Author SHA1 Message Date
clawbot 946c8a4b41 Make the routewatch tests pass on a loaded host (closes #213)
check / check (push) Canceled after 0s
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 00:06:53 +00:00
72 changed files with 2325 additions and 11057 deletions

No files matched your search

+2 -3
View File
@@ -93,12 +93,11 @@
**/*.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 databases # context, so these would otherwise ship inside it. The daemon's database
# are db.sqlite and cache.db, with their -wal and -shm files while it runs. # is db.sqlite, with its -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
+1 -3
View File
@@ -68,12 +68,10 @@ 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
# databases are db.sqlite and cache.db, with their -wal and -shm files # database is db.sqlite, with its -wal and -shm files while it runs.
# 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
+1 -1
View File
@@ -105,7 +105,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
ARG CACHEBUST ARG CACHEBUST
# Create non-root user # Create non-root user
RUN useradd -u 1000 -m routewatch RUN useradd -r -u 1000 -m routewatch
RUN mkdir -p /var/lib/berlin.sneak.app.routewatch && chown routewatch:routewatch /var/lib/berlin.sneak.app.routewatch RUN mkdir -p /var/lib/berlin.sneak.app.routewatch && chown routewatch:routewatch /var/lib/berlin.sneak.app.routewatch
+581 -940
View File
File diff suppressed because it is too large. Load diff
+255 -406
View File
@@ -10,284 +10,143 @@
# Status # Status
RouteWatch is pre-1.0, with no git tags. `main` last took `next` on 2026-10-27, pre-1.0. No git tags. `main` last took `next` on 2026-10-06, through
through https://git.eeqj.de/sneak/routewatch/pulls/166. https://git.eeqj.de/sneak/routewatch/pulls/6. The linter and the tests are
https://git.eeqj.de/sneak/routewatch/pulls/202 carries the commits since then phases of the Docker build, and the Gitea workflow runs `script/cibuild` (the
into `main`. It is labelled `merge-ready` and waits for sneak. format check of the Go code and the markdown, both phases, then the image) on
every push. The image sets memory ceilings for a 5 GiB container (README
The linter and the tests are phases of the Docker build. The Gitea workflow runs "Memory") and the README says how to run it under upaas (README "Running under
`script/cibuild` on every push. That script runs the two phases and checks the upaas"). A 25-hour run of `a9b6860` on the live feed peaked at about 0.6 GiB
formatting of the Go code and the markdown. Then it builds the image. (https://git.eeqj.de/sneak/routewatch/issues/3). A run of `825afa2` on the live
feed found the prefix handler dropping about a quarter of its updates because
The image sets memory ceilings for a 5 GiB container (README "Memory"). README its route writes were slower than the feed
"Running under upaas" says how to run it. (https://git.eeqj.de/sneak/routewatch/issues/96); the cheaper writes since then
are measured by a benchmark, not yet on the live feed.
Five runs of `next` on the live feed have ended since 2026-10-27, from three
hours to five days long. The runs found the handlers dropping updates for five
causes, and the WHOIS fetcher asking a registry that had refused it. Each is
fixed on `next`, and its Completed Steps entry below names its issue. A 21-hour
run of `742e759`, which has every fix but one, dropped no update except after
the feed stalled. That cause, https://git.eeqj.de/sneak/routewatch/issues/229,
is fixed on `next`.
A run of `e58c663` on the live feed began at 09:19 UTC on 2026-11-10
(https://git.eeqj.de/sneak/routewatch/issues/232). It is to confirm that fix.
Next Step lists what its outcome reports. The seven IP lookup additions of
https://git.eeqj.de/sneak/routewatch/issues/203 landed after it began, so it
does not exercise them.
The order of the project's remaining work is kept on
https://git.eeqj.de/sneak/routewatch/issues/86.
# Next Step # Next Step
Post the outcome of the run of `e58c663` on Run `next` on the live feed, as README "Running under upaas" describes, until
https://git.eeqj.de/sneak/routewatch/issues/232. The run lasts at least 24 the routing table stops growing. Post its size and memory figures on
hours. If the feed has not stalled or reconnected by then, the run goes on until https://git.eeqj.de/sneak/routewatch/issues/122. The same run makes the final
it does, up to 72 hours in all. The outcome says: check https://git.eeqj.de/sneak/routewatch/issues/96 names: whether the prefix
handler still drops updates after the first hour. If it does, a new issue
- whether the feed stalled or reconnected follows with the numbers. Then an audit of the code at the commit that run
- whether any handler dropped an update, and the most messages the prefix tested.
handler's queue held at once
- the most messages the prefix handler held back at once
- the size of the `origin_changes` table on disk
- the process's peak memory against 5 GiB
File an issue for each problem the run finds.
# Completed Steps # Completed Steps
- 2026-11-10: `README.md` and this file are read whole against the rules of - 2026-10-27: the tests of `internal/routewatch` no longer fail on a loaded
https://git.eeqj.de/sneak/routewatch/issues/157, and every statement except
measured figures and what outside services do is checked against the code on
`next`. Four README sentences failed the prose rules. Five disagreed with the
code. Each is rewritten. Status and Next Step describe the live-feed run in
progress (closes https://git.eeqj.de/sneak/routewatch/issues/251).
- 2026-11-10: the image creates the `routewatch` user as a regular user with UID
1000, so the build no longer warns about the system UID range (closes
https://git.eeqj.de/sneak/routewatch/issues/248).
- 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 two ProtonVPN lists from a public mirror of
Proton's server list. `protonvpn` holds the /24 networks of ProtonVPN's
servers, and `protonvpn_entry` holds the servers' IPv4 and IPv6 addresses
(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
in memory and in `cache.db` for the record's TTL. A TTL is the time for which
a DNS record may be kept (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 waits for something that should happen are now 15 seconds. Tests
that depend on a short idle timeout or a request limit run on a fake clock
(closes https://git.eeqj.de/sneak/routewatch/issues/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 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 batch, which under the race detector can take longer. A test now waits up to
seconds for each step it expects. The tests of the handlers' limits now give 15 seconds for each step it expects. The tests of the handlers' limits give
the handlers small limits. So the package no longer runs past its 90-second the handlers small ones, so the package no longer runs past its 90-second
limit (closes #213, #215) limit (closes #213, #215)
- 2026-10-27: The server works out the home page's cards every minute until it - 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 stops. It used to work them out only once, at startup: the end of the context
given to `Start` stopped the refreshes (closes #211) that `Start` is given stopped the refreshes (closes #211)
- 2026-10-27: README "Rationale" says why RouteWatch exists. RouteWatch answers - 2026-10-27: README "Rationale" says why RouteWatch exists: to answer our other
our other services' questions about IP addresses, from its own routing table services' questions about IP addresses, from its own routing table and the
and the WHOIS details it keeps. The section still says what RIS Live does not WHOIS details it keeps. It still says what RIS Live does not give (closes
give (closes #204) #204)
- 2026-10-27: Every JSON answer carries `@meta`. A panic on a JSON route answers - 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 405 500 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 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 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 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 the message of an error answer. A test checks `@meta` on every JSON route, in
its successes and its errors (closes #201) 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 - 2026-10-27: every value in a JSON answer that has a unit is a number, with the
at the end of the field name. `@meta.execution_time` is now unit at the end of its field name. `@meta.execution_time` is now
`execution_time_ms`. In the stats, `uptime` is now `uptime_seconds`, `execution_time_ms`. The stats' `uptime`, `connection_duration` and
`connection_duration` is now `connection_duration_seconds`, and `memory_usage` `memory_usage` are now `uptime_seconds`, `connection_duration_seconds` and
is now `memory_usage_bytes`. `whois_stats.current_interval` is now `memory_usage_bytes`. `whois_stats.current_interval` is now
`whois_stats.current_interval_seconds`. They used to be strings such as "12 `current_interval_seconds`. They used to be strings such as "12 ms",
ms", "1h18m34s" or "1.1 GB". `connection_duration_seconds` is null while the "1h18m34s" or "1.1 GB". `connection_duration_seconds` is null while the feed
feed is not connected. `API_POLICIES.md` is vendored from `sneak/prompts`, and is not connected. `API_POLICIES.md` is vendored from `sneak/prompts`, and
`REPO_POLICIES.md` is re-vendored (closes #199) `REPO_POLICIES.md` re-vendored (closes #199)
- 2026-10-27: Every result of the IP lookup has the same fields. A field without - 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 a value is null. It used to be left out. An address with no live route has
routing table has every route and AS field set to null. `ptr` is an empty list every route and AS field set to null, and `ptr` is an empty list when there
when there are no PTR names. The new field `num_origins` gives the number of are no PTR names. New fields give the number of origin ASes of the netblock,
origin ASes of the netblock, and `origin_asns` gives which they are (closes in `num_origins`, and which they are, in `origin_asns` (closes #200)
#200) - 2026-10-27: with `TRUSTED_PROXIES` unset, the server trusts reverse proxies at
- 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 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 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. to give the proxy's address. A list in `TRUSTED_PROXIES` replaces the default,
`TRUSTED_PROXIES` set but empty trusts no proxy (closes #198) and `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 - 2026-10-27: the home page has cards with figures of the routing table: the
card shows the newest and the oldest kept route. One shows the newest and the newest and oldest kept route, the newest and oldest updated AS, the AS with
oldest updated AS. One shows the AS with the most prefixes. One shows the ASes the most prefixes, the ASes with a single prefix, and fifteen well-known
with a single prefix. One shows fifteen well-known networks. Two cards count networks. Two cards count the bogon announcements and the prefixes with more
the bogon announcements and the prefixes with more than one origin AS. They than one origin AS, and link to the new pages `/bogons` and
link to the new pages `/bogons` and `/multiple-origins`, which list them. A `/multiple-origins` that list them. A new package, `internal/bogon`, tells
new package, `internal/bogon`, tells which prefixes and AS numbers are which prefixes and AS numbers are reserved. The server works the figures out
reserved. The server works the figures out once a minute (closes #154) once a minute (closes #154)
- 2026-10-27: The per-peer route tables are gone, with the code that wrote, - 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. It writes the table's changes every second. It also stores table in memory and writes the table's changes every second. It also stores
each new prefix with its first-seen time. The image's memory limits fit a full each new prefix with its first-seen time. The image's memory limits are set
routing table of about 1 GB. `GOMEMLIMIT` is 2.5 GiB. The writing connection's for a full routing table of about 1 GB: `GOMEMLIMIT` is 2.5 GiB, the writing
page cache is 512 MiB. SQLite's soft and hard heap limits are 768 MiB and 1 connection's page cache 512 MiB, and SQLite's heap limits 768 MiB and 1 GiB
GiB (closes #122) (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. Only the kept prefix page and API list every peer that carries the prefix, with an AS path,
routes show an AS path, a next hop and a time. The stats count the origins next hop and time only for the kept routes. The stats count the origins whose
whose kept routes were all withdrawn, in `origins_without_kept_route` (part of kept routes were all withdrawn, in `origins_without_kept_route` (part of #122)
- 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 prefix, AS and peer handlers make a timed write on every tick - 2026-10-27: the database keeps a copy of the whole routing table in a new
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,
Another reads the whole table back into memory at startup. Nothing uses them and another reads the whole table back into memory at startup. Nothing uses
yet (part of #122) them 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. It also keeps the two newest of their routes. Nothing it, one bit per peer, and the two newest of their routes. Nothing uses it yet
uses it yet (part of #122) (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, two Spamhaus DROP lists and the Tor exit list. RouteWatch FireHOL lists, Spamhaus DROP and the Tor exit list. RouteWatch downloads each
downloads each list on its own schedule and answers from copies in memory. The list on its own schedule and answers from copies in memory. The copies are
copies are also kept in the state directory's `blocklists` directory. IP also kept in the state directory's `blocklists` directory. IP lookup answers
lookup answers carry `Cache-Control`. An address with no route now has a carry `Cache-Control`. An address with no live route now has a result too,
result too, without route fields. So the IP lookup no longer answers 404 without route fields, so the IP lookup no longer answers 404 (closes #158)
(closes #158) - 2026-10-27: the home page has an IP information API card. It shows the `curl`
- 2026-10-27: The home page has an IP information API card. It shows the `curl` command that looks up the visitor's own address at `/ip/{addr}`, and that
command that looks up the visitor's own address at `/ip/{addr}`. It also shows command's live answer (closes #156)
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
- 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. Prefixes of one mask length are listed by address. They used shortest first, and prefixes of one mask length by address. They used to be
to be sorted by address first, then by mask length (closes #153) listed by address (closes #153)
- 2026-10-27: The connection status on `/` and `/status` gets a spinner. It - 2026-10-27: on `/` and `/status`, a spinner beside the status turns one frame
turns one frame each time the stats show more messages than the time before. each time the stats show more messages than the time before. A page that has
After three refreshes with no new messages, the page shows "stale" in red not seen more messages for three refreshes shows "stale" and the time since
instead. Next to it is the time since the last fresh answer (closes #152) then instead, in red (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 is NIC.br's answer with each accented letter LACNIC's answer for such an AS comes from NIC.br, Brazil's registry, with each
replaced. NIC.br is Brazil's registry. The details now come from NIC.br's own accented letter replaced. The details now come from NIC.br's own server,
server, `whois.registro.br`. When that query fails, the details from LACNIC's `whois.registro.br`. When that query fails, the details from LACNIC's answer
answer are kept and a warning is logged. RouteWatch stops asking NIC.br for an are kept and a warning is logged. After NIC.br answers that RouteWatch is over
hour after NIC.br says RouteWatch is over its query limit (closes #174) its query limit, RouteWatch stops asking NIC.br for an hour (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)
@@ -296,192 +155,182 @@ File an issue for each problem the run finds.
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 before it is parsed WHOIS answer that is not valid UTF-8 is decoded as Latin-1, which RIPE and
and stored. RIPE and APNIC send Latin-1 (closes #165) APNIC send, before it is parsed and stored (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". It used to print Go durations such as "5 minutes ago" or "2 weeks ago", instead of Go durations such as "360h0m0s
"360h0m0s ago". An age under a minute reads "now" or in seconds. An age over a ago". An age under a minute reads in seconds, and one over a month in months
month reads in months or years instead of a date (closes #163) 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. It keeps the later of the two last-seen times. An old two first-seen times and the later of the two last-seen times. An old update
update from a collector catching up on a backlog no longer moves last seen from a collector catching up on a backlog no longer moves last seen back
back (closes #162) (closes #162)
- 2026-10-26: The status page shows "Route Churn/min". That is the number of - 2026-10-26: the status page shows "Route Churn/min", the number of prefix
prefix announcements and withdrawals from all peers in the last full clock announcements and withdrawals, from all peers, in the last full clock minute.
