Take in an admin's edits of the state files while running (closes #68)
check / check (push) Successful in 3m35s

smallwebwaf watches SWWAF_STATE_DIR with fsnotify and takes in a saved
edit of a state file in place of what it held. It knows its own writes
by the SHA-256 of what it last read or wrote; each write first takes in
an edit made since. An edit that does not parse is renamed to
<name>.bad at the next write. Each edit taken in or set aside is logged
and counted. Every ban on a netblock is checked, and the next ban is
worked out from the one that ended last. README.md says how to add and
lift a ban.

Judgement call: a broken edit is set aside at the next write, since an
editor's file can be read half written.

Model: opus-5-5
This commit is contained in:
2026-10-06 10:55:44 +00:00
parent 234c5eac60
commit 64930a00fc
13 changed files with 1142 additions and 178 deletions
+270 -76
View File
@@ -1,14 +1,17 @@
// Package state keeps smallwebwaf's state in JSON files in
// SWWAF_STATE_DIR, as the "Persistent state" section of SPEC.md describes:
// bans.json holds the bans, clients.json each client's counters and
// history, and lookups.json GeoJS's answers. Load reads them at start, and
// Run and WriteAll write them, each from a snapshot its part takes under
// its own lock, so that no request waits on the disk.
// history, and lookups.json GeoJS's answers. Load reads them at start,
// Watch takes in an admin's edit of one while smallwebwaf runs, and Run
// and WriteAll write them. The disk is read and written outside the
// parts' locks, which are held only to take a snapshot or to put in what
// a file holds, so that no request waits on the disk.
package state
import (
"bytes"
"context"
"crypto/sha256"
"encoding/json"
"errors"
"fmt"
@@ -17,8 +20,10 @@ import (
"net/netip"
"os"
"path/filepath"
"sync"
"time"
"github.com/fsnotify/fsnotify"
"sneak.berlin/go/smallwebwaf/internal/bans"
"sneak.berlin/go/smallwebwaf/internal/lookup"
"sneak.berlin/go/smallwebwaf/internal/metrics"
@@ -61,15 +66,26 @@ type Params struct {
// Now tells the time by which the counters' buckets run out, normally
// time.Now in UTC.
Now func() time.Time
// ProcessLog receives what was read, and the writes that fail.
// ProcessLog receives what was read and taken in, the edits set aside,
// and the writes that fail.
ProcessLog *slog.Logger
// Metrics count each file's writes.
// Metrics count each file's writes, and the edits taken in and set
// aside.
Metrics *metrics.Metrics
}
// Files are the state files of a running smallwebwaf.
type Files struct {
params Params
// mu is held while a file is read for an edit, and while it is
// written, so that Watch and the writes take turns. No request takes
// it.
mu sync.Mutex
// sums are the SHA-256 sums of what each file held, by name, when
// smallwebwaf last read or wrote it. A file that holds anything else
// has been edited since.
sums map[string][sha256.Size]byte
}
// bansFile is bans.json, indented for an admin to read and edit.
@@ -120,41 +136,28 @@ func Load(params Params) (*Files, error) {
return nil, fmt.Errorf("SWWAF_STATE_DIR cannot be written: %w", err)
}
var (
bansIn bansFile
clientsIn clientsFile
lookupsIn lookupsFile
)
f := &Files{params: params, sums: map[string][sha256.Size]byte{}}
err = errors.Join(
read(params.Dir, bansJSON, &bansIn),
read(params.Dir, clientsJSON, &clientsIn),
read(params.Dir, lookupsJSON, &lookupsIn),
)
bansRead, bansErr := f.read(bansJSON)
clientsRead, clientsErr := f.read(clientsJSON)
lookupsRead, lookupsErr := f.read(lookupsJSON)
err = errors.Join(bansErr, clientsErr, lookupsErr)
if err != nil {
return nil, err
}
held := make([]bans.Ban, 0, len(bansIn.Bans))
for _, entry := range bansIn.Bans {
held = append(held, entry.ban())
}
params.Ledger.Load(held)
params.Limiter.Load(clientsIn.Clients, params.Now())
params.GeoJS.Load(lookupsIn.Lookups)
params.ProcessLog.Info("read the state files", "directory", params.Dir,
"bans", len(bansIn.Bans), "clients", len(clientsIn.Clients),
"lookups", len(lookupsIn.Lookups))
"bans", bansRead, "clients", clientsRead, "lookups", lookupsRead)
return &Files{params: params}, nil
return f, nil
}
// Run writes bans.json WriteDelay after a ban is made, with every ban
// made in between, and every file every CounterInterval, until ctx is
// done. A write that fails is logged, and the file is written again at
// its next write.
