Files
homelab/edu_master/k8s/alerts.yaml
T
forust 5cf0c90258
renovate-ci / validate-renovate (push) Skipped
ci / lint-yaml (push) Successful in 2s
ci / lint-dockerfiles (push) Successful in 1s
ci / validate (push) Successful in 1s
ci / build (push) Skipped
ci / lint-prettier (pull_request) Successful in 4s
ci / lint-ruff (pull_request) Successful in 1s
ci / lint-prettier (push) Successful in 2s
ci / lint-ruff (push) Successful in 0s
ci / lint-yaml (pull_request) Successful in 2s
ci / lint-dockerfiles (pull_request) Successful in 0s
ci / validate (pull_request) Successful in 1s
ci / build (pull_request) Skipped
renovate-ci / validate-renovate (pull_request) Successful in 7s
style: prettier formatting for edu_master alerts and postgres readme
2026-09-23 16:10:33 +02:00

78 lines
3.6 KiB
YAML

apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
name: edu-master-webinar
namespace: edu-master
labels:
release: prometheus-stack
spec:
groups:
- name: edu_master.webinar
rules:
# No successful webinar check for 5m (~2-3 missed 2-min checks).
# Catches: playwright hangs/timeouts, version skew, site changes, hung job.
- alert: WebinarCheckerNoSuccessfulCheck
expr: |
(time() - webinar_check_last_success_timestamp_seconds > 300)
and (webinar_check_last_run_timestamp_seconds > 0)
for: 2m
labels:
severity: critical
annotations:
summary: "Webinar checker has no successful check for 5m"
description: "edu-master/webinar-checker: last successful webinar check was {{ $value | humanizeDuration }} ago. Checks are failing or hanging (see consecutive failures alert). Notifications about new webinars are NOT being sent."
# Fast path: 3 consecutive failures (~6+ min at 2-min interval).
- alert: WebinarCheckerConsecutiveFailures
expr: |
webinar_check_consecutive_failures >= 3
for: 5m
labels:
severity: critical
annotations:
summary: "Webinar checker failing consecutively"
description: 'edu-master/webinar-checker: {{ $value }} consecutive webinar check failures (timeout / playwright error / page error). Check pod logs (Loki: {namespace="edu-master", container="webinar-checker"}).'
# Metrics endpoint not scraped for 10m: pod down, metrics server dead, or ServiceMonitor broken.
- alert: WebinarCheckerScrapeDown
expr: |
absent(webinar_check_last_run_timestamp_seconds) == 1
for: 10m
labels:
severity: critical
annotations:
summary: "Webinar checker metrics missing"
description: "edu-master/webinar-checker: no metrics series for 10m. Pod may be down, metrics server dead, or ServiceMonitor/Service broken. Webinar checks are unobserved."
# EDU session lost: session-keeper down or credentials expired. Without PHPSESSID every check is skipped.
- alert: EduPhpsessidMissing
expr: |
edu_phpsessid_present == 0
for: 10m
labels:
severity: critical
annotations:
summary: "EDU_PHPSESSID missing"
description: "edu-master: EDU_PHPSESSID absent from redis for 10m. Webinar/diari/schedule checks are all skipped. Check session-keeper logs and EDU credentials."
# Hard deps: checker and playwright deployments unavailable.
- alert: WebinarCheckerDeploymentDown
expr: |
kube_deployment_status_replicas_unavailable{deployment="webinar-checker", namespace="edu-master"} > 0
for: 10m
labels:
severity: critical
annotations:
summary: "Webinar checker deployment unavailable"
description: "edu-master/webinar-checker deployment has {{ $value }} unavailable replica(s) for 10m."
- alert: PlaywrightServiceDown
expr: |
kube_deployment_status_replicas_unavailable{deployment="playwright-service", namespace="edu-master"} > 0
for: 10m
labels:
severity: critical
annotations:
summary: "Playwright service unavailable"
description: "edu-master/playwright-service deployment has {{ $value }} unavailable replica(s) for 10m. All webinar/diari/schedule checks fail without it."