fix(scheduler): Cert-Renewal-Alerts pro Domain statt aggregierter Zählung (v1.1.143)
- certrenewer.Result.FailedDomains []string — jeder fehlgeschlagene Domain-Name wird erfasst (Issue/Parse/Write-Fehler) - runRenewer: pro Domain eigener Alert + eigener Dedupe-Key statt einem shared "cert.renew_failed"-Key; Alert-Message nennt jetzt den Domain-Namen und gibt Hinweis auf ACME/DNS-Debugging Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -41,7 +41,7 @@ import (
|
||||
"git.netcell-it.de/projekte/edgeguard-native/internal/services/tlscerts"
|
||||
)
|
||||
|
||||
var version = "1.1.142"
|
||||
var version = "1.1.143"
|
||||
|
||||
const (
|
||||
// renewTickInterval — how often we re-evaluate expiring certs.
|
||||
@@ -1062,11 +1062,18 @@ func runRenewer(ctx context.Context, r *certrenewer.Service, a *alerts.Service,
|
||||
slog.Info("scheduler: renewer pass complete",
|
||||
"checked", res.Checked, "renewed", res.Renewed,
|
||||
"failed", res.Failed, "skipped", res.Skipped)
|
||||
if a != nil && res.Failed > 0 && d != nil && d.shouldFire("cert.renew_failed") {
|
||||
_, _ = a.Fire(ctx, "cert.renew_failed", alerts.SeverityError,
|
||||
"Cert-Renewal teilweise fehlgeschlagen",
|
||||
fmt.Sprintf("Renewer-Cycle: %d checked, %d renewed, %d failed, %d skipped",
|
||||
res.Checked, res.Renewed, res.Failed, res.Skipped))
|
||||
if a != nil && d != nil {
|
||||
for _, domain := range res.FailedDomains {
|
||||
key := "cert.renew_failed:" + domain
|
||||
if !d.shouldFire(key) {
|
||||
continue
|
||||
}
|
||||
_, _ = a.Fire(ctx, "cert.renew_failed", alerts.SeverityError,
|
||||
"Cert-Renewal fehlgeschlagen: "+domain,
|
||||
"Let's Encrypt Erneuerung für "+domain+" ist fehlgeschlagen. "+
|
||||
"Prüfe ACME-Konfiguration und DNS-Erreichbarkeit. "+
|
||||
"Nächster Versuch beim nächsten Renewer-Tick (alle 6h).")
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user