// its next write. Each write takes in an admin's edit of its file first,
// as writeFile describes.
func (f *Files) Run(ctx context.Context) {
interval := time.NewTicker(f.params.CounterInterval)
defer interval.Stop()
@@ -172,7 +175,7 @@ func (f *Files) Run(ctx context.Context) {
case <-bansDue:
bansDue = nil
f.logFailure(f.writeBans())
f.logFailure(f.writeFile(bansJSON))
case <-interval.C:
f.logFailure(f.WriteAll())
}
@@ -182,7 +185,50 @@ func (f *Files) Run(ctx context.Context) {
// WriteAll writes every state file, as smallwebwaf stops. A file that
// fails does not keep the others from being written.
func (f *Files) WriteAll() error {
return errors.Join(f.writeBans(), f.writeClients(), f.writeLookups())
return errors.Join(f.writeFile(bansJSON), f.writeFile(clientsJSON),
f.writeFile(lookupsJSON))
}
// Watch watches Dir until ctx is done, and takes in an admin's edit of a
// state file as soon as it is saved: what the file holds replaces what
// smallwebwaf held for it. An edit that does not parse is left for the
// file's next write, which sets it aside, since a file can be read while
// an editor is still writing it. If Dir cannot be watched, that is
// logged, and an edit is taken in only before its file is written.
func (f *Files) Watch(ctx context.Context) {
watcher, err := fsnotify.NewWatcher()
if err == nil {
defer func() {
_ = watcher.Close()
}()
err = watcher.Add(f.params.Dir)
}
if err != nil {
f.params.ProcessLog.Error("cannot watch the state files for edits",
"error", err.Error())
return
}
f.params.ProcessLog.Info("watching the state files for edits",
"directory", f.params.Dir)
for {
select {
case <-ctx.Done():
return
case event := <-watcher.Events:
switch name := filepath.Base(event.Name); name {
case bansJSON, clientsJSON, lookupsJSON:
f.fileChanged(name)
}
case err = <-watcher.Errors:
f.params.ProcessLog.Warn("watching the state files failed",
"error", err.Error())
}
}
}
// logFailure logs a write that failed.
@@ -193,52 +239,209 @@ func (f *Files) logFailure(err error) {
}
}
// writeBans writes bans.json.
func (f *Files) writeBans() error {
held := f.params.Ledger.Snapshot()
// fileChanged takes in what the state file name holds, as Watch sees it
// change, if that is an edit made since smallwebwaf last read or wrote
// the file. A file that cannot be read or does not parse is left for its
// next write.
func (f *Files) fileChanged(name string) {
f.mu.Lock()
defer f.mu.Unlock()
file := bansFile{Version: version, Bans: make([]banEntry, 0, len(held))}
for _, ban := range held {
file.Bans = append(file.Bans, newBanEntry(ban))
data, changed, err := f.readChanged(name)
if err != nil || !changed {
return
}
data, err := json.MarshalIndent(file, "", " ")
if err != nil {
return fmt.Errorf("encode %s: %w", bansJSON, err)
}
return f.writeCounted(bansJSON, append(data, '\n'))
_ = f.takeInEdit(name, data)
}
// writeClients writes clients.json.
func (f *Files) writeClients() error {
data, err := encodeOnePerLine("clients", f.params.Limiter.Snapshot())
// takeInEdit takes in data, an edit of the state file name, as takeIn
// does, and counts and logs it. Every edit taken in while smallwebwaf
// runs, by Watch or by a write, is taken in here. An edit that does not
// parse is neither counted nor logged, and takeIn's error returned.
func (f *Files) takeInEdit(name string, data []byte) error {
_, err := f.takeIn(name, data)
if err != nil {
return fmt.Errorf("encode %s: %w", clientsJSON, err)
return err
}
return f.writeCounted(clientsJSON, data)
// Counted before it is logged, so that the count is there once the
// log line is.
f.params.Metrics.StateFileEditTakenIn(name)
f.params.ProcessLog.Info("took in an edit of a state file",
"file", filepath.Join(f.params.Dir, name))
return nil
}
// writeLookups writes lookups.json.
