fix(symlinkguard): deliver alerts beside the scan, not inside it
CI / Lint / Test / Vet (pull_request) Successful in 54s
CI / Mirror to GitHub (pull_request) Skipped

Watch flushed the alert queue in the scan goroutine. With a hung ntfy
(accepts, never answers until the 10 s timeout) and a full queue, one
flush took ~6 notify timeouts, so a planted symlink stayed readable for
several intervals instead of at most one.

Delivery now runs in its own goroutine that owns the queue. The scan
hands alerts over on a bounded channel without blocking; an alert that
does not fit is counted in the never-dropped summary, so the
"delivered or counted" property holds.

Repro test (interval 50 ms, notifier latency 40 ms, full queue): worst
link lifetime 243 ms before, under 2 intervals after.

Closes #164

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-05 09:34:27 +02:00
co-authored by Claude Opus 5.5
parent 0bd0fbf03e
commit b7a10485af
2 changed files with 97 additions and 2 deletions
@@ -496,3 +496,42 @@ func TestWatchDropsAPoisonMessageAndCountsIt(t *testing.T) {
return false
}, 3*time.Second, 5*time.Millisecond, "the dropped poison alert is counted in a summary")
}
// hungNotifier answers every Notify only after latency, with an outage error:
// an ntfy that accepts connections but never responds until its timeout.
type hungNotifier struct{ latency time.Duration }
func (h hungNotifier) Notify(ctx context.Context, _ string) error {
select {
case <-time.After(h.latency):
case <-ctx.Done():
}
return errors.New("ntfy timeout")
}
// hyperguild#164: alerts were flushed in the scan goroutine, so with a hung
// ntfy and a full queue one flush (6 x latency) delayed the next scan and a
// planted link stayed for ~5 intervals. Delivery now runs beside the scan.
func TestWatchLinkLifetimeStaysUnderTwoIntervalsWithAHungNotifier(t *testing.T) {
const interval = 50 * time.Millisecond
brain := t.TempDir()
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
go Watch(ctx, brain, interval, hungNotifier{latency: 40 * time.Millisecond})
// Fill the queue: one removal alert per tick, more than maxPending.
for i := 0; i < maxPending+3; i++ {
link := filepath.Join(brain, "fill"+strconv.Itoa(i))
require.NoError(t, os.Symlink(t.TempDir(), link))
require.Eventually(t, func() bool { _, err := os.Lstat(link); return os.IsNotExist(err) }, 5*time.Second, time.Millisecond)
}
var worst time.Duration
for i := 0; i < 8; i++ {
link := filepath.Join(brain, "probe"+strconv.Itoa(i))
require.NoError(t, os.Symlink(t.TempDir(), link))
planted := time.Now()
require.Eventually(t, func() bool { _, err := os.Lstat(link); return os.IsNotExist(err) }, 5*time.Second, time.Millisecond)
worst = max(worst, time.Since(planted))
}
assert.LessOrEqual(t, worst, 2*interval, "worst link lifetime %v with a hung notifier", worst)
}