minute. `/api/v1/stats` reports it as `route_churn_per_min` in `stream`. It `/api/v1/stats` reports it as `route_churn_per_min` in `stream`, which
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. RIPE counts those objects APNIC and AFRINIC leave out person and role objects, which RIPE counts against
against a daily limit per address. A refused query is logged with the RIR's a daily limit per address. A refused query is logged with the RIR's error line
error line (closes #159) (closes #159)
- 2026-10-26: The home page's AS name search works. It lists the ASes whose - 2026-10-26: the home page's AS name search lists the ASes whose handle or
handle or description holds the text, as links to their pages. The new description holds the text, as links to their pages, from the new
`/api/v1/search/as` answers it. The search ignores case. When the database has `/api/v1/search/as`; the search ignores case. When the database has no record
no record of an AS, its page takes the handle and description from the AS list of an AS, its page takes the handle and description from the AS list built
built into RouteWatch. It still lists the AS's prefixes (closes #151) into RouteWatch and 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,
README "Database Schema" matches `schema.sql`. The rest of the README matches "Database Schema" matches `schema.sql`, and the rest of the README matches the
the code. This file is brought up to date (closes #72) code; this file 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. The prefix tables lose their duplicate index. A route their random UUID keys and the prefix tables their duplicate index, a route
update sets only the columns that change. Every write goes through one update sets only the columns that change, and 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 checkpoint of the WAL (SQLite's write-ahead log), the - 2026-10-19: the WAL checkpoint, the incremental vacuum and ANALYZE take the
incremental vacuum and `ANALYZE` take the database lock that every batch write database lock every batch write holds, so a vacuum no longer fails with
holds. So a vacuum no longer fails with "database is locked". An `ANALYZE` no "database is locked" and an ANALYZE no longer makes a batch write lose its
longer makes a batch write lose its updates. `ANALYZE` runs as updates; ANALYZE runs as `PRAGMA optimize` with an analysis limit (closes #94)
`PRAGMA optimize` with an analysis limit (closes #94) - 2026-10-19: shutdown stops the streamer first, and each handler writes
- 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
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,
which means no known origin. It used to have the set's last member as its no known origin, instead of the set's last member, and the set adds no
origin. The set adds no peerings. The pages show such a route as having no peerings; the pages show such a route as having no known origin (closes #75)
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. It - 2026-10-19: `bgp_peer_count` counts every peer the feed has heard from, not
used to count only the peers whose session opened since startup. It drops a only those whose session opened since startup, and drops a peer whose session
peer whose session goes down (closes #74) 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`. The linter is `golangci-lint` v2.14.0 with its configuration. Lint `0653579`: golangci-lint v2.14.0 and its configuration, lint and test as
and test are `Dockerfile` phases that keep Go's and `golangci-lint`'s caches. `Dockerfile` phases that keep Go's and golangci-lint's caches, markdown
`make fmt` also formats the markdown with `prettier`. The agent guidance moves formatted with prettier, agent guidance in `AGENTS.md`; the code is fixed for
to `AGENTS.md`. The code is fixed for what the new linter configuration finds what the new linter configuration finds (closes #52)
(closes #52) - 2026-10-19: the streamer reads feed lines up to 1 MiB, so a line over 64 KiB
- 2026-10-19: The streamer reads feed lines up to 1 MiB. A line over 64 KiB used no longer ends the connection (closes #76)
to end the connection (closes #76) - 2026-10-19: a peer's live routes are removed when its BGP session goes down;
- 2026-10-19: A peer's live routes are removed when its BGP session goes down. `STATE` messages are never dropped for backpressure, and one that finds its
`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. They used to read every route of that length. They list each index lookups instead of reading every route of that length, and list each
prefix once (closes #66) prefix once (closes #66)
- 2026-10-19: A request past its time limit answers 504 instead of 408. - 2026-10-19: a request past its time limit answers 504 instead of 408, and
`/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. A withdrawal removes it with a new origin AS replaces the peer's route and 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. The health check reports the feed disconnected nothing for 60 seconds, and 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. It used to read every route of each origin AS (closes #67) query instead of reading 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. It used to run on without a web server (closes #73) on its port, instead of running on without it (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. Any valid way of writing a prefix finds its routes does not parse answers 400, and any valid way of writing a prefix finds its
(closes #71) routes (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. It used - 2026-10-14: a prefix batch keeps each peer's last update for a prefix, instead
to keep one update per prefix across all peers (closes #54) of 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. The - 2026-10-03: `/api/v1/stats` serves the prefix distribution from memory, seeded
distribution is seeded at startup and adjusted on every live-route write. So a at startup and adjusted on every live-route write, so a request no longer
request no longer reads every live route (closes #30) 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,
The setting goes in the connection string, so it is set before the file is through the connection string so it is set before the file is first written,
first written. Each periodic incremental vacuum now returns up to 1000 free and each periodic incremental vacuum now returns up to 1000 free pages; the
pages. The late `PRAGMA auto_vacuum` in `Initialize`, which SQLite ignored, is late `PRAGMA auto_vacuum` in `Initialize`, which SQLite ignored, is gone
gone (closes #43) (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. The IPv4 range columns are gone. Prefixes from the feed are the prefix index, and the IPv4 range columns are gone. Prefixes from the feed
stored in one text form. So an IPv6 withdrawal, which the feed sends are 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
into the page footer. It used to stamp `unknown`. The value comes from (`git describe --tags --always`) into the page footer instead of `unknown`:
`git describe --tags --always`. `.dockerignore` sends `.git` without `.dockerignore` sends `.git` without `.git/config`, a `VERSION` build argument
`.git/config`. A `VERSION` build argument takes precedence. `make build` takes precedence, and `make build` stamps the same value (closes #46)
stamps the same value (closes #46) - 2026-09-29: the entrypoint creates the data directory if it is missing and
- 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
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. So they stay out of the source and `.env` out of the Docker build context, and so out of the source archive
archive in the image (closes #39) in the image (closes #39)
- 2026-09-29: The README's first line names the MIT licence and the author. The - 2026-09-29: README first line names the MIT license and the author; the
License section says MIT and links `LICENSE`. An Author section is added. This License section now says MIT and links `LICENSE`, and an Author section was
file is brought up to date (closes #38) added; this file brought up to date (closes #38)
- 2026-09-29: `LICENSE` is added, with the MIT licence (closes #1) - 2026-09-29: MIT `LICENSE` (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. A second `Stop` no longer closes the handing a message to the handler queues, and a second `Stop` no longer closes
queues again (closes #34) the 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. It gets the instead of `runuser`, so the daemon receives the signal itself and 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: RouteWatch is ready to run under upaas. A set but invalid `PORT`, - 2026-09-28: 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 gains a "Running under upaas" section (closes #31) follows `PORT`, README "Running under upaas" section (closes #31)
- 2026-09-22: The database statistics are kept in memory. The counts are seeded - 2026-09-22: realtime in-memory database statistics: counts seeded at startup
at startup and adjusted on every write. The oldest and newest route times come and adjusted on every write, oldest/newest route timestamps via index-end
from a lookup at each end of an index. `/api/v1/stats` no longer scans the lookups; `/api/v1/stats` no longer scans the tables (closes #27)
tables (closes #27) - 2026-09-21: batch writes take the write lock when their transaction begins
- 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
(`_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 the number of glibc malloc - 2026-09-21: `MALLOC_ARENA_MAX=2` in the image caps glibc malloc arenas, so
arenas. So memory outside the Go runtime no longer grows with the core count memory outside the Go runtime no longer grows with the core count (closes #23)
(closes #23) - 2026-09-21: `GOMEMLIMIT=1536MiB` in the image; README Memory section with the
- 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 are fixed. The stats handlers leaked after a - 2026-09-21: two goroutine leaks fixed: the stats handlers after a timeout and
timeout. The streamer's tickers leaked on every reconnect (closes #12) the streamer's tickers 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` is added. A Gitea workflow runs `script/cibuild` - 2026-09-21: `.editorconfig`, and a Gitea workflow that 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. - 2026-09-21: the peering handler's AS-path map holds at most 500,000 paths and
Every 30 seconds it is swapped for an empty one instead of copied (closes #10) is swapped for an empty one every 30 seconds instead of copied (closes #10)
- 2026-09-21: SQLite's memory is bounded across the whole connection pool. Each - 2026-09-21: SQLite memory bounded across the whole connection pool: a 64 MiB
connection has a 64 MiB page cache. The heap limits are 1 GiB soft and 1.5 GiB page cache on each connection, 1 GiB soft and 1.5 GiB hard heap limits (closes
hard (closes #8) #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 runs in a separate stage on a `golangci-lint` image pinned by digest linting in a separate stage on a golangci-lint image pinned by digest (closes
(closes #5) #5)
- 2026-09-21: `make test` skips the live feed test, with `-short`. So - 2026-09-21: `make test` skips the live-network feed test (`-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: The scripts-to-rule-them-all layout is adopted. `script/` holds - 2026-07-07 Adopted scripts-to-rule-them-all: `script/` entrypoints, Makefile
the entrypoints. The `Makefile` targets `check`, `test`, `lint`, `fmt` and shims, README Entrypoints section
`fmt-check` call them. So do `bootstrap`, `setup`, `docker` and `hooks`. - 2026-02-22: repo policy compliance: required policy files, .gitignore update,
README gains an "Entrypoints" section Makefile fmt-check/check/docker/hooks targets, gofmt pass
- 2026-02-22: The repo is brought in line with the repo policies. The required (repo-policies-compliance, unmerged)
policy files are added. `.gitignore` is updated. The `Makefile` gains - 2026-01-01: WAL checkpointing: periodic (5s), on startup with logging,
`fmt-check`, `check`, `docker` and `hooks` targets. The Go code is formatted TRUNCATE mode; fixed slow queries
with `gofmt`. The work was on the branch `repo-policies-compliance`, unmerged - 2025-12-31: status page: navbar, home page with search, oldest/newest route
when this entry was written timestamps, NULL handling in WHOIS stats; container runs as routewatch user
- 2026-01-01: The WAL is checkpointed every 5 seconds, and at startup with a log with proper state dir
line. Checkpoints run in `TRUNCATE` mode. This fixed slow queries - 2025-12-30: structured HTTP request logging, increased timeouts, CIDR prefix
- 2025-12-31: The pages get a navigation bar and a home page with a search. The URL routing fixes, status page metrics and footer
status page shows the oldest and newest route times. The WHOIS stats query - 2025-12-29: Dockerfile multi-stage build with source archive; SQLite
handles `NULL`. The container runs as the `routewatch` user with the right incremental vacuum for non-blocking space reclamation
state directory - 2025-07-27: initial RouteWatch BGP stream monitor
- 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.
+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 = 15 * time.Second const parseTimeLimit = 2 * 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
+2 -7
View File
@@ -8,15 +8,11 @@ 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 v0.45.0 golang.org/x/term v0.33.0
golang.org/x/text v0.43.0 golang.org/x/text v0.43.0
) )
@@ -24,6 +20,5 @@ 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/net v0.57.0 // indirect golang.org/x/sys v0.34.0 // indirect
golang.org/x/sys v0.49.0 // indirect
) )
+10 -20
View File
@@ -1,5 +1,7 @@
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=
@@ -8,20 +10,14 @@ 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/maxmind/mmdbwriter v1.2.0 h1:hyvDopImmgvle3aR8AaddxXnT0iQH2KWJX3vNfkwzYM= github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
github.com/maxmind/mmdbwriter v1.2.0/go.mod h1:EQmKHhk2y9DRVvyNxwCLKC5FrkXZLx4snc5OlLY5XLE= github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
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 v1.12.1 h1:EuwCh5fleGS7H32xRwO3wRGT7DxrDhLAT6FF8MpWDWE= github.com/stretchr/testify v1.8.1 h1:w7B6lhMri9wdJUVmEZPGGhZzrYTPvgJArz7wNPgYKsk=
github.com/stretchr/testify v1.12.1/go.mod h1:MDEgiDPPsNp5cuIrHPPCyornHKgEVbtFUmoNlxoYthg= github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
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=
@@ -32,18 +28,12 @@ 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/net v0.57.0 h1:K5+3DljvIuDG9/Jv9rvyMywYNFCQ9RSUY6OOTTkT+tE= golang.org/x/sys v0.34.0 h1:H5Y5sJ2L2JRdyv7ROF1he/lPdvFsd0mJHFw2ThKHxLA=
golang.org/x/net v0.57.0/go.mod h1:KpXc8iv+r3XplLAG/f7Jsf9RPszJzdR0f58q9vGOuEU= golang.org/x/sys v0.34.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
golang.org/x/sync v0.24.0 h1:iqiDrGoDgyuvAKrhLQthUEzU/R378N78gXbBjxed7oA= golang.org/x/term v0.33.0 h1:NuFncQrRcaRvVmgRkvM3j/F00gWIAlcmlB8ACEKmGIg=
golang.org/x/sync v0.24.0/go.mod h1:sUUOizhqBxiL6pEWpqNLUiaJn1ShEbZ6BBqskPbjZm0= golang.org/x/term v0.33.0/go.mod h1:s18+ql9tYWp1IfpV9DmCtQDDSRBUjKaw9M1eAv5UeF0=
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=
@@ -1,7 +1,7 @@
// Package iplist downloads public IP lists on a schedule, keeps the last good // Package blocklist downloads public IP blocklists on a schedule, keeps the
// copy of each on disk and in memory, and answers which lists contain an // last good copy of each on disk and in memory, and answers which lists
// address. // contain an address.
package iplist package blocklist
import ( import (
"context" "context"
@@ -29,41 +29,9 @@ 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 IP list. // List is one public blocklist.
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
@@ -80,9 +48,6 @@ 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.
@@ -93,10 +58,6 @@ 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.
@@ -119,9 +80,9 @@ type Params struct {
Logger *slog.Logger Logger *slog.Logger
} }
// IPLists keeps a copy of each list and answers which lists contain an // Blocklists 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 IPLists struct { type Blocklists struct {
dir string dir string
lists []List lists []List
logger *slog.Logger logger *slog.Logger
@@ -136,12 +97,12 @@ type IPLists struct {
done chan struct{} done chan struct{}
} }
// New returns an IPLists with no copies. Start loads them. // New returns a Blocklists with no copies. Start loads them.
func New(params Params) *IPLists { func New(params Params) *Blocklists {
return &IPLists{ return &Blocklists{
dir: params.Dir, dir: params.Dir,
lists: params.Lists, lists: params.Lists,
logger: params.Logger.With("component", "iplists"), logger: params.Logger.With("component", "blocklists"),
copies: make(map[string]listCopy), copies: make(map[string]listCopy),
done: make(chan struct{}), done: make(chan struct{}),
} }
@@ -150,7 +111,7 @@ func New(params Params) *IPLists {
// 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 *IPLists) Lookup(addr netip.Addr) []Listing { func (b *Blocklists) Lookup(addr netip.Addr) []Listing {
b.mu.RLock() b.mu.RLock()
defer b.mu.RUnlock() defer b.mu.RUnlock()
@@ -163,7 +124,6 @@ func (b *IPLists) 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,
}) })
} }
} }
@@ -173,7 +133,7 @@ func (b *IPLists) 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 *IPLists) ShortestInterval() time.Duration { func (b *Blocklists) ShortestInterval() time.Duration {
var shortest time.Duration var shortest time.Duration
for i, list := range b.lists { for i, list := range b.lists {
@@ -187,7 +147,7 @@ func (b *IPLists) 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 *IPLists) updated(name string) time.Time { func (b *Blocklists) updated(name string) time.Time {
b.mu.RLock() b.mu.RLock()
defer b.mu.RUnlock() defer b.mu.RUnlock()
@@ -196,7 +156,7 @@ func (b *IPLists) 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 *IPLists) copyValidators(name string) validators { func (b *Blocklists) copyValidators(name string) validators {
b.mu.RLock() b.mu.RLock()
defer b.mu.RUnlock() defer b.mu.RUnlock()
@@ -204,7 +164,7 @@ func (b *IPLists) copyValidators(name string) validators {
} }
// setCopy makes c the named list's copy. // setCopy makes c the named list's copy.
func (b *IPLists) setCopy(name string, c listCopy) { func (b *Blocklists) setCopy(name string, c listCopy) {
b.mu.Lock() b.mu.Lock()
defer b.mu.Unlock() defer b.mu.Unlock()
@@ -212,7 +172,7 @@ func (b *IPLists) 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 *IPLists) setUpdated(name string, t time.Time) { func (b *Blocklists) setUpdated(name string, t time.Time) {
b.mu.Lock() b.mu.Lock()
defer b.mu.Unlock() defer b.mu.Unlock()
@@ -0,0 +1,494 @@
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
}
}
@@ -1,4 +1,4 @@
package iplist package blocklist
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, iCloud Private Relay, is about 12 MiB. // bytes. The largest list, FireHOL abusers, is about 2.5 MiB.
maxDownloadSize = 200 << 20 maxDownloadSize = 16 << 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 *IPLists) Start(ctx context.Context) { func (b *Blocklists) 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 IP lists directory", b.logger.Error("Failed to create the blocklists directory",
"dir", b.dir, "error", err) "dir", b.dir, "error", err)
} }
@@ -90,7 +90,7 @@ func (b *IPLists) 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 an IP list copy", b.logger.Error("Failed to load a blocklist copy",
"list", list.Name, "error", loadErr) "list", list.Name, "error", loadErr)
} }
@@ -104,20 +104,20 @@ func (b *IPLists) Start(ctx context.Context) {
b.run(ctx, nextDownload) b.run(ctx, nextDownload)
}() }()
b.logger.Info("IP list downloads started", "dir", b.dir) b.logger.Info("Blocklist 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 *IPLists) Stop(ctx context.Context) { func (b *Blocklists) Stop(ctx context.Context) {
b.stop() b.stop()
select { select {
case <-b.done: case <-b.done:
b.logger.Info("IP list downloads stopped") b.logger.Info("Blocklist downloads stopped")
case <-ctx.Done(): case <-ctx.Done():
b.logger.Warn("Stop deadline passed before the IP list downloads " + b.logger.Warn("Stop deadline passed before the blocklist downloads " +
"stopped") "stopped")
} }
} }
@@ -125,7 +125,7 @@ func (b *IPLists) 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 *IPLists) run(ctx context.Context, nextDownload []time.Time) { func (b *Blocklists) 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 *IPLists) run(ctx context.Context, nextDownload []time.Time) {
} }
if err != nil { if err != nil {
b.logger.Error("IP list download failed; keeping the "+ b.logger.Error("Blocklist download failed; keeping the "+
"previous copy", "list", list.Name, "error", err) "previous copy", "list", list.Name, "error", err)
} }
@@ -169,7 +169,7 @@ func (b *IPLists) 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 *IPLists) download(ctx context.Context, list List) error { func (b *Blocklists) 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 *IPLists) 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 *IPLists) replaceCopy(list List, body io.Reader, sent validators) error { func (b *Blocklists) 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 *IPLists) replaceCopy(list List, body io.Reader, sent validators) error
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 an IP list", "list", list.Name) b.logger.Info("Downloaded a new version of a blocklist", "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 an IP list copy", b.logger.Error("Failed to keep the validators of a blocklist 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 *IPLists) markCurrent(list List) error { func (b *Blocklists) 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 *IPLists) markCurrent(list List) error {
} }
b.setUpdated(list.Name, now) b.setUpdated(list.Name, now)
b.logger.Debug("IP list copy is still current", "list", list.Name) b.logger.Debug("Blocklist copy is still current", "list", list.Name)
return nil return nil
} }
@@ -312,7 +312,7 @@ func (b *IPLists) 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 *IPLists) loadCopy(list List) error { func (b *Blocklists) 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
+93
View File
@@ -0,0 +1,93 @@
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,
},
}
}
+158
View File
@@ -0,0 +1,158 @@
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
}
+2 -11
View File
@@ -1,5 +1,5 @@
// Package bogon tells whether a prefix, an address or an AS number is reserved: // Package bogon tells whether a prefix or an AS number is reserved: set aside
// set aside for a special purpose, so that no network should announce it on the // 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 // internet. A route is a bogon announcement when its prefix is reserved or its
// origin AS is. // origin AS is.
