(ip) addr, err := netip.ParseAddr(ip)
if err != nil { if err != nil {
return nil, fmt.Errorf("%w: %s", ErrInvalidIP, ip) return IPInfo{}, fmt.Errorf("%w: %s", ErrInvalidIP, ip)
} }
summary, found := s.table.Lookup(addr) summary, found := s.table.Lookup(addr)
if !found { if !found {
return nil, fmt.Errorf("%w for IP %s", ErrNoRoute, ip) return IPInfo{}, fmt.Errorf("%w for IP %s", ErrNoRoute, ip)
} }
firstSeen, err := s.db.GetPrefixFirstSeen(ctx, summary.Prefix) firstSeen, err := s.db.GetPrefixFirstSeen(ctx, summary.Prefix)
if err != nil { if err != nil {
return nil, err return IPInfo{}, err
} }
asInfo, err := s.db.GetASWHOIS(ctx, summary.OriginASN) asInfo, err := s.db.GetASWHOIS(ctx, summary.OriginASN)
if err != nil { if err != nil {
return nil, err return IPInfo{}, err
} }
info := &IPInfo{ info := IPInfo{
IP: ip, Netblock: new(summary.Prefix.String()),
Netblock: summary.Prefix.String(), MaskLength: new(summary.Prefix.Bits()),
MaskLength: summary.Prefix.Bits(), IPVersion: new(ipVersionOf(summary.Prefix)),
IPVersion: ipVersionOf(summary.Prefix), NumPeers: new(summary.Peers),
NumPeers: summary.Peers, ASN: new(summary.OriginASN),
ASN: summary.OriginASN, NumOrigins: new(len(summary.OriginASNs)),
ASName: asInfo.ASName, OriginASNs: summary.OriginASNs,
Handle: asInfo.Handle, ASName: nilIfEmpty(asInfo.ASName),
Description: asInfo.Description, Handle: nilIfEmpty(asInfo.Handle),
OrgName: asInfo.OrgName, Description: nilIfEmpty(asInfo.Description),
OrgID: asInfo.OrgID, OrgName: nilIfEmpty(asInfo.OrgName),
Address: asInfo.Address, OrgID: nilIfEmpty(asInfo.OrgID),
CountryCode: asInfo.CountryCode, Address: nilIfEmpty(asInfo.Address),
AbuseEmail: asInfo.AbuseEmail, CountryCode: nilIfEmpty(asInfo.CountryCode),
RIR: asInfo.RIR, AbuseEmail: nilIfEmpty(asInfo.AbuseEmail),
FirstSeen: firstSeen, RIR: nilIfEmpty(asInfo.RIR),
LastSeen: summary.Newest,
NeedsWHOISRefresh: needsWHOISRefresh(asInfo), NeedsWHOISRefresh: needsWHOISRefresh(asInfo),
} }
if summary.Newest != nil { if !firstSeen.IsZero() {
info.LastSeen = *summary.Newest info.FirstSeen = &firstSeen
} }
return info, nil return info, nil
} }
// nilIfEmpty returns a pointer to s, or nil when s is empty, so that JSON
// gives a detail the database does not hold as null.
func nilIfEmpty(s string) *string {
if s == "" {
return nil
}
return &s
}
// needsWHOISRefresh says whether the WHOIS details of asInfo were never // needsWHOISRefresh says whether the WHOIS details of asInfo were never
// fetched or are older than whoisStaleThreshold. AS 0, no known origin, has // fetched or are older than whoisStaleThreshold. AS 0, no known origin, has
// none to fetch. // none to fetch.
@@ -929,23 +986,120 @@ func ipVersionOf(prefix netip.Prefix) int {
return ipVersionV6 return ipVersionV6
} }
// blocklistListings returns the blocklists that list ip. It returns an empty // ipLookupResult returns the result for ip, adding its flags and IP lists to
// list, never nil, so that an answer's blocklists is [] rather than null. // its PTR names and route.
func (s *Server) blocklistListings(ip string) []blocklist.Listing { func (s *Server) ipLookupResult(ip string, ptrs []string, info IPInfo) IPLookupResult {
addr, err := netip.ParseAddr(ip) listings := s.ipListListings(ip)
if s.blocklists == nil || err != nil {
return []blocklist.Listing{} return IPLookupResult{
IP: ip,
PTR: ptrs,
IPInfo: info,
Flags: ipLookupFlags(ip, listings),
VPNProviders: vpnProviders(listings),
IPLists: listings,
}
}
// vpnProviders returns the names of the VPN lists among listings. It returns
// an empty list, never nil, so that an answer's vpn_providers is [] rather
// than null.
func vpnProviders(listings []iplist.Listing) []string {
names := []string{}
for _, listing := range listings {
if listing.VPN {
names = append(names, listing.Name)
}
} }
return s.blocklists.Lookup(addr) return names
}
// ipListListings returns the IP lists that contain ip. It returns an empty
// list, never nil, so that an answer's ip_lists is [] rather than null.
func (s *Server) ipListListings(ip string) []iplist.Listing {
addr, err := netip.ParseAddr(ip)
if s.ipLists == nil || err != nil {
return []iplist.Listing{}
}
return s.ipLists.Lookup(addr)
}
// ipLookupFlags returns the flags of ip, whose IP list entries are listings.
func ipLookupFlags(ip string, listings []iplist.Listing) IPLookupFlags {
return IPLookupFlags{
IsTor: slices.ContainsFunc(listings, func(l iplist.Listing) bool {
return l.Name == iplist.TorExitsList
}),
IsVPN: slices.ContainsFunc(listings, func(l iplist.Listing) bool {
return l.VPN
}),
IsRelay: slices.ContainsFunc(listings, func(l iplist.Listing) bool {
return l.Name == iplist.ICloudPrivateRelayList
}),
IsBogon: isBogon(ip),
}
}
// geoLocations returns where ips are, by address. An address that does not
// parse has no entry. Nor has a reserved one, which is sent to no outside
// source and has no location.
func (s *Server) geoLocations(
ctx context.Context, ips []string,
) map[string]*geo.Location {
if s.geoLocator == nil {
return nil
}
var (
kept []string
addrs []netip.Addr
)
for _, ip := range ips {
addr, err := netip.ParseAddr(ip)
if err != nil || isBogon(ip) {
continue
}
kept = append(kept, ip)
addrs = append(addrs, addr)
}
if len(addrs) == 0 {
return nil
}
answers := s.geoLocator.Lookup(ctx, addrs)
locations := make(map[string]*geo.Location, len(kept))
for i, ip := range kept {
locations[ip] = answers[i]
}
return locations
}
// isBogon says whether the address ip is reserved, as package bogon tells.
func isBogon(ip string) bool {
addr, err := netip.ParseAddr(ip)
if err != nil {
return false
}
_, reserved := bogon.Addr(addr)
return reserved
} }
// setIPLookupCacheControl lets caches keep an IP lookup answer for the // setIPLookupCacheControl lets caches keep an IP lookup answer for the
// shortest blocklist interval, the soonest a blocklist copy can change. The // shortest IP list interval, the soonest an IP list copy can change. The
// answer about the caller's own address is private, so that a shared cache // answer about the caller's own address is private, so that a shared cache
// does not give it to another caller. Without blocklists it sets nothing. // does not give it to another caller. Without IP lists it sets nothing.
func (s *Server) setIPLookupCacheControl(w http.ResponseWriter, ownAddress bool) { func (s *Server) setIPLookupCacheControl(w http.ResponseWriter, ownAddress bool) {
if s.blocklists == nil { if s.ipLists == nil {
return return
} }
@@ -954,7 +1108,7 @@ func (s *Server) setIPLookupCacheControl(w http.ResponseWriter, ownAddress bool)
visibility = cacheControlPrivate visibility = cacheControlPrivate
} }
maxAgeSeconds := int(s.blocklists.ShortestInterval().Seconds()) maxAgeSeconds := int(s.ipLists.ShortestInterval().Seconds())
w.Header().Set(cacheControlHeader, w.Header().Set(cacheControlHeader,
visibility+cacheControlMaxAge+strconv.Itoa(maxAgeSeconds)) visibility+cacheControlMaxAge+strconv.Itoa(maxAgeSeconds))
} }
@@ -1113,15 +1267,19 @@ func publicAddresses(addrs []string) []string {
return public return public
} }
// lookupPTRNames returns the PTR records of ip without their trailing dots, or // lookupPTRNames returns the PTR records of ip without their trailing dots. It
// nil when the lookup fails or runs past ptrLookupTimeout. // returns an empty list, never nil, when there are none and when the lookup
// fails, so that an answer's ptr is [] rather than null.
func (s *Server) lookupPTRNames(ctx context.Context, ip string) []string { func (s *Server) lookupPTRNames(ctx context.Context, ip string) []string {
ctx, cancel := context.WithTimeout(ctx, ptrLookupTimeout) ptrs, err := s.ptrResolver.LookupAddr(ctx, ip)
defer cancel()
ptrs, err := s.resolver.LookupAddr(ctx, ip)
if err != nil { if err != nil {
return nil s.logger.Warn("PTR lookup failed", "ip", ip, "error", err)
return []string{}
}
if ptrs == nil {
return []string{}
} }
// Remove trailing dots from PTR records // Remove trailing dots from PTR records
@@ -1507,27 +1665,24 @@ func (s *Server) handlePrefixDetail() http.HandlerFunc {
routes := prefixRoutes(parsed, origins) routes := prefixRoutes(parsed, origins)
// Prepare template data changes, moreChanges, err := s.prefixOriginChanges(r.Context(), parsed)
data := struct { if deadlinePassed(r.Context()) {
Prefix string http.Error(w, requestTimeoutMessage, http.StatusGatewayTimeout)
MaskLength int
IPVersion int return
Routes []EnhancedRoute
Origins []*ASNInfo
PeerCount int
OriginCount int
CSPNonce string
}{
Prefix: parsed.String(),
MaskLength: parsed.Bits(),
IPVersion: ipVersionOf(parsed),
Routes: routesWithASPathHandles(routes),
Origins: originInfos,
PeerCount: len(routes),
OriginCount: len(originInfos),
CSPNonce: cspNonce(r.Context()),
} }
if err != nil {
s.logger.Error("Failed to get the origin changes", "error", err)
http.Error(w, internalErrorMessage, http.StatusInternalServerError)
return
}
// Prepare template data
data := newPrefixDetailData(parsed, routes, originInfos, changes,
moreChanges, cspNonce(r.Context()))
// Check if context is still valid before writing response // Check if context is still valid before writing response
select { select {
case <-r.Context().Done(): case <-r.Context().Done():
@@ -1579,6 +1734,61 @@ func (s *Server) originASNs(
return infos, nil return infos, nil
} }
// prefixOriginChanges returns prefix's origin changes for the page, newest
// first, at most maxOriginChangesOnPage, and whether there are more.
func (s *Server) prefixOriginChanges(
ctx context.Context, prefix netip.Prefix,
) ([]routetable.OriginChange, bool, error) {
// One more is read to know whether there are more.
changes, err := s.db.GetOriginChanges(ctx, prefix, maxOriginChangesOnPage+1)
if err != nil {
return nil, false, err
}
more := len(changes) > maxOriginChangesOnPage
if more {
changes = changes[:maxOriginChangesOnPage]
}
return changes, more, nil
}
// prefixDetailData is what the prefix detail page is rendered with.
type prefixDetailData struct {
Prefix string
MaskLength int
IPVersion int
Routes []EnhancedRoute
Origins []*ASNInfo
PeerCount int
OriginCount int
OriginChanges []routetable.OriginChange
MoreOriginChanges bool
// MaxOriginChanges is the most origin changes the page shows.
MaxOriginChanges int
CSPNonce string
}
// newPrefixDetailData builds the prefix detail page's data.
func newPrefixDetailData(
parsed netip.Prefix, routes []LiveRoute, originInfos []*ASNInfo,
changes []routetable.OriginChange, moreChanges bool, nonce string,
) prefixDetailData {
return prefixDetailData{
Prefix: parsed.String(),
MaskLength: parsed.Bits(),
IPVersion: ipVersionOf(parsed),
Routes: routesWithASPathHandles(routes),
Origins: originInfos,
PeerCount: len(routes),
OriginCount: len(originInfos),
OriginChanges: changes,
MoreOriginChanges: moreChanges,
MaxOriginChanges: maxOriginChangesOnPage,
CSPNonce: nonce,
}
}
// prefixRoutes returns one route for each peer that carries prefix, by origin // prefixRoutes returns one route for each peer that carries prefix, by origin
// AS in the order of origins. Each origin's kept routes come first, newest // AS in the order of origins. Each origin's kept routes come first, newest
// first, with their AS path, next hop and time. Its other peers follow without // first, with their AS path, next hop and time. Its other peers follow without
internal/server/handlers_internal_test.go
+764 -76
View File
File diff suppressed because it is too large. Load diff
internal/server/handlers_table_internal_test.go
+34 -18
View File
@@ -4,6 +4,8 @@ import (
"encoding/json" "encoding/json"
"net/http" "net/http"
"net/http/httptest" "net/http/httptest"
"net/netip"
"reflect"
"slices" "slices"
"strconv" "strconv"
"strings" "strings"
@@ -75,14 +77,15 @@ func get(t *testing.T, s *Server, path string) *httptest.ResponseRecorder {
// TestIPLookupGivesTheOriginMostPeersCarry looks up an address in a prefix // TestIPLookupGivesTheOriginMostPeersCarry looks up an address in a prefix
// with two origin ASes, through each IP lookup route. The answer names the // with two origin ASes, through each IP lookup route. The answer names the
// origin AS that more peers carry, counts every peer, and gives the time of // origin AS that more peers carry, counts every peer, lists both origin ASes,
// the prefix's newest kept route. The prefix's first-seen time and the AS's // and gives the time of the prefix's newest kept route. The prefix's
// WHOIS details come from the database. // first-seen time and the AS's WHOIS details come from the database. A WHOIS
// detail the database does not hold is null.
func TestIPLookupGivesTheOriginMostPeersCarry(t *testing.T) { func TestIPLookupGivesTheOriginMostPeersCarry(t *testing.T) {
t.Parallel() t.Parallel()
s := newServerWithTable(t, newTwoOriginTable()) s := newServerWithTable(t, newTwoOriginTable())
s.resolver = &fakeResolver{} useFakeResolver(s, &fakeResolver{})
firstSeen := testRouteTime(-1) firstSeen := testRouteTime(-1)
@@ -105,6 +108,26 @@ func TestIPLookupGivesTheOriginMostPeersCarry(t *testing.T) {
t.Fatalf("UpdateASNWHOIS: %v", err) t.Fatalf("UpdateASNWHOIS: %v", err)
} }
// The details the database does not hold, such as org_name, are null.
want := IPInfo{
Netblock: new(testPrefixV4),
MaskLength: new(netip.MustParsePrefix(testPrefixV4).Bits()),
IPVersion: new(ipVersionV4),
NumPeers: new(4),
ASN: new(mostPeersASN),
NumOrigins: new(2),
OriginASNs: []int{mostPeersASN, fewerPeersASN},
ASName: &whois.ASName,
CountryCode: &whois.CountryCode,
FirstSeen: &firstSeen,
LastSeen: new(testRouteTime(5)),
}
wantJSON, err := json.Marshal(want)
if err != nil {
t.Fatalf("encoding %+v: %v", want, err)
}
// ownAddressPath looks up the request's own address, which httptest // ownAddressPath looks up the request's own address, which httptest
// gives as addrInTestPrefixV4. // gives as addrInTestPrefixV4.
for _, path := range []string{ for _, path := range []string{
@@ -115,22 +138,15 @@ func TestIPLookupGivesTheOriginMostPeersCarry(t *testing.T) {
Data IPLookupResponse `json:"data"` Data IPLookupResponse `json:"data"`
} }
err := json.Unmarshal(get(t, s, path).Body.Bytes(), &body) answer := get(t, s, path).Body.Bytes()
if err != nil || len(body.Data.Results) != 1 ||
body.Data.Results[0].IPInfo == nil { err := json.Unmarshal(answer, &body)
t.Fatalf("%s: answer %+v (%v), want one result with a route", if err != nil || len(body.Data.Results) != 1 {
path, body.Data, err) t.Fatalf("%s: answer %s (%v), want one result", path, answer, err)
} }
got := body.Data.Results[0].IPInfo if !reflect.DeepEqual(body.Data.Results[0].IPInfo, want) {
if got.Netblock != testPrefixV4 || got.ASN != mostPeersASN || t.Errorf("%s: answer %s, want the fields %s", path, answer, wantJSON)
got.NumPeers != 4 || !got.LastSeen.Equal(testRouteTime(5)) ||
!got.FirstSeen.Equal(firstSeen) || got.ASName != whois.ASName ||
got.CountryCode != whois.CountryCode {
t.Errorf("%s: route %+v, want %s from AS%d, 4 peers, last seen %v, "+
"first seen %v, %s in %s", path, *got, testPrefixV4,
mostPeersASN, testRouteTime(5), firstSeen, whois.ASName,
whois.CountryCode)
} }
} }
} }
internal/server/home.go
+206
View File
@@ -0,0 +1,206 @@
package server
import (
"context"
"html/template"
"net/http"
"slices"
"time"
"git.eeqj.de/sneak/routewatch/internal/database"
"git.eeqj.de/sneak/routewatch/internal/routetable"
"git.eeqj.de/sneak/routewatch/internal/templates"
asinfo "git.eeqj.de/sneak/routewatch/pkg/asinfo"
)
const (
// homeCardsRefreshInterval is how often the server works out the home
// page's cards again. Some of their figures take a walk over the whole
// routing table, so no request works them out.
homeCardsRefreshInterval = time.Minute
// homeCardsDatabaseTimeout is how long the database read behind the
// cards of the newest and the oldest AS may take.
homeCardsDatabaseTimeout = 4 * time.Second
// maxListedEntries is how many entries the bogon and multiple-origin
// pages list at most.
maxListedEntries = 1000
)
// homeCards is what the home page's cards show. The bogon and multiple-origin
// pages list the entries their cards count. The server works it out every
// homeCardsRefreshInterval and serves this copy in between.
type homeCards struct {
routetable.Overview
// NewestAS and OldestAS are the ASes the asns table last saw most
// recently and longest ago. They are nil when the database did not
// answer or holds no AS.
NewestAS *database.ASN
OldestAS *database.ASN
// WellKnownNetworks are the networks of wellKnownASNs, newest update
// first.
WellKnownNetworks []wellKnownNetwork
}
// wellKnownNetwork is one network on the home page's card of well-known
// networks.
type wellKnownNetwork struct {
ASN int
// Name is its description in the AS list built into RouteWatch.
