watcher: warn of an expiring certificate on every TLS check (closes #204)
check / check (push) Failing after 2m1s

An expiry warning was skipped when the last one for that hostname and
address was sent less than DNSWATCHER_TLS_INTERVAL ago. Each TLS check
runs after a DNS pass of varying length, so two checks can be less than
the interval apart, and a certificate about to expire was warned about on
every check or every other check, at random. TLS checks already start
once per interval, so the in-memory record of when each warning was sent
is removed and every check warns, as the README says.

The test that expected the second check to stay silent is replaced by one
that runs TLS checks on state built in the test, with no DNS.

Model: opus-5-5
This commit was merged in pull request #208.
This commit is contained in:
2026-10-02 01:58:28 +02:00
parent 1f1640d4cd
commit c9510a986c
4 changed files with 74 additions and 67 deletions
+18 -38
View File
@@ -7,7 +7,6 @@ import (
"slices"
"sort"
"strings"
"sync"
"time"
"go.uber.org/fx"
@@ -49,18 +48,16 @@ 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
done chan struct{} // closed when Run returns
firstRun bool
expiryNotifiedMu sync.Mutex
expiryNotified map[string]time.Time
log *slog.Logger
config *config.Config
state *state.State
resolver DNSResolver
portCheck PortChecker
tlsCheck TLSChecker
notify Notifier
cancel context.CancelFunc
done chan struct{} // closed when Run returns
firstRun bool
}
// New creates a new Watcher instance wired into the fx lifecycle.
@@ -69,15 +66,14 @@ 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,
expiryNotified: make(map[string]time.Time),
log: params.Logger.Get(),
config: params.Config,
state: params.State,
resolver: params.Resolver,
portCheck: params.PortCheck,
tlsCheck: params.TLSCheck,
notify: params.Notify,
firstRun: true,
}
lifecycle.Append(fx.Hook{
@@ -1028,22 +1024,6 @@ 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)",