func (f *Files) writeLookups() error {
data, err := encodeOnePerLine("lookups", f.params.GeoJS.Snapshot())
if err != nil {
return fmt.Errorf("encode %s: %w", lookupsJSON, err)
// read takes in the state file name at start, and returns how many
// entries it holds. A missing file holds none.
func (f *Files) read(name string) (int, error) {
data, changed, err := f.readChanged(name)
if err != nil || !changed {
return 0, err
}
return f.writeCounted(lookupsJSON, data)
return f.takeIn(name, data)
}
// writeCounted writes data to the state file name, as write does, and
// counts the write in the metrics.
func (f *Files) writeCounted(name string, data []byte) error {
err := write(f.params.Dir, name, data)
// readChanged returns what the state file name holds, and whether that
// has changed since smallwebwaf last read or wrote the file, as it has
// for a file smallwebwaf never read or wrote. A missing file has not
// changed: it is written again at its next write.
func (f *Files) readChanged(name string) ([]byte, bool, error) {
path := filepath.Join(f.params.Dir, name)
data, err := os.ReadFile(path) //nolint:gosec // a state file, in SWWAF_STATE_DIR
if errors.Is(err, fs.ErrNotExist) {
return nil, false, nil
}
if err != nil {
return nil, false, err
}
return data, sha256.Sum256(data) != f.sums[name], nil
}
// takeIn parses data, what the state file name holds, puts it into the
// part that keeps that state, in place of what the part held, and returns
// how many entries the file holds. An error names the file and, where the
// JSON decoder tells it, the line and column, or else the entry.
func (f *Files) takeIn(name string, data []byte) (int, error) {
path := filepath.Join(f.params.Dir, name)
var entries int
switch name {
case bansJSON:
var file bansFile
err := parse(path, data, &file)
if err != nil {
return 0, err
}
held := make([]bans.Ban, 0, len(file.Bans))
for _, entry := range file.Bans {
held = append(held, entry.ban())
}
f.params.Ledger.Load(held)
entries = len(held)
case clientsJSON:
var file clientsFile
err := parse(path, data, &file)
if err != nil {
return 0, err
}
f.params.Limiter.Load(file.Clients, f.params.Now())
entries = len(file.Clients)
case lookupsJSON:
var file lookupsFile
err := parse(path, data, &file)
if err != nil {
return 0, err
}
f.params.GeoJS.Load(file.Lookups)
entries = len(file.Lookups)
}
f.sums[name] = sha256.Sum256(data)
return entries, nil
}
// writeFile writes the state file name from what smallwebwaf holds. An
// edit made since smallwebwaf last read or wrote the file is taken in
// first, so that it is not overwritten, or set aside if it does not
// parse. A file that cannot be read, or an edit that cannot be set
// aside, is left as it is, and the write given up. Every write is counted
// in the metrics, and one that fails or is given up as a failure.
func (f *Files) writeFile(name string) error {
f.mu.Lock()
defer f.mu.Unlock()
data, changed, err := f.readChanged(name)
if err == nil && changed {
err = f.takeInEdit(name, data)
if err != nil {
err = f.setAside(name, err)
}
}
if err == nil {
data, err = f.encode(name)
if err != nil {
err = fmt.Errorf("encode %s: %w", name, err)
}
}
if err == nil {
err = write(f.params.Dir, name, data)
}
if err == nil {
// The file holds data from here on, even if the directory sync
// fails, so that its next read does not take it for an admin's
// edit.
f.sums[name] = sha256.Sum256(data)
err = syncDirectory(f.params.Dir)
}
f.params.Metrics.StateFileWritten(name, len(data), err)
return err
}
// setAside renames the state file name, an edit that does not parse with
// parseErr, to name.bad, for the admin to mend, and logs it with where in
// the file the error is. If the rename fails, the edit is left as it is,
// and the error returned is parseErr joined with the rename's.
func (f *Files) setAside(name string, parseErr error) error {
path := filepath.Join(f.params.Dir, name)
err := os.Rename(path, path+".bad")
if err != nil {
return errors.Join(parseErr, err)
}
f.params.ProcessLog.Error("set aside an edit of a state file that does not parse",
"file", path+".bad", "error", parseErr.Error())
f.params.Metrics.StateFileEditSetAside(name)
return nil
}
// encode returns the state file name as smallwebwaf writes it, from a
// snapshot of the part that keeps that state.
