Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add metrics for certificate expiration date #131

Merged
merged 1 commit into from
Jun 13, 2023
Merged

Add metrics for certificate expiration date #131

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 10 additions & 9 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -888,15 +888,16 @@ Metrics are exposed for Prometheus if the command line option `--server-port-htt
The endpoint URL is `http://<pod-ip>:<port>/metrics`.
Besides the default Go metrics, the following cert-management specific metrics are provided:

| Name | Labels | Description |
| -------------------------------------------- | -------------------- | ---------------------------------------------- |
| cert_management_acme_account_registrations | uri, email, issuer | ACME account registrations |
| cert_management_acme_orders | issuer, success, dns_challenges, renew | Number of ACME orders |
| cert_management_cert_entries | issuer, issuertype | Total number of certificate objects per issuer |
| cert_management_acme_active_dns_challenges | issuer | Currently active number of ACME DNS challenges |
| cert_management_overdue_renewal_certificates | - | Number of certificate objects with certificate's renewal overdue |
| cert_management_revoked_certificates | - | Number of certificate objects with revoked certificate |
| cert_management_secrets | classification | Number of certificate secrets per classification (only updated on startup and every 24h on GC of secrets). Currently there are three classifications: `total` = total number of certificate secrets on the source cluster, `revoked` = number of revoked certificate secrets, `backup`= number of backups of certificate secrets (every certificate has a backup secret in the `kube-system` namespace to allow revocation even if it is not used anymore) |
| Name | Labels | Description |
|----------------------------------------------|----------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| cert_management_acme_account_registrations | uri, email, issuer | ACME account registrations |
| cert_management_acme_orders | issuer, success, dns_challenges, renew | Number of ACME orders |
| cert_management_cert_entries | issuer, issuertype | Total number of certificate objects per issuer |
| cert_management_cert_object_expire | namespace, name | Expire date as Unix time (the number of seconds elapsed since January 1, 1970 UTC) |
| cert_management_acme_active_dns_challenges | issuer | Currently active number of ACME DNS challenges |
| cert_management_overdue_renewal_certificates | - | Number of certificate objects with certificate's renewal overdue |
| cert_management_revoked_certificates | - | Number of certificate objects with revoked certificate |
| cert_management_secrets | classification | Number of certificate secrets per classification (only updated on startup and every 24h on GC of secrets). Currently there are three classifications: `total` = total number of certificate secrets on the source cluster, `revoked` = number of revoked certificate secrets, `backup`= number of backups of certificate secrets (every certificate has a backup secret in the `kube-system` namespace to allow revocation even if it is not used anymore) |


## Troubleshooting
Expand Down
2 changes: 1 addition & 1 deletion build/Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
# SPDX-License-Identifier: Apache-2.0

############# builder #############
FROM golang:1.20.4 AS builder
FROM golang:1.20.5 AS builder

WORKDIR /build
COPY . .
Expand Down
20 changes: 20 additions & 0 deletions pkg/cert/metrics/metrics.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@ func init() {
prometheus.MustRegister(ACMETotalOrders)
prometheus.MustRegister(ACMEActiveDNSChallenges)
prometheus.MustRegister(CertEntries)
prometheus.MustRegister(CertObjectExpire)
prometheus.MustRegister(OverdueCertificates)
prometheus.MustRegister(RevokedCertificates)
prometheus.MustRegister(CertificateSecrets)
Expand Down Expand Up @@ -64,6 +65,15 @@ var (
[]string{"issuertype", "issuer"},
)

// CertObjectExpire is the cert_management_cert_entries_expire gauge.
CertObjectExpire = prometheus.NewGaugeVec(
prometheus.GaugeOpts{
Name: "cert_management_cert_object_expire",
Help: "Expire date as Unix time (the number of seconds elapsed since January 1, 1970 UTC) for each certificate object",
},
[]string{"namespace", "name"},
)

// OverdueCertificates is the cert_management_overdue_renewal_certificates gauge.
OverdueCertificates = prometheus.NewGauge(
prometheus.GaugeOpts{
Expand Down Expand Up @@ -138,3 +148,13 @@ func ReportRevokedCerts(count int) {
func ReportCertificateSecrets(classification string, count int) {
CertificateSecrets.WithLabelValues(classification).Set(float64(count))
}

// ReportCertObjectExpire sets a CertObjectExpire gauge entry.
func ReportCertObjectExpire(namespace, name string, unixSeconds int64) {
CertObjectExpire.WithLabelValues(namespace, name).Set(float64(unixSeconds))
}

// DeleteObjectEntriesExpire deletes a CertObjectExpire gauge entry.
func DeleteObjectEntriesExpire(namespace, name string) {
CertObjectExpire.DeleteLabelValues(namespace, name)
}
16 changes: 16 additions & 0 deletions pkg/controller/issuer/core/support.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -389,6 +389,7 @@ func updateTypeStatus(mod *resources.ModificationState, status **runtime.RawExte
func (s *Support) AddCertificate(cert *api.Certificate) {
certObjName, issuerKey := s.calcAssocObjectNames(cert)
s.state.AddCertAssoc(issuerKey, certObjName)
s.reportCertificateExpires(cert.Namespace, cert.Name, cert.Status.ExpirationDate)
s.reportCertificateMetrics(issuerKey)
}

Expand All @@ -397,6 +398,7 @@ func (s *Support) RemoveCertificate(certObjName resources.ObjectName) {
s.state.RemoveCertAssoc(certObjName)
s.ClearCertRenewalOverdue(certObjName)
s.ClearCertRevoked(certObjName)
s.reportCertificateExpiresRemoved(certObjName.Namespace(), certObjName.Name())
s.reportAllCertificateMetrics()
}

Expand All @@ -411,6 +413,20 @@ func (s *Support) reportAllCertificateMetrics() {
}
}

func (s *Support) reportCertificateExpires(namespace, name string, expires *string) {
var seconds int64 = 0
if expires != nil {
if expireTime, err := time.Parse(time.RFC3339, *expires); err == nil {
seconds = expireTime.Unix()
}
}
metrics.ReportCertObjectExpire(namespace, name, seconds)
}

func (s *Support) reportCertificateExpiresRemoved(namespace, name string) {
metrics.DeleteObjectEntriesExpire(namespace, name)
}

func (s *Support) calcAssocObjectNames(cert *api.Certificate) (resources.ObjectName, utils.IssuerKey) {
certObjName := newObjectName(cert.Namespace, cert.Name)

Expand Down