Name string
// Prefixes is how many prefixes it originates.
Prefixes int
// Newest is the time of its newest kept route, or nil when it keeps none.
Newest *time.Time
}
// listPageData is what the bogon and multiple-origin pages are rendered with.
type listPageData struct {
// CSPNonce is the nonce the page's style block carries.
CSPNonce string
// Cards is the copy of the home page's cards, or nil before the server
// has first worked them out.
Cards *homeCards
}
// The AS numbers of the networks the home page lists as well known.
const (
appleASN = 714
googleASN = 15169
amazonASN = 16509
microsoftASN = 8075
metaASN = 32934
cloudflareASN = 13335
akamaiASN = 20940
netflixASN = 2906
dodNetworkInfoCtrASN = 721
cogentASN = 174
hurricaneElectricASN = 6939
level3ASN = 3356
arelionASN = 1299
nttASN = 2914
mitASN = 3
)
// wellKnownASNs returns the AS numbers of the networks the home page lists as
// well known: large companies, large transit networks, the US Department of
// Defense's Network Information Center and a university.
func wellKnownASNs() []int {
return []int{
appleASN, googleASN, amazonASN, microsoftASN, metaASN, cloudflareASN,
akamaiASN, netflixASN, dodNetworkInfoCtrASN, cogentASN,
hurricaneElectricASN, level3ASN, arelionASN, nttASN, mitASN,
}
}
// keepHomeCardsFresh works out the home page's cards now, and again every
// interval until ctx ends.
func (s *Server) keepHomeCardsFresh(ctx context.Context, interval time.Duration) {
ticker := time.NewTicker(interval)
defer ticker.Stop()
for {
s.refreshHomeCards(ctx)
select {
case <-ctx.Done():
return
case <-ticker.C:
}
}
}
// refreshHomeCards works out the home page's cards and keeps them for the
// pages to serve. When the database does not answer, the failure is logged
// and the cards of the newest and the oldest AS stay empty.
func (s *Server) refreshHomeCards(ctx context.Context) {
cards := &homeCards{
Overview: s.table.Overview(maxListedEntries),
WellKnownNetworks: s.wellKnownNetworks(),
}
ctx, cancel := context.WithTimeout(ctx, homeCardsDatabaseTimeout)
defer cancel()
newest, oldest, err := s.db.GetLastSeenASes(ctx)
if err != nil {
s.logger.Warn("Failed to read the newest and the oldest AS", "error", err)
} else {
cards.NewestAS, cards.OldestAS = newest, oldest
}
s.cards.Store(cards)
}
// wellKnownNetworks returns the networks of wellKnownASNs, each with how many
// prefixes it originates and the time of its newest kept route. They come
// newest first, and those that keep no route last.
func (s *Server) wellKnownNetworks() []wellKnownNetwork {
asns := wellKnownASNs()
networks := make([]wellKnownNetwork, 0, len(asns))
for _, asn := range asns {
originated := s.table.OriginatedPrefixes(asn)
network := wellKnownNetwork{ASN: asn, Prefixes: len(originated)}
if info, ok := asinfo.Get(asn); ok {
network.Name = info.Description
}
for _, p := range originated {
if p.Newest != nil &&
(network.Newest == nil || p.Newest.After(*network.Newest)) {
network.Newest = p.Newest
}
}
networks = append(networks, network)
}
slices.SortStableFunc(networks, func(a, b wellKnownNetwork) int {
switch {
case a.Newest == nil && b.Newest == nil:
return 0
case a.Newest == nil:
return 1
case b.Newest == nil:
return -1
}
return b.Newest.Compare(*a.Newest)
})
return networks
}
// handleBogons returns a handler that serves the page listing the bogon
// announcements.
func (s *Server) handleBogons() http.HandlerFunc {
return s.listPageHandler(templates.BogonsTemplate())
}
// handleMultipleOrigins returns a handler that serves the page listing the
// prefixes announced by more than one origin AS.
func (s *Server) handleMultipleOrigins() http.HandlerFunc {
return s.listPageHandler(templates.MultipleOriginsTemplate())
}
// listPageHandler returns a handler that renders tmpl, a page that lists
// entries the home page's cards count, from the copy of the cards.
func (s *Server) listPageHandler(tmpl *template.Template) http.HandlerFunc {
return func(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Content-Type", "text/html; charset=utf-8")
err := tmpl.Execute(w, listPageData{
CSPNonce: cspNonce(r.Context()),
Cards: s.cards.Load(),
})
if err != nil {
s.logger.Error("Failed to render a list page", "error", err)
http.Error(w, "Internal Server Error", http.StatusInternalServerError)
}
}
}
internal/server/home_internal_test.go
+423
View File
@@ -0,0 +1,423 @@
package server
import (
"context"
"net/netip"
"strconv"
"strings"
"testing"
"testing/synctest"
"time"
"git.eeqj.de/sneak/routewatch/internal/database"
"git.eeqj.de/sneak/routewatch/internal/routetable"
)
// The ASes of the routing table that newCardsTable fills. Each card test
// finds one of them on its card.
const (
twoPrefixASN = 13335 // originates two prefixes, the most
newestRouteASN = 15169 // the newest route
oldestRouteASN = 3 // the oldest route
secondOrigin = 16509 // a second origin AS of twoPrefixASN's prefix
privateUseASN = 64512 // reserved, so its route is a bogon announcement
)
// Paths of the pages that list what two of the home page's cards count.
const (
bogonsPath = "/bogons"
multipleOriginsPath = "/multiple-origins"
)
// cardsNotReadyText is what the pages say before the cards are first worked
// out.
const cardsNotReadyText = "being worked out"
// newCardsTable returns a routing table in which:
// - twoPrefixASN originates 1.0.0.0/24 and 1.0.4.0/22;
// - secondOrigin originates 1.0.0.0/24 too, which so has two origin ASes;
// - newestRouteASN's 8.8.8.0/24 has the newest route;
// - oldestRouteASN's 18.0.0.0/8 has the oldest;
// - privateUseASN originates 10.0.0.0/8, carried by two peers: a bogon
// announcement for both its prefix and its AS.
//
// The last four ASes originate one prefix each.
func newCardsTable() *routetable.Table {
table := emptyTable()
announce(table, "1.0.0.0/24", twoPrefixASN, testPeer(1), testRouteTime(10))
announce(table, "1.0.4.0/22", twoPrefixASN, testPeer(1), testRouteTime(5))
announce(table, "1.0.0.0/24", secondOrigin, testPeer(3), testRouteTime(12))
announce(table, "8.8.8.0/24", newestRouteASN, testPeer(2), testRouteTime(20))
announce(table, "18.0.0.0/8", oldestRouteASN, testPeer(2), testRouteTime(1))
announce(table, "10.0.0.0/8", privateUseASN, testPeer(1), testRouteTime(15))
announce(table, "10.0.0.0/8", privateUseASN, testPeer(2), testRouteTime(15))
return table
}
// homeCard returns the HTML of the home page's card with heading, up to the
// end of the card.
func homeCard(t *testing.T, page, heading string) string {
t.Helper()
_, card, found := strings.Cut(page, "<h2>"+heading+"</h2>")
if !found {
t.Fatalf("the home page has no card %q", heading)
}
card, _, _ = strings.Cut(card, "</div>")
return card
}
// asLink returns the HTML attribute of a link to the AS page of asn.
func asLink(asn int) string {
return `href="/as/` + strconv.Itoa(asn) + `"`
}
// TestHomePageCardsShowTheTableFigures fills a routing table and the asns
// table, works out the cards, and checks that each card shows its figure. The
// cards are worked out in a synctest bubble, whose clock is fake, so a stall on
// the host does not use up the 4-second limit on their database read.
func TestHomePageCardsShowTheTableFigures(t *testing.T) {
t.Parallel()
const (
newestSeenASN = 6939
oldestSeenASN = 174
)
s := newServerWithTable(t, newCardsTable())
err := s.db.GetOrCreateASNBatch(map[int]database.SeenTimes{
newestSeenASN: {First: testRouteTime(0), Last: testRouteTime(30)},
oldestSeenASN: {First: testRouteTime(-30), Last: testRouteTime(-30)},
})
if err != nil {
t.Fatalf("GetOrCreateASNBatch: %v", err)
}
synctest.Test(t, func(t *testing.T) {
s.refreshHomeCards(t.Context())
})
page := get(t, s, "/").Body.String()
tests := []struct {
heading string
want []string
}{
{"Newest Updated Route", []string{
"8.8.8.0/24", asLink(newestRouteASN),
testRouteTime(20).Format(routeTimeFormat),
}},
{"Oldest Updated Route", []string{
"18.0.0.0/8", asLink(oldestRouteASN),
testRouteTime(1).Format(routeTimeFormat),
}},
{"Newest Updated AS", []string{
asLink(newestSeenASN), testRouteTime(30).Format(routeTimeFormat),
}},
{"Oldest Updated AS", []string{
asLink(oldestSeenASN), testRouteTime(-30).Format(routeTimeFormat),
}},
{"AS with the Most Prefixes", []string{
asLink(twoPrefixASN), "Prefixes it originates: 2",
}},
{"ASes with the Fewest Prefixes", []string{
"ASes that originate a single prefix: 4", asLink(newestRouteASN),
"8.8.8.0/24",
}},
{"Bogon Announcements", []string{`href="/bogons">1<`}},
{"Prefixes with Several Origins", []string{`href="/multiple-origins">1<`}},
}
for _, tc := range tests {
card := homeCard(t, page, tc.heading)
for _, want := range tc.want {
if !strings.Contains(card, want) {
t.Errorf("card %q does not hold %s: %s", tc.heading, want, card)
}
}
}
// The well-known networks come newest update first, and those without
// a route after them.
networks := homeCard(t, page, "Well-Known Networks")
order := []int{newestRouteASN, secondOrigin, twoPrefixASN, oldestRouteASN, 714}
last := -1
for _, asn := range order {
i := strings.Index(networks, asLink(asn))
if i <= last {
t.Fatalf("well-known networks: AS%d is not after the ASes before "+
"it in %v: %s", asn, order, networks)
}
last = i
}
if !strings.Contains(networks, "<td>2</td>") {
t.Errorf("well-known networks: no network with 2 prefixes: %s", networks)
}
}
// TestListPagesListTheirEntries checks the rows of the bogon and multiple-origin
// pages for the table of newCardsTable.
func TestListPagesListTheirEntries(t *testing.T) {
t.Parallel()
s := newServerWithTable(t, newCardsTable())
s.refreshHomeCards(t.Context())
pages := map[string][]string{
bogonsPath: {
"Bogon announcements: 1.", "10.0.0.0/8", asLink(privateUseASN),
"<td>2</td>",
"Private-Use (10.0.0.0/8); Private-Use (AS64512-AS65534)",
},
multipleOriginsPath: {
"Prefixes announced by more than one origin AS: 1.", "1.0.0.0/24",
asLink(twoPrefixASN), asLink(secondOrigin), ">1 peer<",
},
}
for path, wants := range pages {
page := get(t, s, path).Body.String()
for _, want := range wants {
if !strings.Contains(page, want) {
t.Errorf("%s does not hold %s", path, want)
}
}
}
}
// TestListPagesListAtMostMaxListedEntries fills a table with more prefixes than
// the list pages list, each announced by two origin ASes in reserved address
// space. Each page lists maxListedEntries of them and gives how many there are
// in all.
func TestListPagesListAtMostMaxListedEntries(t *testing.T) {
t.Parallel()
const prefixCount = maxListedEntries + 1
table := emptyTable()
addr := netip.MustParseAddr("10.0.0.0")
for range prefixCount {
prefix := netip.PrefixFrom(addr, addr.BitLen()).String()
announce(table, prefix, twoPrefixASN, testPeer(1), testRouteTime(0))
announce(table, prefix, secondOrigin, testPeer(2), testRouteTime(0))
addr = addr.Next()
}
s := newServerWithTable(t, table)
s.refreshHomeCards(t.Context())
listed := "The first " + strconv.Itoa(maxListedEntries) + " are listed"
tests := []struct {
path string
total string
}{
{bogonsPath, "Bogon announcements: " + strconv.Itoa(2*prefixCount) + "."},
{multipleOriginsPath, "Prefixes announced by more than one origin AS: " +
strconv.Itoa(prefixCount) + "."},
}
for _, tc := range tests {
page := get(t, s, tc.path).Body.String()
rows := strings.Count(page, `class="prefix-link"`)
if rows != maxListedEntries {
t.Errorf("%s lists %d entries, want %d", tc.path, rows,
maxListedEntries)
}
if !strings.Contains(page, tc.total) || !strings.Contains(page, listed) {
t.Errorf("%s does not say %q and %q", tc.path, tc.total, listed)
}
}
}
// TestPagesServeTheCopyOfTheCards checks that the pages show the cards as they
// were last worked out, not as the routing table is now, and that they say so
// before the cards are first worked out.
func TestPagesServeTheCopyOfTheCards(t *testing.T) {
t.Parallel()
table := emptyTable()
announce(table, "1.0.0.0/24", twoPrefixASN, testPeer(1), testRouteTime(0))
s := newServerWithTable(t, table)
for _, path := range []string{"/", bogonsPath, multipleOriginsPath} {
if !strings.Contains(get(t, s, path).Body.String(), cardsNotReadyText) {
t.Errorf("%s does not say the cards are %s", path, cardsNotReadyText)
}
}
s.refreshHomeCards(t.Context())
announce(table, "8.8.8.0/24", newestRouteASN, testPeer(2), testRouteTime(1))
card := homeCard(t, get(t, s, "/").Body.String(), "Newest Updated Route")
if !strings.Contains(card, "1.0.0.0/24") {
t.Errorf("before the cards are worked out again, the newest route "+
"is not the one they were worked out with: %s", card)
}
s.refreshHomeCards(t.Context())
card = homeCard(t, get(t, s, "/").Body.String(), "Newest Updated Route")
if !strings.Contains(card, "8.8.8.0/24") {
t.Errorf("after the cards are worked out again, the newest route is "+
"not the table's: %s", card)
}
}
// TestKeepHomeCardsFreshWorksThemOutEveryInterval runs keepHomeCardsFresh with
// a short interval. It works the cards out at once, again after the table
// changes, and stops when its context ends.
func TestKeepHomeCardsFreshWorksThemOutEveryInterval(t *testing.T) {
t.Parallel()
const (
interval = 10 * time.Millisecond
maxWait = 15 * time.Second
)
table := emptyTable()
announce(table, "1.0.0.0/24", twoPrefixASN, testPeer(1), testRouteTime(0))
s := newServerWithTable(t, table)
ctx, cancel := context.WithCancel(t.Context())
stopped := make(chan struct{})
go func() {
s.keepHomeCardsFresh(ctx, interval)
close(stopped)
}()
newestRouteASNIs := func(asn int) bool {
cards := s.cards.Load()
return cards != nil && cards.NewestRoute != nil &&
cards.NewestRoute.OriginASN == asn
}
waitUntil(t, maxWait, func() bool { return newestRouteASNIs(twoPrefixASN) })
announce(table, "8.8.8.0/24", newestRouteASN, testPeer(2), testRouteTime(1))
waitUntil(t, maxWait, func() bool { return newestRouteASNIs(newestRouteASN) })
cancel()
select {
case <-stopped:
case <-time.After(maxWait):
t.Fatal("keepHomeCardsFresh did not stop when its context ended")
}
}
// TestStartedServerWorksOutTheCards starts a server and waits until its home
// page shows the cards.
func TestStartedServerWorksOutTheCards(t *testing.T) {
t.Parallel()
const maxWait = 15 * time.Second
s := newServerWithTable(t, newCardsTable())
err := s.Start(t.Context())
if err != nil {
t.Fatalf("Start: %v", err)
}
defer func() { _ = s.Stop(context.Background()) }()
waitUntil(t, maxWait, func() bool {
return !strings.Contains(get(t, s, "/").Body.String(), cardsNotReadyText)
})
card := homeCard(t, get(t, s, "/").Body.String(), "Newest Updated Route")
if !strings.Contains(card, "8.8.8.0/24") {
t.Errorf("the newest route is not the table's: %s", card)
}
}
// TestStartedServerWorksOutTheCardsUntilStop starts a server with a context
// that ends as soon as Start returns. It runs in a synctest bubble, whose clock
// is fake: time.Sleep there moves the clock on and returns at once. The server
// must work the cards out again a minute later, and no more after Stop. Each
// time it works them out, it keeps a new copy. Before the fix the end of
// Start's context stopped the goroutine that works them out.
func TestStartedServerWorksOutTheCardsUntilStop(t *testing.T) {
t.Parallel()
// The server is made outside the bubble. The streamer's metrics start a
// goroutine that never returns, and a bubble waits for each of its
// goroutines to return.
s := newServerWithTable(t, newCardsTable())
synctest.Test(t, func(t *testing.T) {
ctx, cancel := context.WithCancel(t.Context())
err := s.Start(ctx)
if err != nil {
t.Fatalf("Start: %v", err)
}
cancel()
// The bubble's clock moves only while each of its goroutines waits
// on the bubble, and the goroutine that serves HTTP waits on the
// network. The test sends no request, so it closes the HTTP server.
_ = s.srv.Close()
synctest.Wait()
started := s.cards.Load()
if started == nil {
t.Fatal("the server did not work out the cards when it started")
}
time.Sleep(homeCardsRefreshInterval)
synctest.Wait()
if s.cards.Load() == started {
t.Error("the server did not work out the cards again a minute " +
"after its start context ended")
}
err = s.Stop(t.Context())
if err != nil {
t.Fatalf("Stop: %v", err)
}
stopped := s.cards.Load()
time.Sleep(homeCardsRefreshInterval)
synctest.Wait()
if s.cards.Load() != stopped {
t.Error("the server worked out the cards again after Stop")
}
})
}
// waitUntil fails the test unless done reports true within maxWait.
func waitUntil(t *testing.T, maxWait time.Duration, done func() bool) {
t.Helper()
const pollInterval = 5 * time.Millisecond
deadline := time.Now().Add(maxWait)
for !done() {
if time.Now().After(deadline) {
t.Fatalf("the cards did not change within %s", maxWait)
}
time.Sleep(pollInterval)
}
}
internal/server/middleware.go
+19 -7
View File
@@ -16,6 +16,7 @@ import (
"time" "time"
"github.com/go-chi/chi/v5" "github.com/go-chi/chi/v5"
"github.com/go-chi/chi/v5/middleware"
) )
// responseWriter wraps http.ResponseWriter to capture the response // responseWriter wraps http.ResponseWriter to capture the response
@@ -53,6 +54,15 @@ func (rw *responseWriter) Header() http.Header {
return rw.ResponseWriter.Header() return rw.ResponseWriter.Header()
} }
// The @meta object JSONResponseMiddleware adds to a JSON answer: its key, and
// the keys of its fields.
const (
jsonKeyMeta = "@meta"
metaKeyTimeZone = "time_zone"
metaKeyAPIVersion = "api_version"
metaKeyExecutionTimeMs = "execution_time_ms"
)
// JSONResponseMiddleware is an HTTP middleware that wraps all JSON responses // JSONResponseMiddleware is an HTTP middleware that wraps all JSON responses
// with a @meta field containing execution metadata. The metadata includes the // with a @meta field containing execution metadata. The metadata includes the
// time zone (always UTC), API version, and request execution time in milliseconds. // time zone (always UTC), API version, and request execution time in milliseconds.