// //
@@ -42,15 +42,6 @@ func Prefix(prefix netip.Prefix) (string, bool) {
return holder.name + " (" + holder.prefix.String() + ")", true 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 // ASN returns why asn is reserved, and true, when it is. It returns "" and
// false when asn is not reserved. // false when asn is not reserved.
func ASN(asn int) (string, bool) { func ASN(asn int) (string, bool) {
+2 -38
View File
@@ -8,9 +8,6 @@ import (
"git.eeqj.de/sneak/routewatch/internal/bogon" "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) { func TestPrefix(t *testing.T) {
t.Parallel() t.Parallel()
@@ -19,8 +16,8 @@ func TestPrefix(t *testing.T) {
// want is why the prefix is reserved, or "" when it is not. // want is why the prefix is reserved, or "" when it is not.
want string want string
}{ }{
{"10.1.2.0/24", privateUseTen}, {"10.1.2.0/24", "Private-Use (10.0.0.0/8)"},
{"10.0.0.0/8", privateUseTen}, {"10.0.0.0/8", "Private-Use (10.0.0.0/8)"},
{"192.0.2.0/24", "Documentation (TEST-NET-1) (192.0.2.0/24)"}, {"192.0.2.0/24", "Documentation (TEST-NET-1) (192.0.2.0/24)"},
{"2001:db8:1::/48", "Documentation (2001:db8::/32)"}, {"2001:db8:1::/48", "Documentation (2001:db8::/32)"},
{"fd00::/8", "Unique-Local (fc00::/7)"}, {"fd00::/8", "Unique-Local (fc00::/7)"},
@@ -59,39 +56,6 @@ func TestPrefix(t *testing.T) {
} }
} }
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) { func TestASN(t *testing.T) {
t.Parallel() t.Parallel()
-51
View File
@@ -1,51 +0,0 @@
// 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
}
-64
View File
@@ -1,64 +0,0 @@
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")
}
}
-24
View File
@@ -1,24 +0,0 @@
-- 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
);
+6 -26
View File
@@ -72,34 +72,17 @@ 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 // waiting for it, may take while a reader is open: well under the busy
// longBusyTimeoutMs, with room for a stall on a busy host. // timeout, which a checkpoint that waits for the reader takes.
readerCheckpointLimit = 15 * time.Second readerCheckpointLimit = 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 readerCheckpointLimit. // wait for the reader plus a second, well under the busy timeout.
truncateCheckpointLimit = truncateBusyTimeoutMs*time.Millisecond + truncateCheckpointLimit = truncateBusyTimeoutMs*time.Millisecond +
readerCheckpointLimit time.Second
) )
// 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
@@ -290,7 +273,7 @@ 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.PeersDown([]string{peerA}) table.PeerDown(peerA)
writeTableChanges(t, db, table) writeTableChanges(t, db, table)
var before int var before int
@@ -596,8 +579,6 @@ 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)
@@ -709,7 +690,6 @@ func TestCheckpointEmptiesWALOnceNoReadIsOpen(t *testing.T) {
} }
fillWALPastLimit(ctx, t, db) fillWALPastLimit(ctx, t, db)
setLongBusyTimeout(ctx, t, db)
started := time.Now() started := time.Now()
+2 -11
View File
@@ -1,7 +1,6 @@
// Package database provides SQLite storage for BGP routing data: ASNs, // Package database provides SQLite storage for BGP routing data: ASNs,
// prefixes, announcements, peerings, BGP peers and origin changes. Its routes // prefixes, announcements, peerings and BGP peers. Its routes table holds a
// table holds a copy of the whole routing table that internal/routetable // copy of the whole routing table that internal/routetable keeps in memory.
// keeps in memory.
package database package database
import ( import (
@@ -56,14 +55,6 @@ 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
-172
View File
@@ -1,172 +0,0 @@
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
}
@@ -1,217 +0,0 @@
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))
}
}
+2 -3
View File
@@ -34,7 +34,6 @@ 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"
) )
@@ -108,7 +107,7 @@ 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.PeersDown([]string{peerC}) source.PeerDown(peerC)
announceTo(source, tablePrefixV6, asB, peerE, 70) announceTo(source, tablePrefixV6, asB, peerE, 70)
writeTableChanges(t, db, source) writeTableChanges(t, db, source)
@@ -134,7 +133,7 @@ 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.PeersDown([]string{peerB}) table.PeerDown(peerB)
announceTo(table, tablePrefixShortV4, asB, peerD, 50) announceTo(table, tablePrefixShortV4, asB, peerD, 50)
} }
+1 -17
View File
@@ -119,20 +119,4 @@ 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);
-253
View File
@@ -1,253 +0,0 @@
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)
}
}
-349
View File
@@ -1,349 +0,0 @@
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
}
-151
View File
@@ -1,151 +0,0 @@
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
}
-232
View File
@@ -1,232 +0,0 @@
// 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")
}
}
File diff suppressed because it is too large. Load diff
-992
View File
@@ -1,992 +0,0 @@
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
}
}
-209
View File
@@ -1,209 +0,0 @@
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,
},
}
}
-435
View File
@@ -1,435 +0,0 @@
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)
}
-324
View File
@@ -1,324 +0,0 @@
// 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)
}
}
-951
View File
@@ -1,951 +0,0 @@
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)
}
}
-200
View File
@@ -1,200 +0,0 @@
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-_."
-103
View File
@@ -1,103 +0,0 @@
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
}
-302
View File
@@ -1,302 +0,0 @@
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)
}
}
+10 -15
View File
@@ -10,6 +10,10 @@ import (
"git.eeqj.de/sneak/routewatch/internal/ristypes" "git.eeqj.de/sneak/routewatch/internal/ristypes"
) )
// walkBatch is how many prefixes the walk over the whole table reads in one
// hold of the read lock. The updates waiting for the lock get it in between.
const walkBatch = 10000
// Overview holds figures about the whole table. Working them out takes a walk // 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. // over every prefix, so a caller asks for them now and then and keeps them.
type Overview struct { type Overview struct {
@@ -79,9 +83,8 @@ type OriginPeers struct {
// Overview works out the table's overview. It lists at most maxListed bogon // 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: // 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 // the first in prefix order. It walks over every prefix, but holds the read
// of walkBatch. After each batch, it lets the table's lock go for as long as // lock for walkBatch prefixes at a time.
// it held the lock for the batch.
func (t *Table) Overview(maxListed int) Overview { func (t *Table) Overview(maxListed int) Overview {
var overview Overview var overview Overview
@@ -111,18 +114,15 @@ func (t *Table) Overview(maxListed int) Overview {
} }
// walkPrefixes calls visit with every prefix of the table and its origins. It // 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 // holds the read lock, but lets it go after every walkBatch prefixes, so the
// lets the table's lock go for as long as it held the lock for the batch. // updates waiting for it get in. A prefix that is added or removed in such a
// During a walk over many batches, updates can then take the lock about half // gap may or may not be visited, as Go allows for a map that changes during a
// of the time. The walk may or may not visit a prefix that is added or removed // range over it. visit must not keep origins once it returns.
// 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)) { func (t *Table) walkPrefixes(visit func(prefix netip.Prefix, origins []*origin)) {
t.mu.RLock() t.mu.RLock()
defer t.mu.RUnlock() defer t.mu.RUnlock()
visited := 0 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 {
@@ -131,13 +131,8 @@ func (t *Table) walkPrefixes(visit func(prefix netip.Prefix, origins []*origin))
visited++ visited++
if visited%walkBatch == 0 { if visited%walkBatch == 0 {
held := time.Since(batchStart)
t.mu.RUnlock() t.mu.RUnlock()
time.Sleep(held)
t.mu.RLock() t.mu.RLock()
batchStart = time.Now()
} }
} }
} }
@@ -131,61 +131,3 @@ func TestWalkPrefixesLetsUpdatesIn(t *testing.T) {
"before its second batch") "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
}
+1 -1
View File
@@ -227,7 +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.PeersDown([]string{peerC}) table.PeerDown(peerC)
checkCounts(t, table, routetable.Counts{ checkCounts(t, table, routetable.Counts{
Pairs: 2, Pairs: 2,
Peers: 3, Peers: 3,
+13 -83
View File
@@ -2,9 +2,7 @@
// 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. It also records each prefix and // route reads that the pages and the API need.
// origin AS pair's origin changes: when it gains its first peer and when it
// loses its last.
package routetable package routetable
import ( import (
@@ -29,11 +27,6 @@ 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
@@ -93,9 +86,6 @@ 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.
@@ -131,24 +121,11 @@ 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),
@@ -157,7 +134,6 @@ 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)
}), }),
@@ -224,60 +200,24 @@ func (t *Table) Withdraw(prefix netip.Prefix, peer string) {
} }
} }
// PeersDown applies the sessions of peers going down: each of the peers leaves // PeerDown applies a peer's session going down: the peer leaves every peer
// every peer set, and every route of each is dropped. When any of them carries // set, and every route of it is dropped. When the peer carries any prefix, it
// a prefix, PeersDown visits every prefix in the table once, in batches of // visits every prefix in the table.
// walkBatch. After each batch, it lets the table's lock go for as long as it func (t *Table) PeerDown(peer string) {
// 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()
// numbers holds the number of each of the peers that carries a prefix. number, known := t.peerNumbers[peer]
numbers := make([]uint, 0, len(peers)) if !known || t.peerPrefixes[number] == 0 {
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 {
for _, number := range numbers { o := originWithPeer(origins, number)
o := originWithPeer(origins, number) if o != nil {
if o != nil { t.leave(prefix, o, number)
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()
} }
} }
} }
@@ -287,9 +227,8 @@ func (t *Table) PeersDown(peers []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 and no origin change, so // Unlike an update, Load records no change, so TakeChanges does not hand the
// TakeChanges does not hand the pair back to be written again. Loading a pair // pair back to be written again. Loading a pair twice changes nothing.
// 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.
@@ -480,7 +419,6 @@ 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.
@@ -490,8 +428,6 @@ 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)
@@ -505,10 +441,6 @@ 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
@@ -567,8 +499,7 @@ 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, and a withdrawn origin // origin that no peer carries any more is removed.
// 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,
) { ) {
@@ -577,7 +508,6 @@ 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)
} }
} }
@@ -1,69 +0,0 @@
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
}
+11 -44
View File
@@ -69,10 +69,10 @@ func withdraw(peer string) step {
} }
} }
// peersDown is the step of the sessions of peers going down. // peerDown is the step of peer's session going down.
func peersDown(peers ...string) step { func peerDown(peer string) step {
return func(table *routetable.Table, _ netip.Prefix) { return func(table *routetable.Table, _ netip.Prefix) {
table.PeersDown(peers) table.PeerDown(peer)
} }
} }
@@ -272,28 +272,21 @@ 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),
peersDown(peerB)}, peerDown(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), peersDown(peerB)}, withdraw(peerB), peerDown(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 TestPeersDownLeavesEveryPrefix(t *testing.T) { func TestPeerDownLeavesEveryPrefix(t *testing.T) {
t.Parallel() t.Parallel()
table := routetable.New(routetable.Params{}) table := routetable.New(routetable.Params{})
@@ -310,7 +303,7 @@ func TestPeersDownLeavesEveryPrefix(t *testing.T) {
} }
table.Announce(prefixes[0], asB, routeOf(peerB, asB, 20)) table.Announce(prefixes[0], asB, routeOf(peerB, asB, 20))
table.PeersDown([]string{peerA}) table.PeerDown(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)}}}
@@ -340,32 +333,6 @@ func TestPeersDownLeavesEveryPrefix(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()
@@ -391,7 +358,7 @@ 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},
{peersDown(peerA), 0}, {peerDown(peerA), 0},
} }
for i, s := range steps { for i, s := range steps {
@@ -497,7 +464,7 @@ 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.PeersDown([]string{peerA}) table.PeerDown(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{
@@ -506,7 +473,7 @@ 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.PeersDown([]string{peerA}) table.PeerDown(peerA)
checkChanges(t, table, []change{}, map[string]uint{}) checkChanges(t, table, []change{}, map[string]uint{})
} }
@@ -650,7 +617,7 @@ 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.PeersDown([]string{peerB}) }, func(int) { table.PeerDown(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()) },
+17 -116
View File
@@ -9,21 +9,17 @@ 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/cachedb" "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/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"
@@ -65,15 +61,12 @@ type RouteWatch struct {
peeringHandler *PeeringHandler peeringHandler *PeeringHandler
asnFetcher *ASNFetcher asnFetcher *ASNFetcher
dbMaintainer *DBMaintainer dbMaintainer *DBMaintainer
ipLists *iplist.IPLists blocklists *blocklist.Blocklists
cacheDB *sql.DB
ptrCache *ptr.Cache
geoLocator *geo.Locator
} }
// ipListsDirName is the directory in the state directory that holds the IP // blocklistsDirName is the directory in the state directory that holds the
// list copies. // blocklist copies.
const ipListsDirName = "iplists" const blocklistsDirName = "blocklists"
// New creates a new RouteWatch instance // New creates a new RouteWatch instance
func New(deps Dependencies) *RouteWatch { func New(deps Dependencies) *RouteWatch {
@@ -145,27 +138,17 @@ 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 IP list copies from disk and start downloading the lists. // Load the blocklist copies from disk and start downloading the lists.
// The HTTP handlers read the server's IP lists without a lock, so they // The HTTP handlers read the server's blocklists without a lock, so they
// are set before the handlers run. // are set before the handlers run.
ipLists := iplist.New(iplist.Params{ blocklists := blocklist.New(blocklist.Params{
Dir: filepath.Join(rw.config.StateDir, ipListsDirName), Dir: filepath.Join(rw.config.StateDir, blocklistsDirName),
Lists: iplist.Lists(), Lists: blocklist.Lists(),
Logger: rw.logger.Logger, Logger: rw.logger.Logger,
}) })
ipLists.Start(ctx) blocklists.Start(ctx)
rw.ipLists = ipLists rw.blocklists = blocklists
rw.server.SetIPLists(ipLists) rw.server.SetBlocklists(blocklists)
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)
@@ -185,9 +168,8 @@ 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
// IP list downloads, the HTTP server, the geolocation cache and the PTR cache, // blocklist downloads and the HTTP server, and last the database, which it
// and last the database, which it checkpoints and closes. Each stage waits at // checkpoints and closes. Each stage waits at most until ctx ends, so
// 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.
@@ -237,8 +219,8 @@ func (rw *RouteWatch) Shutdown(ctx context.Context) {
rw.dbMaintainer.Stop(ctx) rw.dbMaintainer.Stop(ctx)
} }
if rw.ipLists != nil { if rw.blocklists != nil {
rw.ipLists.Stop(ctx) rw.blocklists.Stop(ctx)
} }
err := rw.server.Stop(ctx) err := rw.server.Stop(ctx)
@@ -247,12 +229,6 @@ 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
@@ -266,81 +242,6 @@ 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.
@@ -8,8 +8,6 @@ import (
"net/http" "net/http"
"net/http/httptest" "net/http/httptest"
"net/netip" "net/netip"
"os"
"path/filepath"
"slices" "slices"
"strconv" "strconv"
"strings" "strings"
@@ -332,23 +330,6 @@ 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()
@@ -420,7 +401,7 @@ func TestRouteWatchLiveFeed(t *testing.T) {
// Create streamer // Create streamer
s := streamer.New(logger, metricsTracker) s := streamer.New(logger, metricsTracker)
// The state directory holds the IP list copies Run downloads. // The state directory holds the blocklist copies Run downloads.
cfg := &config.Config{ cfg := &config.Config{
StateDir: t.TempDir(), StateDir: t.TempDir(),
MaxRuntime: 5 * time.Second, MaxRuntime: 5 * time.Second,
@@ -663,8 +644,9 @@ func TestShutdownDoesNotWaitForABlockedWrite(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: pathOfASes(asnBatchSize)}}) []*ristypes.RISMessage{{Path: fill}})
ctx, cancel := context.WithTimeout(t.Context(), deadline) ctx, cancel := context.WithTimeout(t.Context(), deadline)
defer cancel() defer cancel()
@@ -785,74 +767,3 @@ 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)
}
}
+97 -47
View File
@@ -18,34 +18,43 @@ 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 ASes in a full batch, which wakes the // asnBatchSize is the number of ASN operations to batch together
// 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 records every AS in the AS paths of BGP UPDATE messages. Its batch // ASHandler processes Autonomous System Number (ASN) information extracted from
// holds the earliest and the latest time of each AS's updates. The flush // BGP UPDATE messages. It uses batched database operations to efficiently store
// goroutine writes the batch to the database when it holds asnBatchSize ASes, // ASN data, collecting operations into batches that are flushed either when the
// and every asnBatchTimeout. // batch reaches a size threshold or after a timeout period.
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 // batchMaxSize is asnBatchMaxSize. Only HandleMessage reads it, so a test
// the batch under mu and writes it after releasing mu. So HandleMessage // may lower it before it hands the handler a message.
// never waits for a database write. batchMaxSize int
mu sync.Mutex
// batch holds the earliest and the latest time of the updates for each AS // Batching. mu guards batch and writing only: the flush goroutine takes
// since the flush goroutine last took it. It holds one entry per AS, // the batch under mu and writes it after releasing mu, so HandleMessage
// however many updates arrive. // waits for a database write only while batch is at batchMaxSize.
batch map[int]database.SeenTimes mu sync.Mutex
// writing is how many ASes the flush goroutine took from batch and has batch []asnOp
// not finished writing. // writing is how many operations the flush goroutine took from batch
writing int // and has not finished writing.
writing int
// batchTaken is signalled when the flush goroutine takes batch; its L is
// &mu.
batchTaken sync.Cond
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.
@@ -53,10 +62,16 @@ 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
// writes the collected ASes to the database. The caller must call Stop when // flushes accumulated ASN operations to the database. The caller must call
// finished, to write the pending ASes and end the background goroutine. // Stop when finished to ensure all pending operations are flushed and the
// 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)
} }
@@ -68,13 +83,15 @@ func newASHandler(
db database.Store, logger *logger.Logger, batchTimeout time.Duration, db database.Store, logger *logger.Logger, batchTimeout time.Duration,
) *ASHandler { ) *ASHandler {
h := &ASHandler{ h := &ASHandler{
db: db, db: db,
logger: logger, logger: logger,
batch: make(map[int]database.SeenTimes), batchMaxSize: asnBatchMaxSize,
batchFullCh: make(chan struct{}, 1), batch: make([]asnOp, 0, asnBatchSize),
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
// 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)
@@ -98,25 +115,48 @@ func (h *ASHandler) QueueCapacity() int {
return asHandlerQueueSize return asHandlerQueueSize
} }
// HandleMessage adds the time of msg to the batch entry of each AS in its AS // HandleMessage processes a RIS Live BGP message by extracting all ASNs from
// path, the origin AS and the members of an AS set included. When the batch // the AS path and queuing them for batch insertion into the database. The
// holds asnBatchSize ASes, HandleMessage wakes the flush goroutine to write it. // origin ASN and all transit ASNs are recorded with their associated
// 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()
// The origin AS is the last AS of the sequence, so the loop adds it too. // While the batch is at its maximum size, wait until the flush goroutine
// takes it. Meanwhile the handler takes nothing off its queue, which
// fills, and the streamer drops messages for it.
for len(h.batch) >= h.batchMaxSize {
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 {
seen := h.batch[asn] h.batch = append(h.batch, asnOp{
seen.Add(msg.ParsedTimestamp) number: asn,
h.batch[asn] = seen timestamp: timestamp,
})
} }
} }
// 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 taking updates until the write // waits in batchFullCh and the batch keeps growing until the write ends
// ends. // or the batch reaches batchMaxSize.
if len(h.batch) >= asnBatchSize { if len(h.batch) >= asnBatchSize {
select { select {
case h.batchFullCh <- struct{}{}: case h.batchFullCh <- struct{}{}:
@@ -125,11 +165,10 @@ func (h *ASHandler) HandleMessage(msg *ristypes.RISMessage) {
} }
} }
// Stop stops the flush goroutine and waits for it until ctx ends. The flush // Stop stops the flush goroutine, which writes the operations the handler holds
// goroutine writes the batch before it returns, unless ctx has ended. A write // before it returns, and waits for it until ctx ends. Once ctx has ended the
// still running when the process exits is lost. Stop logs how many entries are // flush goroutine skips that last write, and a write still running is lost
// not written, in the batch being written and in the next batch. An AS in both // when the process exits, so Stop logs how many operations are not written.
