fix: deduplicate TLS expiry warnings to prevent notification spam (closes #18)
Some checks failed
Check / check (pull_request) Failing after 5m31s
Some checks failed
Check / check (pull_request) Failing after 5m31s
checkTLSExpiry fired every monitoring cycle with no deduplication, causing notification spam for expiring certificates. Added an in-memory map tracking the last notification time per domain/IP pair, suppressing re-notification within the TLS check interval. Added TestTLSExpiryWarningDedup to verify deduplication works.
This commit is contained in:
@@ -6,6 +6,7 @@ import (
|
||||
"log/slog"
|
||||
"sort"
|
||||
"strings"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
"go.uber.org/fx"
|
||||
@@ -40,15 +41,17 @@ type Params struct {
|
||||
|
||||
// Watcher orchestrates all monitoring checks on a schedule.
|
||||
type Watcher struct {
|
||||
log *slog.Logger
|
||||
config *config.Config
|
||||
state *state.State
|
||||
resolver DNSResolver
|
||||
portCheck PortChecker
|
||||
tlsCheck TLSChecker
|
||||
notify Notifier
|
||||
cancel context.CancelFunc
|
||||
firstRun bool
|
||||
log *slog.Logger
|
||||
config *config.Config
|
||||
state *state.State
|
||||
resolver DNSResolver
|
||||
portCheck PortChecker
|
||||
tlsCheck TLSChecker
|
||||
notify Notifier
|
||||
cancel context.CancelFunc
|
||||
firstRun bool
|
||||
expiryNotifiedMu sync.Mutex
|
||||
expiryNotified map[string]time.Time
|
||||
}
|
||||
|
||||
// New creates a new Watcher instance wired into the fx lifecycle.
|
||||
@@ -57,14 +60,15 @@ func New(
|
||||
params Params,
|
||||
) (*Watcher, error) {
|
||||
w := &Watcher{
|
||||
log: params.Logger.Get(),
|
||||
config: params.Config,
|
||||
state: params.State,
|
||||
resolver: params.Resolver,
|
||||
portCheck: params.PortCheck,
|
||||
tlsCheck: params.TLSCheck,
|
||||
notify: params.Notify,
|
||||
firstRun: true,
|
||||
log: params.Logger.Get(),
|
||||
config: params.Config,
|
||||
state: params.State,
|
||||
resolver: params.Resolver,
|
||||
portCheck: params.PortCheck,
|
||||
tlsCheck: params.TLSCheck,
|
||||
notify: params.Notify,
|
||||
firstRun: true,
|
||||
expiryNotified: make(map[string]time.Time),
|
||||
}
|
||||
|
||||
lifecycle.Append(fx.Hook{
|
||||
@@ -100,14 +104,15 @@ func NewForTest(
|
||||
n Notifier,
|
||||
) *Watcher {
|
||||
return &Watcher{
|
||||
log: slog.Default(),
|
||||
config: cfg,
|
||||
state: st,
|
||||
resolver: res,
|
||||
portCheck: pc,
|
||||
tlsCheck: tc,
|
||||
notify: n,
|
||||
firstRun: true,
|
||||
log: slog.Default(),
|
||||
config: cfg,
|
||||
state: st,
|
||||
resolver: res,
|
||||
portCheck: pc,
|
||||
tlsCheck: tc,
|
||||
notify: n,
|
||||
firstRun: true,
|
||||
expiryNotified: make(map[string]time.Time),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -691,6 +696,22 @@ func (w *Watcher) checkTLSExpiry(
|
||||
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(
|
||||
"Host: %s\nIP: %s\nCN: %s\n"+
|
||||
"Expires: %s (%.0f days)",
|
||||
|
||||
@@ -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) {
|
||||
t.Parallel()
|
||||
|
||||
|
||||
Reference in New Issue
Block a user