feat: update jinja delimiters back to default (#1269)

* feat: update jinja delimiters back to default

Signed-off-by: Devin Buhl <devin@buhl.casa>

* feat: remove cert-manager promrules

Signed-off-by: Devin Buhl <devin@buhl.casa>

* fix: update talos csr approver

Signed-off-by: Devin Buhl <devin@buhl.casa>

---------

Signed-off-by: Devin Buhl <devin@buhl.casa>
This commit is contained in:
Devin Buhl authored and GitHub committed 2024-01-29 17:11:37 -05:00
1 parent 5fa8b9685a
commit df642e5425
55 files changed
+295 -358

No files matched your search

@@ -3,4 +3,3 @@ apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization
resources:
- ./helmrelease.yaml
- ./prometheusrule.yaml
@@ -1,59 +0,0 @@
---
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
name: cert-manager.rules
spec:
groups:
- name: cert-manager
rules:
- alert: CertManagerAbsent
expr: |
absent(up{job="cert-manager"})
for: 15m
labels:
severity: critical
annotations:
description: >
New certificates will not be able to be minted, and existing ones can't be renewed until cert-manager is back.
runbook_url: https://gitlab.com/uneeq-oss/cert-manager-mixin/-/blob/master/RUNBOOK.md#certmanagerabsent
summary: "Cert Manager has dissapeared from Prometheus service discovery."
- name: certificates
rules:
- alert: CertManagerCertExpirySoon
expr: |
avg by (exported_namespace, namespace, name) (certmanager_certificate_expiration_timestamp_seconds - time()) < (21 * 24 * 3600)
for: 15m
labels:
severity: warning
annotations:
description: >
The domain that this cert covers will be unavailable after {{ $value | humanizeDuration }}.
Clients using endpoints that this cert protects will start to fail in {{ $value | humanizeDuration }}.
runbook_url: https://gitlab.com/uneeq-oss/cert-manager-mixin/-/blob/master/RUNBOOK.md#certmanagercertexpirysoon
summary: |
The cert {{ $labels.name }} is {{ $value | humanizeDuration }} from expiry, it should have renewed over a week ago.
- alert: CertManagerCertNotReady
expr: |
max by (name, exported_namespace, namespace, condition) (certmanager_certificate_ready_status{condition!="True"} == 1)
for: 15m
labels:
severity: critical
annotations:
description: >
This certificate has not been ready to serve traffic for at least
10m. If the cert is being renewed or there is another valid cert, the ingress
controller _may_ be able to serve that instead.
runbook_url: https://gitlab.com/uneeq-oss/cert-manager-mixin/-/blob/master/RUNBOOK.md#certmanagercertnotready
summary: "The cert {{ $labels.name }} is not ready to serve traffic."
- alert: CertManagerHittingRateLimits
expr: |
sum by (host) (rate(certmanager_http_acme_client_request_count{status="429"}[5m])) > 0
for: 15m
labels:
severity: critical
annotations:
description: >
Depending on the rate limit, cert-manager may be unable to generate certificates for up to a week.
runbook_url: https://gitlab.com/uneeq-oss/cert-manager-mixin/-/blob/master/RUNBOOK.md#certmanagerhittingratelimits
summary: "Cert manager hitting LetsEncrypt rate limits."
@@ -4,4 +4,4 @@ kind: Secret
metadata:
name: cert-manager-secret
stringData:
api-token: "#{ cloudflare.token }#"
api-token: "{{ cloudflare.token }}"
@@ -18,7 +18,7 @@ spec:
interval: 30m
retryInterval: 1m
timeout: 5m
#% if cloudflare.enabled %#
{% if cloudflare.enabled %}
---
apiVersion: kustomize.toolkit.fluxcd.io/v1
kind: Kustomization
@@ -41,4 +41,4 @@ spec:
interval: 30m
retryInterval: 1m
timeout: 5m
#% endif %#
{% endif %}