@@ -106,10 +116,10 @@ func JSONResponseMiddleware(next http.Handler) http.Handler {
} }
// Add @meta field // Add @meta field
originalResponse["@meta"] = map[string]any{ originalResponse[jsonKeyMeta] = map[string]any{
"time_zone": "UTC", metaKeyTimeZone: "UTC",
"api_version": 1, metaKeyAPIVersion: 1,
"execution_time": fmt.Sprintf("%d ms", execTime.Milliseconds()), metaKeyExecutionTimeMs: execTime.Milliseconds(),
} }
// Write the enhanced response // Write the enhanced response
@@ -145,7 +155,8 @@ func deadlinePassed(ctx context.Context) bool {
// has passed, it answers 504 with the error message "Request timeout". A 4xx // has passed, it answers 504 with the error message "Request timeout". A 4xx
// keeps its status, with the status's standard text as the message. For other // keeps its status, with the status's standard text as the message. For other
// errors, it returns "Internal server error", with status 500 if the original // errors, it returns "Internal server error", with status 500 if the original
// status was 200. // status was 200. A panic in the handler answers 500 with "Internal server
// error" too.
// //
// Non-JSON responses are passed through unchanged. // Non-JSON responses are passed through unchanged.
func JSONValidationMiddleware(next http.Handler) http.Handler { func JSONValidationMiddleware(next http.Handler) http.Handler {
@@ -157,8 +168,9 @@ func JSONValidationMiddleware(next http.Handler) http.Handler {
statusCode: http.StatusOK, statusCode: http.StatusOK,
} }
// Serve the request // Serve the request. Recoverer logs a panic in the handler and turns it
next.ServeHTTP(rw, r) // into a 500 without a body, which gets the JSON error body below.
middleware.Recoverer(next).ServeHTTP(rw, r)
// Check if it's meant to be a JSON response // Check if it's meant to be a JSON response
contentType := rw.Header().Get("Content-Type") contentType := rw.Header().Get("Content-Type")
internal/server/middleware_internal_test.go
+371 -1
View File
@@ -1,25 +1,41 @@
package server package server
import ( import (
"bytes"
"context"
"encoding/json" "encoding/json"
"io"
"log/slog"
"net"
"net/http" "net/http"
"net/http/httptest" "net/http/httptest"
"net/netip" "net/netip"
"os"
"regexp"
"strings" "strings"
"testing" "testing"
"testing/synctest"
"time" "time"
"git.eeqj.de/sneak/routewatch/internal/config"
"git.eeqj.de/sneak/routewatch/internal/database"
"git.eeqj.de/sneak/routewatch/internal/logger"
"git.eeqj.de/sneak/routewatch/internal/metrics"
"git.eeqj.de/sneak/routewatch/internal/streamer"
) )
// The addresses the forwarding tests use: the client a proxy names in // The addresses the forwarding tests use: the client a proxy names in
// X-Forwarded-For, the range of trusted proxies, a peer inside it, and a peer // X-Forwarded-For, the range of trusted proxies, a peer inside it, and a peer
// outside it, which lies in testPrefixV4 so that an IP lookup of it finds a // outside it, which lies in testPrefixV4 so that an IP lookup of it finds a
// route. // route. reverseProxyPeer is a reverse proxy at a private address, as Docker
// gives one.
const ( const (
forwardedClient = "203.0.113.9" forwardedClient = "203.0.113.9"
trustedProxyRange = "10.0.0.0/8" trustedProxyRange = "10.0.0.0/8"
trustedPeer = "10.0.0.2:1234" trustedPeer = "10.0.0.2:1234"
untrustedPeerAddr = "192.0.2.1" untrustedPeerAddr = "192.0.2.1"
untrustedPeer = untrustedPeerAddr + ":1234" untrustedPeer = untrustedPeerAddr + ":1234"
reverseProxyPeer = "172.19.0.14:1234"
) )
// TestResponsesCarrySecurityHeaders checks that a page, a JSON route and a // TestResponsesCarrySecurityHeaders checks that a page, a JSON route and a
@@ -87,6 +103,225 @@ func TestJSONValidationKeeps4xxWithoutBody(t *testing.T) {
checkJSONErrorMessage(t, name, rec, http.StatusText(http.StatusBadRequest)) checkJSONErrorMessage(t, name, rec, http.StatusText(http.StatusBadRequest))
} }
// TestJSONAnswersPutNoUnitInAString sends a request to each JSON route and
// checks each answer. Its @meta.execution_time_ms is a number, and none of its
// strings is a number with a unit, such as "12 ms", "1.1 GB" or "1h18m34s"
// (https://git.eeqj.de/sneak/routewatch/issues/199). The health check answers
// 503, since the stream is not connected, and the last path matches no route.
func TestJSONAnswersPutNoUnitInAString(t *testing.T) {
t.Parallel()
numberWithUnit := regexp.MustCompile(
`^([0-9]+(\.[0-9]+)? ?(ns|µs|ms|s|m|h|B|kB|MB|GB|TB))+$`)
s := newServerWithTestRoutes(t)
useFakeResolver(s, &fakeResolver{})
s.SetASNFetcher(fixedIntervalASNFetcher{interval: time.Second})
paths := []string{
statusJSONPath,
statsPath,
healthCheckPath,
"/api/v1/ip/" + untrustedPeerAddr,
"/ip/" + untrustedPeerAddr,
asJSONPath,
"/api/v1/prefix/" + testPrefixV4,
"/api/v1/search/as?q=google",
"/api/v1/no-such-route",
}
for _, path := range paths {
rec := httptest.NewRecorder()
s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
t.Context(), http.MethodGet, path, nil))
var answer map[string]any
err := json.Unmarshal(rec.Body.Bytes(), &answer)
if err != nil {
t.Errorf("%s: decoding the answer: %v; answer %s", path, err, rec.Body)
continue
}
meta, _ := answer["@meta"].(map[string]any)
if _, ok := meta["execution_time_ms"].(float64); !ok {
t.Errorf("%s: @meta.execution_time_ms is not a number: %s",
path, rec.Body)
}
for _, value := range stringsIn(answer) {
if numberWithUnit.MatchString(value) {
t.Errorf("%s: %q is a number with a unit in a string", path, value)
}
}
}
}
// TestJSONAnswersCarryMeta sends requests to every JSON route through the
// server's router, and checks that each answer carries @meta with its three
// fields. The answers include successes, and errors that the handlers, the
// router and the middleware write. Before the fix a panic in a handler, and a
// method /status.json or the health check does not take, answered with an
// empty body (https://git.eeqj.de/sneak/routewatch/issues/201).
//
// The requests run in a synctest bubble, whose clock is fake, so a stall on
// the host does not use up the 2-second limit of the health check or the
// 4-second limit of the stats handlers.
func TestJSONAnswersCarryMeta(t *testing.T) {
t.Parallel()
// JSON routes whose handlers write nothing or panic, so that the JSON
// check on the route writes the error answer itself.
const (
writesNothingPath = "/writes-nothing.json"
panicsPath = "/panics.json"
)
s := newServerWithTestRoutes(t)
useFakeResolver(s, &fakeResolver{})
s.streamer.GetMetricsTracker().SetConnected(true)
s.router.Get(writesNothingPath, JSONValidationMiddleware(http.HandlerFunc(
func(http.ResponseWriter, *http.Request) {})).ServeHTTP)
s.router.Get(panicsPath, JSONValidationMiddleware(http.HandlerFunc(
func(http.ResponseWriter, *http.Request) { panic(errDiskIO) })).ServeHTTP)
failing := New(failingDB{}, newTestTable(),
streamer.New(logger.New(), metrics.New()), logger.New(), &config.Config{})
useFakeResolver(failing, &fakeResolver{})
tests := []struct {
method string
path string
wantCode int
}{
// Answers that succeed
{http.MethodGet, statusJSONPath, http.StatusOK},
{http.MethodGet, healthCheckPath, http.StatusOK},
{http.MethodGet, "/ip", http.StatusOK},
{http.MethodGet, ownAddressPath, http.StatusOK},
{http.MethodGet, "/ip/" + addrInTestPrefixV4, http.StatusOK},
{http.MethodGet, statsPath, http.StatusOK},
{http.MethodGet, "/api/v1/ip/" + addrInTestPrefixV4, http.StatusOK},
{http.MethodGet, asJSONPath, http.StatusOK},
{http.MethodGet, "/api/v1/prefix/" + testPrefixV4, http.StatusOK},
{http.MethodGet, "/api/v1/search/as?q=google", http.StatusOK},
// Errors the handlers write
{http.MethodGet, "/ip/no-such-host.example", http.StatusBadRequest},
{http.MethodGet, "/api/v1/ip/no-such-host.example", http.StatusBadRequest},
{http.MethodGet, "/api/v1/as/foo", http.StatusBadRequest},
{http.MethodGet, "/api/v1/as/0", http.StatusNotFound},
{http.MethodGet, "/api/v1/prefix/192.0.2.0/33", http.StatusBadRequest},
{http.MethodGet, "/api/v1/prefix/198.51.100.0/24", http.StatusNotFound},
{http.MethodGet, "/api/v1/search/as", http.StatusBadRequest},
// Errors the router and the middleware write
{http.MethodGet, "/api/v1/no-such-route", http.StatusNotFound},
{http.MethodGet, "/ip/192.0.2.1/nothing", http.StatusNotFound},
{http.MethodPost, statsPath, http.StatusMethodNotAllowed},
{http.MethodPost, ownAddressPath, http.StatusMethodNotAllowed},
{http.MethodPost, statusJSONPath, http.StatusMethodNotAllowed},
{http.MethodPut, healthCheckPath, http.StatusMethodNotAllowed},
{http.MethodGet, writesNothingPath, http.StatusInternalServerError},
{http.MethodGet, panicsPath, http.StatusInternalServerError},
}
synctest.Test(t, func(t *testing.T) {
for _, tt := range tests {
checkAnswerCarriesMeta(t, s, httptest.NewRequestWithContext(
t.Context(), tt.method, tt.path, nil), tt.wantCode)
}
// A request whose time limit has already passed answers 504. The
// handlers write the answers of the first five routes, and the JSON
// check on the route writes the last.
pastTimeLimit, cancel := context.WithDeadline(t.Context(), time.Now())
defer cancel()
for _, path := range []string{
statusJSONPath, statsPath, "/ip/" + addrInTestPrefixV4,
"/api/v1/ip/" + addrInTestPrefixV4, asJSONPath, writesNothingPath,
} {
checkAnswerCarriesMeta(t, s, httptest.NewRequestWithContext(
pastTimeLimit, http.MethodGet, path, nil), http.StatusGatewayTimeout)
}
// With a store whose reads fail, the health check answers 503, and
// the handlers of the other routes 500.
checkAnswerCarriesMeta(t, failing, httptest.NewRequestWithContext(
t.Context(), http.MethodGet, healthCheckPath, nil),
http.StatusServiceUnavailable)
for _, path := range []string{
statusJSONPath, statsPath, asJSONPath,
"/api/v1/ip/" + addrInTestPrefixV4, "/ip/" + addrInTestPrefixV4,
} {
checkAnswerCarriesMeta(t, failing, httptest.NewRequestWithContext(
t.Context(), http.MethodGet, path, nil), http.StatusInternalServerError)
}
})
}
// checkAnswerCarriesMeta serves req through the server's router, and checks
// that it answers wantCode with @meta and its three fields.
func checkAnswerCarriesMeta(
t *testing.T, s *Server, req *http.Request, wantCode int,
) {
t.Helper()
// The values README "JSON API" gives the two fields that never change.
const (
wantTimeZone = "UTC"
wantAPIVersion = 1
)
name := req.Method + " " + req.URL.String()
rec := httptest.NewRecorder()
s.router.ServeHTTP(rec, req)
if rec.Code != wantCode {
t.Errorf("%s: status %d, want %d; body %s", name, rec.Code, wantCode, rec.Body)
}
var answer map[string]any
err := json.Unmarshal(rec.Body.Bytes(), &answer)
if err != nil {
t.Errorf("%s: decoding the answer %q: %v", name, rec.Body, err)
return
}
meta, _ := answer[jsonKeyMeta].(map[string]any)
_, timeIsNumber := meta[metaKeyExecutionTimeMs].(float64)
if meta[metaKeyTimeZone] != wantTimeZone ||
meta[metaKeyAPIVersion] != float64(wantAPIVersion) || !timeIsNumber {
t.Errorf("%s: @meta %v, want time_zone %q, api_version %d and a "+
"number in execution_time_ms", name, meta, wantTimeZone, wantAPIVersion)
}
}
// stringsIn returns every string in a decoded JSON value, at any depth.
func stringsIn(value any) []string {
var found []string
switch v := value.(type) {
case string:
found = append(found, v)
case []any:
for _, item := range v {
found = append(found, stringsIn(item)...)
}
case map[string]any:
for _, item := range v {
found = append(found, stringsIn(item)...)
}
}
return found
}
// TestPagesCarryTheCSPNonce checks that every script and style block of each // TestPagesCarryTheCSPNonce checks that every script and style block of each
// page carries the nonce its Content-Security-Policy header names, so that the // page carries the nonce its Content-Security-Policy header names, so that the
// browser runs and applies them, that each answer has a nonce of its own, and // browser runs and applies them, that each answer has a nonce of its own, and
@@ -183,6 +418,141 @@ func TestForwardedForFromUntrustedPeerIsIgnored(t *testing.T) {
} }
} }
// TestDefaultTrustedProxiesGiveTheForwardedClient builds the server from the
// configuration with TRUSTED_PROXIES unset. A request from a reverse proxy at
// a private address must be looked up by /ip/, shown on the home page's card
// and logged as the client its X-Forwarded-For names. A direct request from a
// public address with a forged X-Forwarded-For keeps its own address. Before
// the fix no proxy was trusted unless TRUSTED_PROXIES named it, so /ip/ gave
// the proxy's address (https://git.eeqj.de/sneak/routewatch/issues/198).
func TestDefaultTrustedProxiesGiveTheForwardedClient(t *testing.T) {
t.Setenv("PORT", "")
t.Setenv("XDG_DATA_HOME", "")
// t.Setenv puts the variable back when the test ends.
t.Setenv("TRUSTED_PROXIES", "")
err := os.Unsetenv("TRUSTED_PROXIES")
if err != nil {
t.Fatal(err)
}
cfg, err := config.New()
if err != nil {
t.Fatalf("config.New: %v", err)
}
var requestLog bytes.Buffer
s := newServerWithConfig(t, cfg, &requestLog)
tests := []struct {
name string
peer string
want string
}{
{"through a reverse proxy", reverseProxyPeer, forwardedClient},
{"direct from a public address", untrustedPeer, untrustedPeerAddr},
}
for _, tt := range tests {
requestLog.Reset()
get := func(path string) *httptest.ResponseRecorder {
req := httptest.NewRequestWithContext(t.Context(), http.MethodGet, path, nil)
req.RemoteAddr = tt.peer
req.Header.Set("X-Forwarded-For", forwardedClient)
rec := httptest.NewRecorder()
s.router.ServeHTTP(rec, req)
return rec
}
var answer struct {
Data IPLookupResponse `json:"data"`
}
rec := get("/ip/")
err := json.Unmarshal(rec.Body.Bytes(), &answer)
if err != nil {
t.Fatalf("%s: decoding the answer %q: %v", tt.name, rec.Body, err)
}
if answer.Data.Query != tt.want {
t.Errorf("%s: /ip/ looked up %q, want %q", tt.name, answer.Data.Query, tt.want)
}
page := get("/").Body.String()
if !strings.Contains(page, `data-client-ip="`+tt.want+`"`) {
t.Errorf("%s: the home page's card does not hold %s", tt.name, tt.want)
}
logged := loggedAddresses(requestLog.String())
if len(logged) == 0 {
t.Errorf("%s: the request log names no address", tt.name)
}
for _, addr := range logged {
if addr != tt.want {
t.Errorf("%s: the request log gives %s, want %s", tt.name, addr, tt.want)
}
}
}
}
// newServerWithConfig returns a server built with cfg, on a new database, that
// reads the routes of newTestTable and logs its requests as JSON to
// requestLog.
func newServerWithConfig(
t *testing.T, cfg *config.Config, requestLog io.Writer,
) *Server {
t.Helper()
cfg.StateDir = t.TempDir()
db, err := database.New(cfg, logger.New())
if err != nil {
t.Fatalf("database.New: %v", err)
}
t.Cleanup(func() { _ = db.Close() })
s := New(db, newTestTable(), streamer.New(logger.New(), metrics.New()),
&logger.Logger{Logger: slog.New(slog.NewJSONHandler(requestLog, nil))}, cfg)
useFakeResolver(s, &fakeResolver{})
return s
}
// loggedAddresses returns the address each line of the JSON request log
// names, without the port a direct request is logged with.
func loggedAddresses(requestLog string) []string {
var addrs []string
for line := range strings.Lines(requestLog) {
//nolint:tagliatelle // the field name is the key the request log uses
var entry struct {
RemoteAddr string `json:"remote_addr"`
}
err := json.Unmarshal([]byte(line), &entry)
if err != nil || entry.RemoteAddr == "" {
continue
}
addr, _, err := net.SplitHostPort(entry.RemoteAddr)
if err != nil {
addr = entry.RemoteAddr
}
addrs = append(addrs, addr)
}
return addrs
}
// TestRealIPMiddlewareTrustsOnlyConfiguredProxies checks which address // TestRealIPMiddlewareTrustsOnlyConfiguredProxies checks which address
// RealIPMiddleware gives a request: the TCP peer, unless the peer is a trusted // RealIPMiddleware gives a request: the TCP peer, unless the peer is a trusted
// proxy; then the last X-Forwarded-For entry that is not a trusted proxy, // proxy; then the last X-Forwarded-For entry that is not a trusted proxy,
internal/server/models.go
+28 -21
View File
@@ -38,30 +38,37 @@ type PrefixDistribution struct {
Count int `json:"count"` Count int `json:"count"`
} }
// IPInfo represents comprehensive IP information for the /ip endpoint // IPInfo is what the IP lookup knows about the route of an address and that
// route's origin AS. A field is nil, null in JSON, when its value is not known.