// batches counts twice.
func (h *ASHandler) Stop(ctx context.Context) { func (h *ASHandler) Stop(ctx context.Context) {
h.stopCh <- ctx h.stopCh <- ctx
@@ -144,14 +183,14 @@ 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 batches", "batch_entries", unwritten) "its updates", "updates", unwritten)
} }
} }
// takeBatch returns the pending ASes and leaves an empty batch in their place // takeBatch returns the pending operations and leaves an empty batch in their
// for HandleMessage to fill. They count in writing until flushBatch has written // place for HandleMessage to fill. They count in writing until flushBatch has
// them. // written them.
func (h *ASHandler) takeBatch() map[int]database.SeenTimes { func (h *ASHandler) takeBatch() []asnOp {
h.mu.Lock() h.mu.Lock()
defer h.mu.Unlock() defer h.mu.Unlock()
@@ -161,7 +200,8 @@ func (h *ASHandler) takeBatch() map[int]database.SeenTimes {
batch := h.batch batch := h.batch
h.writing = len(batch) h.writing = len(batch)
h.batch = make(map[int]database.SeenTimes) h.batch = make([]asnOp, 0, asnBatchSize)
h.batchTaken.Broadcast()
return batch return batch
} }
@@ -174,11 +214,21 @@ 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(batch) err := h.db.GetOrCreateASNBatch(asns)
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(batch)) "error", err, "count", len(asns))
} }
h.mu.Lock() h.mu.Lock()
+7 -24
View File
@@ -5,43 +5,28 @@ 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, in one batch into a // whose path carries an AS the database does not hold yet, the second 5
// real database. The second is 5 seconds after the first, and the handler gets // seconds after the first, in one batch into a real database. The AS is stored
// it first. The AS is stored first seen at the time of the first update and // first seen at the time of the first update and last seen at the time of the
// last seen at the time of the second. // 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{ h := &ASHandler{db: db, logger: logger.New(), batchMaxSize: asnBatchMaxSize}
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(second)
h.HandleMessage(first) h.HandleMessage(first)
h.HandleMessage(second)
h.flushBatch() h.flushBatch()
asn, _, err := db.GetAS(t.Context(), testASNA) asn, _, err := db.GetAS(t.Context(), testASNA)
@@ -69,9 +54,7 @@ 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{ h := &ASHandler{db: store, logger: logger.New(), batchMaxSize: asnBatchMaxSize}
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)
+5 -31
View File
@@ -187,33 +187,25 @@ func (f *ASNFetcher) recordSuccess() {
f.statsMu.Unlock() f.statsMu.Unlock()
} }
// lengthenInterval makes the interval 1.5 times as long, up to maxInterval. // recordFailure increases the interval on failed fetch using exponential backoff.
// A failed lookup and a skipped one both lengthen it. func (f *ASNFetcher) recordFailure() {
func (f *ASNFetcher) lengthenInterval() {
f.intervalMu.Lock() f.intervalMu.Lock()
defer f.intervalMu.Unlock() f.consecutiveFails++
// 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", f.logger.Debug("Increased fetch interval due to failure",
"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()
@@ -295,16 +287,6 @@ 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()
@@ -325,14 +307,6 @@ 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()
@@ -13,7 +13,6 @@ 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
@@ -132,151 +131,6 @@ 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.
+46 -148
View File
@@ -5,7 +5,6 @@ import (
"context" "context"
"encoding/json" "encoding/json"
"fmt" "fmt"
"io"
"log/slog" "log/slog"
"slices" "slices"
"sync" "sync"
@@ -175,18 +174,15 @@ 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"`
HeldMessages int `json:"held_messages"` Paths int `json:"paths"`
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 io.Writer) *logger.Logger { func newErrorLogger(logs *bytes.Buffer) *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}))}
} }
@@ -473,42 +469,6 @@ 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
@@ -522,81 +482,33 @@ 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)
logged := stopPrefixHandlerWithBlockedWrite(t, blocking, stopWhileAWriteIsBlocked(t, blocking, h, h.done,
tableWriteBlockingStore{blockingStore: blocking}, &logs, []*ristypes.RISMessage{prefixAnnouncement(fill)},
prefixAnnouncement(fill), prefixAnnouncement([]string{extraPrefix})) prefixAnnouncement([]string{extraPrefix}))
if logged.TableChanges != 2 { if logged := lastLogged(t, &logs); 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()
const wantEntries = asnBatchSize + 1 // Each message gives an update for its origin AS and one for each AS
// 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: pathOfASes(asnBatchSize)}}, []*ristypes.RISMessage{{Path: fill}},
&ristypes.RISMessage{Path: ristypes.ASPath{Sequence: []int{testASNB}}}) &ristypes.RISMessage{Path: ristypes.ASPath{Sequence: []int{testASNB}}})
store.mu.Lock() store.mu.Lock()
@@ -606,27 +518,26 @@ 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.BatchEntries != wantEntries { if logged := lastLogged(t, &logs); logged.Updates != wantUpdates {
t.Errorf("Stop logged %d batch entries not written, want %d", t.Errorf("Stop logged %d updates not written, want %d",
logged.BatchEntries, wantEntries) logged.Updates, wantUpdates)
} }
} }
// 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 full batch holds the fill's ASes again, and testASNB. The stop // waits. The stop deadline passes meanwhile. When the write ends, the flush
// deadline passes meanwhile. When the write ends, the flush goroutine must stop // goroutine must stop instead of writing the batch.
// 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.RISMessage{Path: pathOfASes(asnBatchSize)} fill := ristypes.ASPath{Sequence: slices.Repeat([]int{testASNA}, asnBatchSize)}
full := ristypes.ASPath{Sequence: slices.Repeat([]int{testASNB}, asnBatchSize)}
stopWhileAWriteIsBlocked(t, store, h, h.done, stopWhileAWriteIsBlocked(t, store, h, h.done,
[]*ristypes.RISMessage{fill}, []*ristypes.RISMessage{{Path: fill}},
fill, &ristypes.RISMessage{Path: full})
&ristypes.RISMessage{Path: ristypes.ASPath{Sequence: []int{testASNB}}})
store.mu.Lock() store.mu.Lock()
defer store.mu.Unlock() defer store.mu.Unlock()
@@ -792,8 +703,9 @@ 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: pathOfASes(asnBatchSize)}}, []*ristypes.RISMessage{{Path: fill}},
&ristypes.RISMessage{Path: ristypes.ASPath{Sequence: []int{testASNB}}}) &ristypes.RISMessage{Path: ristypes.ASPath{Sequence: []int{testASNB}}})
store.mu.Lock() store.mu.Lock()
@@ -850,41 +762,25 @@ func TestPrefixHandlerWaitsAtTheMaximumBatchSize(t *testing.T) {
} }
} }
// TestASHandlerNeverWaitsForAWrite starts a write that the store holds. Then it func TestASHandlerWaitsAtTheMaximumBatchSize(t *testing.T) {
// 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)
h.batchMaxSize = asnBatchSize
fill := ristypes.ASPath{Sequence: slices.Repeat([]int{testASNA}, asnBatchSize)}
toMax := ristypes.ASPath{Sequence: slices.Repeat([]int{testASNA}, asnBatchSize)}
handleAtMaxBatchSize(t, store, h,
[]*ristypes.RISMessage{{Path: fill}},
[]*ristypes.RISMessage{{Path: toMax}},
&ristypes.RISMessage{Path: ristypes.ASPath{Sequence: []int{testASNB}}})
defer stopInTime(t, h) store.mu.Lock()
defer store.releaseWrites() defer store.mu.Unlock()
startBlockedWrite(t, store, h, if !store.asns[testASNB] {
[]*ristypes.RISMessage{{Path: pathOfASes(asnBatchSize)}}) t.Errorf("Stop did not write AS%d, handled after the batch reached its "+
"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))
} }
} }
@@ -948,11 +844,13 @@ func TestHandlersWakeTheFlushGoroutineWhenTheBatchIsFull(t *testing.T) {
batchSize: asnBatchSize, batchSize: asnBatchSize,
handle: func(n int) chan struct{} { handle: func(n int) chan struct{} {
h := &ASHandler{ h := &ASHandler{
batch: make(map[int]database.SeenTimes), batchMaxSize: asnBatchMaxSize,
batchFullCh: make(chan struct{}, 1), batchFullCh: make(chan struct{}, 1),
} }
// Each of the path's n ASes is one entry of the batch. // The origin AS and each AS in the path are one update each.
h.HandleMessage(&ristypes.RISMessage{Path: pathOfASes(n)}) h.HandleMessage(&ristypes.RISMessage{
Path: ristypes.ASPath{Sequence: slices.Repeat([]int{testASNA}, n-1)},
})
return h.batchFullCh return h.batchFullCh
}, },
-27
View File
@@ -25,10 +25,6 @@ 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
@@ -37,9 +33,6 @@ 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
@@ -87,7 +80,6 @@ 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,
) )
} }
@@ -119,9 +111,6 @@ 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:
@@ -138,10 +127,6 @@ 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)
} }
} }
} }
@@ -190,18 +175,6 @@ 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(
+53 -287
View File
@@ -15,15 +15,12 @@ import (
) )
const ( const (
// prefixHandlerQueueSize is the most messages the handler's queue holds. // prefixHandlerQueueSize is the queue capacity for prefix tracking
// While the routing table's Overview or PeersDown walks every prefix, it // operations, about 4 seconds of feed at peak. The streamer drops updates
// holds the table's lock about half of the time. The handler then applies // rather than blocks when a queue is full (a STATE message is held until
// updates more slowly. When the feed pauses for some seconds and then // there is room), so this bounds memory. Batches still flush on a timer
// catches up, its backlog can arrive faster than that, and the queue // (prefixBatchTimeout).
// holds the backlog. The streamer drops an update that finds the queue prefixHandlerQueueSize = 20000
// 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
@@ -47,25 +44,6 @@ 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
@@ -74,19 +52,8 @@ 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.
// //
// The table's PeersDown applies sessions going down. It visits every prefix, // Each flush writes the table's changes to the database. It also stores each
// which takes seconds on a full table. So the handler runs PeersDown on a // prefix the updates name with the time it was first seen.
// 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
@@ -99,14 +66,11 @@ type PrefixHandler struct {
// tableChangesPerWrite is maxTableChangesPerWrite, except in tests that // tableChangesPerWrite is maxTableChangesPerWrite, except in tests that
// give a smaller one. // give a smaller one.
tableChangesPerWrite int tableChangesPerWrite int
// originChangesPerWrite is maxOriginChangesPerWrite, except in tests that
// give a smaller one.
originChangesPerWrite int
// Batching. mu guards batch, writing, writingTableChanges and // Batching. mu guards batch, writing and writingTableChanges only: the
// writingOriginChanges: the flush goroutine takes them under mu and // flush goroutine takes them under mu and writes them after releasing
// writes them after releasing mu, so HandleMessage waits for a database // mu, so HandleMessage waits for a database write only while batch is at
// write only while batch is at batchMaxSize. // 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
@@ -115,9 +79,6 @@ 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
@@ -126,26 +87,6 @@ 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
@@ -200,21 +141,17 @@ func newPrefixHandler(
batchTimeout time.Duration, tableChangesPerWrite int, 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),
batchMaxSize: prefixBatchMaxSize, batchMaxSize: prefixBatchMaxSize,
tableChangesPerWrite: tableChangesPerWrite, tableChangesPerWrite: tableChangesPerWrite,
originChangesPerWrite: maxOriginChangesPerWrite, 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{}),
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)
@@ -242,102 +179,11 @@ func (h *PrefixHandler) QueueCapacity() int {
return prefixHandlerQueueSize return prefixHandlerQueueSize
} }
// HandleMessage processes a message to track prefix information. A message // HandleMessage processes a message to track prefix information
// 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.startPeerDown(msg.Peer) h.table.PeerDown(msg.Peer)
} }
return return
@@ -352,6 +198,9 @@ func (h *PrefixHandler) applyMessage(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.
@@ -412,88 +261,39 @@ func (h *PrefixHandler) applyMessage(msg *ristypes.RISMessage) {
} }
} }
// startPeerDown adds peer to downPeers. It starts peerDown on a new goroutine // Stop stops the flush goroutine, which makes one last flush before it returns,
// unless peerDown is running. The caller holds mu. The peer's messages are // and waits for it until ctx ends. That flush writes at most
// held back until peerDown has applied them. Messages held back for an earlier // tableChangesPerWrite of the routing table's changes, and the prefixes of
// session of the peer going down, and not yet applied, stay held back. // the updates the handler holds. Once ctx has ended the flush goroutine skips
func (h *PrefixHandler) startPeerDown(peer string) { // that last flush, and a write still running is lost when the process exits. A
_, goingDown := h.heldBack[peer] // failed write of the table's changes is not retried either. Stop logs how many
if !goingDown { // updates and how many of the table's changes are not written.
h.heldBack[peer] = []*ristypes.RISMessage{} func (h *PrefixHandler) Stop(ctx context.Context) {
h.stopCh <- ctx
select {
case <-h.done:
case <-ctx.Done():
} }
h.downPeers = append(h.downPeers, peer) h.mu.Lock()
unwritten := h.writing + len(h.batch)
tableChanges := h.writingTableChanges + h.table.ChangeCount()
h.mu.Unlock()
if h.peerDownRunning { if unwritten == 0 && tableChanges == 0 {
return return
} }
h.peerDownRunning = true if ctx.Err() != nil {
h.peerDowns.Add(1) h.logger.Error("Stop deadline passed before the prefix handler wrote "+
"its updates", "updates", unwritten, "table_changes", tableChanges)
go h.peerDown() return
}
// 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)
}
} }
}
// applyHeldBack applies the messages held back from peer, in order. It takes h.logger.Error("The prefix handler stopped before it wrote everything",
// mu for one message at a time, so HandleMessage takes new messages in "updates", unwritten, "table_changes", tableChanges)
// 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
@@ -515,12 +315,11 @@ func (h *PrefixHandler) takeBatch() []seenPrefix {
return batch return batch
} }
// flushBatch writes the routing table's changes and origin changes, then // flushBatch writes the routing table's changes, then takes the pending batch
// takes the pending batch and stores the prefixes it names, without holding // and stores the prefixes it names, without holding the mutex during the
// the mutex during the writes. // 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 {
@@ -622,39 +421,6 @@ 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
@@ -237,83 +237,6 @@ func TestPrefixHandlerStopLogsNothingWhenItWroteEverything(t *testing.T) {
} }
} }
// TestPrefixHandlerStopLogsTheMessagesHeldBack stops a prefix handler with a
// deadline that has passed, while a peer's PeersDown is held up and one message
// 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 // longerThanAnyTest is a timer interval that no test lasts. A test gives it to
// newPrefixHandler, newASHandler, newPeerHandler or newPeeringHandler when the // newPrefixHandler, newASHandler, newPeerHandler or newPeeringHandler when the
// handler must write only when its batch is full, when the test says, or on // handler must write only when its batch is full, when the test says, or on
@@ -324,33 +247,15 @@ const longerThanAnyTest = time.Hour
// 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: table, table: routetable.New(routetable.Params{}),
batchMaxSize: prefixBatchMaxSize, batchMaxSize: prefixBatchMaxSize,
tableChangesPerWrite: maxTableChangesPerWrite, 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 {
@@ -1,181 +0,0 @@
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")
}
}
@@ -7,10 +7,8 @@ import (
"log/slog" "log/slog"
"net/netip" "net/netip"
"reflect" "reflect"
"runtime"
"slices" "slices"
"strings" "strings"
"sync"
"testing" "testing"
"time" "time"
@@ -103,359 +101,6 @@ 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
@@ -554,9 +199,8 @@ func TestPrefixHandlerKeepsThePathOfAPathEndingInASet(t *testing.T) {
} }
} }
// checkTableCases hands the messages of each case to a new prefix handler. It // checkTableCases hands the messages of each case to a new prefix handler and
// checks the handler's routing table once the handler's PeersDown calls have // checks its routing table right after, with no flush.
// returned, with no flush.
func checkTableCases(t *testing.T, tests []tableCase) { func checkTableCases(t *testing.T, tests []tableCase) {
t.Helper() t.Helper()
@@ -569,28 +213,17 @@ func checkTableCases(t *testing.T, tests []tableCase) {
h.HandleMessage(msg) h.HandleMessage(msg)
} }
h.peerDowns.Wait() for prefix, want := range tt.want {
checkTableOrigins(t, h.table, tt.want) got := tableOrigins(h.table, prefix)
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 {
@@ -865,7 +498,6 @@ 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
@@ -904,7 +536,6 @@ 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())
+53 -238
View File
@@ -15,10 +15,8 @@ import (
"strings" "strings"
"time" "time"
"git.eeqj.de/sneak/routewatch/internal/bogon" "git.eeqj.de/sneak/routewatch/internal/blocklist"
"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"
@@ -40,9 +38,12 @@ 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. Ten PTR lookups // each address costs two database reads and a PTR lookup.