func (f *Files) encode(name string) ([]byte, error) {
switch name {
case bansJSON:
held := f.params.Ledger.Snapshot()
file := bansFile{Version: version, Bans: make([]banEntry, 0, len(held))}
for _, ban := range held {
file.Bans = append(file.Bans, newBanEntry(ban))
}
data, err := json.MarshalIndent(file, "", " ")
if err != nil {
return nil, err
}
return append(data, '\n'), nil
case clientsJSON:
return encodeOnePerLine("clients", f.params.Limiter.Snapshot())
default: // lookups.json
return encodeOnePerLine("lookups", f.params.GeoJS.Snapshot())
}
}
// newBanEntry returns ban as bans.json holds it.
func newBanEntry(ban bans.Ban) banEntry {
entry := banEntry{Netblock: ban.Netblock, Start: ban.Start, Notes: ban.Notes}
@@ -389,28 +592,16 @@ func checkWritable(dir string) error {
return errors.Join(file.Close(), os.Remove(file.Name()))
}
// read reads the state file name in dir into file, a pointer to that
// file's struct, and checks its entries. A missing file leaves file as it
// is.
func read(dir, name string, file stateFile) error {
path := filepath.Join(dir, name)
data, err := os.ReadFile(path) //nolint:gosec // a state file, in SWWAF_STATE_DIR
if errors.Is(err, fs.ErrNotExist) {
return nil
}
if err != nil {
return err
}
// parse reads data, what the state file at path holds, into file, a
// pointer to that file's struct, and checks its entries.
func parse(path string, data []byte, file stateFile) error {
// The version is read first, so that a file of another version is
// refused for that, and not for an entry this version cannot read.
var header struct {
Version int `json:"version"`
}
err = json.Unmarshal(data, &header)
err := json.Unmarshal(data, &header)
if err == nil && header.Version != version {
err = fmt.Errorf("%w %d, where this smallwebwaf reads version %d",
errVersion, header.Version, version)
@@ -463,7 +654,7 @@ func position(data []byte, err error) string {
// write writes data to the file name in dir so that a crash at any
// moment leaves either the old file or the new one, whole: data goes to a
// temporary file in the same directory, which is synced and renamed over
// name, and then the directory is synced, so that the rename lasts.
// name. syncDirectory must follow, so that the rename lasts.
func write(dir, name string, data []byte) error {
path := filepath.Join(dir, name)
temporary := path + ".tmp"
@@ -475,10 +666,13 @@ func write(dir, name string, data []byte) error {
if err != nil {
_ = os.Remove(temporary)
return err
}
return err
}
// syncDirectory syncs dir to the disk, so that a rename in it lasts.
func syncDirectory(dir string) error {
directory, err := os.Open(dir) //nolint:gosec // SWWAF_STATE_DIR itself
if err != nil {
return err
+481 -11
View File
@@ -3,7 +3,10 @@ package state_test
import (
"context"
"encoding/json"
"io/fs"
"log/slog"
"maps"
"net"
"net/http"
"net/http/httptest"
"net/netip"
@@ -28,6 +31,13 @@ const (
bansJSON = "bans.json"
clientsJSON = "clients.json"
lookupsJSON = "lookups.json"
// What the process log says once Watch watches the directory, and as
// it takes in an edit.
watching = "watching the state files for edits"
tookIn = "took in an edit of a state file"
// maxLogLines is how many lines of the process log wait for a test to
// read them.
maxLogLines = 64
)
// permanentBansJSON is bans.json holding permanentBan.
@@ -290,7 +300,7 @@ func TestUnwritableDirectoryStopsTheStart(t *testing.T) {
}
}
// The two tests below run Run in a synctest bubble, where time is a clock
// The three tests below run Run in a synctest bubble, where time is a clock
// of the test's own: time.Sleep moves it on at once, and synctest.Wait
// returns once Run waits for its next write, so that every write due by
// then is on disk.
@@ -302,7 +312,7 @@ func TestBansWrittenOnceWriteDelayAfterABan(t *testing.T) {
dir := t.TempDir()
params := newParams(dir)
params.WriteDelay = 10 * time.Second
run(t, load(t, params))
run(t, load(t, params).Run)
// A second ban, made while the first waits to be written, puts the
// write off no further, and is written with it.
@@ -347,7 +357,7 @@ func TestEveryFileWrittenEveryCounterInterval(t *testing.T) {
dir := t.TempDir()
params := newParams(dir)
params.CounterInterval = time.Minute
run(t, load(t, params))
run(t, load(t, params).Run)
// The files are removed once written, so that each interval shows
// them written again.