// Every field is nil for an address with no route.
// //
//nolint:tagliatelle // field names are the existing JSON API //nolint:tagliatelle // field names are the existing JSON API
type IPInfo struct { type IPInfo struct {
IP string `json:"ip"` // Netblock is the most specific prefix that holds the address.
Netblock string `json:"netblock"` Netblock *string `json:"netblock"`
MaskLength int `json:"mask_length"` MaskLength *int `json:"mask_length"`
IPVersion int `json:"ip_version"` IPVersion *int `json:"ip_version"`
NumPeers int `json:"num_peers"` NumPeers *int `json:"num_peers"`
// AS information // ASN is the origin AS that the most peers carry the netblock with.
ASN int `json:"asn"` ASN *int `json:"asn"`
ASName string `json:"as_name,omitempty"` // NumOrigins and OriginASNs are how many origin ASes peers carry the
Handle string `json:"handle,omitempty"` // netblock with, and which, in AS number order.
Description string `json:"description,omitempty"` NumOrigins *int `json:"num_origins"`
OrgName string `json:"org_name,omitempty"` OriginASNs []int `json:"origin_asns"`
OrgID string `json:"org_id,omitempty"` // The details the database holds about the AS in ASN.
Address string `json:"address,omitempty"` ASName *string `json:"as_name"`
CountryCode string `json:"country_code,omitempty"` Handle *string `json:"handle"`
AbuseEmail string `json:"abuse_email,omitempty"` Description *string `json:"description"`
RIR string `json:"rir,omitempty"` OrgName *string `json:"org_name"`
// Timestamps. LastSeen is zero, and left out of JSON, when the prefix OrgID *string `json:"org_id"`
// keeps no route. Address *string `json:"address"`
FirstSeen time.Time `json:"first_seen"` CountryCode *string `json:"country_code"`
LastSeen time.Time `json:"last_seen,omitzero"` AbuseEmail *string `json:"abuse_email"`
RIR *string `json:"rir"`
// FirstSeen is when RouteWatch first saw the netblock. LastSeen is the
// time of the netblock's newest kept route.
FirstSeen *time.Time `json:"first_seen"`
LastSeen *time.Time `json:"last_seen"`
// Indicates if WHOIS data needs refresh (not serialized) // Indicates if WHOIS data needs refresh (not serialized)
NeedsWHOISRefresh bool `json:"-"` NeedsWHOISRefresh bool `json:"-"`
} }
internal/server/prefix_originchanges_internal_test.go
+230
View File
@@ -0,0 +1,230 @@
package server
import (
"fmt"
"net/http"
"net/http/httptest"
"net/netip"
"strings"
"testing"
"git.eeqj.de/sneak/routewatch/internal/config"
"git.eeqj.de/sneak/routewatch/internal/database"
"git.eeqj.de/sneak/routewatch/internal/logger"
"git.eeqj.de/sneak/routewatch/internal/metrics"
"git.eeqj.de/sneak/routewatch/internal/ristypes"
"git.eeqj.de/sneak/routewatch/internal/routetable"
"git.eeqj.de/sneak/routewatch/internal/streamer"
)
// testUncarriedASN is an AS the test's routing table does not carry for the prefix.
const testUncarriedASN = 64501
// newPrefixDetailServer returns a server whose routing table holds testPrefixV4
// with origin AS 64500, and whose database holds the given origin changes.
func newPrefixDetailServer(
t *testing.T, changes []routetable.OriginChange,
) *Server {
t.Helper()
db, err := database.New(&config.Config{StateDir: t.TempDir()}, logger.New())
if err != nil {
t.Fatalf("database.New: %v", err)
}
t.Cleanup(func() { _ = db.Close() })
table := emptyTable()
announce(table, testPrefixV4, 64500, testPeer(1), testRouteTime(0))
err = db.WriteOriginChanges(changes)
if err != nil {
t.Fatalf("WriteOriginChanges: %v", err)
}
return New(db, table, streamer.New(logger.New(), metrics.New()),
logger.New(), &config.Config{})
}
// TestPrefixDetailShowsOriginChanges checks that the prefix page shows the
// origin changes newest first, with the announced and withdrawn rows and the
// AS link. The rows use an AS the routing table does not carry for the
// prefix, so the link comes from the origin changes table.
func TestPrefixDetailShowsOriginChanges(t *testing.T) {
t.Parallel()
prefix := netip.MustParsePrefix(testPrefixV4)
s := newPrefixDetailServer(t, []routetable.OriginChange{
{Prefix: prefix, OriginASN: testUncarriedASN, Announced: true,
PeerCount: 1, Time: testRouteTime(1)},
{Prefix: prefix, OriginASN: testUncarriedASN, Announced: false,
PeerCount: 0, Time: testRouteTime(2)},
})
rec := httptest.NewRecorder()
s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
t.Context(), http.MethodGet, "/prefix/"+testPrefixV4, nil))
if rec.Code != http.StatusOK {
t.Fatalf("status %d, want %d; body %s", rec.Code, http.StatusOK, rec.Body)
}
page := rec.Body.String()
withdrawn := strings.Index(page, "Withdrawn")
announced := strings.Index(page, "Announced")
if withdrawn < 0 || announced < 0 {
t.Fatalf("page does not show the announced and withdrawn rows")
}
// The withdrawn row is newer, so it comes first.
if withdrawn > announced {
t.Errorf("the withdrawn row is not shown before the announced row")
}
if !strings.Contains(page, `href="/as/64501"`) {
t.Errorf("page does not link to AS64501")
}
}
// TestPrefixDetailShowsOriginZeroAsNoKnownOrigin checks that the origin
// changes table shows AS 0 as no known origin, without a link to AS0.
func TestPrefixDetailShowsOriginZeroAsNoKnownOrigin(t *testing.T) {
t.Parallel()
prefix := netip.MustParsePrefix(testPrefixV4)
s := newPrefixDetailServer(t, []routetable.OriginChange{
{Prefix: prefix, OriginASN: ristypes.NoOrigin, Announced: true,
PeerCount: 1, Time: testRouteTime(1)},
})
rec := httptest.NewRecorder()
s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
t.Context(), http.MethodGet, "/prefix/"+testPrefixV4, nil))
if rec.Code != http.StatusOK {
t.Fatalf("status %d, want %d; body %s", rec.Code, http.StatusOK, rec.Body)
}
page := rec.Body.String()
if !strings.Contains(page, "No known origin") {
t.Errorf("page does not say the origin change has no known origin")
}
if strings.Contains(page, `href="/as/0"`) {
t.Errorf("page links to AS0")
}
}
// TestPrefixDetailSaysWhenThereAreMoreChangesThanItShows checks that the
// prefix page says so when a prefix has more origin changes than the page's
// limit.
func TestPrefixDetailSaysWhenThereAreMoreChangesThanItShows(t *testing.T) {
t.Parallel()
prefix := netip.MustParsePrefix(testPrefixV4)
changes := make([]routetable.OriginChange, 0, maxOriginChangesOnPage+1)
for i := range maxOriginChangesOnPage + 1 {
changes = append(changes, routetable.OriginChange{
Prefix: prefix, OriginASN: 64500, Announced: true, PeerCount: 1,
Time: testRouteTime(i),
})
}
s := newPrefixDetailServer(t, changes)
rec := httptest.NewRecorder()
s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
t.Context(), http.MethodGet, "/prefix/"+testPrefixV4, nil))
if rec.Code != http.StatusOK {
t.Fatalf("status %d, want %d; body %s", rec.Code, http.StatusOK, rec.Body)
}
page := rec.Body.String()
note := fmt.Sprintf("more than %d changes", maxOriginChangesOnPage)
if !strings.Contains(page, note) {
t.Errorf("page does not say there are more than %d changes",
maxOriginChangesOnPage)
}
if got := strings.Count(page, "<td>Announced</td>"); got != maxOriginChangesOnPage {
t.Errorf("page shows %d change rows, want %d", got,
maxOriginChangesOnPage)
}
}
// TestPrefixDetailShowsNoNoteAtTheLimit checks that a prefix with exactly the
// page's limit of origin changes shows all of them and no note.
func TestPrefixDetailShowsNoNoteAtTheLimit(t *testing.T) {
t.Parallel()
prefix := netip.MustParsePrefix(testPrefixV4)
changes := make([]routetable.OriginChange, 0, maxOriginChangesOnPage)
for i := range maxOriginChangesOnPage {
changes = append(changes, routetable.OriginChange{
Prefix: prefix, OriginASN: 64500, Announced: true, PeerCount: 1,
Time: testRouteTime(i),
})
}
s := newPrefixDetailServer(t, changes)
rec := httptest.NewRecorder()
s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
t.Context(), http.MethodGet, "/prefix/"+testPrefixV4, nil))
if rec.Code != http.StatusOK {
t.Fatalf("status %d, want %d; body %s", rec.Code, http.StatusOK, rec.Body)
}
page := rec.Body.String()
if strings.Contains(page, "more than") {
t.Errorf("page says there are more changes, but a prefix has %d",
maxOriginChangesOnPage)
}
if got := strings.Count(page, "<td>Announced</td>"); got != maxOriginChangesOnPage {
t.Errorf("page shows %d change rows, want %d", got,
maxOriginChangesOnPage)
}
}
// TestPrefixDetailShowsOriginChangeTimeAndPeerCount checks that a row shows
// its time and its peer count.
func TestPrefixDetailShowsOriginChangeTimeAndPeerCount(t *testing.T) {
t.Parallel()
prefix := netip.MustParsePrefix(testPrefixV4)
s := newPrefixDetailServer(t, []routetable.OriginChange{
{Prefix: prefix, OriginASN: 64500, Announced: true, PeerCount: 7,
Time: testRouteTime(5)},
})
rec := httptest.NewRecorder()
s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
t.Context(), http.MethodGet, "/prefix/"+testPrefixV4, nil))
if rec.Code != http.StatusOK {
t.Fatalf("status %d, want %d; body %s", rec.Code, http.StatusOK, rec.Body)
}
page := rec.Body.String()
if !strings.Contains(page, "2026-01-02 03:09:05") {
t.Errorf("page does not show the origin change's time")
}
if !strings.Contains(page, "<td>7</td>") {
t.Errorf("page does not show the origin change's peer count")
}
}
internal/server/routes.go
+30 -7
View File
@@ -8,8 +8,8 @@ import (
"github.com/go-chi/chi/v5/middleware" "github.com/go-chi/chi/v5/middleware"
) )
// The error messages the JSON routes under /api/v1 and /ip answer with when no // The error messages the JSON routes answer with when no route matches the
// route matches the path, and when none takes the method. // path, and when the route does not take the method.
const ( const (
notFoundMessage = "Not found" notFoundMessage = "Not found"
methodNotAllowedMessage = "Method not allowed" methodNotAllowedMessage = "Method not allowed"
@@ -19,6 +19,13 @@ const (
jsonRoutesAllow = "GET, HEAD" jsonRoutesAllow = "GET, HEAD"
) )
// The paths of the status figures and the health check, the two JSON routes
// outside /api/v1 and /ip.
const (
statusJSONPath = "/status.json"
healthCheckPath = "/.well-known/healthcheck.json"
)
// setupRoutes configures the HTTP routes // setupRoutes configures the HTTP routes
func (s *Server) setupRoutes() { func (s *Server) setupRoutes() {
r := chi.NewRouter() r := chi.NewRouter()
@@ -32,6 +39,8 @@ func (s *Server) setupRoutes() {
r.Use(middleware.RequestID) r.Use(middleware.RequestID)
r.Use(RealIPMiddleware(s.trustedProxies)) r.Use(RealIPMiddleware(s.trustedProxies))
r.Use(RequestLoggerMiddleware(s.logger.Logger)) // Structured request logging r.Use(RequestLoggerMiddleware(s.logger.Logger)) // Structured request logging
// Recoverer answers a panic on a page. JSONValidationMiddleware recovers a
// panic on a JSON route itself, so that the answer is JSON with @meta.
r.Use(middleware.Recoverer) r.Use(middleware.Recoverer)
r.Use(JSONResponseMiddleware) r.Use(JSONResponseMiddleware)
// Timeout must come after JSONResponseMiddleware, which sends its answer // Timeout must come after JSONResponseMiddleware, which sends its answer
@@ -43,11 +52,6 @@ func (s *Server) setupRoutes() {
// Routes // Routes
r.Get("/", s.handleIndex()) r.Get("/", s.handleIndex())
r.Get("/status", s.handleStatusHTML()) r.Get("/status", s.handleStatusHTML())
r.Get("/status.json", JSONValidationMiddleware(s.handleStatusJSON()).ServeHTTP)
r.Get(
"/.well-known/healthcheck.json",
JSONValidationMiddleware(s.handleHealthCheck()).ServeHTTP,
)
// AS and prefix detail pages // AS and prefix detail pages
r.Get("/as/{asn}", s.handleASDetail()) r.Get("/as/{asn}", s.handleASDetail())
@@ -55,6 +59,10 @@ func (s *Server) setupRoutes() {
r.Get("/prefixlength/{length}", s.handlePrefixLength()) r.Get("/prefixlength/{length}", s.handlePrefixLength())
r.Get("/prefixlength6/{length}", s.handlePrefixLength6()) r.Get("/prefixlength6/{length}", s.handlePrefixLength6())
// The pages that list what two of the home page's cards count
r.Get("/bogons", s.handleBogons())
r.Get("/multiple-origins", s.handleMultipleOrigins())
// The JSON routes answer a path or method they do not take with the JSON // The JSON routes answer a path or method they do not take with the JSON
// error body, as they answer everything else. // error body, as they answer everything else.
jsonNotFound := func(w http.ResponseWriter, _ *http.Request) { jsonNotFound := func(w http.ResponseWriter, _ *http.Request) {
@@ -66,6 +74,21 @@ func (s *Server) setupRoutes() {
s.writeJSONError(w, http.StatusMethodNotAllowed, methodNotAllowedMessage) s.writeJSONError(w, http.StatusMethodNotAllowed, methodNotAllowedMessage)
} }
// The status figures and the health check. chi sets one 405 answer for a
// whole router. These two routes are on the pages' router, whose 405 stays
// chi's own. So each method they do not take is routed to the JSON 405
// here.
r.Get(statusJSONPath, JSONValidationMiddleware(s.handleStatusJSON()).ServeHTTP)
r.Get(healthCheckPath, JSONValidationMiddleware(s.handleHealthCheck()).ServeHTTP)
for _, method := range []string{
http.MethodPost, http.MethodPut, http.MethodPatch, http.MethodDelete,
http.MethodOptions, http.MethodTrace, http.MethodConnect,
} {
r.MethodFunc(method, statusJSONPath, jsonMethodNotAllowed)
r.MethodFunc(method, healthCheckPath, jsonMethodNotAllowed)
}
// IP info JSON endpoints (replaces old /ip redirect) // IP info JSON endpoints (replaces old /ip redirect)
r.Route("/ip", func(r chi.Router) { r.Route("/ip", func(r chi.Router) {
r.Use(JSONValidationMiddleware) r.Use(JSONValidationMiddleware)
internal/server/routes_internal_test.go
+24 -4
View File
@@ -5,6 +5,7 @@ import (
"net/http" "net/http"
"net/http/httptest" "net/http/httptest"
"testing" "testing"
"testing/synctest"
) )
// TestRoutesAnswerHEAD sends HEAD for a page and JSON routes through the // TestRoutesAnswerHEAD sends HEAD for a page and JSON routes through the
@@ -12,15 +13,23 @@ import (
// lookup of the caller's own address, are in the list because chi's GetHead // lookup of the caller's own address, are in the list because chi's GetHead
// does not reach them. Before the fix every route answered HEAD with 405 // does not reach them. Before the fix every route answered HEAD with 405
// (https://git.eeqj.de/sneak/routewatch/issues/111). // (https://git.eeqj.de/sneak/routewatch/issues/111).
//
// The requests run in a synctest bubble, whose clock is fake, so a stall on
// the host does not use up the stats handlers' 4-second limit. The resolver
// is fake because no time limit would cut off a real DNS lookup in a bubble.
func TestRoutesAnswerHEAD(t *testing.T) { func TestRoutesAnswerHEAD(t *testing.T) {
t.Parallel() t.Parallel()
s := newServerWithTestRoutes(t) s := newServerWithTestRoutes(t)
s.resolver = &fakeResolver{}
for _, path := range []string{"/", statsPath, "/ip", "/ip/"} { for _, path := range []string{"/", statusJSONPath, statsPath, "/ip", "/ip/"} {
rec := httptest.NewRecorder() rec := httptest.NewRecorder()
s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
t.Context(), http.MethodHead, path, nil)) synctest.Test(t, func(t *testing.T) {
s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
t.Context(), http.MethodHead, path, nil))
})
if rec.Code != http.StatusOK { if rec.Code != http.StatusOK {
t.Errorf("HEAD %s: status %d, want %d; body %s", t.Errorf("HEAD %s: status %d, want %d; body %s",
@@ -31,10 +40,13 @@ func TestRoutesAnswerHEAD(t *testing.T) {
// TestJSONRoutesAnswerUnmatchedRequestsWithJSONErrors sends a method the JSON // TestJSONRoutesAnswerUnmatchedRequestsWithJSONErrors sends a method the JSON
// routes do not take, and a path none of them matches, to each group of JSON // routes do not take, and a path none of them matches, to each group of JSON
// routes through the server's router. Each must answer with the JSON error // routes through the server's router. It also sends a method they do not take
// to /status.json and the health check. Each must answer with the JSON error
// body, and a 405 must name the methods the routes take in its Allow header. // body, and a 405 must name the methods the routes take in its Allow header.
// Before the fix a 405 said "Internal server error" and a 404 was chi's plain // Before the fix a 405 said "Internal server error" and a 404 was chi's plain
// text answer (https://git.eeqj.de/sneak/routewatch/issues/111). // text answer (https://git.eeqj.de/sneak/routewatch/issues/111).