// 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
@@ -87,10 +88,6 @@ 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"`
@@ -489,7 +486,6 @@ 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"`
@@ -574,7 +570,6 @@ 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()) /
@@ -764,12 +759,9 @@ type IPLookupResponse struct {
Errors []string `json:"errors,omitempty"` Errors []string `json:"errors,omitempty"`
} }
// IPLookupResult is the answer for one address: its PTR names, its flags, its // IPLookupResult is the answer for one address: its PTR names, its live route
// live route and that route's AS, the IP lists that contain it, and where it // and that route's AS, and the blocklists that list it. Every result has every
// is. Every result has every field. The fields of IPInfo are null when the // field. The fields of IPInfo are null when the address has no live route.
// address has no live route.
//
//nolint:tagliatelle // snake_case keys, as the Go style guide asks
type IPLookupResult struct { type IPLookupResult struct {
IPInfo IPInfo
@@ -777,35 +769,8 @@ type IPLookupResult struct {
// PTR is empty, never nil, when the address has no PTR names. // PTR is empty, never nil, when the address has no PTR names.
PTR []string `json:"ptr"` PTR []string `json:"ptr"`
Flags IPLookupFlags `json:"flags"` // Blocklists has one entry for each blocklist the address is on.
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.
@@ -846,8 +811,6 @@ 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)
@@ -883,9 +846,12 @@ func (s *Server) handleIPInfo() http.HandlerFunc {
return return
} }
result := s.ipLookupResult(ip, ptrs, ipInfo) response.Results = append(response.Results, IPLookupResult{
result.Geo = locations[ip] IP: ip,
response.Results = append(response.Results, result) PTR: ptrs,
IPInfo: ipInfo,
Blocklists: s.blocklistListings(ip),
})
if ipInfo.NeedsWHOISRefresh { if ipInfo.NeedsWHOISRefresh {
refreshASNs[*ipInfo.ASN] = true refreshASNs[*ipInfo.ASN] = true
@@ -986,120 +952,23 @@ func ipVersionOf(prefix netip.Prefix) int {
return ipVersionV6 return ipVersionV6
} }
// ipLookupResult returns the result for ip, adding its flags and IP lists to // blocklistListings returns the blocklists that list ip. It returns an empty
// its PTR names and route. // list, never nil, so that an answer's blocklists is [] rather than null.
func (s *Server) ipLookupResult(ip string, ptrs []string, info IPInfo) IPLookupResult { func (s *Server) blocklistListings(ip string) []blocklist.Listing {
listings := s.ipListListings(ip)
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 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) addr, err := netip.ParseAddr(ip)
if s.ipLists == nil || err != nil { if s.blocklists == nil || err != nil {
return []iplist.Listing{} return []blocklist.Listing{}
} }
return s.ipLists.Lookup(addr) return s.blocklists.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 IP list interval, the soonest an IP list copy can change. The // shortest blocklist interval, the soonest a blocklist 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 IP lists it sets nothing. // does not give it to another caller. Without blocklists it sets nothing.
func (s *Server) setIPLookupCacheControl(w http.ResponseWriter, ownAddress bool) { func (s *Server) setIPLookupCacheControl(w http.ResponseWriter, ownAddress bool) {
if s.ipLists == nil { if s.blocklists == nil {
return return
} }
@@ -1108,7 +977,7 @@ func (s *Server) setIPLookupCacheControl(w http.ResponseWriter, ownAddress bool)
visibility = cacheControlPrivate visibility = cacheControlPrivate
} }
maxAgeSeconds := int(s.ipLists.ShortestInterval().Seconds()) maxAgeSeconds := int(s.blocklists.ShortestInterval().Seconds())
w.Header().Set(cacheControlHeader, w.Header().Set(cacheControlHeader,
visibility+cacheControlMaxAge+strconv.Itoa(maxAgeSeconds)) visibility+cacheControlMaxAge+strconv.Itoa(maxAgeSeconds))
} }
@@ -1268,17 +1137,15 @@ func publicAddresses(addrs []string) []string {
} }
// lookupPTRNames returns the PTR records of ip without their trailing dots. It // lookupPTRNames returns the PTR records of ip without their trailing dots. It
// returns an empty list, never nil, when there are none and when the lookup // returns an empty list, never nil, when there are none, when the lookup fails
// fails, so that an answer's ptr is [] rather than null. // and when it runs past ptrLookupTimeout, 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 {
ptrs, err := s.ptrResolver.LookupAddr(ctx, ip) ctx, cancel := context.WithTimeout(ctx, ptrLookupTimeout)
if err != nil { defer cancel()
s.logger.Warn("PTR lookup failed", "ip", ip, "error", err)
return []string{} ptrs, err := s.resolver.LookupAddr(ctx, ip)
} if err != nil || ptrs == nil {
if ptrs == nil {
return []string{} return []string{}
} }
@@ -1665,23 +1532,26 @@ func (s *Server) handlePrefixDetail() http.HandlerFunc {
routes := prefixRoutes(parsed, origins) routes := prefixRoutes(parsed, origins)
changes, moreChanges, err := s.prefixOriginChanges(r.Context(), parsed)
if deadlinePassed(r.Context()) {
http.Error(w, requestTimeoutMessage, http.StatusGatewayTimeout)
return
}
if err != nil {
s.logger.Error("Failed to get the origin changes", "error", err)
http.Error(w, internalErrorMessage, http.StatusInternalServerError)
return
}
// Prepare template data // Prepare template data
data := newPrefixDetailData(parsed, routes, originInfos, changes, data := struct {
moreChanges, cspNonce(r.Context())) Prefix string
MaskLength int
IPVersion int
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()),
}
// Check if context is still valid before writing response // Check if context is still valid before writing response
select { select {
@@ -1734,61 +1604,6 @@ 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
+127 -537
View File
@@ -15,19 +15,15 @@ import (
"slices" "slices"
"strconv" "strconv"
"strings" "strings"
"sync"
"sync/atomic" "sync/atomic"
"testing" "testing"
"testing/synctest"
"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/metrics" "git.eeqj.de/sneak/routewatch/internal/metrics"
"git.eeqj.de/sneak/routewatch/internal/ptr"
"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"
@@ -177,9 +173,6 @@ type tableStats struct {
// carried 203.0.113.0/24, the two with kept routes withdrew it, so its origin // carried 203.0.113.0/24, the two with kept routes withdrew it, so its origin
// keeps no route. The oldest and newest routes are those of the other two // keeps no route. The oldest and newest routes are those of the other two
// prefixes. // prefixes.
//
// The requests run in a synctest bubble, whose clock is fake, so a stall on
// the host does not use up the handlers' 4-second limit.
func TestStatsHandlersAnswerFromMemory(t *testing.T) { func TestStatsHandlersAnswerFromMemory(t *testing.T) {
t.Parallel() t.Parallel()
@@ -225,11 +218,7 @@ func TestStatsHandlersAnswerFromMemory(t *testing.T) {
for name, handler := range handlers { for name, handler := range handlers {
rec := httptest.NewRecorder() rec := httptest.NewRecorder()
handler(rec, httptest.NewRequestWithContext(t.Context(), http.MethodGet, "/", nil))
synctest.Test(t, func(t *testing.T) {
handler(rec,
httptest.NewRequestWithContext(t.Context(), http.MethodGet, "/", nil))
})
if rec.Code != http.StatusOK { if rec.Code != http.StatusOK {
t.Errorf("%s: status %d, want %d; body %s", t.Errorf("%s: status %d, want %d; body %s",
@@ -264,20 +253,15 @@ func TestStatsHandlersAnswerFromMemory(t *testing.T) {
// TestStatsAnswerCarriesChurnPerMinute checks that the stream object of the // TestStatsAnswerCarriesChurnPerMinute checks that the stream object of the
// /api/v1/stats answer holds route_churn_per_min as a whole number, and no // /api/v1/stats answer holds route_churn_per_min as a whole number, and no
// longer route_churn_per_sec, the moving average it replaces // longer route_churn_per_sec, the moving average it replaces
// (https://git.eeqj.de/sneak/routewatch/issues/160). The request runs in a // (https://git.eeqj.de/sneak/routewatch/issues/160).
// synctest bubble, whose clock is fake, so a stall on the host does not use up
// the handler's 4-second limit.
func TestStatsAnswerCarriesChurnPerMinute(t *testing.T) { func TestStatsAnswerCarriesChurnPerMinute(t *testing.T) {
t.Parallel() t.Parallel()
s := newServerWithTestRoutes(t) s := newServerWithTestRoutes(t)
rec := httptest.NewRecorder() rec := httptest.NewRecorder()
s.handleStats()(rec,
synctest.Test(t, func(t *testing.T) { httptest.NewRequestWithContext(t.Context(), http.MethodGet, statsPath, nil))
s.handleStats()(rec,
httptest.NewRequestWithContext(t.Context(), http.MethodGet, statsPath, nil))
})
if rec.Code != http.StatusOK { if rec.Code != http.StatusOK {
t.Fatalf("status %d, want %d; body %s", rec.Code, http.StatusOK, rec.Body) t.Fatalf("status %d, want %d; body %s", rec.Code, http.StatusOK, rec.Body)
@@ -311,51 +295,6 @@ func TestStatsAnswerCarriesChurnPerMinute(t *testing.T) {
} }
} }
// heldBackMessages is how many messages heldBackHandler holds back.
const heldBackMessages = 7
// heldBackHandler is a stream handler that wants no message and holds back
// heldBackMessages messages.
type heldBackHandler struct{}
func (heldBackHandler) WantsMessage(string) bool { return false }
func (heldBackHandler) HandleMessage(*ristypes.RISMessage) {}
func (heldBackHandler) QueueCapacity() int { return 1 }
func (heldBackHandler) HeldBackCount() int { return heldBackMessages }
// TestStatsAnswerGivesHowManyMessagesAHandlerHoldsBack registers a handler
// that holds back messages. Its figures in /api/v1/stats, which the status
// page shows, must give how many. The request runs in a synctest bubble, whose
// clock is fake, so a stall on the host does not use up the handler's 4-second
// limit.
func TestStatsAnswerGivesHowManyMessagesAHandlerHoldsBack(t *testing.T) {
t.Parallel()
s := newServerWithTestRoutes(t)
s.streamer.RegisterHandler(heldBackHandler{})
var answer []byte
synctest.Test(t, func(t *testing.T) {
answer = get(t, s, statsPath).Body.Bytes()
})
var body struct {
Data StatsResponse `json:"data"`
}
err := json.Unmarshal(answer, &body)
if err != nil {
t.Fatalf("decoding the answer: %v", err)
}
stats := body.Data.HandlerStats
if len(stats) != 1 || stats[0].HeldBackCount != heldBackMessages {
t.Errorf("handler figures %+v, want one handler holding back %d "+
"messages", stats, heldBackMessages)
}
}
// fixedIntervalASNFetcher is a WHOIS fetcher that does nothing and reports // fixedIntervalASNFetcher is a WHOIS fetcher that does nothing and reports
// interval as its wait between fetches. // interval as its wait between fetches.
type fixedIntervalASNFetcher struct { type fixedIntervalASNFetcher struct {
@@ -388,9 +327,7 @@ type unitStats struct {
// names. They used to be strings with the unit in them, such as "1h18m34s" or // names. They used to be strings with the unit in them, such as "1h18m34s" or
// "1.1 GB" (https://git.eeqj.de/sneak/routewatch/issues/199). The stream has // "1.1 GB" (https://git.eeqj.de/sneak/routewatch/issues/199). The stream has
// never connected, so the uptime is 0. The memory use in /api/v1/stats is the // never connected, so the uptime is 0. The memory use in /api/v1/stats is the
// same number of bytes as its gc.heap_alloc_bytes. The requests run in a // same number of bytes as its gc.heap_alloc_bytes.
// synctest bubble, whose clock is fake, so a stall on the host does not use up
// the handlers' 4-second limit.
func TestStatsAnswersGiveUnitsInFieldNames(t *testing.T) { func TestStatsAnswersGiveUnitsInFieldNames(t *testing.T) {
t.Parallel() t.Parallel()
@@ -400,11 +337,7 @@ func TestStatsAnswersGiveUnitsInFieldNames(t *testing.T) {
s.SetASNFetcher(fixedIntervalASNFetcher{interval: fetchInterval}) s.SetASNFetcher(fixedIntervalASNFetcher{interval: fetchInterval})
for _, path := range []string{statusJSONPath, statsPath} { for _, path := range []string{statusJSONPath, statsPath} {
var answer []byte answer := get(t, s, path).Body.Bytes()
synctest.Test(t, func(t *testing.T) {
answer = get(t, s, path).Body.Bytes()
})
var body struct { var body struct {
Data unitStats `json:"data"` Data unitStats `json:"data"`
@@ -445,89 +378,82 @@ func TestStatsAnswersGiveUnitsInFieldNames(t *testing.T) {
// connection_duration_seconds of /api/v1/stats is null while the stream is not // connection_duration_seconds of /api/v1/stats is null while the stream is not
// connected, and a whole number of seconds once it is. It used to be the // connected, and a whole number of seconds once it is. It used to be the
// string "disconnected", or a Go duration such as "1h18m34s" // string "disconnected", or a Go duration such as "1h18m34s"
// (https://git.eeqj.de/sneak/routewatch/issues/199). The test runs in a // (https://git.eeqj.de/sneak/routewatch/issues/199).
// synctest bubble, whose clock is fake, so a stall on the host does not use up
// the handler's 4-second limit.
func TestStatsAnswerGivesConnectionDurationInSeconds(t *testing.T) { func TestStatsAnswerGivesConnectionDurationInSeconds(t *testing.T) {
t.Parallel() t.Parallel()
s := newServerWithTestRoutes(t) s := newServerWithTestRoutes(t)
synctest.Test(t, func(t *testing.T) { connectionDuration := func() json.RawMessage {
connectionDuration := func() json.RawMessage { answer := get(t, s, statsPath).Body.Bytes()
answer := get(t, s, statsPath).Body.Bytes()
var body struct { var body struct {
Data map[string]json.RawMessage `json:"data"` Data map[string]json.RawMessage `json:"data"`
}
err := json.Unmarshal(answer, &body)
if err != nil {
t.Fatalf("decoding the answer: %v; answer %s", err, answer)
}
duration, ok := body.Data["connection_duration_seconds"]
if !ok {
t.Fatalf("no connection_duration_seconds: %s", answer)
}
return duration
} }
disconnected := connectionDuration() err := json.Unmarshal(answer, &body)
if string(disconnected) != "null" { if err != nil {
t.Errorf("disconnected: connection_duration_seconds = %s, want null", t.Fatalf("decoding the answer: %v; answer %s", err, answer)
disconnected)
} }
s.streamer.GetMetricsTracker().SetConnected(true) duration, ok := body.Data["connection_duration_seconds"]
if !ok {
var seconds int64 t.Fatalf("no connection_duration_seconds: %s", answer)
connected := connectionDuration()
err := json.Unmarshal(connected, &seconds)
if err != nil || seconds != 0 {
t.Errorf("just connected: connection_duration_seconds = %s, want 0",
connected)
} }
})
return duration
}
disconnected := connectionDuration()
if string(disconnected) != "null" {
t.Errorf("disconnected: connection_duration_seconds = %s, want null",
disconnected)
}
s.streamer.GetMetricsTracker().SetConnected(true)
var seconds int64
connected := connectionDuration()
err := json.Unmarshal(connected, &seconds)
if err != nil || seconds != 0 {
t.Errorf("just connected: connection_duration_seconds = %s, want 0",
connected)
}
} }
// TestStreamDurationsCountSeconds checks that the uptime and the connection // TestStreamDurationsCountSeconds checks that the uptime and the connection
// duration of a stream that connected 90 seconds ago are both 90. A stream // duration of a stream that connected 90 seconds ago are both 90. A stream
// that has never connected has an uptime of 0, and one that is not connected // that has never connected has an uptime of 0, and one that is not connected
// has no connection duration. The test runs in a synctest bubble, whose clock // has no connection duration.
// is fake, so a stall on the host does not add to the 90 seconds.
func TestStreamDurationsCountSeconds(t *testing.T) { func TestStreamDurationsCountSeconds(t *testing.T) {
t.Parallel() t.Parallel()
synctest.Test(t, func(t *testing.T) { const connectedFor = 90 * time.Second
const connectedFor = 90 * time.Second
connectedSince := time.Now().Add(-connectedFor) connectedSince := time.Now().Add(-connectedFor)
want := int64(connectedFor / time.Second) want := int64(connectedFor / time.Second)
if got := uptimeSeconds(connectedSince); got != want { if got := uptimeSeconds(connectedSince); got != want {
t.Errorf("uptimeSeconds = %d, want %d", got, want) t.Errorf("uptimeSeconds = %d, want %d", got, want)
} }
if got := uptimeSeconds(time.Time{}); got != 0 { if got := uptimeSeconds(time.Time{}); got != 0 {
t.Errorf("uptimeSeconds before any connection = %d, want 0", got) t.Errorf("uptimeSeconds before any connection = %d, want 0", got)
} }
switch got := connectionDurationSeconds(true, connectedSince); { switch got := connectionDurationSeconds(true, connectedSince); {
case got == nil: case got == nil:
t.Errorf("connectionDurationSeconds = nil, want %d", want) t.Errorf("connectionDurationSeconds = nil, want %d", want)
case *got != want: case *got != want:
t.Errorf("connectionDurationSeconds = %d, want %d", *got, want) t.Errorf("connectionDurationSeconds = %d, want %d", *got, want)
} }
if got := connectionDurationSeconds(false, connectedSince); got != nil { if got := connectionDurationSeconds(false, connectedSince); got != nil {
t.Errorf("connectionDurationSeconds while not connected = %d, want nil", t.Errorf("connectionDurationSeconds while not connected = %d, want nil",
*got) *got)
} }
})
} }
// newTestTable returns a routing table that holds a route for testPrefixV4, // newTestTable returns a routing table that holds a route for testPrefixV4,
@@ -560,11 +486,8 @@ func newServerWithTable(t *testing.T, table *routetable.Table) *Server {
t.Cleanup(func() { _ = db.Close() }) t.Cleanup(func() { _ = db.Close() })
s := New(db, table, streamer.New(logger.New(), metrics.New()), logger.New(), return New(db, table, streamer.New(logger.New(), metrics.New()), logger.New(),
&config.Config{}) &config.Config{})
useFakeResolver(s, &fakeResolver{})
return s
} }
// TestPrefixDetailHandlersParsePrefix checks that both prefix pages find a // TestPrefixDetailHandlersParsePrefix checks that both prefix pages find a
@@ -1174,9 +1097,7 @@ func (failingDB) GetPrefixFirstSeen(
// with the driver's error text. It also sends a prefix that does not parse. // with the driver's error text. It also sends a prefix that does not parse.