@@ -364,6 +374,44 @@ func TestEveryFileWrittenEveryCounterInterval(t *testing.T) {
})
}
func TestEditJustBeforeAScheduledWriteSurvivesIt(t *testing.T) {
t.Parallel()
synctest.Test(t, func(t *testing.T) {
dir := t.TempDir()
params := newParams(dir)
params.WriteDelay = 10 * time.Second
run(t, load(t, params).Run)
// A ban, and bans.json written with it.
params.Ledger.BanForLimit(netip.MustParsePrefix("203.0.113.9/32"),
midnight(), bans.Notes{})
time.Sleep(params.WriteDelay)
synctest.Wait()
// A second ban is to be written WriteDelay later. Just before
// then, an admin saves bans.json with the first ban lifted and
// another added.
params.Ledger.BanForLimit(netip.MustParsePrefix("203.0.113.10/32"),
midnight(), bans.Notes{})
time.Sleep(params.WriteDelay - time.Nanosecond)
synctest.Wait()
edit(t, dir, bansJSON, permanentBansJSON)
// The write takes the edit in first, and writes it back. The second
// ban, made after the admin opened the file, is lost, as "Edits
// while running" in SPEC.md says.
time.Sleep(time.Nanosecond)
synctest.Wait()
if got := readFile(t, filepath.Join(dir, bansJSON)); got != permanentBansJSON {
t.Errorf("bans.json holds\n%s\nwant the edit", got)
}
wantEqual(t, bansJSON, params.Ledger.Snapshot(), []bans.Ban{permanentBan()})
})
}
func TestFailedWriteLeavesTheFileAsItWas(t *testing.T) {
t.Parallel()
@@ -459,24 +507,359 @@ func TestWritesAreCountedInTheMetrics(t *testing.T) {
float64(len(permanentBansJSON)))
}
func TestFailedRenameLeavesNoTemporaryFile(t *testing.T) {
func TestFileThatCannotBeReadIsNotWrittenOver(t *testing.T) {
t.Parallel()
dir := t.TempDir()
files := load(t, newParams(dir))
path := filepath.Join(dir, bansJSON)
params := newParams(dir)
files := load(t, params)
// A directory named bans.json cannot be renamed over.
err := os.Mkdir(filepath.Join(dir, bansJSON), 0o700)
// bans.json is a socket, which cannot be opened as a file, even by
// root, as the tests run in Docker, but which a rename could replace.
// Whether it holds an edit cannot be told, so it is left as it is.
socket, err := (&net.ListenConfig{}).Listen(t.Context(), "unix", path)
if err != nil {
t.Fatalf("listen: %v", err)
}
defer func() {
_ = socket.Close()
}()
err = files.WriteAll()
if err == nil {
t.Error("writing with bans.json unreadable did not fail")
}
info, err := os.Lstat(path)
if err != nil || info.Mode().Type() != fs.ModeSocket {
t.Errorf("bans.json is now %v (%v), want the socket", info, err)
}
wantFiles(t, dir, bansJSON, clientsJSON, lookupsJSON)
wantWriteFailed(t, params, bansJSON)
}
func TestBrokenEditThatCannotBeSetAsideIsNotWrittenOver(t *testing.T) {
t.Parallel()
const broken = `{"version": 1, "bans": [`
dir := t.TempDir()
path := filepath.Join(dir, bansJSON)
params := newParams(dir)
files := load(t, params)
// A directory named bans.json.bad cannot be renamed over, so the
// broken edit cannot be set aside, and is left as it is.
edit(t, dir, bansJSON, broken)
err := os.Mkdir(path+".bad", 0o700)
if err != nil {
t.Fatalf("mkdir: %v", err)
}
err = files.WriteAll()
if err == nil {
t.Error("writing over a directory did not fail")
t.Error("writing with bans.json.bad in the way did not fail")
}
if got := readFile(t, path); got != broken {
t.Errorf("bans.json holds\n%s\nwant the edit", got)
}
wantWriteFailed(t, params, bansJSON)
}
func TestEditOfEachFileTakenIn(t *testing.T) {
t.Parallel()
dir := t.TempDir()
params := newParams(dir)
lines := logInto(&params)
fill(params)
files := load(t, params)
err := files.WriteAll()
if err != nil {
t.Fatalf("write: %v", err)
}
watch(t, files, lines)
// Each edit holds one entry, for a client the parts did not hold, and
// takes the place of everything the part held.