// /status.json and the health check gave chi's empty 405
// (https://git.eeqj.de/sneak/routewatch/issues/201).
func TestJSONRoutesAnswerUnmatchedRequestsWithJSONErrors(t *testing.T) { func TestJSONRoutesAnswerUnmatchedRequestsWithJSONErrors(t *testing.T) {
t.Parallel() t.Parallel()
@@ -48,6 +60,14 @@ func TestJSONRoutesAnswerUnmatchedRequestsWithJSONErrors(t *testing.T) {
}{ }{
{http.MethodPost, statsPath, http.StatusMethodNotAllowed, methodNotAllowedMessage}, {http.MethodPost, statsPath, http.StatusMethodNotAllowed, methodNotAllowedMessage},
{http.MethodPost, "/ip/", http.StatusMethodNotAllowed, methodNotAllowedMessage}, {http.MethodPost, "/ip/", http.StatusMethodNotAllowed, methodNotAllowedMessage},
{
http.MethodDelete, statusJSONPath,
http.StatusMethodNotAllowed, methodNotAllowedMessage,
},
{
http.MethodOptions, healthCheckPath,
http.StatusMethodNotAllowed, methodNotAllowedMessage,
},
{http.MethodGet, "/api/v1/nothing", http.StatusNotFound, notFoundMessage}, {http.MethodGet, "/api/v1/nothing", http.StatusNotFound, notFoundMessage},
{http.MethodGet, "/ip/192.0.2.1/nothing", http.StatusNotFound, notFoundMessage}, {http.MethodGet, "/ip/192.0.2.1/nothing", http.StatusNotFound, notFoundMessage},
} }
internal/server/server.go
+84 -19
View File
@@ -1,12 +1,14 @@
// Package server serves RouteWatch's web pages and JSON API: // Package server serves RouteWatch's web pages and JSON API:
// - the home page, the status figures and the health check // - the home page, the status figures and the health check
// - the pages that list the bogon announcements and the prefixes announced
// by more than one origin AS
// - the AS, prefix and prefix length pages, and the JSON answers behind them // - the AS, prefix and prefix length pages, and the JSON answers behind them
// - the IP lookups // - the IP lookups
// - the AS name search // - the AS name search
// //
// Every route it shows comes from the routing table in memory. AS names, // Every route it shows comes from the routing table in memory. AS names,
// WHOIS details and the times a prefix and an AS were first seen come from // WHOIS details, the times a prefix and an AS were first seen, and a prefix's
// the database. // origin changes come from the database.
package server package server
import ( import (
@@ -17,11 +19,13 @@ import (
"net/http" "net/http"
"net/netip" "net/netip"
"strconv" "strconv"
"sync/atomic"
"time" "time"
"git.eeqj.de/sneak/routewatch/internal/blocklist"
"git.eeqj.de/sneak/routewatch/internal/config" "git.eeqj.de/sneak/routewatch/internal/config"
"git.eeqj.de/sneak/routewatch/internal/database" "git.eeqj.de/sneak/routewatch/internal/database"
"git.eeqj.de/sneak/routewatch/internal/geo"
"git.eeqj.de/sneak/routewatch/internal/iplist"
"git.eeqj.de/sneak/routewatch/internal/logger" "git.eeqj.de/sneak/routewatch/internal/logger"
"git.eeqj.de/sneak/routewatch/internal/routetable" "git.eeqj.de/sneak/routewatch/internal/routetable"
"git.eeqj.de/sneak/routewatch/internal/streamer" "git.eeqj.de/sneak/routewatch/internal/streamer"
@@ -42,20 +46,30 @@ type ASNFetcher interface {
GetStats() ASNFetcherStats GetStats() ASNFetcherStats
} }
// Blocklists tells which public blocklists list an address, from copies it // IPLists tells which public IP lists contain an address, from copies it keeps
// keeps in memory, as *blocklist.Blocklists does. // in memory, as *iplist.IPLists does.
type Blocklists interface { type IPLists interface {
Lookup(addr netip.Addr) []blocklist.Listing Lookup(addr netip.Addr) []iplist.Listing
ShortestInterval() time.Duration ShortestInterval() time.Duration
} }
// dnsResolver looks up the addresses of host names and the names of addresses // dnsResolver looks up the addresses of host names in DNS, as *net.Resolver
// in DNS, as *net.Resolver does. // does.
type dnsResolver interface { type dnsResolver interface {
LookupHost(ctx context.Context, host string) ([]string, error) LookupHost(ctx context.Context, host string) ([]string, error)
}
// PTRResolver looks up the PTR names of addresses, as *ptr.Cache does.
type PTRResolver interface {
LookupAddr(ctx context.Context, addr string) ([]string, error) LookupAddr(ctx context.Context, addr string) ([]string, error)
} }
// GeoLocator finds where addresses are, as *geo.Locator does. It returns one
// entry for each address, nil when no source answers.
type GeoLocator interface {
Lookup(ctx context.Context, addrs []netip.Addr) []*geo.Location
}
// Server provides HTTP endpoints for status monitoring // Server provides HTTP endpoints for status monitoring
type Server struct { type Server struct {
router *chi.Mux router *chi.Mux
@@ -66,15 +80,32 @@ type Server struct {
port int port int
srv *http.Server srv *http.Server
asnFetcher ASNFetcher asnFetcher ASNFetcher
blocklists Blocklists ipLists IPLists
// trustedProxies are the reverse proxies whose X-Forwarded-For header // trustedProxies are the reverse proxies whose X-Forwarded-For header
// RealIPMiddleware believes // RealIPMiddleware believes
trustedProxies []netip.Prefix trustedProxies []netip.Prefix
// resolver makes the IP lookup's DNS lookups: net.DefaultResolver, or a // resolver looks up the IP lookup's host names: net.DefaultResolver, or a
// fake in tests // fake in tests
resolver dnsResolver resolver dnsResolver
// ptrResolver looks up the IP lookup's PTR names. SetPTRResolver sets it.
ptrResolver PTRResolver
// geoLocator finds where the IP lookup's addresses are. SetGeoLocator
// sets it.
geoLocator GeoLocator
// cards is the copy of the home page's cards that the pages serve, nil
// until the server first works them out
cards atomic.Pointer[homeCards]
// stopCards ends the goroutine that works out the cards, and
// cardsStopped is closed once it has returned. Both are nil until Start
// starts the goroutine.
stopCards context.CancelFunc
cardsStopped chan struct{}
} }
// New creates a new HTTP server that reads routes from table, the routing // New creates a new HTTP server that reads routes from table, the routing
@@ -103,7 +134,9 @@ func New(
// Start listens on the configured port and serves HTTP in the background. // Start listens on the configured port and serves HTTP in the background.
// It returns an error if it cannot listen, for example because the port is // It returns an error if it cannot listen, for example because the port is
// already in use. ctx bounds only opening the port, not serving. // already in use. ctx bounds opening the port, not serving. Once listening,
// the server works out the home page's cards every minute until Stop: the end
// of ctx does not stop it.
func (s *Server) Start(ctx context.Context) error { func (s *Server) Start(ctx context.Context) error {
const ( const (
network = "tcp" network = "tcp"
@@ -140,12 +173,22 @@ func (s *Server) Start(ctx context.Context) error {
} }
}() }()
ctx, s.stopCards = context.WithCancel(context.WithoutCancel(ctx))
s.cardsStopped = make(chan struct{})
go func() {
defer close(s.cardsStopped)
s.keepHomeCardsFresh(ctx, homeCardsRefreshInterval)
}()
return nil return nil
} }
// Stop stops the HTTP server. It waits, until ctx ends, for the requests in // Stop stops the goroutine that works out the home page's cards, and waits
// progress to finish, and then closes the connections of those still running // until it has returned or ctx ends. It then stops the HTTP server. It waits,
// and returns ctx's error. // until ctx ends, for the requests in progress to finish, and then closes the
// connections of those still running and returns ctx's error.
func (s *Server) Stop(ctx context.Context) error { func (s *Server) Stop(ctx context.Context) error {
if s.srv == nil { if s.srv == nil {
return nil return nil
@@ -153,6 +196,16 @@ func (s *Server) Stop(ctx context.Context) error {
s.logger.Info("Stopping HTTP server") s.logger.Info("Stopping HTTP server")
// Start returns before it starts the goroutine when it cannot listen.
if s.stopCards != nil {
s.stopCards()
select {
case <-s.cardsStopped:
case <-ctx.Done():
}
}
err := s.srv.Shutdown(ctx) err := s.srv.Shutdown(ctx)
if err != nil { if err != nil {
return errors.Join(err, s.srv.Close()) return errors.Join(err, s.srv.Close())
@@ -161,14 +214,26 @@ func (s *Server) Stop(ctx context.Context) error {
return nil return nil
} }
// SetPTRResolver sets what looks up the IP lookup's PTR names. Call it before
// Start: the handlers read it without a lock.
func (s *Server) SetPTRResolver(resolver PTRResolver) {
s.ptrResolver = resolver
}
// SetGeoLocator sets what finds where the IP lookup's addresses are. Call it
// before Start: the handlers read it without a lock.
func (s *Server) SetGeoLocator(locator GeoLocator) {
s.geoLocator = locator
}
// SetASNFetcher sets the ASN WHOIS fetcher for on-demand lookups. Call it // SetASNFetcher sets the ASN WHOIS fetcher for on-demand lookups. Call it
// before Start: the handlers read the fetcher without a lock. // before Start: the handlers read the fetcher without a lock.
func (s *Server) SetASNFetcher(fetcher ASNFetcher) { func (s *Server) SetASNFetcher(fetcher ASNFetcher) {
s.asnFetcher = fetcher s.asnFetcher = fetcher
} }
// SetBlocklists sets the blocklists the IP lookups report. Call it before // SetIPLists sets the IP lists the IP lookups report. Call it before Start:
// Start: the handlers read the blocklists without a lock. // the handlers read the IP lists without a lock.
func (s *Server) SetBlocklists(blocklists Blocklists) { func (s *Server) SetIPLists(ipLists IPLists) {
s.blocklists = blocklists s.ipLists = ipLists
} }
internal/server/server_internal_test.go
+2 -2
View File
@@ -22,10 +22,10 @@ func TestStopClosesTheConnectionOfARequestStillRunning(t *testing.T) {
stopDeadline = 100 * time.Millisecond stopDeadline = 100 * time.Millisecond
// waitTimeout is how long the test waits for the request to reach // waitTimeout is how long the test waits for the request to reach
// the handler, and then for the client to see its connection closed. // the handler, and then for the client to see its connection closed.
waitTimeout = 2 * time.Second waitTimeout = 15 * time.Second
// readHeaderTimeout bounds the test server's read of the request // readHeaderTimeout bounds the test server's read of the request
// header, as every http.Server must. // header, as every http.Server must.
readHeaderTimeout = time.Second readHeaderTimeout = waitTimeout
) )
release := make(chan struct{}) release := make(chan struct{})
internal/streamer/streamer.go
+22 -45
View File
@@ -12,7 +12,6 @@ import (
"fmt" "fmt"
"io" "io"
"math" "math"
"math/rand"
"net/http" "net/http"
"sync" "sync"
"sync/atomic" "sync/atomic"
@@ -58,10 +57,6 @@ const (
// Well above an extended BGP message (RFC 8654) in hex plus its prefixes // Well above an extended BGP message (RFC 8654) in hex plus its prefixes
maxLineSize = bytesPerMB maxLineSize = bytesPerMB
maxConcurrentHandlers = 800 // Maximum number of concurrent message handlers maxConcurrentHandlers = 800 // Maximum number of concurrent message handlers
// Backpressure constants
backpressureThreshold = 0.5 // Start dropping at 50% queue utilization
backpressureSlope = 2.0 // Slope for linear drop probability increase
) )
// messageTypeNotification is the type of a BGP NOTIFICATION message, which ends // messageTypeNotification is the type of a BGP NOTIFICATION message, which ends
@@ -93,9 +88,8 @@ type MessageHandler interface {
// QueueCapacity returns the desired queue capacity for this handler. // QueueCapacity returns the desired queue capacity for this handler.
// Handlers that process quickly can have larger queues to buffer bursts. // Handlers that process quickly can have larger queues to buffer bursts.
// When the queue fills up, messages will be dropped according to the // While the queue is full, the streamer drops the handler's messages,
// backpressure algorithm, except STATE messages, which are held until // except STATE messages, which are held until there is room.
// there is room.
QueueCapacity() int QueueCapacity() int
} }
@@ -126,8 +120,8 @@ type handlerInfo struct {
// Streamer manages a connection to the RIPE RIS Live streaming API for receiving // Streamer manages a connection to the RIPE RIS Live streaming API for receiving
// real-time BGP UPDATE messages. It handles automatic reconnection with exponential // real-time BGP UPDATE messages. It handles automatic reconnection with exponential
// backoff, dispatches messages to registered handlers via per-handler queues, and // backoff and dispatches messages to registered handlers via per-handler queues.
// implements backpressure to prevent queue overflow during high traffic periods. // Its read loop never waits for room on a queue (see queueMessage).
type Streamer struct { type Streamer struct {
logger *logger.Logger logger *logger.Logger
client *http.Client client *http.Client
@@ -144,7 +138,6 @@ type Streamer struct {
workers sync.WaitGroup // the handler workers; Stop waits for them workers sync.WaitGroup // the handler workers; Stop waits for them
metrics *metrics.Tracker metrics *metrics.Tracker
totalDropped atomic.Uint64 // Total dropped messages across all handlers totalDropped atomic.Uint64 // Total dropped messages across all handlers
random *rand.Rand // Random number generator for backpressure drops
bgpPeers map[string]bool // Track active BGP peers by peer IP bgpPeers map[string]bool // Track active BGP peers by peer IP
bgpPeersMu sync.RWMutex // Protects bgpPeers map bgpPeersMu sync.RWMutex // Protects bgpPeers map
} }
@@ -168,8 +161,6 @@ func New(logger *logger.Logger, metrics *metrics.Tracker) *Streamer {
}, },
handlers: make([]*handlerInfo, 0), handlers: make([]*handlerInfo, 0),
metrics: metrics, metrics: metrics,
//nolint:gosec // Non-cryptographic randomness is fine for backpressure
random: rand.New(rand.NewSource(time.Now().UnixNano())),
bgpPeers: make(map[string]bool), bgpPeers: make(map[string]bool),
} }
} }
@@ -351,6 +342,10 @@ type HandlerStats struct {
AvgProcessTime time.Duration AvgProcessTime time.Duration
MinProcessTime time.Duration MinProcessTime time.Duration
MaxProcessTime time.Duration MaxProcessTime time.Duration
// HeldBackCount is how many messages the handler holds back to apply
// later: what its HeldBackCount method returns, or 0 for a handler
// without one.
HeldBackCount int
} }
// GetHandlerStats returns a snapshot of performance statistics for all registered // GetHandlerStats returns a snapshot of performance statistics for all registered
@@ -392,6 +387,11 @@ func (s *Streamer) GetHandlerStats() []HandlerStats {
info.metrics.mu.Unlock() info.metrics.mu.Unlock()
holder, holdsBack := info.handler.(interface{ HeldBackCount() int })
if holdsBack {
hs.HeldBackCount = holder.HeldBackCount()
}
stats = append(stats, hs) stats = append(stats, hs)
} }
@@ -399,7 +399,7 @@ func (s *Streamer) GetHandlerStats() []HandlerStats {
} }
// GetDroppedMessages returns the total number of messages dropped across all // GetDroppedMessages returns the total number of messages dropped across all
// handlers due to queue overflow or backpressure. This counter is monotonically // handlers because their queue was full. This counter is monotonically
// increasing and is safe to call concurrently. // increasing and is safe to call concurrently.
func (s *Streamer) GetDroppedMessages() uint64 { func (s *Streamer) GetDroppedMessages() uint64 {
return s.totalDropped.Load() return s.totalDropped.Load()
@@ -882,13 +882,13 @@ func (s *Streamer) dispatchMessage(
// msg instead. It never waits for room, so a full queue does not hold up the // msg instead. It never waits for room, so a full queue does not hold up the
// read loop. // read loop.
// //
// A message is dropped while the queue is filling up (shouldDropForBackpressure) // A message that finds the queue full is dropped, except a STATE message. A
// or full, except a STATE message: one whose state is down is the only notice // STATE message whose state is down is the only notice that all of a peer's
// that all of a peer's routes are gone. A STATE message skips the random drop, // routes are gone. A STATE message that finds the queue full is held in
// and one that finds the queue full is held in info.heldState. Held messages // info.heldState instead. Held messages go into the queue, oldest first, when a
// go into the queue, oldest first, before anything else for the handler, as // later message for the handler finds room, or when Stop is called. While any
// soon as there is room, or when Stop is called; while any is still held, the // message is held, the handler's other messages are dropped, so none of them
// handler's other messages are dropped, so none of them overtakes a held down. // overtakes a held STATE message.
// //
// The held list stays small: a STATE message is a few hundred bytes and the // The held list stays small: a STATE message is a few hundred bytes and the
// feed sends about ten a second, so a queue full for a minute holds about 600. // feed sends about ten a second, so a queue full for a minute holds about 600.
@@ -907,7 +907,7 @@ func (s *Streamer) queueMessage(
return true return true
} }
if len(info.heldState) > 0 || s.shouldDropForBackpressure(info) { if len(info.heldState) > 0 {
return false return false
} }
@@ -923,26 +923,3 @@ func trySend(queue chan *ristypes.RISMessage, msg *ristypes.RISMessage) bool {
return false return false
} }
} }
// shouldDropForBackpressure determines if a message should be dropped based on
// queue utilization
func (s *Streamer) shouldDropForBackpressure(info *handlerInfo) bool {
// Calculate queue utilization
queueLen := len(info.queue)
queueCap := cap(info.queue)
utilization := float64(queueLen) / float64(queueCap)
// No drops below threshold
if utilization < backpressureThreshold {
return false
}
// Calculate drop probability (0.0 at threshold, 1.0 at 100% full)
dropProbability := (utilization - backpressureThreshold) * backpressureSlope
if dropProbability > 1.0 {
dropProbability = 1.0
}
// Random drop based on probability
return s.random.Float64() < dropProbability
}
internal/streamer/streamer_internal_test.go
+190 -73
View File
@@ -5,6 +5,7 @@ import (
"context" "context"
"encoding/json" "encoding/json"
"errors" "errors"
"fmt"
"io" "io"
"log/slog" "log/slog"
"net/http" "net/http"
@@ -13,6 +14,7 @@ import (
"strings" "strings"
"sync/atomic" "sync/atomic"
"testing" "testing"
"testing/synctest"
"time" "time"
"git.eeqj.de/sneak/routewatch/internal/logger" "git.eeqj.de/sneak/routewatch/internal/logger"
@@ -258,6 +260,65 @@ func TestHeldStateMessagesKeepTheirPlaceInTheQueue(t *testing.T) {
} }
} }
// burstQueueCapacity is the size of a burstHandler's queue.
const burstQueueCapacity = 1000
// burstHandler wants UPDATE messages and has a queue of burstQueueCapacity.