// No answer may carry the driver's or the prefix parser's text. Before the fix // No answer may carry the driver's or the prefix parser's text. Before the fix
// the answers sent it to the client // the answers sent it to the client
// (https://git.eeqj.de/sneak/routewatch/issues/108). The requests run in a // (https://git.eeqj.de/sneak/routewatch/issues/108).
// synctest bubble, whose clock is fake, so a stall on the host does not use up
// the stats handlers' 4-second limit.
func TestJSONRoutesDoNotSendErrorDetails(t *testing.T) { func TestJSONRoutesDoNotSendErrorDetails(t *testing.T) {
t.Parallel() t.Parallel()
@@ -1197,11 +1118,8 @@ func TestJSONRoutesDoNotSendErrorDetails(t *testing.T) {
for _, tt := range tests { for _, tt := range tests {
rec := httptest.NewRecorder() rec := httptest.NewRecorder()
s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
synctest.Test(t, func(t *testing.T) { t.Context(), http.MethodGet, tt.path, nil))
s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
t.Context(), http.MethodGet, tt.path, nil))
})
if rec.Code != tt.wantCode { if rec.Code != tt.wantCode {
t.Errorf("%s: status %d, want %d; body %s", t.Errorf("%s: status %d, want %d; body %s",
@@ -1258,7 +1176,7 @@ func TestIPLookupAnswers500WhenDatabaseReadFails(t *testing.T) {
s := New(failingIPLookupDB{}, newTestTable(), s := New(failingIPLookupDB{}, newTestTable(),
streamer.New(logger.New(), metrics.New()), logger.New(), &config.Config{}) streamer.New(logger.New(), metrics.New()), logger.New(), &config.Config{})
useFakeResolver(s, &fakeResolver{}) s.resolver = &fakeResolver{}
tests := []struct { tests := []struct {
path string path string
@@ -1294,19 +1212,16 @@ func TestIPLookupAnswers500WhenDatabaseReadFails(t *testing.T) {
} }
} }
// errNoSuchHost is what fakeResolver answers a host name lookup it has no // errNoSuchHost is what fakeResolver answers a lookup it has no answer for
// addresses for with. // with.
var errNoSuchHost = errors.New("no such host") var errNoSuchHost = errors.New("no such host")
// fakeResolver answers a host name lookup with the addresses hosts lists for // fakeResolver answers a host name lookup with the addresses hosts lists for
// the name. It answers a PTR lookup with the names ptrs lists for the address, // the name, and a PTR lookup with no names or, when ptrNeverAnswers is set,
// and with no names and no error, as the real one does, when ptrs lists none. // not at all: it waits until the lookup's context ends. hostLookups counts the
// When ptrNeverAnswers is set, a PTR lookup fails after ptr.LookupTimeout, as // host name lookups.
// the real one does when no resolver answers. hostLookups counts the host name
// lookups.
type fakeResolver struct { type fakeResolver struct {
hosts map[string][]string hosts map[string][]string
ptrs map[string][]string
ptrNeverAnswers bool ptrNeverAnswers bool
hostLookups atomic.Int64 hostLookups atomic.Int64
@@ -1323,23 +1238,14 @@ func (r *fakeResolver) LookupHost(_ context.Context, host string) ([]string, err
return addrs, nil return addrs, nil
} }
func (r *fakeResolver) LookupAddr(ctx context.Context, addr string) ([]string, error) { func (r *fakeResolver) LookupAddr(ctx context.Context, _ string) ([]string, error) {
if r.ptrNeverAnswers { if r.ptrNeverAnswers {
ctx, cancel := context.WithTimeout(ctx, ptr.LookupTimeout)
defer cancel()
<-ctx.Done() <-ctx.Done()
return nil, ctx.Err() return nil, ctx.Err()
} }
return r.ptrs[addr], nil return nil, errNoSuchHost
}
// useFakeResolver makes r answer the server's host name and PTR lookups.
func useFakeResolver(s *Server, r *fakeResolver) {
s.resolver = r
s.ptrResolver = r
} }
// countingIPLookupDB embeds database.Store (left nil) and answers the IP // countingIPLookupDB embeds database.Store (left nil) and answers the IP
@@ -1410,7 +1316,7 @@ func TestIPLookupRefusesTooManyAddresses(t *testing.T) {
s := New(db, newTestTable(), streamer.New(logger.New(), metrics.New()), s := New(db, newTestTable(), streamer.New(logger.New(), metrics.New()),
logger.New(), &config.Config{}) logger.New(), &config.Config{})
resolver := &fakeResolver{hosts: hosts} resolver := &fakeResolver{hosts: hosts}
useFakeResolver(s, resolver) s.resolver = resolver
rec := httptest.NewRecorder() rec := httptest.NewRecorder()
s.router.ServeHTTP(rec, httptest.NewRequestWithContext( s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
@@ -1445,21 +1351,17 @@ const addrInTestPrefixV4 = "192.0.2.1"
// TestIPLookupKeepsRouteWhenPTRLookupDoesNotAnswer looks up a routed address // TestIPLookupKeepsRouteWhenPTRLookupDoesNotAnswer looks up a routed address
// with a resolver that never answers its PTR lookup. Once the PTR lookup's own // with a resolver that never answers its PTR lookup. Once the PTR lookup's own
// limit passes, the lookup answers 200 with the route and an empty ptr. Before // limit passes, the lookup answers 200 with the route. Before the fix the PTR
// the fix the PTR lookup ran until the request's time limit, and the lookup // lookup ran until the request's time limit, and the lookup answered 504
// answered 504 without the route // without the route (https://git.eeqj.de/sneak/routewatch/issues/110).
// (https://git.eeqj.de/sneak/routewatch/issues/110).
func TestIPLookupKeepsRouteWhenPTRLookupDoesNotAnswer(t *testing.T) { func TestIPLookupKeepsRouteWhenPTRLookupDoesNotAnswer(t *testing.T) {
t.Parallel() t.Parallel()
s := newServerWithTestRoutes(t) s := newServerWithTestRoutes(t)
useFakeResolver(s, &fakeResolver{ptrNeverAnswers: true}) s.resolver = &fakeResolver{ptrNeverAnswers: true}
// The request's time limit passes well after the PTR lookup's, so that a // The request's time limit passes after the PTR lookup's.
// stall on a busy host does not use up the difference. ctx, cancel := context.WithTimeout(t.Context(), 2*ptrLookupTimeout)
const requestTimeLimit = ptr.LookupTimeout + 15*time.Second
ctx, cancel := context.WithTimeout(t.Context(), requestTimeLimit)
defer cancel() defer cancel()
rec := httptest.NewRecorder() rec := httptest.NewRecorder()
@@ -1483,339 +1385,56 @@ func TestIPLookupKeepsRouteWhenPTRLookupDoesNotAnswer(t *testing.T) {
*body.Data.Results[0].Netblock != testPrefixV4 { *body.Data.Results[0].Netblock != testPrefixV4 {
t.Errorf("answer %s, want one result in %s", rec.Body, testPrefixV4) t.Errorf("answer %s, want one result in %s", rec.Body, testPrefixV4)
} }
if !strings.Contains(rec.Body.String(), `"ptr":[]`) {
t.Errorf("answer %s, want an empty ptr list", rec.Body)
}
} }
// addrInTestPrefixV6 is an address in testPrefixV6, which // addrInTestPrefixV6 is an address in testPrefixV6, which
// newServerWithTestRoutes stores a route for. // newServerWithTestRoutes stores a route for.
const addrInTestPrefixV6 = "2001:db8::1" const addrInTestPrefixV6 = "2001:db8::1"
// testIPListInterval is fakeIPLists' shortest interval. // testBlocklistInterval is fakeBlocklists' shortest interval.
const testIPListInterval = 15 * time.Minute const testBlocklistInterval = 15 * time.Minute
// ownAddressPath is the IP lookup of the caller's own address. // ownAddressPath is the IP lookup of the caller's own address.
const ownAddressPath = "/ip/" const ownAddressPath = "/ip/"
// listedUnroutedAddr is an address that fakeIPLists lists, outside the routes // listedUnroutedAddr is an address that fakeBlocklists lists, outside the
// newServerWithTestRoutes stores. // routes newServerWithTestRoutes stores.
const listedUnroutedAddr = "203.0.113.1" const listedUnroutedAddr = "203.0.113.1"
// torExitAddr is the address that fakeIPLists lists on the Tor exit list. // fakeBlocklists has one list, which lists addrInTestPrefixV4 and
const torExitAddr = "203.0.113.2" // listedUnroutedAddr and no other address.
type fakeBlocklists struct{}
// relayAddr is the address that fakeIPLists lists on the iCloud Private Relay func testListing() blocklist.Listing {
// list. return blocklist.Listing{
const relayAddr = "203.0.113.5"
// The addresses that fakeIPLists lists on one and on two VPN lists, and the
// names of those lists.
const (
oneVPNListAddr = "203.0.113.3"
twoVPNListsAddr = "203.0.113.4"
testVPNList = "test_vpn"
otherTestVPN = "other_test_vpn"
)
// fakeIPLists has five lists. The test list holds addrInTestPrefixV4,
// listedUnroutedAddr and twoVPNListsAddr. The Tor exit list holds torExitAddr.
// The iCloud Private Relay list holds relayAddr. The test VPN list holds
// oneVPNListAddr and twoVPNListsAddr, and the other test VPN list holds
// twoVPNListsAddr.
type fakeIPLists struct{}
func testListing() iplist.Listing {
return iplist.Listing{
Name: "test_list", Name: "test_list",
Description: "On the test list", Description: "On the test list",
Updated: time.Date(2026, 10, 27, 4, 0, 0, 0, time.UTC), Updated: time.Date(2026, 10, 27, 4, 0, 0, 0, time.UTC),
} }
} }
func (fakeIPLists) Lookup(addr netip.Addr) []iplist.Listing { func (fakeBlocklists) Lookup(addr netip.Addr) []blocklist.Listing {
if addr == netip.MustParseAddr(addrInTestPrefixV4) || if addr == netip.MustParseAddr(addrInTestPrefixV4) ||
addr == netip.MustParseAddr(listedUnroutedAddr) { addr == netip.MustParseAddr(listedUnroutedAddr) {
return []iplist.Listing{testListing()} return []blocklist.Listing{testListing()}
} }
if addr == netip.MustParseAddr(torExitAddr) { return []blocklist.Listing{}
return []iplist.Listing{{Name: iplist.TorExitsList}}
}
if addr == netip.MustParseAddr(relayAddr) {
return []iplist.Listing{{Name: iplist.ICloudPrivateRelayList}}
}
if addr == netip.MustParseAddr(oneVPNListAddr) {
return []iplist.Listing{{Name: testVPNList, VPN: true}}
}
if addr == netip.MustParseAddr(twoVPNListsAddr) {
return []iplist.Listing{
{Name: otherTestVPN, VPN: true},
testListing(),
{Name: testVPNList, VPN: true},
}
}
return []iplist.Listing{}
} }
func (fakeIPLists) ShortestInterval() time.Duration { func (fakeBlocklists) ShortestInterval() time.Duration {
return testIPListInterval return testBlocklistInterval
} }
// TestIPLookupFlags looks up addresses with and without a route. Every result // TestIPLookupReportsBlocklists looks up two routed addresses, one of them on
// has every flag, under the JSON keys the API documents. // a blocklist. The listed address's result names the list, says what it means
func TestIPLookupFlags(t *testing.T) { // and when it was updated. The other's result has an empty list.
t.Parallel() func TestIPLookupReportsBlocklists(t *testing.T) {
s := newServerWithTestRoutes(t)
useFakeResolver(s, &fakeResolver{})
s.SetIPLists(fakeIPLists{})
tests := []struct {
name string
addr string
tor bool
relay bool
bogon bool
}{
{"on the Tor exit list", torExitAddr, true, false, true},
{"on the iCloud Private Relay list", relayAddr, false, true, true},
{"on another list", listedUnroutedAddr, false, false, true},
{"routed IPv4", addrInTestPrefixV4, false, false, true},
{"routed IPv6", addrInTestPrefixV6, false, false, true},
{"private IPv4", "10.0.0.1", false, false, true},
{"loopback IPv4", "127.0.0.1", false, false, true},
{"public IPv4", "1.1.1.1", false, false, false},
{"private IPv6", "fd00::1", false, false, true},
{"loopback IPv6", "::1", false, false, true},
{"public IPv6", "2606:4700:4700::1111", false, false, false},
{"public IPv4 in IPv6 form", "::ffff:1.1.1.1", false, false, false},
{"private IPv4 in IPv6 form", "::ffff:10.0.0.1", false, false, true},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
path := "/api/v1/ip/" + tt.addr
results := resultFields(t, get(t, s, path).Body.Bytes())
if len(results) != 1 {
t.Fatalf("%s: %d results, want 1", path, len(results))
}
var got map[string]bool
err := json.Unmarshal(results[0]["flags"], &got)
if err != nil {
t.Fatalf("%s: decoding flags %s: %v", path, results[0]["flags"], err)
}
want := map[string]bool{
"is_tor": tt.tor, "is_vpn": false, "is_relay": tt.relay,
"is_bogon": tt.bogon,
}
if !maps.Equal(got, want) {
t.Errorf("%s: flags %v, want %v", path, got, want)
}
})
}
}
// fakeGeoLocator answers every address with location, and keeps the addresses
// of each call. It is safe for the concurrent subtests that share it.
type fakeGeoLocator struct {
location *geo.Location
mu sync.Mutex
calls [][]netip.Addr
}
func (f *fakeGeoLocator) Lookup(
_ context.Context, addrs []netip.Addr,
) []*geo.Location {
f.mu.Lock()
defer f.mu.Unlock()
f.calls = append(f.calls, addrs)
answers := make([]*geo.Location, len(addrs))
for i := range addrs {
answers[i] = f.location
}
return answers
}
// TestIPLookupGivesTheGeoObject looks up two public addresses. They go to the
// locator in one call, and each result has the geo object under the keys the
// API documents. These addresses are public, because a reserved one is not
// looked up.
func TestIPLookupGivesTheGeoObject(t *testing.T) {
t.Parallel()
s := newServerWithTestRoutes(t)
useFakeResolver(s, &fakeResolver{})
locator := &fakeGeoLocator{location: &geo.Location{
CountryCode: new("DE"),
City: new("Berlin"),
Latitude: new(52.5),
Source: "geojs",
Updated: testRouteTime(0),
}}
s.SetGeoLocator(locator)
path := "/api/v1/ip/1.1.1.1,8.8.8.8"
results := resultFields(t, get(t, s, path).Body.Bytes())
if len(results) != 2 {
t.Fatalf("%s: %d results, want 2", path, len(results))
}
if len(locator.calls) != 1 || len(locator.calls[0]) != 2 {
t.Errorf("locator calls %v, want one with both addresses", locator.calls)
}
var got map[string]json.RawMessage
err := json.Unmarshal(results[0]["geo"], &got)
if err != nil {
t.Fatalf("decoding geo %s: %v", results[0]["geo"], err)
}
wantKeys := []string{
"accuracy_radius_km", "city", "continent_code", "country",
"country_code", "latitude", "longitude", "region", "source",
"time_zone", "updated",
}
if keys := slices.Sorted(maps.Keys(got)); !slices.Equal(keys, wantKeys) {
t.Errorf("geo keys %v, want %v", keys, wantKeys)
}
if string(got["city"]) != `"Berlin"` || string(got["latitude"]) != "52.5" ||
string(got["region"]) != jsonNull {
t.Errorf("wrong geo %s", results[0]["geo"])
}
}
// TestIPLookupOfAReservedAddressHasNoGeo looks up a reserved address alone and
// beside a public one. The reserved one never reaches the locator, and its geo
// is null.
func TestIPLookupOfAReservedAddressHasNoGeo(t *testing.T) {
t.Parallel()
s := newServerWithTestRoutes(t)
useFakeResolver(s, &fakeResolver{})
locator := &fakeGeoLocator{location: &geo.Location{Source: "geojs"}}
s.SetGeoLocator(locator)
results := resultFields(t, get(t, s, "/api/v1/ip/"+addrInTestPrefixV4).Body.Bytes())
if len(results) != 1 || string(results[0]["geo"]) != jsonNull {
t.Fatalf("results %v, want one with geo null", results)
}
if len(locator.calls) != 0 {
t.Errorf("locator calls %v, want none", locator.calls)
}
results = resultFields(t,
get(t, s, "/api/v1/ip/"+addrInTestPrefixV4+",1.1.1.1").Body.Bytes())
if len(results) != 2 || string(results[0]["geo"]) != jsonNull ||
string(results[1]["geo"]) == jsonNull {
t.Errorf("results %v, want geo only for the public address", results)
}
if len(locator.calls) != 1 || len(locator.calls[0]) != 1 {
t.Errorf("locator calls %v, want one with one address", locator.calls)
}
}
// TestIPLookupGeoIsNullWhenNoSourceAnswers checks an address the locator has
// no answer for.
func TestIPLookupGeoIsNullWhenNoSourceAnswers(t *testing.T) {
t.Parallel()
s := newServerWithTestRoutes(t)
useFakeResolver(s, &fakeResolver{})
s.SetGeoLocator(&fakeGeoLocator{})
results := resultFields(t, get(t, s, "/api/v1/ip/1.1.1.1").Body.Bytes())
if len(results) != 1 || string(results[0]["geo"]) != jsonNull {
t.Errorf("results %v, want one with geo null", results)
}
}
// TestIPLookupReportsVPNProviders looks up addresses on no list, on a list
// that is not a VPN list, on one VPN list and on two. is_vpn says whether any
// VPN list holds the address, and vpn_providers names only those lists. An
// address on none has [], not null.
