fix: deduplicate TLS expiry warnings to prevent notification spam (closes #18) #22

Merged
sneak merged 2 commits from fix/tls-expiry-dedup into main 2026-02-28 12:08:46 +01:00
2 changed files with 101 additions and 25 deletions

View File

@@ -6,6 +6,7 @@ import (
"log/slog" "log/slog"
"sort" "sort"
"strings" "strings"
"sync"
"time" "time"
"go.uber.org/fx" "go.uber.org/fx"
@@ -49,6 +50,8 @@ type Watcher struct {
notify Notifier notify Notifier
cancel context.CancelFunc cancel context.CancelFunc
firstRun bool firstRun bool
expiryNotifiedMu sync.Mutex
expiryNotified map[string]time.Time
} }
// New creates a new Watcher instance wired into the fx lifecycle. // New creates a new Watcher instance wired into the fx lifecycle.
@@ -65,6 +68,7 @@ func New(
tlsCheck: params.TLSCheck, tlsCheck: params.TLSCheck,
notify: params.Notify, notify: params.Notify,
firstRun: true, firstRun: true,
expiryNotified: make(map[string]time.Time),
} }
lifecycle.Append(fx.Hook{ lifecycle.Append(fx.Hook{
@@ -108,6 +112,7 @@ func NewForTest(
tlsCheck: tc, tlsCheck: tc,
notify: n, notify: n,
firstRun: true, firstRun: true,
expiryNotified: make(map[string]time.Time),
} }
} }
@@ -691,6 +696,22 @@ func (w *Watcher) checkTLSExpiry(
return return
} }
// Deduplicate expiry warnings: don't re-notify for the same
// hostname within the TLS check interval.
dedupKey := fmt.Sprintf("expiry:%s:%s", hostname, ip)
w.expiryNotifiedMu.Lock()
lastNotified, seen := w.expiryNotified[dedupKey]
if seen && time.Since(lastNotified) < w.config.TLSInterval {
w.expiryNotifiedMu.Unlock()
return
}
w.expiryNotified[dedupKey] = time.Now()
w.expiryNotifiedMu.Unlock()
msg := fmt.Sprintf( msg := fmt.Sprintf(
"Host: %s\nIP: %s\nCN: %s\n"+ "Host: %s\nIP: %s\nCN: %s\n"+
"Expires: %s (%.0f days)", "Expires: %s (%.0f days)",

View File

@@ -506,6 +506,61 @@ func TestTLSExpiryWarning(t *testing.T) {
} }
} }
func TestTLSExpiryWarningDedup(t *testing.T) {
t.Parallel()
cfg := defaultTestConfig(t)
cfg.Hostnames = []string{"www.example.com"}
cfg.TLSInterval = 24 * time.Hour
w, deps := newTestWatcher(t, cfg)
deps.resolver.allRecords["www.example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"1.2.3.4"}},
}
deps.resolver.ipAddresses["www.example.com"] = []string{
"1.2.3.4",
}
deps.portChecker.results["1.2.3.4:80"] = true
deps.portChecker.results["1.2.3.4:443"] = true
deps.tlsChecker.certs["1.2.3.4:www.example.com"] = &tlscheck.CertificateInfo{
CommonName: "www.example.com",
Issuer: "DigiCert",
NotAfter: time.Now().Add(3 * 24 * time.Hour),
SubjectAlternativeNames: []string{
"www.example.com",
},
}
ctx := t.Context()
// First run = baseline, no notifications
w.RunOnce(ctx)
// Second run should fire one expiry warning
w.RunOnce(ctx)
// Third run should NOT fire another warning (dedup)
w.RunOnce(ctx)
notifications := deps.notifier.getNotifications()
expiryCount := 0
for _, n := range notifications {
if n.Title == "TLS Expiry Warning: www.example.com" {
expiryCount++
}
}
if expiryCount != 1 {
t.Errorf(
"expected exactly 1 expiry warning (dedup), got %d",
expiryCount,
)
}
}
func TestGracefulShutdown(t *testing.T) { func TestGracefulShutdown(t *testing.T) {
t.Parallel() t.Parallel()