// Tests read what it is handed from its queue, so HandleMessage does nothing.
type burstHandler struct{}
func (burstHandler) WantsMessage(messageType string) bool {
return messageType == ristypes.MessageTypeUpdate
}
func (burstHandler) QueueCapacity() int { return burstQueueCapacity }
func (burstHandler) HandleMessage(*ristypes.RISMessage) {}
// TestUpdatesDroppedOnlyWhenTheQueueIsFull has the server send one UPDATE more
// than the handler's queue holds, each with its own timestamp. Nothing takes
// messages off the queue meanwhile. The streamer must queue the updates in
// feed order until the queue is full, and drop only the last one.
func TestUpdatesDroppedOnlyWhenTheQueueIsFull(t *testing.T) {
t.Parallel()
const (
firstTimestamp = 1700000000
lineFormat = `{"type":"ris_message","data":{"type":"UPDATE",` +
`"peer":"192.0.2.1","peer_asn":"64496","timestamp":%d}}` + "\n"
)
var lines strings.Builder
for i := range burstQueueCapacity + 1 {
fmt.Fprintf(&lines, lineFormat, firstTimestamp+i)
}
s := New(logger.New(), metrics.New())
s.RegisterHandler(burstHandler{})
streamLines(t, s, lines.String())
dropped := s.GetHandlerStats()[0].DroppedCount
if dropped != 1 {
t.Errorf("%d updates dropped, want only the one that found the queue "+
"full", dropped)
}
queue := s.handlers[0].queue
if len(queue) != burstQueueCapacity {
t.Fatalf("%d updates queued, want %d", len(queue), burstQueueCapacity)
}
for i := range burstQueueCapacity {
msg := <-queue
if msg.Timestamp != float64(firstTimestamp+i) {
t.Fatalf("update %d on the queue has timestamp %.0f, want %d",
i, msg.Timestamp, firstTimestamp+i)
}
}
}
// takeAll takes the messages off queue, as a handler's worker would, and sends // takeAll takes the messages off queue, as a handler's worker would, and sends
// them on the returned channel once queue is closed. // them on the returned channel once queue is closed.
func takeAll(queue chan *ristypes.RISMessage) chan []*ristypes.RISMessage { func takeAll(queue chan *ristypes.RISMessage) chan []*ristypes.RISMessage {
@@ -338,7 +399,7 @@ func TestStopQueuesTheHeldStateMessages(t *testing.T) {
const ( const (
held = 2 held = 2
lines = held + 1 lines = held + 1
maxWait = 5 * time.Second maxWait = 15 * time.Second
) )
srv := httptest.NewServer(http.HandlerFunc( srv := httptest.NewServer(http.HandlerFunc(
@@ -418,15 +479,15 @@ func TestStopQueuesTheHeldStateMessages(t *testing.T) {
// TestStopReturnsByItsDeadline stops a streamer whose handler has a full queue // TestStopReturnsByItsDeadline stops a streamer whose handler has a full queue
// and a STATE message held for it, and a worker that stays busy until the test // and a STATE message held for it, and a worker that stays busy until the test
// ends, as one does whose handler waits for a database write. Stop must return // ends, as one does whose handler waits for a database write. Stop must return
// within its deadline plus a small margin instead of waiting for room on the // within its deadline plus a margin instead of waiting for room on the queue
// queue and for the worker, and log as not handed over the held message and // and for the worker, and log as not handed over the held message and every
// every message on the queue. // message on the queue.
func TestStopReturnsByItsDeadline(t *testing.T) { func TestStopReturnsByItsDeadline(t *testing.T) {
t.Parallel() t.Parallel()
const ( const (
deadline = 100 * time.Millisecond deadline = 100 * time.Millisecond
margin = 2 * time.Second margin = 15 * time.Second
) )
var logs bytes.Buffer var logs bytes.Buffer
@@ -517,7 +578,7 @@ func TestStopBeforeMessageReachesQueues(t *testing.T) {
func TestReconnectWhenStreamEnds(t *testing.T) { func TestReconnectWhenStreamEnds(t *testing.T) {
t.Parallel() t.Parallel()
endResponse := func(http.ResponseWriter, *http.Request) {} endResponse := pipeTransport{write: func(context.Context, io.Writer) {}}
checkReconnect(t, endResponse, streamIdleTimeout) checkReconnect(t, endResponse, streamIdleTimeout)
} }
@@ -529,9 +590,8 @@ func TestReconnectWhenStreamGoesIdle(t *testing.T) {
const idleTimeout = 50 * time.Millisecond const idleTimeout = 50 * time.Millisecond
holdResponse := func(w http.ResponseWriter, r *http.Request) { holdResponse := pipeTransport{
flush(w) write: func(ctx context.Context, _ io.Writer) { <-ctx.Done() },
<-r.Context().Done()
} }
checkReconnect(t, holdResponse, idleTimeout) checkReconnect(t, holdResponse, idleTimeout)
} }
@@ -544,16 +604,51 @@ func TestReconnectWhenServerNeverAnswers(t *testing.T) {
const idleTimeout = 50 * time.Millisecond const idleTimeout = 50 * time.Millisecond
neverAnswer := func(_ http.ResponseWriter, r *http.Request) { neverAnswer := roundTripFunc(
<-r.Context().Done() func(req *http.Request) (*http.Response, error) {
} <-req.Context().Done()
return nil, req.Context().Err()
},
)
checkReconnect(t, neverAnswer, idleTimeout) checkReconnect(t, neverAnswer, idleTimeout)
} }
// TestStreamNotDroppedWhileLinesArrive has the server send lines well within // pipeTransport answers every request with a response whose body write fills.
// the idle timeout for several times the timeout, then end the response. Each // The body fails when the request's context ends, as a connection's does.
// line must start the idle timeout over, so the stream lasts until the server // write gets that context, so that it can end when the request does.
// ends it instead of being dropped as idle. type pipeTransport struct {
write func(context.Context, io.Writer)
}
func (p pipeTransport) RoundTrip(req *http.Request) (*http.Response, error) {
body, w := io.Pipe()
context.AfterFunc(req.Context(), func() {
_ = w.CloseWithError(req.Context().Err())
})
go func(ctx context.Context) {
p.write(ctx, w)
_ = w.Close()
}(req.Context())
return &http.Response{StatusCode: http.StatusOK, Body: body}, nil
}
// roundTripFunc makes a function an http.RoundTripper.
type roundTripFunc func(*http.Request) (*http.Response, error)
func (f roundTripFunc) RoundTrip(req *http.Request) (*http.Response, error) {
return f(req)
}
// TestStreamNotDroppedWhileLinesArrive has a response send lines well within
// the idle timeout for several times the timeout, then end. Each line must
// start the idle timeout over, so the stream lasts until the response ends
// instead of being dropped as idle. It runs in a synctest bubble, whose clock
// is fake, so a stall on the host does not use up the timeout.
func TestStreamNotDroppedWhileLinesArrive(t *testing.T) { func TestStreamNotDroppedWhileLinesArrive(t *testing.T) {
t.Parallel() t.Parallel()
@@ -563,26 +658,35 @@ func TestStreamNotDroppedWhileLinesArrive(t *testing.T) {
sendFor = 5 * idleTimeout sendFor = 5 * idleTimeout
) )
srv := httptest.NewServer(http.HandlerFunc( // The streamer is made outside the bubble. Its metrics start a goroutine
func(w http.ResponseWriter, _ *http.Request) { // that never returns, and a bubble waits for each of its goroutines to
// return.
s := New(logger.New(), metrics.New())
s.idleTimeout = idleTimeout
s.client = &http.Client{Transport: pipeTransport{
write: func(ctx context.Context, w io.Writer) {
deadline := time.Now().Add(sendFor) deadline := time.Now().Add(sendFor)
for time.Now().Before(deadline) { for time.Now().Before(deadline) {
_, _ = io.WriteString(w, updateLine) _, _ = io.WriteString(w, updateLine)
flush(w) // The wait ends with the stream. A bubble's clock stops when
time.Sleep(lineInterval) // the test function returns, and a goroutine then still
// asleep panics the test binary.
select {
case <-ctx.Done():
return
case <-time.After(lineInterval):
}
} }
})) },
defer srv.Close() }}
s := New(logger.New(), metrics.New()) synctest.Test(t, func(t *testing.T) {
s.url = srv.URL err := s.stream(context.Background())
s.idleTimeout = idleTimeout if !errors.Is(err, errStreamEnded) {
t.Fatalf("stream returned %v, want %v", err, errStreamEnded)
err := s.stream(context.Background()) }
if !errors.Is(err, errStreamEnded) { })
t.Fatalf("stream returned %v, want %v", err, errStreamEnded)
}
} }
// TestStreamReadsLongLine has the server send one UPDATE line of about // TestStreamReadsLongLine has the server send one UPDATE line of about
@@ -646,7 +750,7 @@ func TestHandlerStatsReadWhileMessagesAreDropped(t *testing.T) {
const ( const (
lines = 5 lines = 5
wantDropped = lines - 2 wantDropped = lines - 2
maxWait = 5 * time.Second maxWait = 15 * time.Second
) )
srv := httptest.NewServer(http.HandlerFunc( srv := httptest.NewServer(http.HandlerFunc(
@@ -760,61 +864,70 @@ func streamLines(t *testing.T, s *Streamer, lines string) {
// line and then stays open. The streamer must come back for a second // line and then stays open. The streamer must come back for a second
// response, must not be marked connected when it does, and must handle the // response, must not be marked connected when it does, and must handle the
// UPDATE in it. // UPDATE in it.
//
// It runs in a synctest bubble, whose clock is fake, so a stall on the host
// does not use up the idle timeout. The fake server gets the requests in the
// order the streamer makes them, because no real connection carries them.
func checkReconnect( func checkReconnect(
t *testing.T, firstResponse http.HandlerFunc, idleTimeout time.Duration, t *testing.T, firstResponse http.RoundTripper, idleTimeout time.Duration,
) { ) {
t.Helper() t.Helper()
const maxWait = 5 * time.Second const maxWait = 15 * time.Second
// The tracker is made outside the bubble. It starts a goroutine that never
// returns, and a bubble waits for each of its goroutines to return.
tracker := metrics.New() tracker := metrics.New()
connectedAtReconnect := make(chan bool, 1)
var requests atomic.Int32 synctest.Test(t, func(t *testing.T) {
connectedAtReconnect := make(chan bool, 1)
laterResponse := pipeTransport{
write: func(ctx context.Context, w io.Writer) {
_, _ = io.WriteString(w, updateLine)
srv := httptest.NewServer(http.HandlerFunc( <-ctx.Done()
func(w http.ResponseWriter, r *http.Request) { },
if requests.Add(1) == 1 { }
firstResponse(w, r)
return var requests atomic.Int32
}
select { s := New(logger.New(), tracker)
case connectedAtReconnect <- tracker.IsConnected(): s.client = &http.Client{Transport: roundTripFunc(
default: func(req *http.Request) (*http.Response, error) {
} if requests.Add(1) == 1 {
return firstResponse.RoundTrip(req)
}
_, _ = io.WriteString(w, updateLine) select {
case connectedAtReconnect <- tracker.IsConnected():
default:
}
flush(w) return laterResponse.RoundTrip(req)
<-r.Context().Done() },
})) )}
defer srv.Close() s.idleTimeout = idleTimeout
s.minBackoff = time.Millisecond
handler := updateHandler{handled: make(chan struct{}, 1)}
s.RegisterHandler(handler)
s := New(logger.New(), tracker) err := s.Start(t.Context())
s.url = srv.URL if err != nil {
s.idleTimeout = idleTimeout t.Fatalf("Start returned error: %v", err)
s.minBackoff = time.Millisecond }
handler := updateHandler{handled: make(chan struct{}, 1)} defer s.Stop(t.Context())
s.RegisterHandler(handler)
err := s.Start(t.Context()) select {
if err != nil { case <-handler.handled:
t.Fatalf("Start returned error: %v", err) case <-time.After(maxWait):
} t.Fatalf("no message from a second response handled within %s", maxWait)
defer s.Stop(t.Context()) }
select { if <-connectedAtReconnect {
case <-handler.handled: t.Error("streamer was still marked connected when it came back " +
case <-time.After(maxWait): "for a second response")
t.Fatalf("no message from a second response handled within %s", maxWait) }
} })
if <-connectedAtReconnect {
t.Error("streamer was still marked connected when it came back " +
"for a second response")
}
} }
// settledGoroutineCount lets transient goroutines finish, then reports the // settledGoroutineCount lets transient goroutines finish, then reports the
@@ -836,9 +949,13 @@ func settledGoroutineCount() int {
return prev return prev
} }
// waitForGoroutines waits until the goroutine count drops to target or below. // waitForGoroutines waits up to 15 seconds for the goroutine count to drop to
// target or below.
func waitForGoroutines(target int) bool { func waitForGoroutines(target int) bool {
for range 100 { const maxWait = 15 * time.Second
deadline := time.Now().Add(maxWait)
for time.Now().Before(deadline) {
if runtime.NumGoroutine() <= target { if runtime.NumGoroutine() <= target {
return true return true
} }
internal/templates/bogons.html
+170
View File
@@ -0,0 +1,170 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Bogon Announcements - RouteWatch</title>
<style nonce="{{.CSPNonce}}">
* {
box-sizing: border-box;
}
body {
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
margin: 0;
padding: 0;
background: #f5f5f5;
}
/* Navbar styles */
.navbar {
background: #2c3e50;
padding: 0 20px;
display: flex;
align-items: center;
justify-content: space-between;
height: 56px;
box-shadow: 0 2px 4px rgba(0,0,0,0.1);
}
.navbar-brand {
display: flex;
align-items: center;
gap: 8px;
font-size: 18px;
font-weight: 600;
}
.navbar-brand a {
color: white;
text-decoration: none;
}
.navbar-brand a:hover {
color: #ecf0f1;
}
.navbar-brand .by {
font-weight: normal;
color: #95a5a6;
font-size: 14px;
}
.navbar-brand .author {
color: #3498db;
font-weight: normal;
}
.navbar-brand .author:hover {
text-decoration: underline;
}
.navbar-links {
display: flex;
gap: 20px;
}
.navbar-links a {
color: #ecf0f1;
text-decoration: none;
font-size: 14px;
padding: 8px 12px;
border-radius: 4px;
transition: background-color 0.2s;
}
.navbar-links a:hover {
background: rgba(255,255,255,0.1);
}
/* Main content */
.main-content {
max-width: 1200px;
margin: 0 auto;
padding: 20px;
}
h1 {
color: #333;
margin-bottom: 10px;
}
.subtitle {
color: #666;
margin-bottom: 30px;
}
table {
width: 100%;
border-collapse: collapse;
background: white;
box-shadow: 0 2px 4px rgba(0,0,0,0.1);
border-radius: 8px;
overflow: hidden;
}
th {
background: #f8f9fa;
padding: 12px;
text-align: left;
font-weight: 600;
color: #333;
border-bottom: 2px solid #dee2e6;
}
td {
padding: 12px;
border-bottom: 1px solid #eee;
}
tr:last-child td {
border-bottom: none;
}
tr:hover {
background: #f8f9fa;
}
a {
color: #0066cc;
text-decoration: none;
}
a:hover {
text-decoration: underline;
}
.prefix-link {
font-family: 'SF Mono', Monaco, 'Cascadia Mono', 'Roboto Mono', Consolas, 'Courier New', monospace;
}
</style>
</head>
<body>
<nav class="navbar">
<div class="navbar-brand">
<a href="/">routewatch</a>
<span class="by">by</span>
<a href="https://sneak.berlin" class="author">@sneak</a>
</div>
<div class="navbar-links">
<a href="/">Home</a>
<a href="/status">Status</a>
</div>
</nav>
<main class="main-content">
<h1>Bogon Announcements</h1>
{{ with .Cards }}
<p class="subtitle">
Bogon announcements: {{ .BogonCount }}.
A bogon announcement is a route that announces a reserved prefix, or that comes from a reserved AS number.
{{ if lt (len .Bogons) .BogonCount }}The first {{ len .Bogons }} are listed, in prefix order.{{ end }}
The list is worked out once a minute.