client := netip.MustParsePrefix("198.51.100.7/32")
edit(t, dir, bansJSON, `{"version": 1, "bans": [{"netblock": "198.51.100.7/32", `+
`"start": "2026-10-06T00:00:00Z", "expires": null}]}`)
wantTakenIn(t, lines, dir, bansJSON)
wantEqual(t, bansJSON, params.Ledger.Snapshot(),
[]bans.Ban{{Netblock: client, Start: midnight()}})
edit(t, dir, clientsJSON, `{"version": 1, "clients": [`+
`{"client": "198.51.100.7/32", "history": {"requests": 7}}]}`)
wantTakenIn(t, lines, dir, clientsJSON)
wantEqual(t, clientsJSON, params.Limiter.Snapshot(),
[]ratelimit.Client{{Client: client, History: ratelimit.History{Requests: 7}}})
edit(t, dir, lookupsJSON, `{"version": 1, "lookups": [{"client": "198.51.100.7/32", `+
`"country": "FR", "answered": "2026-10-06T00:00:00Z"}]}`)
wantTakenIn(t, lines, dir, lookupsJSON)
wantEqual(t, lookupsJSON, params.GeoJS.Snapshot(),
[]lookup.Answer{{Client: client, Country: "FR", Answered: midnight()}})
}
func TestOwnWritesAreNotTakenIn(t *testing.T) {
t.Parallel()
dir := t.TempDir()
params := newParams(dir)
lines := logInto(&params)
fill(params)
files := load(t, params)
watch(t, files, lines)
// Every file is written while watched, and then lookups.json edited:
// the first edit taken in is that one.
err := files.WriteAll()
if err != nil {
t.Fatalf("write: %v", err)
}
edit(t, dir, lookupsJSON, `{"version": 1, "lookups": []}`)
wantTakenIn(t, lines, dir, lookupsJSON)
}
func TestFileRenamedOverAStateFileTakenIn(t *testing.T) {
t.Parallel()
dir := t.TempDir()
path := filepath.Join(dir, bansJSON)
params := newParams(dir)
lines := logInto(&params)
files := load(t, params)
err := files.WriteAll()
if err != nil {
t.Fatalf("write: %v", err)
}
watch(t, files, lines)
// The admin mends bans.json.bad and moves it back, as editors that
// save by renaming do with a file of their own: nothing is written
// into bans.json itself. An edit of clients.json after it must be
// taken in second.
edit(t, dir, bansJSON+".bad", permanentBansJSON)
err = os.Rename(path+".bad", path)
if err != nil {
t.Fatalf("rename: %v", err)
}
edit(t, dir, clientsJSON, `{"version": 1, "clients": []}`)
wantTakenIn(t, lines, dir, bansJSON)
wantEqual(t, bansJSON, params.Ledger.Snapshot(), []bans.Ban{permanentBan()})
}
func TestBanAddedAndLiftedThroughBansJSON(t *testing.T) {
t.Parallel()
dir := t.TempDir()
params := newParams(dir)
lines := logInto(&params)
watch(t, load(t, params), lines)
client := netip.MustParseAddr("203.0.113.9")
// An entry added, as an admin writes it, bans its netblock.
edit(t, dir, bansJSON, `{"version": 1, "bans": [{"netblock": "203.0.113.0/24", `+
`"start": "2026-10-06T00:00:00Z", "expires": null}]}`)
wantTakenIn(t, lines, dir, bansJSON)
_, banned := params.Ledger.Check(client, midnight())
if !banned {
t.Error("the ban added to bans.json does not refuse")
}
// The entry removed lifts the ban.
edit(t, dir, bansJSON, `{"version": 1, "bans": []}`)
wantTakenIn(t, lines, dir, bansJSON)
_, banned = params.Ledger.Check(client, midnight())
if banned {
t.Error("the ban removed from bans.json still refuses")
}
}
func TestBrokenEditSetAsideAtTheNextWrite(t *testing.T) {
t.Parallel()
// It ends a ban's entry with a comma.