func TestIPLookupReportsVPNProviders(t *testing.T) {
t.Parallel() t.Parallel()
s := newServerWithTestRoutes(t) s := newServerWithTestRoutes(t)
s.resolver = &fakeResolver{} s.resolver = &fakeResolver{}
s.SetIPLists(fakeIPLists{}) s.SetBlocklists(fakeBlocklists{})
tests := []struct {
name string
addr string
isVPN string
providers string
}{
{"on no list", "1.1.1.1", "false", `[]`},
{"on a list that is not a VPN list", listedUnroutedAddr, "false", `[]`},
{"on one VPN list", oneVPNListAddr, "true", `["` + testVPNList + `"]`},
{
"on two VPN lists", twoVPNListsAddr, "true",
`["` + otherTestVPN + `","` + testVPNList + `"]`,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
path := "/api/v1/ip/" + tt.addr
results := resultFields(t, get(t, s, path).Body.Bytes())
if len(results) != 1 {
t.Fatalf("%s: %d results, want 1", path, len(results))
}
var flags map[string]json.RawMessage
err := json.Unmarshal(results[0]["flags"], &flags)
if err != nil {
t.Fatalf("%s: decoding flags %s: %v", path, results[0]["flags"], err)
}
if got := string(flags["is_vpn"]); got != tt.isVPN {
t.Errorf("%s: is_vpn %s, want %s", path, got, tt.isVPN)
}
if got := string(results[0]["vpn_providers"]); got != tt.providers {
t.Errorf("%s: vpn_providers %s, want %s", path, got, tt.providers)
}
})
}
}
// TestIPLookupReportsIPLists looks up two routed addresses, one of them on an
// IP list. The listed address's result names the list, says what it means and
// when it was updated. The other's result has an empty list.
func TestIPLookupReportsIPLists(t *testing.T) {
t.Parallel()
s := newServerWithTestRoutes(t)
useFakeResolver(s, &fakeResolver{})
s.SetIPLists(fakeIPLists{})
rec := httptest.NewRecorder() rec := httptest.NewRecorder()
s.router.ServeHTTP(rec, httptest.NewRequestWithContext(t.Context(), s.router.ServeHTTP(rec, httptest.NewRequestWithContext(t.Context(),
@@ -1842,15 +1461,15 @@ func TestIPLookupReportsIPLists(t *testing.T) {
want := testListing() want := testListing()
listed := results[0].IPLists listed := results[0].Blocklists
if len(listed) != 1 || listed[0].Name != want.Name || if len(listed) != 1 || listed[0].Name != want.Name ||
listed[0].Description != want.Description || listed[0].Description != want.Description ||
!listed[0].Updated.Equal(want.Updated) { !listed[0].Updated.Equal(want.Updated) {
t.Errorf("%s: ip_lists %+v, want [%+v]", results[0].IP, listed, want) t.Errorf("%s: blocklists %+v, want [%+v]", results[0].IP, listed, want)
} }
if !strings.Contains(rec.Body.String(), `"ip_lists":[]`) { if !strings.Contains(rec.Body.String(), `"blocklists":[]`) {
t.Errorf("answer %s, want an empty ip_lists list for %s", t.Errorf("answer %s, want an empty blocklists list for %s",
rec.Body, addrInTestPrefixV6) rec.Body, addrInTestPrefixV6)
} }
} }
@@ -1880,19 +1499,20 @@ func resultFields(t *testing.T, answer []byte) []map[string]json.RawMessage {
return body.Data.Results return body.Data.Results
} }
// TestIPLookupReportsIPListsOfAnAddressWithNoRoute looks up a listed address // TestIPLookupReportsBlocklistsOfAnAddressWithNoRoute looks up a listed
// that has no live route, alone and beside a routed address. Each answer is // address that has no live route, alone and beside a routed address. Each
// 200 and has a result for the address, with its IP lists and every route // answer is 200 and has a result for the address, with its blocklists and
// field set to null. Before the fix the lookup of that address alone answered // every route field set to null. Before the fix the lookup of that address
// 404, and beside a routed address it was only named in errors, so its IP // alone answered 404, and beside a routed address it was only named in
// lists were never reported. After that fix the result still left out the // errors, so its blocklists were never reported. After that fix the result
// route fields (https://git.eeqj.de/sneak/routewatch/issues/200). // still left out the route fields
func TestIPLookupReportsIPListsOfAnAddressWithNoRoute(t *testing.T) { // (https://git.eeqj.de/sneak/routewatch/issues/200).
func TestIPLookupReportsBlocklistsOfAnAddressWithNoRoute(t *testing.T) {
t.Parallel() t.Parallel()
s := newServerWithTestRoutes(t) s := newServerWithTestRoutes(t)
useFakeResolver(s, &fakeResolver{}) s.resolver = &fakeResolver{}
s.SetIPLists(fakeIPLists{}) s.SetBlocklists(fakeBlocklists{})
// routeFields are the fields of a result that come from the address's // routeFields are the fields of a result that come from the address's
// route and that route's origin AS. // route and that route's origin AS.
@@ -1948,10 +1568,10 @@ func TestIPLookupReportsIPListsOfAnAddressWithNoRoute(t *testing.T) {
} }
result := body.Data.Results[i] result := body.Data.Results[i]
if len(result.IPLists) != 1 || if len(result.Blocklists) != 1 ||
result.IPLists[0].Name != testListing().Name { result.Blocklists[0].Name != testListing().Name {
t.Errorf("%s: ip_lists %+v, want [%+v]", t.Errorf("%s: blocklists %+v, want [%+v]",
target, result.IPLists, testListing()) target, result.Blocklists, testListing())
} }
} }
} }
@@ -1969,10 +1589,10 @@ func TestIPLookupResultsHaveTheSameFields(t *testing.T) {
t.Parallel() t.Parallel()
s := newServerWithTestRoutes(t) s := newServerWithTestRoutes(t)
useFakeResolver(s, &fakeResolver{hosts: map[string][]string{ s.resolver = &fakeResolver{hosts: map[string][]string{
twoAddressHostName: {addrInTestPrefixV4, listedUnroutedAddr}, twoAddressHostName: {addrInTestPrefixV4, listedUnroutedAddr},
}}) }}
s.SetIPLists(fakeIPLists{}) s.SetBlocklists(fakeBlocklists{})
// want is the fields of the first result. // want is the fields of the first result.
var want []string var want []string
@@ -2004,7 +1624,7 @@ func TestIPLookupOfAnAddressWithoutPTRNamesOrStoredNetblock(t *testing.T) {
t.Parallel() t.Parallel()
s := newServerWithTestRoutes(t) s := newServerWithTestRoutes(t)
useFakeResolver(s, &fakeResolver{}) s.resolver = &fakeResolver{}
path := "/api/v1/ip/" + addrInTestPrefixV4 path := "/api/v1/ip/" + addrInTestPrefixV4
@@ -2026,42 +1646,16 @@ func TestIPLookupOfAnAddressWithoutPTRNamesOrStoredNetblock(t *testing.T) {
} }
} }
// TestIPLookupGivesPTRNamesWithoutTrailingDots looks up an address whose PTR
// name the resolver gives fully qualified. The result's ptr holds the name
// without its trailing dot.
func TestIPLookupGivesPTRNamesWithoutTrailingDots(t *testing.T) {
t.Parallel()
s := newServerWithTestRoutes(t)
useFakeResolver(s, &fakeResolver{ptrs: map[string][]string{
addrInTestPrefixV4: {"host.example.com."},
}})
path := "/api/v1/ip/" + addrInTestPrefixV4
results := resultFields(t, get(t, s, path).Body.Bytes())
if len(results) != 1 {
t.Fatalf("%s: %d results, want 1", path, len(results))
}
got := string(results[0]["ptr"])
want := `["host.example.com"]`
if got != want {
t.Errorf("%s: ptr is %s, want %s", path, got, want)
}
}
// TestIPLookupAnswersMayBeCached checks the Cache-Control header of the IP // TestIPLookupAnswersMayBeCached checks the Cache-Control header of the IP
// lookup answers. Caches may keep them for the IP lists' shortest interval, // lookup answers. Caches may keep them for the blocklists' shortest interval,
// and only the caller's own browser may keep the answer about the caller's // and only the caller's own browser may keep the answer about the caller's
// own address. // own address.
func TestIPLookupAnswersMayBeCached(t *testing.T) { func TestIPLookupAnswersMayBeCached(t *testing.T) {
t.Parallel() t.Parallel()
s := newServerWithTestRoutes(t) s := newServerWithTestRoutes(t)
useFakeResolver(s, &fakeResolver{}) s.resolver = &fakeResolver{}
s.SetIPLists(fakeIPLists{}) s.SetBlocklists(fakeBlocklists{})
tests := []struct { tests := []struct {
path string path string
@@ -2111,10 +1705,10 @@ func TestIPLookupHidesPrivateAddresses(t *testing.T) {
t.Parallel() t.Parallel()
s := newServerWithTestRoutes(t) s := newServerWithTestRoutes(t)
useFakeResolver(s, &fakeResolver{hosts: map[string][]string{ s.resolver = &fakeResolver{hosts: map[string][]string{
internalHostName: {internalHostAddr}, internalHostName: {internalHostAddr},
"mixed.test": {internalHostAddr, addrInTestPrefixV4}, "mixed.test": {internalHostAddr, addrInTestPrefixV4},
}}) }}
notPublic := internalHostName + ": " + hostNotPublicMessage notPublic := internalHostName + ": " + hostNotPublicMessage
@@ -2595,13 +2189,9 @@ func settledGoroutineCount() int {
return prev return prev
} }
// waitForGoroutines waits up to 15 seconds for the goroutine count to drop to // waitForGoroutines waits until the goroutine count drops to target or below.
// target or below.
func waitForGoroutines(target int) bool { func waitForGoroutines(target int) bool {
const maxWait = 15 * time.Second for range 100 {
deadline := time.Now().Add(maxWait)
for time.Now().Before(deadline) {
if runtime.NumGoroutine() <= target { if runtime.NumGoroutine() <= target {
return true return true
} }
@@ -85,7 +85,7 @@ func TestIPLookupGivesTheOriginMostPeersCarry(t *testing.T) {
t.Parallel() t.Parallel()
s := newServerWithTable(t, newTwoOriginTable()) s := newServerWithTable(t, newTwoOriginTable())
useFakeResolver(s, &fakeResolver{}) s.resolver = &fakeResolver{}
firstSeen := testRouteTime(-1) firstSeen := testRouteTime(-1)
+4 -8
View File
@@ -76,9 +76,7 @@ func asLink(asn int) string {
} }
// TestHomePageCardsShowTheTableFigures fills a routing table and the asns // TestHomePageCardsShowTheTableFigures fills a routing table and the asns
// table, works out the cards, and checks that each card shows its figure. The // table, works out the cards, and checks that each card shows its figure.
// 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) { func TestHomePageCardsShowTheTableFigures(t *testing.T) {
t.Parallel() t.Parallel()
@@ -97,9 +95,7 @@ func TestHomePageCardsShowTheTableFigures(t *testing.T) {
t.Fatalf("GetOrCreateASNBatch: %v", err) t.Fatalf("GetOrCreateASNBatch: %v", err)
} }
synctest.Test(t, func(t *testing.T) { s.refreshHomeCards(t.Context())
s.refreshHomeCards(t.Context())
})
page := get(t, s, "/").Body.String() page := get(t, s, "/").Body.String()
@@ -283,7 +279,7 @@ func TestKeepHomeCardsFreshWorksThemOutEveryInterval(t *testing.T) {
const ( const (
interval = 10 * time.Millisecond interval = 10 * time.Millisecond
maxWait = 15 * time.Second maxWait = 5 * time.Second
) )
table := emptyTable() table := emptyTable()
@@ -325,7 +321,7 @@ func TestKeepHomeCardsFreshWorksThemOutEveryInterval(t *testing.T) {
func TestStartedServerWorksOutTheCards(t *testing.T) { func TestStartedServerWorksOutTheCards(t *testing.T) {
t.Parallel() t.Parallel()
const maxWait = 15 * time.Second const maxWait = 5 * time.Second
s := newServerWithTable(t, newCardsTable()) s := newServerWithTable(t, newCardsTable())
+36 -43
View File
@@ -14,7 +14,6 @@ import (
"regexp" "regexp"
"strings" "strings"
"testing" "testing"
"testing/synctest"
"time" "time"
"git.eeqj.de/sneak/routewatch/internal/config" "git.eeqj.de/sneak/routewatch/internal/config"
@@ -115,7 +114,7 @@ func TestJSONAnswersPutNoUnitInAString(t *testing.T) {
`^([0-9]+(\.[0-9]+)? ?(ns|µs|ms|s|m|h|B|kB|MB|GB|TB))+$`) `^([0-9]+(\.[0-9]+)? ?(ns|µs|ms|s|m|h|B|kB|MB|GB|TB))+$`)
s := newServerWithTestRoutes(t) s := newServerWithTestRoutes(t)
useFakeResolver(s, &fakeResolver{}) s.resolver = &fakeResolver{}
s.SetASNFetcher(fixedIntervalASNFetcher{interval: time.Second}) s.SetASNFetcher(fixedIntervalASNFetcher{interval: time.Second})
paths := []string{ paths := []string{
@@ -164,10 +163,6 @@ func TestJSONAnswersPutNoUnitInAString(t *testing.T) {
// router and the middleware write. Before the fix a panic in a handler, and a // 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 // method /status.json or the health check does not take, answered with an
// empty body (https://git.eeqj.de/sneak/routewatch/issues/201). // 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) { func TestJSONAnswersCarryMeta(t *testing.T) {
t.Parallel() t.Parallel()
@@ -179,17 +174,13 @@ func TestJSONAnswersCarryMeta(t *testing.T) {
) )
s := newServerWithTestRoutes(t) s := newServerWithTestRoutes(t)
useFakeResolver(s, &fakeResolver{}) s.resolver = &fakeResolver{}
s.streamer.GetMetricsTracker().SetConnected(true) s.streamer.GetMetricsTracker().SetConnected(true)
s.router.Get(writesNothingPath, JSONValidationMiddleware(http.HandlerFunc( s.router.Get(writesNothingPath, JSONValidationMiddleware(http.HandlerFunc(
func(http.ResponseWriter, *http.Request) {})).ServeHTTP) func(http.ResponseWriter, *http.Request) {})).ServeHTTP)
s.router.Get(panicsPath, JSONValidationMiddleware(http.HandlerFunc( s.router.Get(panicsPath, JSONValidationMiddleware(http.HandlerFunc(
func(http.ResponseWriter, *http.Request) { panic(errDiskIO) })).ServeHTTP) 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 { tests := []struct {
method string method string
path string path string
@@ -225,40 +216,42 @@ func TestJSONAnswersCarryMeta(t *testing.T) {
{http.MethodGet, panicsPath, http.StatusInternalServerError}, {http.MethodGet, panicsPath, http.StatusInternalServerError},
} }
synctest.Test(t, func(t *testing.T) { for _, tt := range tests {
for _, tt := range tests { checkAnswerCarriesMeta(t, s, httptest.NewRequestWithContext(
checkAnswerCarriesMeta(t, s, httptest.NewRequestWithContext( t.Context(), tt.method, tt.path, nil), tt.wantCode)
t.Context(), tt.method, tt.path, nil), tt.wantCode) }
}
// A request whose time limit has already passed answers 504. The // A request whose time limit has already passed answers 504. The handlers
// handlers write the answers of the first five routes, and the JSON // write the answers of the first five routes, and the JSON check on the
// check on the route writes the last. // route writes the last.
pastTimeLimit, cancel := context.WithDeadline(t.Context(), time.Now()) pastTimeLimit, cancel := context.WithDeadline(t.Context(), time.Now())
defer cancel() defer cancel()
for _, path := range []string{ for _, path := range []string{
statusJSONPath, statsPath, "/ip/" + addrInTestPrefixV4, statusJSONPath, statsPath, "/ip/" + addrInTestPrefixV4,
"/api/v1/ip/" + addrInTestPrefixV4, asJSONPath, writesNothingPath, "/api/v1/ip/" + addrInTestPrefixV4, asJSONPath, writesNothingPath,
} { } {
checkAnswerCarriesMeta(t, s, httptest.NewRequestWithContext( checkAnswerCarriesMeta(t, s, httptest.NewRequestWithContext(
pastTimeLimit, http.MethodGet, path, nil), http.StatusGatewayTimeout) pastTimeLimit, http.MethodGet, path, nil), http.StatusGatewayTimeout)
} }
// With a store whose reads fail, the health check answers 503, and // With a store whose reads fail, the health check answers 503, and the
// the handlers of the other routes 500. // handlers of the other routes 500.
failing := New(failingDB{}, newTestTable(),
streamer.New(logger.New(), metrics.New()), logger.New(), &config.Config{})
failing.resolver = &fakeResolver{}
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( checkAnswerCarriesMeta(t, failing, httptest.NewRequestWithContext(
t.Context(), http.MethodGet, healthCheckPath, nil), t.Context(), http.MethodGet, path, nil), http.StatusInternalServerError)
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 // checkAnswerCarriesMeta serves req through the server's router, and checks
@@ -268,7 +261,7 @@ func checkAnswerCarriesMeta(
) { ) {
t.Helper() t.Helper()
// The values README "JSON API" gives the two fields that never change. // The values README "API v1" gives the two fields that never change.