</p>
<table>
<thead>
<tr>
<th>Prefix</th>
<th>Origin AS</th>
<th>Peers</th>
<th>Why it is a bogon</th>
</tr>
</thead>
<tbody>
{{ range .Bogons }}
<tr>
<td><a href="{{ prefixURL .Prefix.String }}" class="prefix-link">{{ .Prefix }}</a></td>
<td>{{ if .OriginASN }}<a href="/as/{{ .OriginASN }}">AS{{ .OriginASN }}</a>{{ else }}No known origin{{ end }}</td>
<td>{{ .Peers }}</td>
<td>{{ range $i, $reason := .Reasons }}{{ if $i }}; {{ end }}{{ $reason }}{{ end }}</td>
</tr>
{{ end }}
</tbody>
</table>
{{ else }}
<p class="subtitle">The list is being worked out. Reload the page in a minute.</p>
{{ end }}
</main>
</body>
</html>
internal/templates/index.html
+156 -11
View File
@@ -276,6 +276,52 @@
margin-top: 12px; margin-top: 12px;
} }
/* Cards with figures of the routing table, worked out once a minute */
#table-cards p,
#well-known p {
margin: 0 0 8px 0;
font-size: 14px;
}
#table-cards a,
#well-known a {
color: #3498db;
text-decoration: none;
}
#table-cards a:hover,
#well-known a:hover {
text-decoration: underline;
}
#table-cards .card-figure {
font-size: 32px;
font-weight: bold;
}
#table-cards .card-detail,
#table-cards .card-time {
color: #7f8c8d;
font-size: 12px;
}
#table-cards .prefix {
font-family: 'SF Mono', Monaco, 'Cascadia Mono', 'Roboto Mono', Consolas, 'Courier New', monospace;
}
#well-known {
margin-bottom: 40px;
}
#well-known table {
width: 100%;
border-collapse: collapse;
font-size: 14px;
}
#well-known th,
#well-known td {
text-align: left;
padding: 8px 4px;
border-bottom: 1px solid #eee;
}
#well-known th {
color: #7f8c8d;
font-weight: 600;
}
/* Footer */ /* Footer */
.footer { .footer {
margin-top: 40px; margin-top: 40px;
@@ -381,6 +427,109 @@
</div> </div>
</div> </div>
{{ with .Cards }}
<div class="search-section" id="table-cards">
<div class="search-card">
<h2>Newest Updated Route</h2>
{{ with .NewestRoute }}
<p><a href="{{ prefixURL .Prefix.String }}" class="prefix">{{ .Prefix }}</a> from {{ if .OriginASN }}<a href="/as/{{ .OriginASN }}">AS{{ .OriginASN }}</a>{{ else }}no known origin{{ end }}</p>
<p class="card-time">{{ .Time.UTC.Format "2006-01-02 15:04:05" }} UTC, {{ timeSince .Time }}</p>
{{ else }}
<p>The routing table keeps no route yet.</p>
{{ end }}
</div>
<div class="search-card">
<h2>Oldest Updated Route</h2>
{{ with .OldestRoute }}
<p><a href="{{ prefixURL .Prefix.String }}" class="prefix">{{ .Prefix }}</a> from {{ if .OriginASN }}<a href="/as/{{ .OriginASN }}">AS{{ .OriginASN }}</a>{{ else }}no known origin{{ end }}</p>
<p class="card-time">{{ .Time.UTC.Format "2006-01-02 15:04:05" }} UTC, {{ timeSince .Time }}</p>
{{ else }}
<p>The routing table keeps no route yet.</p>
{{ end }}
</div>
<div class="search-card">
<h2>Newest Updated AS</h2>
{{ with .NewestAS }}
<p><a href="/as/{{ .ASN }}">AS{{ .ASN }}</a> {{ .Handle }}</p>
<p class="card-detail">{{ .Description }}</p>
<p class="card-time">Last seen {{ .LastSeen.UTC.Format "2006-01-02 15:04:05" }} UTC, {{ timeSince .LastSeen }}</p>
{{ else }}
<p>No AS has been seen yet.</p>
{{ end }}
</div>
<div class="search-card">
<h2>Oldest Updated AS</h2>
{{ with .OldestAS }}
<p><a href="/as/{{ .ASN }}">AS{{ .ASN }}</a> {{ .Handle }}</p>
<p class="card-detail">{{ .Description }}</p>
<p class="card-time">Last seen {{ .LastSeen.UTC.Format "2006-01-02 15:04:05" }} UTC, {{ timeSince .LastSeen }}</p>
{{ else }}
<p>No AS has been seen yet.</p>
{{ end }}
</div>
<div class="search-card">
<h2>AS with the Most Prefixes</h2>
{{ if .MostPrefixes }}
<p><a href="/as/{{ .MostPrefixesASN }}">AS{{ .MostPrefixesASN }}</a></p>
<p>Prefixes it originates: {{ .MostPrefixes }}</p>
{{ else }}
<p>No AS originates a prefix yet.</p>
{{ end }}
</div>
<div class="search-card">
<h2>ASes with the Fewest Prefixes</h2>
<p>ASes that originate a single prefix: {{ .SinglePrefixASes }}</p>
{{ with .NewestSinglePrefix }}
<p>The most recently updated of them: <a href="/as/{{ .OriginASN }}">AS{{ .OriginASN }}</a>, with <a href="{{ prefixURL .Prefix.String }}" class="prefix">{{ .Prefix }}</a></p>
<p class="card-time">{{ .Time.UTC.Format "2006-01-02 15:04:05" }} UTC, {{ timeSince .Time }}</p>
{{ end }}
</div>
<div class="search-card">
<h2>Bogon Announcements</h2>
<p class="card-figure"><a href="/bogons">{{ .BogonCount }}</a></p>
<p>Routes that announce a reserved prefix, or that come from a reserved AS number</p>
</div>
<div class="search-card">
<h2>Prefixes with Several Origins</h2>
<p class="card-figure"><a href="/multiple-origins">{{ .MultipleOriginCount }}</a></p>
<p>Prefixes announced by more than one origin AS</p>
</div>
</div>
<div class="search-card" id="well-known">
<h2>Well-Known Networks</h2>
<table>
<thead>
<tr>
<th>Network</th>
<th>Prefixes</th>
<th>Last Update</th>
</tr>
</thead>
<tbody>
{{ range .WellKnownNetworks }}
<tr>
<td><a href="/as/{{ .ASN }}">AS{{ .ASN }}</a> {{ .Name }}</td>
<td>{{ .Prefixes }}</td>
<td>{{ with .Newest }}{{ timeSince . }}{{ else }}no route{{ end }}</td>
</tr>
{{ end }}
</tbody>
</table>
</div>
{{ else }}
<div class="search-card" id="well-known">
<p>The figures of the routing table are being worked out. Reload the page in a minute.</p>
</div>
{{ end }}
<div class="search-card" id="ip-api"> <div class="search-card" id="ip-api">
<h2>IP Information API</h2> <h2>IP Information API</h2>
<p>The API answers what RouteWatch knows about an IP address, such as its AS number and country. <code>/ip/</code> with no address answers for the caller's own address.</p> <p>The API answers what RouteWatch knows about an IP address, such as its AS number and country. <code>/ip/</code> with no address answers for the caller's own address.</p>
@@ -395,6 +544,8 @@
<span>{{appLicense}}</span> <span>{{appLicense}}</span>
<span class="separator">|</span> <span class="separator">|</span>
<span><a href="{{appGitCommitURL}}">{{appGitRevision}}</a></span> <span><a href="{{appGitCommitURL}}">{{appGitRevision}}</a></span>
<span class="separator">|</span>
<span>IP Geolocation by <a href="https://db-ip.com">DB-IP</a></span>
</footer> </footer>
<script nonce="{{.CSPNonce}}"> <script nonce="{{.CSPNonce}}">
@@ -565,7 +716,8 @@
}); });
}); });
// IP lookup // IP lookup: show the whole JSON answer, its @meta and an error answer
// included, as the IP information API card does.
document.getElementById('ip-form').addEventListener('submit', function(e) { document.getElementById('ip-form').addEventListener('submit', function(e) {
e.preventDefault(); e.preventDefault();
const ip = document.getElementById('ip-input').value.trim(); const ip = document.getElementById('ip-input').value.trim();
@@ -581,18 +733,11 @@
fetch('/ip/' + encodeURIComponent(ip)) fetch('/ip/' + encodeURIComponent(ip))
.then(response => response.json()) .then(response => response.json())
.then(response => { .then(answer => {
contentEl.classList.remove('loading'); contentEl.className = '';
if (response.status === 'error') { contentEl.textContent = JSON.stringify(answer, null, 2);
contentEl.className = 'error';
contentEl.textContent = 'Error: ' + response.error.msg;
} else {
contentEl.className = '';
contentEl.textContent = JSON.stringify(response.data, null, 2);
}
}) })
.catch(error => { .catch(error => {
contentEl.classList.remove('loading');
contentEl.className = 'error'; contentEl.className = 'error';
contentEl.textContent = 'Error: ' + error.message; contentEl.textContent = 'Error: ' + error.message;
}); });
internal/templates/multiple_origins.html
+182
View File
@@ -0,0 +1,182 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Prefixes with Several Origins - RouteWatch</title>
<style nonce="{{.CSPNonce}}">
* {
box-sizing: border-box;
}
body {
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
margin: 0;
padding: 0;
background: #f5f5f5;
}
/* Navbar styles */
.navbar {
background: #2c3e50;
padding: 0 20px;
display: flex;
align-items: center;
justify-content: space-between;
height: 56px;
box-shadow: 0 2px 4px rgba(0,0,0,0.1);
}
.navbar-brand {
display: flex;
align-items: center;
gap: 8px;
font-size: 18px;
font-weight: 600;
}
.navbar-brand a {
color: white;
text-decoration: none;
}
.navbar-brand a:hover {
color: #ecf0f1;
}
.navbar-brand .by {
font-weight: normal;
color: #95a5a6;
font-size: 14px;
}
.navbar-brand .author {
color: #3498db;
font-weight: normal;
}
.navbar-brand .author:hover {
text-decoration: underline;
}
.navbar-links {
display: flex;
gap: 20px;
}
.navbar-links a {
color: #ecf0f1;
text-decoration: none;
font-size: 14px;
padding: 8px 12px;
border-radius: 4px;
transition: background-color 0.2s;
}
.navbar-links a:hover {
background: rgba(255,255,255,0.1);
}
/* Main content */
.main-content {
max-width: 1200px;
margin: 0 auto;
padding: 20px;
}
h1 {
color: #333;
margin-bottom: 10px;
}
.subtitle {
color: #666;
margin-bottom: 30px;
}
table {
width: 100%;
border-collapse: collapse;
background: white;
box-shadow: 0 2px 4px rgba(0,0,0,0.1);
border-radius: 8px;
overflow: hidden;
}
th {
background: #f8f9fa;
padding: 12px;
text-align: left;
font-weight: 600;
color: #333;
border-bottom: 2px solid #dee2e6;
}
td {
padding: 12px;
border-bottom: 1px solid #eee;
vertical-align: top;
}
tr:last-child td {
border-bottom: none;
}
tr:hover {
background: #f8f9fa;
}
a {
color: #0066cc;
text-decoration: none;
}
a:hover {
text-decoration: underline;
}
.prefix-link {
font-family: 'SF Mono', Monaco, 'Cascadia Mono', 'Roboto Mono', Consolas, 'Courier New', monospace;
}
.origins {
list-style: none;
margin: 0;
padding: 0;
}
.peers {
color: #666;
font-size: 0.9em;
}
</style>
</head>
<body>
<nav class="navbar">
<div class="navbar-brand">
<a href="/">routewatch</a>
<span class="by">by</span>
<a href="https://sneak.berlin" class="author">@sneak</a>
</div>
<div class="navbar-links">
<a href="/">Home</a>
<a href="/status">Status</a>
</div>
</nav>
<main class="main-content">
<h1>Prefixes with Several Origin ASes</h1>
{{ with .Cards }}
<p class="subtitle">
Prefixes announced by more than one origin AS: {{ .MultipleOriginCount }}.
Such a prefix can be a hijack.
{{ if lt (len .MultipleOrigins) .MultipleOriginCount }}The first {{ len .MultipleOrigins }} are listed, in prefix order.{{ end }}
The list is worked out once a minute.
</p>
<table>
<thead>
<tr>
<th>Prefix</th>
<th>Origin ASes</th>
</tr>
</thead>
<tbody>
{{ range .MultipleOrigins }}
<tr>
<td><a href="{{ prefixURL .Prefix.String }}" class="prefix-link">{{ .Prefix }}</a></td>
<td>
<ul class="origins">
{{ range .Origins }}
<li>{{ if .ASN }}<a href="/as/{{ .ASN }}">AS{{ .ASN }}</a>{{ else }}No known origin{{ end }} <span class="peers">{{ .Peers }} {{ if eq .Peers 1 }}peer{{ else }}peers{{ end }}</span></li>
{{ end }}
</ul>
</td>
</tr>
{{ end }}
</tbody>
</table>
{{ else }}
<p class="subtitle">The list is being worked out. Reload the page in a minute.</p>
{{ end }}
</main>
</body>
</html>
internal/templates/prefix_detail.html
+35
View File
@@ -299,6 +299,41 @@
</div> </div>
{{end}} {{end}}
{{if .OriginChanges}}
<div class="origins-section">
<h3>Origin Changes</h3>
{{if .MoreOriginChanges}}
<p>There are more than {{.MaxOriginChanges}} changes. Showing the newest {{.MaxOriginChanges}}.</p>
{{end}}
<table class="route-table">
<thead>
<tr>
<th>Time (UTC)</th>
<th>Change</th>
<th>Origin AS</th>
<th>Peers</th>
</tr>
</thead>
<tbody>
{{range .OriginChanges}}
<tr>
<td>{{.Time.Format "2006-01-02 15:04:05"}}</td>
<td>{{if .Announced}}Announced{{else}}Withdrawn{{end}}</td>
<td>
{{if .OriginASN}}
<a href="/as/{{.OriginASN}}" class="as-link">AS{{.OriginASN}}</a>
{{else}}
No known origin
{{end}}
</td>
<td>{{.PeerCount}}</td>
</tr>
{{end}}
</tbody>
</table>
</div>
{{end}}
{{if .Routes}} {{if .Routes}}
<div class="routes-section"> <div class="routes-section">
<div class="routes-header"> <div class="routes-header">
internal/templates/status.html
+24 -5
View File
@@ -401,6 +401,8 @@
const REFRESH_PERIOD_MS = 2000; const REFRESH_PERIOD_MS = 2000;
const STALE_AFTER_REFRESHES = 3; const STALE_AFTER_REFRESHES = 3;
const MS_PER_SECOND = 1000; const MS_PER_SECOND = 1000;
const SECONDS_PER_MINUTE = 60;
const SECONDS_PER_HOUR = 3600;
const SPINNER_FRAMES = ['⠋', '⠙', '⠹', '⠸', '⠼', '⠴', '⠦', '⠧', '⠇', '⠏']; const SPINNER_FRAMES = ['⠋', '⠙', '⠹', '⠸', '⠼', '⠴', '⠦', '⠧', '⠇', '⠏'];
const SPINNER_COLOURS = ['#e74c3c', '#e67e22', '#f1c40f', '#27ae60', '#3498db', '#9b59b6']; const SPINNER_COLOURS = ['#e74c3c', '#e67e22', '#f1c40f', '#27ae60', '#3498db', '#9b59b6'];
@@ -443,7 +445,18 @@
function formatNumber(num) { function formatNumber(num) {
return num.toLocaleString(); return num.toLocaleString();
} }
// formatDuration writes a number of seconds in hours, minutes and
// seconds, such as "1h 18m 34s" or "18.2s", with at most one decimal.
function formatDuration(totalSeconds) {
const hours = Math.floor(totalSeconds / SECONDS_PER_HOUR);
const minutes = Math.floor(totalSeconds % SECONDS_PER_HOUR / SECONDS_PER_MINUTE);
const seconds = parseFloat((totalSeconds % SECONDS_PER_MINUTE).toFixed(1));
if (hours > 0) return hours + 'h ' + minutes + 'm ' + seconds + 's';
if (minutes > 0) return minutes + 'm ' + seconds + 's';
return seconds + 's';
}
function formatProcessingTime(ms) { function formatProcessingTime(ms) {
if (ms < 0.001) { if (ms < 0.001) {
return (ms * 1000).toFixed(0) + ' µs'; return (ms * 1000).toFixed(0) + ' µs';
@@ -528,6 +541,10 @@
<span class="metric-label">Dropped</span> <span class="metric-label">Dropped</span>
<span class="metric-value ${handler.dropped_count > 0 ? 'disconnected' : ''}">${formatNumber(handler.dropped_count)}</span> <span class="metric-value ${handler.dropped_count > 0 ? 'disconnected' : ''}">${formatNumber(handler.dropped_count)}</span>
</div> </div>
<div class="metric">
<span class="metric-label">Held Back</span>
<span class="metric-value">${formatNumber(handler.held_back_count)}</span>
</div>
<div class="metric"> <div class="metric">
<span class="metric-label">Avg Time</span> <span class="metric-label">Avg Time</span>
<span class="metric-value">${formatProcessingTime(handler.avg_process_time_ms)}</span> <span class="metric-value">${formatProcessingTime(handler.avg_process_time_ms)}</span>
@@ -619,11 +636,13 @@
noteMessageCount(data.total_messages); noteMessageCount(data.total_messages);
// Update all metrics // Update all metrics
document.getElementById('uptime').textContent = data.uptime; document.getElementById('uptime').textContent = formatDuration(data.uptime_seconds);
document.getElementById('go_version').textContent = data.go_version; document.getElementById('go_version').textContent = data.go_version;
document.getElementById('goroutines').textContent = formatNumber(data.goroutines); document.getElementById('goroutines').textContent = formatNumber(data.goroutines);
document.getElementById('memory_usage').textContent = data.memory_usage; document.getElementById('memory_usage').textContent = formatBytes(data.memory_usage_bytes);
document.getElementById('connection_duration').textContent = data.connection_duration; // connection_duration_seconds is null while the stream is not connected.
document.getElementById('connection_duration').textContent =
data.connection_duration_seconds === null ? 'disconnected' : formatDuration(data.connection_duration_seconds);
document.getElementById('reconnect_count').textContent = formatNumber(data.reconnect_count); document.getElementById('reconnect_count').textContent = formatNumber(data.reconnect_count);
document.getElementById('total_messages').textContent = formatNumber(data.total_messages); document.getElementById('total_messages').textContent = formatNumber(data.total_messages);
document.getElementById('messages_per_sec').textContent = formatNumber(Math.round(data.messages_per_sec)); document.getElementById('messages_per_sec').textContent = formatNumber(Math.round(data.messages_per_sec));
@@ -672,7 +691,7 @@
const errorsEl = document.getElementById('whois_errors'); const errorsEl = document.getElementById('whois_errors');
errorsEl.textContent = formatNumber(data.whois_stats.errors_last_hour); errorsEl.textContent = formatNumber(data.whois_stats.errors_last_hour);
errorsEl.className = 'metric-value' + (data.whois_stats.errors_last_hour > 0 ? ' disconnected' : ''); errorsEl.className = 'metric-value' + (data.whois_stats.errors_last_hour > 0 ? ' disconnected' : '');
document.getElementById('whois_interval').textContent = data.whois_stats.current_interval; document.getElementById('whois_interval').textContent = formatDuration(data.whois_stats.current_interval_seconds);
} }
// Update handler stats // Update handler stats
internal/templates/templates.go
+34
View File
@@ -27,6 +27,12 @@ var prefixDetailHTML string
//go:embed prefix_length.html //go:embed prefix_length.html
var prefixLengthHTML string var prefixLengthHTML string
//go:embed bogons.html
var bogonsHTML string
//go:embed multiple_origins.html
var multipleOriginsHTML string
// Templates contains all parsed templates // Templates contains all parsed templates
type Templates struct { type Templates struct {
// Index is the template for the home page // Index is the template for the home page
@@ -39,6 +45,11 @@ type Templates struct {
PrefixDetail *template.Template PrefixDetail *template.Template
// PrefixLength is the template for displaying prefixes by length // PrefixLength is the template for displaying prefixes by length
PrefixLength *template.Template PrefixLength *template.Template
// Bogons is the template of the page that lists the bogon announcements
Bogons *template.Template
// MultipleOrigins is the template of the page that lists the prefixes
// announced by more than one origin AS
MultipleOrigins *template.Template
} }
var ( var (
@@ -116,6 +127,18 @@ func initTemplates() {
if err != nil { if err != nil {
panic("failed to parse prefix length template: " + err.Error()) panic("failed to parse prefix length template: " + err.Error())
} }
defaultTemplates.Bogons, err = template.New("bogons").
Funcs(funcs).Parse(bogonsHTML)
if err != nil {
panic("failed to parse bogons template: " + err.Error())
}
defaultTemplates.MultipleOrigins, err = template.New("multipleOrigins").