const broken = "{\n \"version\": 1,\n \"bans\": [\n" +
" {\"netblock\": \"203.0.113.9/32\",}\n ]\n}\n"
dir := t.TempDir()
path := filepath.Join(dir, bansJSON)
params := newParams(dir)
lines := logInto(&params)
params.Ledger.Load([]bans.Ban{permanentBan()})
files := load(t, params)
err := files.WriteAll()
if err != nil {
t.Fatalf("write: %v", err)
}
watch(t, files, lines)
// While smallwebwaf runs, the broken edit is left as it is: an edit
// of clients.json, made after it and taken in, shows that it has been
// seen.
edit(t, dir, bansJSON, broken)
edit(t, dir, clientsJSON, `{"version": 1, "clients": []}`)
wantTakenIn(t, lines, dir, clientsJSON)
wantFiles(t, dir, bansJSON, clientsJSON, lookupsJSON)
// The next write sets it aside, logged with where the error is, and
// writes bans.json again from what smallwebwaf still holds.
err = files.WriteAll()
if err != nil {
t.Fatalf("write: %v", err)
}
line := lines.waitFor(t, "set aside an edit of a state file that does not parse")
message, _ := line["error"].(string)
if line["file"] != path+".bad" ||
!strings.HasPrefix(message, path+", line 4, column 39: ") {
t.Errorf("set aside with %v", line)
}
wantFiles(t, dir, bansJSON, bansJSON+".bad", clientsJSON, lookupsJSON)
if got := readFile(t, path+".bad"); got != broken {
t.Errorf("bans.json.bad holds\n%s\nwant the edit", got)
}
if got := readFile(t, path); got != permanentBansJSON {
t.Errorf("bans.json holds\n%s\nwant\n%s", got, permanentBansJSON)
}
}
func TestEditsTakenInAreCountedInTheMetrics(t *testing.T) {
t.Parallel()
dir := t.TempDir()
params := newParams(dir)
lines := logInto(&params)
files := load(t, params)
// One edit is taken in by the write of its file, before Watch runs,
// and one by Watch.
edit(t, dir, bansJSON, `{"version": 1, "bans": []}`)
err := files.WriteAll()
if err != nil {
t.Fatalf("write: %v", err)
}
watch(t, files, lines)
edit(t, dir, bansJSON, permanentBansJSON)
wantTakenIn(t, lines, dir, bansJSON)
wantMetric(t, scrape(t, params),
`smallwebwaf_state_file_edits_taken_in_total{file="bans.json"}`, 2)
}
func TestEditTakenInByAWriteIsLoggedAsWatchLogsIt(t *testing.T) {
t.Parallel()
dir := t.TempDir()
params := newParams(dir)
lines := logInto(&params)
files := load(t, params)
// An edit taken in by Watch, which is then stopped.
ctx, stop := context.WithCancel(t.Context())
stopped := make(chan struct{})
go func() {
files.Watch(ctx)
close(stopped)
}()
lines.waitFor(t, watching)
edit(t, dir, bansJSON, `{"version": 1, "bans": []}`)
byWatch := lines.waitFor(t, tookIn)
stop()
<-stopped
// An edit taken in by the write of its file. Nothing logs after the
// write, so the log is closed, and a write that does not log the edit
// fails the test at once instead of waiting for the line.
edit(t, dir, bansJSON, permanentBansJSON)
err := files.WriteAll()
if err != nil {
t.Fatalf("write: %v", err)
}
close(lines)
byWrite := lines.waitFor(t, tookIn)
// The two lines differ only in their time.
delete(byWatch, "time")
delete(byWrite, "time")
if !maps.Equal(byWrite, byWatch) {
t.Errorf("the write logged %v, where Watch logged %v", byWrite, byWatch)
}
}
func TestEditsSetAsideAreCountedInTheMetrics(t *testing.T) {
t.Parallel()
dir := t.TempDir()
params := newParams(dir)
files := load(t, params)
edit(t, dir, bansJSON, `{"version": 1, "bans": [`)
err := files.WriteAll()
if err != nil {
t.Fatalf("write: %v", err)
}
wantMetric(t, scrape(t, params),
`smallwebwaf_state_file_edits_set_aside_total{file="bans.json"}`, 1)
}
func TestDirectoryThatCannotBeWatchedIsLogged(t *testing.T) {
t.Parallel()
dir := t.TempDir()
params := newParams(dir)
lines := logInto(&params)
files := load(t, params)
err := os.Remove(dir)
if err != nil {
t.Fatalf("remove: %v", err)
}
// Watch returns at once.
files.Watch(t.Context())
line := lines.waitFor(t, "cannot watch the state files for edits")
if line["level"] != "ERROR" {
t.Errorf("logged as %v", line)
}
}
// midnight is the time of the tests' clock.