const ( const (
wantTimeZone = "UTC" wantTimeZone = "UTC"
wantAPIVersion = 1 wantAPIVersion = 1
@@ -521,7 +514,7 @@ func newServerWithConfig(
s := New(db, newTestTable(), streamer.New(logger.New(), metrics.New()), s := New(db, newTestTable(), streamer.New(logger.New(), metrics.New()),
&logger.Logger{Logger: slog.New(slog.NewJSONHandler(requestLog, nil))}, cfg) &logger.Logger{Logger: slog.New(slog.NewJSONHandler(requestLog, nil))}, cfg)
useFakeResolver(s, &fakeResolver{}) s.resolver = &fakeResolver{}
return s return s
} }
@@ -1,230 +0,0 @@
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")
}
}
+2 -11
View File
@@ -5,7 +5,6 @@ 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
@@ -13,23 +12,15 @@ 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{"/", statusJSONPath, statsPath, "/ip", "/ip/"} { for _, path := range []string{"/", statusJSONPath, statsPath, "/ip", "/ip/"} {
rec := httptest.NewRecorder() rec := httptest.NewRecorder()
s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
synctest.Test(t, func(t *testing.T) { t.Context(), http.MethodHead, path, nil))
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",
+15 -45
View File
@@ -7,8 +7,8 @@
// - 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, the times a prefix and an AS were first seen, and a prefix's // WHOIS details and the times a prefix and an AS were first seen come from
// origin changes come from the database. // the database.
package server package server
import ( import (
@@ -22,10 +22,9 @@ import (
"sync/atomic" "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"
@@ -46,30 +45,20 @@ type ASNFetcher interface {
GetStats() ASNFetcherStats GetStats() ASNFetcherStats
} }
// IPLists tells which public IP lists contain an address, from copies it keeps // Blocklists tells which public blocklists list an address, from copies it
// in memory, as *iplist.IPLists does. // keeps in memory, as *blocklist.Blocklists does.
type IPLists interface { type Blocklists interface {
Lookup(addr netip.Addr) []iplist.Listing Lookup(addr netip.Addr) []blocklist.Listing
ShortestInterval() time.Duration ShortestInterval() time.Duration
} }
// dnsResolver looks up the addresses of host names in DNS, as *net.Resolver // dnsResolver looks up the addresses of host names and the names of addresses
// does. // in DNS, as *net.Resolver 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
@@ -80,23 +69,16 @@ type Server struct {
port int port int
srv *http.Server srv *http.Server
asnFetcher ASNFetcher asnFetcher ASNFetcher
ipLists IPLists blocklists Blocklists
// 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 looks up the IP lookup's host names: net.DefaultResolver, or a // resolver makes the IP lookup's DNS lookups: 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 // cards is the copy of the home page's cards that the pages serve, nil
// until the server first works them out // until the server first works them out
cards atomic.Pointer[homeCards] cards atomic.Pointer[homeCards]
@@ -214,26 +196,14 @@ 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
} }
// SetIPLists sets the IP lists the IP lookups report. Call it before Start: // SetBlocklists sets the blocklists the IP lookups report. Call it before
// the handlers read the IP lists without a lock. // Start: the handlers read the blocklists without a lock.
func (s *Server) SetIPLists(ipLists IPLists) { func (s *Server) SetBlocklists(blocklists Blocklists) {
s.ipLists = ipLists s.blocklists = blocklists
} }
+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 = 15 * time.Second waitTimeout = 2 * 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 = waitTimeout readHeaderTimeout = time.Second
) )
release := make(chan struct{}) release := make(chan struct{})
+45 -22
View File
@@ -12,6 +12,7 @@ import (
"fmt" "fmt"
"io" "io"
"math" "math"
"math/rand"
"net/http" "net/http"
"sync" "sync"
"sync/atomic" "sync/atomic"
@@ -57,6 +58,10 @@ 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
@@ -88,8 +93,9 @@ 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.
// While the queue is full, the streamer drops the handler's messages, // When the queue fills up, messages will be dropped according to the
// except STATE messages, which are held until there is room. // backpressure algorithm, except STATE messages, which are held until
// there is room.
QueueCapacity() int QueueCapacity() int
} }
@@ -120,8 +126,8 @@ 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 and dispatches messages to registered handlers via per-handler queues. // backoff, dispatches messages to registered handlers via per-handler queues, and
// Its read loop never waits for room on a queue (see queueMessage). // implements backpressure to prevent queue overflow during high traffic periods.
type Streamer struct { type Streamer struct {
logger *logger.Logger logger *logger.Logger
client *http.Client client *http.Client
@@ -138,6 +144,7 @@ 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
} }
@@ -161,6 +168,8 @@ 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),
} }
} }
@@ -342,10 +351,6 @@ 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
@@ -387,11 +392,6 @@ 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 because their queue was full. This counter is monotonically // handlers due to queue overflow or backpressure. 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 that finds the queue full is dropped, except a STATE message. A // A message is dropped while the queue is filling up (shouldDropForBackpressure)
// STATE message whose state is down is the only notice that all of a peer's // or full, except a STATE message: one whose state is down is the only notice
// routes are gone. A STATE message that finds the queue full is held in // that all of a peer's routes are gone. A STATE message skips the random drop,
// info.heldState instead. Held messages go into the queue, oldest first, when a // and one that finds the queue full is held in info.heldState. Held messages
// later message for the handler finds room, or when Stop is called. While any // go into the queue, oldest first, before anything else for the handler, as
// message is held, the handler's other messages are dropped, so none of them // soon as there is room, or when Stop is called; while any is still held, the
// overtakes a held STATE message. // handler's other messages are dropped, so none of them overtakes a held down.
// //
// 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 { if len(info.heldState) > 0 || s.shouldDropForBackpressure(info) {
return false return false
} }
@@ -923,3 +923,26 @@ 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
}
+73 -190
View File
@@ -5,7 +5,6 @@ import (
"context" "context"
"encoding/json" "encoding/json"
"errors" "errors"
"fmt"
"io" "io"
"log/slog" "log/slog"
"net/http" "net/http"
@@ -14,7 +13,6 @@ 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"
@@ -260,65 +258,6 @@ 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 {
@@ -399,7 +338,7 @@ func TestStopQueuesTheHeldStateMessages(t *testing.T) {
const ( const (
held = 2 held = 2
lines = held + 1 lines = held + 1
maxWait = 15 * time.Second maxWait = 5 * time.Second
) )
srv := httptest.NewServer(http.HandlerFunc( srv := httptest.NewServer(http.HandlerFunc(
@@ -479,15 +418,15 @@ 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 margin instead of waiting for room on the queue // within its deadline plus a small margin instead of waiting for room on the
// and for the worker, and log as not handed over the held message and every // queue and for the worker, and log as not handed over the held message and
// message on the queue. // every 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 = 15 * time.Second margin = 2 * time.Second
) )
var logs bytes.Buffer var logs bytes.Buffer
@@ -578,7 +517,7 @@ func TestStopBeforeMessageReachesQueues(t *testing.T) {
func TestReconnectWhenStreamEnds(t *testing.T) { func TestReconnectWhenStreamEnds(t *testing.T) {
t.Parallel() t.Parallel()
endResponse := pipeTransport{write: func(context.Context, io.Writer) {}} endResponse := func(http.ResponseWriter, *http.Request) {}
checkReconnect(t, endResponse, streamIdleTimeout) checkReconnect(t, endResponse, streamIdleTimeout)
} }
@@ -590,8 +529,9 @@ func TestReconnectWhenStreamGoesIdle(t *testing.T) {
const idleTimeout = 50 * time.Millisecond const idleTimeout = 50 * time.Millisecond
holdResponse := pipeTransport{ holdResponse := func(w http.ResponseWriter, r *http.Request) {
write: func(ctx context.Context, _ io.Writer) { <-ctx.Done() }, flush(w)
<-r.Context().Done()
} }
checkReconnect(t, holdResponse, idleTimeout) checkReconnect(t, holdResponse, idleTimeout)
} }
@@ -604,51 +544,16 @@ func TestReconnectWhenServerNeverAnswers(t *testing.T) {
const idleTimeout = 50 * time.Millisecond const idleTimeout = 50 * time.Millisecond
neverAnswer := roundTripFunc( neverAnswer := func(_ http.ResponseWriter, r *http.Request) {
func(req *http.Request) (*http.Response, error) { <-r.Context().Done()
<-req.Context().Done() }
return nil, req.Context().Err()
},
)
checkReconnect(t, neverAnswer, idleTimeout) checkReconnect(t, neverAnswer, idleTimeout)
} }
// pipeTransport answers every request with a response whose body write fills. // TestStreamNotDroppedWhileLinesArrive has the server send lines well within
// The body fails when the request's context ends, as a connection's does. // the idle timeout for several times the timeout, then end the response. Each
// write gets that context, so that it can end when the request does. // line must start the idle timeout over, so the stream lasts until the server
type pipeTransport struct { // ends it instead of being dropped as idle.
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()
@@ -658,35 +563,26 @@ func TestStreamNotDroppedWhileLinesArrive(t *testing.T) {
sendFor = 5 * idleTimeout sendFor = 5 * idleTimeout
) )
// The streamer is made outside the bubble. Its metrics start a goroutine srv := httptest.NewServer(http.HandlerFunc(
// that never returns, and a bubble waits for each of its goroutines to func(w http.ResponseWriter, _ *http.Request) {
// 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)
// The wait ends with the stream. A bubble's clock stops when flush(w)
// the test function returns, and a goroutine then still time.Sleep(lineInterval)
// asleep panics the test binary.
select {
case <-ctx.Done():
return
case <-time.After(lineInterval):
}
} }
}, }))
}} defer srv.Close()
synctest.Test(t, func(t *testing.T) { s := New(logger.New(), metrics.New())
err := s.stream(context.Background()) s.url = srv.URL
if !errors.Is(err, errStreamEnded) { s.idleTimeout = idleTimeout
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
@@ -750,7 +646,7 @@ func TestHandlerStatsReadWhileMessagesAreDropped(t *testing.T) {
const ( const (
lines = 5 lines = 5
wantDropped = lines - 2 wantDropped = lines - 2
maxWait = 15 * time.Second maxWait = 5 * time.Second
) )
srv := httptest.NewServer(http.HandlerFunc( srv := httptest.NewServer(http.HandlerFunc(
@@ -864,70 +760,61 @@ 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.RoundTripper, idleTimeout time.Duration, t *testing.T, firstResponse http.HandlerFunc, idleTimeout time.Duration,
) { ) {
t.Helper() t.Helper()
const maxWait = 15 * time.Second const maxWait = 5 * 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)
synctest.Test(t, func(t *testing.T) { var requests atomic.Int32
connectedAtReconnect := make(chan bool, 1)
laterResponse := pipeTransport{
write: func(ctx context.Context, w io.Writer) {
_, _ = io.WriteString(w, updateLine)
<-ctx.Done() srv := httptest.NewServer(http.HandlerFunc(
}, func(w http.ResponseWriter, r *http.Request) {
} if requests.Add(1) == 1 {
firstResponse(w, r)
var requests atomic.Int32 return
}
s := New(logger.New(), tracker) select {
s.client = &http.Client{Transport: roundTripFunc( case connectedAtReconnect <- tracker.IsConnected():
func(req *http.Request) (*http.Response, error) { default:
if requests.Add(1) == 1 { }
return firstResponse.RoundTrip(req)
}
select { _, _ = io.WriteString(w, updateLine)
case connectedAtReconnect <- tracker.IsConnected():
default:
}
return laterResponse.RoundTrip(req) flush(w)
}, <-r.Context().Done()
)} }))
s.idleTimeout = idleTimeout defer srv.Close()
s.minBackoff = time.Millisecond
handler := updateHandler{handled: make(chan struct{}, 1)}
s.RegisterHandler(handler)
err := s.Start(t.Context()) s := New(logger.New(), tracker)
if err != nil { s.url = srv.URL
t.Fatalf("Start returned error: %v", err) s.idleTimeout = idleTimeout
} s.minBackoff = time.Millisecond
defer s.Stop(t.Context()) handler := updateHandler{handled: make(chan struct{}, 1)}
s.RegisterHandler(handler)
select { err := s.Start(t.Context())
case <-handler.handled: if err != nil {
case <-time.After(maxWait): t.Fatalf("Start returned error: %v", err)
t.Fatalf("no message from a second response handled within %s", maxWait) }
} defer s.Stop(t.Context())
if <-connectedAtReconnect { select {
t.Error("streamer was still marked connected when it came back " + case <-handler.handled:
"for a second response") case <-time.After(maxWait):
} 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
@@ -949,13 +836,9 @@ func settledGoroutineCount() int {
return prev return prev
} }
// waitForGoroutines waits up to 15 seconds for the goroutine count to drop to // waitForGoroutines waits until the goroutine count drops to target or below.
// target or below.
func waitForGoroutines(target int) bool { func waitForGoroutines(target int) bool {
const maxWait = 15 * time.Second for range 100 {
deadline := time.Now().Add(maxWait)
for time.Now().Before(deadline) {
if runtime.NumGoroutine() <= target { if runtime.NumGoroutine() <= target {
return true return true
} }
-2
View File
@@ -544,8 +544,6 @@
<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}}">
-35
View File
@@ -299,41 +299,6 @@
</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">
-4
View File
@@ -541,10 +541,6 @@
<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>
-17
View File
@@ -67,23 +67,6 @@ 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".
+36 -82
View File
@@ -12,7 +12,6 @@ import (
"regexp" "regexp"
"strings" "strings"
"sync" "sync"
"syscall"
"time" "time"
"unicode/utf8" "unicode/utf8"
@@ -71,12 +70,12 @@ 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"
// PauseTime is how long the client sends an RIR's or NIC.br's server no // NICbrSkipTime is how long the client stops asking NIC.br after NIC.br
// query after that server refuses a query. queryRegistry says what a // answers that the client is over its query limit. NIC.br publishes
// refusal is. RIPE refuses an address for good when the address keeps // neither the limit nor how long it lasts. An hour outlasts a limit
// passing RIPE's limit (see noPersonalFlag). An hour outlasts a limit // counted per minute or per hour. The ASes looked up meanwhile get
// counted per minute or per hour. // NIC.br's fields when they are next refreshed.
const PauseTime = time.Hour const NICbrSkipTime = time.Hour
// RIR identifiers. // RIR identifiers.
const ( const (
@@ -126,10 +125,6 @@ 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
@@ -161,12 +156,12 @@ type Client struct {
logger *slog.Logger logger *slog.Logger
// mu guards pausedUntil. // mu guards nicbrSkipUntil.
mu sync.Mutex mu sync.Mutex
// pausedUntil maps a server, given as host:port, to the time the client // nicbrSkipUntil is when the client next asks NIC.br, after NIC.br
// may ask it again. // answered that the client is over its query limit.
pausedUntil map[string]time.Time nicbrSkipUntil time.Time
} }
// NewClient creates a new WHOIS client that logs to logger. // NewClient creates a new WHOIS client that logs to logger.
@@ -177,29 +172,23 @@ 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
// NIC.br is paused, as askNICbr says. // is skipped, as askNICbr says.
// //
// It returns ErrNoReferral when IANA refers the AS to no RIR. Its error // It returns ErrNoReferral when IANA refers the AS to no RIR, and another
// wraps ErrPaused when the RIR is paused. It returns another error in each // error when the query to IANA or to the RIR fails, when the RIR refuses
// of these cases: // it, when IANA's answer has neither a referral nor the AS's block, when
// // IANA refers the AS to a server none of the five RIRs run, or when the
// - the query to IANA or to the RIR fails // answer carries none of ASNInfo's fields.
// - 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)
@@ -222,7 +211,7 @@ func (c *Client) LookupASN(ctx context.Context, asn int) (*ASNInfo, error) {
} }
// Query the authoritative RIR // Query the authoritative RIR
rirResp, err := c.queryRegistry(ctx, whoisServer, rirQuery(rir, query)) rirResp, err := c.queryRIR(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)
} }
@@ -252,19 +241,22 @@ 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. The reduced answer pauses NIC.br, as a refusal does. While NIC.br // fields. After the reduced answer, it returns lacnicInfo without asking
// is paused, askNICbr returns lacnicInfo without a warning. The ASes looked // NIC.br until NICbrSkipTime has passed.
// 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
answer, err := c.queryRegistry(ctx, whoisServerNICbr, asQuery) c.mu.Lock()
if errors.Is(err, ErrPaused) { skipping := c.Now().Before(c.nicbrSkipUntil)
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)
@@ -273,11 +265,13 @@ func (c *Client) askNICbr(
} }
if strings.Contains(answer, nicbrLimitReached) { if strings.Contains(answer, nicbrLimitReached) {
c.pause(whoisServerNICbr) c.mu.Lock()
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 pausing NIC.br", "limit, keeping LACNIC's fields and skipping NIC.br",
"asn", asn, "pause_for", PauseTime) "asn", asn, "skip_for", NICbrSkipTime)
return lacnicInfo return lacnicInfo
} }
@@ -315,65 +309,25 @@ func rirQuery(rir, asQuery string) string {
} }
} }
// queryRegistry sends query to the server of an RIR or of NIC.br, and // queryRIR sends query to an RIR's server and returns the answer. An answer
// returns the answer. The client pauses the server for PauseTime when the // holding an error line with which the server refuses the query is an
// server refuses the query. Each of these is a refusal: // error, and the error holds that line.
// 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 nil return answer, 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
+5 -142
View File
@@ -718,10 +718,9 @@ 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 test sets the client's clock. The // client is over its query limit. The first lookup asks NIC.br. The
// first lookup asks NIC.br. The next comes a second before PauseTime has // second, a second before NICbrSkipTime has passed, does not. The third,
// passed, and does not ask NIC.br. The last comes at PauseTime and asks // once NICbrSkipTime has passed, asks again. Each keeps LACNIC's fields.
// NIC.br again. Each keeps LACNIC's fields.
func TestLookupASNSkipsNICbrAfterItsLimit(t *testing.T) { func TestLookupASNSkipsNICbrAfterItsLimit(t *testing.T) {
t.Parallel() t.Parallel()
@@ -741,8 +740,8 @@ func TestLookupASNSkipsNICbrAfterItsLimit(t *testing.T) {
wantAsks int wantAsks int
}{ }{
{after: 0, wantAsks: 1}, {after: 0, wantAsks: 1},
{after: whois.PauseTime - time.Second, wantAsks: 1}, {after: whois.NICbrSkipTime - time.Second, wantAsks: 1},
{after: whois.PauseTime, wantAsks: 2}, {after: whois.NICbrSkipTime, wantAsks: 2},
} { } {
now = start.Add(step.after) now = start.Add(step.after)
@@ -786,142 +785,6 @@ 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.