Funcs(funcs).Parse(multipleOriginsHTML)
if err != nil {
panic("failed to parse multiple origins template: " + err.Error())
}
} }
// Get returns the singleton Templates instance // Get returns the singleton Templates instance
@@ -149,3 +172,14 @@ func PrefixDetailTemplate() *template.Template {
func PrefixLengthTemplate() *template.Template { func PrefixLengthTemplate() *template.Template {
return Get().PrefixLength return Get().PrefixLength
} }
// BogonsTemplate returns the parsed template of the bogon announcements page
func BogonsTemplate() *template.Template {
return Get().Bogons
}
// MultipleOriginsTemplate returns the parsed template of the page of prefixes
// announced by more than one origin AS
func MultipleOriginsTemplate() *template.Template {
return Get().MultipleOrigins
}
internal/templates/templates_test.go
+23 -2
View File
@@ -12,13 +12,17 @@ import (
) )
// renderPage renders a page with the data every page needs, and the visitor's // renderPage renders a page with the data every page needs, and the visitor's
// address, which the home page also needs. // address and the routing table's cards, which the home page also needs. The
// cards are left out, as before the server first works them out.
func renderPage(t *testing.T, tmpl *template.Template) string { func renderPage(t *testing.T, tmpl *template.Template) string {
t.Helper() t.Helper()
var page bytes.Buffer var page bytes.Buffer
err := tmpl.Execute(&page, struct{ CSPNonce, ClientIP string }{}) err := tmpl.Execute(&page, struct {
CSPNonce, ClientIP string
Cards any
}{})
if err != nil { if err != nil {
t.Fatalf("rendering the page: %v", err) t.Fatalf("rendering the page: %v", err)
} }
@@ -63,6 +67,23 @@ func TestFooterLicense(t *testing.T) {
} }
} }
// TestHomePageCreditsDBIP expects the home page's footer to carry the credit
// to DB-IP.
func TestHomePageCreditsDBIP(t *testing.T) {
t.Parallel()
const attribution = `IP Geolocation by <a href="https://db-ip.com">DB-IP</a>`
_, footer, found := strings.Cut(renderPage(t, templates.IndexTemplate()), "<footer")
if !found {
t.Fatal("the page has no footer")
}
if !strings.Contains(footer, attribution) {
t.Errorf("footer does not credit DB-IP: %q", footer)
}
}
// TestFreshnessIndicator renders the home and status pages and expects each to // TestFreshnessIndicator renders the home and status pages and expects each to
// have, right after the status element, the element where the page's script // have, right after the status element, the element where the page's script
// shows its spinner or "stale". // shows its spinner or "stale".
internal/whois/whois.go
+82 -36
View File
@@ -12,6 +12,7 @@ import (
"regexp" "regexp"
"strings" "strings"
"sync" "sync"
"syscall"
"time" "time"
"unicode/utf8" "unicode/utf8"
@@ -70,12 +71,12 @@ const nicbrHeader = "% Copyright (c) Nic.br"
// queries to stop the data being taken in bulk. // queries to stop the data being taken in bulk.
const nicbrLimitReached = "Query rate limit exceeded" const nicbrLimitReached = "Query rate limit exceeded"
// NICbrSkipTime is how long the client stops asking NIC.br after NIC.br // PauseTime is how long the client sends an RIR's or NIC.br's server no
// answers that the client is over its query limit. NIC.br publishes // query after that server refuses a query. queryRegistry says what a
// neither the limit nor how long it lasts. An hour outlasts a limit // refusal is. RIPE refuses an address for good when the address keeps
// counted per minute or per hour. The ASes looked up meanwhile get // passing RIPE's limit (see noPersonalFlag). An hour outlasts a limit
// NIC.br's fields when they are next refreshed. // counted per minute or per hour.
const NICbrSkipTime = time.Hour const PauseTime = time.Hour
// RIR identifiers. // RIR identifiers.
const ( const (
@@ -125,6 +126,10 @@ var (
errAnswerTooLarge = errors.New("WHOIS answer reached the size cap") errAnswerTooLarge = errors.New("WHOIS answer reached the size cap")
) )
// ErrPaused is returned when a lookup needs a server that refused a query
// less than PauseTime ago. The client sends that server nothing meanwhile.
var ErrPaused = errors.New("WHOIS server paused after refusing a query")
// ASNInfo contains parsed WHOIS information for an ASN. // ASNInfo contains parsed WHOIS information for an ASN.
type ASNInfo struct { type ASNInfo struct {
ASN int ASN int
@@ -156,12 +161,12 @@ type Client struct {
logger *slog.Logger logger *slog.Logger
// mu guards nicbrSkipUntil. // mu guards pausedUntil.
mu sync.Mutex mu sync.Mutex
// nicbrSkipUntil is when the client next asks NIC.br, after NIC.br // pausedUntil maps a server, given as host:port, to the time the client
// answered that the client is over its query limit. // may ask it again.
nicbrSkipUntil time.Time pausedUntil map[string]time.Time
} }
// NewClient creates a new WHOIS client that logs to logger. // NewClient creates a new WHOIS client that logs to logger.
@@ -172,23 +177,29 @@ func NewClient(logger *slog.Logger) *Client {
DialContext: dialer.DialContext, DialContext: dialer.DialContext,
Now: time.Now, Now: time.Now,
logger: logger, logger: logger,
pausedUntil: make(map[string]time.Time),
} }
} }
// LookupASN asks IANA which RIR holds the given ASN, asks that RIR, and // LookupASN asks IANA which RIR holds the given ASN, asks that RIR, and
// returns what the RIR's answer says. When LACNIC's answer is NIC.br's, it // returns what the RIR's answer says. When LACNIC's answer is NIC.br's, it
// returns what NIC.br's own server says instead, unless that query fails or // returns what NIC.br's own server says instead, unless that query fails or
// is skipped, as askNICbr says. // NIC.br is paused, as askNICbr says.
// //
// It returns ErrNoReferral when IANA refers the AS to no RIR, and another // It returns ErrNoReferral when IANA refers the AS to no RIR. Its error
// error when the query to IANA or to the RIR fails, when the RIR refuses // wraps ErrPaused when the RIR is paused. It returns another error in each
// it, when IANA's answer has neither a referral nor the AS's block, when // of these cases:
// IANA refers the AS to a server none of the five RIRs run, or when the //
// answer carries none of ASNInfo's fields. // - the query to IANA or to the RIR fails
// - the RIR refuses the query
// - IANA's answer has neither a referral nor the AS's block
// - IANA refers the AS to a server none of the five RIRs run
// - the answer carries none of ASNInfo's fields
func (c *Client) LookupASN(ctx context.Context, asn int) (*ASNInfo, error) { func (c *Client) LookupASN(ctx context.Context, asn int) (*ASNInfo, error) {
// Query IANA first to find the authoritative RIR // Query IANA first to find the authoritative RIR
query := fmt.Sprintf("AS%d", asn) query := fmt.Sprintf("AS%d", asn)
// IANA is never paused, because a pause of IANA would stop every lookup.
ianaResp, err := c.query(ctx, whoisServerIANA, query) ianaResp, err := c.query(ctx, whoisServerIANA, query)
if err != nil { if err != nil {
return nil, fmt.Errorf("IANA query failed: %w", err) return nil, fmt.Errorf("IANA query failed: %w", err)
@@ -211,7 +222,7 @@ func (c *Client) LookupASN(ctx context.Context, asn int) (*ASNInfo, error) {
} }
// Query the authoritative RIR // Query the authoritative RIR
rirResp, err := c.queryRIR(ctx, whoisServer, rirQuery(rir, query)) rirResp, err := c.queryRegistry(ctx, whoisServer, rirQuery(rir, query))
if err != nil { if err != nil {
return nil, fmt.Errorf("RIR query failed: %w", err) return nil, fmt.Errorf("RIR query failed: %w", err)
} }
@@ -241,22 +252,19 @@ func (c *Client) LookupASN(ctx context.Context, asn int) (*ASNInfo, error) {
// askNICbr returns lacnicInfo, what LACNIC's answer says, and logs a // askNICbr returns lacnicInfo, what LACNIC's answer says, and logs a
// warning when the query fails, when NIC.br sends the reduced answer for a // warning when the query fails, when NIC.br sends the reduced answer for a
// client over its limit, or when NIC.br's answer carries none of ASNInfo's // client over its limit, or when NIC.br's answer carries none of ASNInfo's
// fields. After the reduced answer, it returns lacnicInfo without asking // fields. The reduced answer pauses NIC.br, as a refusal does. While NIC.br
// NIC.br until NICbrSkipTime has passed. // is paused, askNICbr returns lacnicInfo without a warning. The ASes looked
// up meanwhile get NIC.br's fields when they are next refreshed.
func (c *Client) askNICbr( func (c *Client) askNICbr(
ctx context.Context, asQuery string, lacnicInfo *ASNInfo, ctx context.Context, asQuery string, lacnicInfo *ASNInfo,
) *ASNInfo { ) *ASNInfo {
asn := lacnicInfo.ASN asn := lacnicInfo.ASN
c.mu.Lock() answer, err := c.queryRegistry(ctx, whoisServerNICbr, asQuery)
skipping := c.Now().Before(c.nicbrSkipUntil) if errors.Is(err, ErrPaused) {
c.mu.Unlock()
if skipping {
return lacnicInfo return lacnicInfo
} }
answer, err := c.query(ctx, whoisServerNICbr, asQuery)
if err != nil { if err != nil {
c.logger.Warn("NIC.br query failed, keeping LACNIC's fields", c.logger.Warn("NIC.br query failed, keeping LACNIC's fields",
"asn", asn, "error", err) "asn", asn, "error", err)
@@ -265,13 +273,11 @@ func (c *Client) askNICbr(
} }
if strings.Contains(answer, nicbrLimitReached) { if strings.Contains(answer, nicbrLimitReached) {
c.mu.Lock() c.pause(whoisServerNICbr)
c.nicbrSkipUntil = c.Now().Add(NICbrSkipTime)
c.mu.Unlock()
c.logger.Warn("NIC.br answered that the client is over its query "+ c.logger.Warn("NIC.br answered that the client is over its query "+
"limit, keeping LACNIC's fields and skipping NIC.br", "limit, keeping LACNIC's fields and pausing NIC.br",
"asn", asn, "skip_for", NICbrSkipTime) "asn", asn, "pause_for", PauseTime)
return lacnicInfo return lacnicInfo
} }
@@ -309,25 +315,65 @@ func rirQuery(rir, asQuery string) string {
} }
} }
// queryRIR sends query to an RIR's server and returns the answer. An answer // queryRegistry sends query to the server of an RIR or of NIC.br, and
// holding an error line with which the server refuses the query is an // returns the answer. The client pauses the server for PauseTime when the
// error, and the error holds that line. // server refuses the query. Each of these is a refusal:
func (c *Client) queryRIR( //
// - a refused connection
// - a reset connection
// - an %ERROR:201: or %ERROR:202: line in the answer
//
// A refusal is returned as an error. While the server is paused,
// queryRegistry sends it nothing and returns an error that wraps ErrPaused.
func (c *Client) queryRegistry(
ctx context.Context, server, query string, ctx context.Context, server, query string,
) (string, error) { ) (string, error) {
c.mu.Lock()
pausedUntil := c.pausedUntil[server]
c.mu.Unlock()
if c.Now().Before(pausedUntil) {
return "", fmt.Errorf("%w: %s until %s", ErrPaused, server,
pausedUntil.UTC().Format(time.RFC3339))
}
answer, err := c.query(ctx, server, query) answer, err := c.query(ctx, server, query)
if err == nil {
err = checkRefusal(answer)
}
if errors.Is(err, errRefused) || errors.Is(err, syscall.ECONNREFUSED) ||
errors.Is(err, syscall.ECONNRESET) {
c.pause(server)
}
if err != nil { if err != nil {
return "", err return "", err
} }
return answer, nil
}
// checkRefusal returns an error holding the first line of answer that
// starts with accessDeniedError or accessLimitError. It returns nil when
// answer has no such line.
func checkRefusal(answer string) error {
for line := range strings.SplitSeq(answer, "\n") { for line := range strings.SplitSeq(answer, "\n") {
if strings.HasPrefix(line, accessDeniedError) || if strings.HasPrefix(line, accessDeniedError) ||
strings.HasPrefix(line, accessLimitError) { strings.HasPrefix(line, accessLimitError) {
return "", fmt.Errorf("%w: %s", errRefused, line) return fmt.Errorf("%w: %s", errRefused, line)
} }
} }
return answer, nil return nil
}
// pause stops queryRegistry from querying server until PauseTime has passed.
func (c *Client) pause(server string) {
c.mu.Lock()
defer c.mu.Unlock()
c.pausedUntil[server] = c.Now().Add(PauseTime)
} }
// query performs a raw WHOIS query to the specified server and returns the // query performs a raw WHOIS query to the specified server and returns the
internal/whois/whois_test.go
+142 -5
View File
@@ -718,9 +718,10 @@ func TestLookupASNKeepsLACNICsAnswerWhenNICbrFails(t *testing.T) {
// TestLookupASNSkipsNICbrAfterItsLimit looks up an AS that NIC.br // TestLookupASNSkipsNICbrAfterItsLimit looks up an AS that NIC.br
// registers three times with one client, while NIC.br answers that the // registers three times with one client, while NIC.br answers that the
// client is over its query limit. The first lookup asks NIC.br. The // client is over its query limit. The test sets the client's clock. The
// second, a second before NICbrSkipTime has passed, does not. The third, // first lookup asks NIC.br. The next comes a second before PauseTime has
// once NICbrSkipTime has passed, asks again. Each keeps LACNIC's fields. // passed, and does not ask NIC.br. The last comes at PauseTime and asks
// NIC.br again. Each keeps LACNIC's fields.
func TestLookupASNSkipsNICbrAfterItsLimit(t *testing.T) { func TestLookupASNSkipsNICbrAfterItsLimit(t *testing.T) {
t.Parallel() t.Parallel()
@@ -740,8 +741,8 @@ func TestLookupASNSkipsNICbrAfterItsLimit(t *testing.T) {
wantAsks int wantAsks int
}{ }{
{after: 0, wantAsks: 1}, {after: 0, wantAsks: 1},
{after: whois.NICbrSkipTime - time.Second, wantAsks: 1}, {after: whois.PauseTime - time.Second, wantAsks: 1},
{after: whois.NICbrSkipTime, wantAsks: 2}, {after: whois.PauseTime, wantAsks: 2},
} { } {
now = start.Add(step.after) now = start.Add(step.after)
@@ -785,6 +786,142 @@ func TestLookupASNReportsARefusal(t *testing.T) {
} }
} }
// resetServer starts a TCP server on the loopback address and returns the
// server's address. The server reads one query on each connection, then
// resets the connection.
func resetServer(t *testing.T) string {
t.Helper()
var listenConfig net.ListenConfig
listener, err := listenConfig.Listen(t.Context(), "tcp", "127.0.0.1:0")
if err != nil {
t.Fatalf("listen: %v", err)
}
t.Cleanup(func() { _ = listener.Close() })
go func() {
for {
conn, err := listener.Accept()
if err != nil {
return
}
_, _ = bufio.NewReader(conn).ReadString('\n')
// Closing a connection whose linger time is zero resets it.
if tcpConn, ok := conn.(*net.TCPConn); ok {
_ = tcpConn.SetLinger(0)
}
_ = conn.Close()
}
}()
return listener.Addr().String()
}
// newRIPEClient returns a client whose fake servers send answers. The
// client adds one to *ripeAsks each time it connects to RIPE's server. When
// reset is true, RIPE's server resets the connection instead of answering.
func newRIPEClient(
t *testing.T, answers map[string]string, reset bool, ripeAsks *int,
) *whois.Client {
t.Helper()
dial := fakeServers(t, answers)
resetAddress := resetServer(t)
client := whois.NewClient(slog.New(slog.DiscardHandler))
client.DialContext = func(
ctx context.Context, network, address string,
) (net.Conn, error) {
if address == ripeServer {
*ripeAsks++
}
if address == ripeServer && reset {
var dialer net.Dialer
return dialer.DialContext(ctx, network, resetAddress)
}
return dial(ctx, network, address)
}
return client
}
// TestLookupASNPausesAServerThatRefuses looks up an AS at RIPE while RIPE
// refuses the query, in each of the ways a server refuses. The test sets
// the client's clock. A lookup a second before PauseTime has passed fails
// with ErrPaused and asks RIPE nothing. A lookup of an AS at APNIC succeeds
// during the pause. A lookup at PauseTime asks RIPE again.
func TestLookupASNPausesAServerThatRefuses(t *testing.T) {
t.Parallel()
for name, test := range map[string]struct {
// ripeAnswer is RIPE's answer. With none, RIPE's server refuses
// the connection, or resets it when reset is true.
ripeAnswer string
reset bool
}{
"access denied": {ripeAnswer: ripeRefusal},
"limit reached": {ripeAnswer: ripeLimitReached + "\n"},
"refused connection": {},
"reset connection": {reset: true},
} {
t.Run(name, func(t *testing.T) {
t.Parallel()
answers := map[string]string{
ianaQuery: ianaReferral,
apnicIANAQuery: "refer: whois.apnic.net\n",
apnicQuery: apnicRecord,
}
if test.ripeAnswer != "" {
answers[ripeQuery] = test.ripeAnswer
}
ripeAsks := 0
client := newRIPEClient(t, answers, test.reset, &ripeAsks)
start := time.Date(2026, 11, 2, 0, 0, 0, 0, time.UTC)
now := start
client.Now = func() time.Time { return now }
_, err := client.LookupASN(t.Context(), testASN)
if err == nil || errors.Is(err, whois.ErrPaused) {
t.Fatalf("LookupASN while RIPE refuses: error %v, want a "+
"refusal", err)
}
now = start.Add(whois.PauseTime - time.Second)
_, err = client.LookupASN(t.Context(), testASN)
if !errors.Is(err, whois.ErrPaused) || ripeAsks != 1 {
t.Errorf("LookupASN during the pause: error %v after %d "+
"queries to RIPE, want ErrPaused after 1", err, ripeAsks)
}
_, err = client.LookupASN(t.Context(), apnicASN)
if err != nil {
t.Errorf("LookupASN of an AS at APNIC during RIPE's "+
"pause: %v", err)
}
now = start.Add(whois.PauseTime)
_, _ = client.LookupASN(t.Context(), testASN)
if ripeAsks != 2 {
t.Errorf("RIPE was asked %d times after the pause, want 2",
ripeAsks)
}
})
}
}
// TestLookupASNFailsWhenTheRIRGivesNoAnswer looks up an AS IANA refers to // TestLookupASNFailsWhenTheRIRGivesNoAnswer looks up an AS IANA refers to
// RIPE when RIPE's server refuses the connection, and when it answers only // RIPE when RIPE's server refuses the connection, and when it answers only
// with an error. Neither is a lookup that found the AS. // with an error. Neither is a lookup that found the AS.