@@ -573,15 +956,16 @@ func load(t *testing.T, params state.Params) *state.Files {
return files
}
// run runs files' writes until the test ends.
func run(t *testing.T, files *state.Files) {
// run runs task, the Run or the Watch of state files, until the test
// ends.
func run(t *testing.T, task func(context.Context)) {
t.Helper()
ctx, stop := context.WithCancel(t.Context())
stopped := make(chan struct{})
go func() {
files.Run(ctx)
task(ctx)
close(stopped)
}()
@@ -591,6 +975,80 @@ func run(t *testing.T, files *state.Files) {
})
}
// watch runs files' Watch until the test ends, and waits until it
// watches the directory.
func watch(t *testing.T, files *state.Files, lines processLog) {
t.Helper()
run(t, files.Watch)
lines.waitFor(t, watching)
}
// processLog receives the lines of a process log, each a JSON object, for
// a test to wait for.
type processLog chan string
// logInto has params' process log write its lines into a new processLog,
// and returns that.
func logInto(params *state.Params) processLog {
lines := make(processLog, maxLogLines)
params.ProcessLog = slog.New(slog.NewJSONHandler(lines, nil))
return lines
}
// Write receives a line of the process log.
func (l processLog) Write(line []byte) (int, error) {
l <- string(line)
return len(line), nil
}
// waitFor returns the next line of the process log whose message is msg,
// passing over the lines before it, or nil if the log is closed first. It
// waits as long as that takes, so that a slow test process cannot fail
// the test.
func (l processLog) waitFor(t *testing.T, msg string) map[string]any {
t.Helper()
for line := range l {
var fields map[string]any
err := json.Unmarshal([]byte(line), &fields)
if err != nil {
t.Fatalf("process log line %q is not JSON: %v", line, err)
}
if fields["msg"] == msg {
return fields
}
}
return nil
}
// wantTakenIn waits for the next edit taken in, and checks that it is of
// the state file name in dir.
func wantTakenIn(t *testing.T, lines processLog, dir, name string) {
t.Helper()
line := lines.waitFor(t, tookIn)
if line["file"] != filepath.Join(dir, name) {
t.Fatalf("took in %v, want an edit of %s", line, name)
}
}
// edit writes content to the state file name in dir, as an admin saves an
// edit of it.
func edit(t *testing.T, dir, name, content string) {
t.Helper()
err := os.WriteFile(filepath.Join(dir, name), []byte(content), 0o600)
if err != nil {
t.Fatalf("write %s: %v", name, err)
}
}
// wantEqual checks that the entries read back from file are those
// written.
func wantEqual[E comparable](t *testing.T, file string, got, want []E) {
@@ -735,6 +1193,18 @@ func metric(t *testing.T, text, series string) float64 {
return 0
}
// wantWriteFailed checks that the metrics of params count one write of the
// state file name, and that it failed.
func wantWriteFailed(t *testing.T, params state.Params, name string) {
t.Helper()
got := scrape(t, params)
file := `{file="` + name + `"}`
wantMetric(t, got, "smallwebwaf_state_file_writes_total"+file, 1)
wantMetric(t, got, "smallwebwaf_state_file_write_failures_total"+file, 1)
}
// wantMetric checks the value of series in text, the metrics, as metric
// reads it.
func wantMetric(t *testing.T, text, series string, want float64) {
+35
View File
@@ -0,0 +1,35 @@
package state
import (
"os"
"path/filepath"
"testing"
)
// The test is on write itself: a state file is read before it is
// written, and a directory in its place fails that read first.
func TestFailedRenameLeavesNoTemporaryFile(t *testing.T) {
t.Parallel()
dir := t.TempDir()
// A directory named bans.json cannot be renamed over.
err := os.Mkdir(filepath.Join(dir, bansJSON), 0o700)
if err != nil {
t.Fatalf("mkdir: %v", err)
}
err = write(dir, bansJSON, []byte("{}\n"))
if err == nil {
t.Error("writing over a directory did not fail")
}
entries, err := os.ReadDir(dir)
if err != nil {
t.Fatalf("read %s: %v", dir, err)
}
if len(entries) != 1 || entries[0].Name() != bansJSON {
t.Errorf("%s holds %v, want only bans.json", dir, entries)
}
}