Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
gitpod-io
GitHub Repository: gitpod-io/gitpod
Path: blob/main/operations/observability/mixins/meta/rules/dashboard.yaml
2500 views
1
apiVersion: monitoring.coreos.com/v1
2
kind: PrometheusRule
3
metadata:
4
labels:
5
prometheus: k8s
6
role: alert-rules
7
name: dashboard-monitoring-rules
8
spec:
9
groups:
10
- name: dashboard
11
rules:
12
- alert: DashboardHighCPUUsage
13
# Reasoning: high rates of CPU consumption should only be temporary.
14
expr: avg(rate(container_cpu_usage_seconds_total{container!="POD", pod=~"dashboard-.*"}[5m])) by (cluster) > 0.1
15
for: 10m
16
labels:
17
# sent to the team internal channel until we fine tuned it
18
severity: warning
19
team: webapp
20
annotations:
21
runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/WebAppServicesHighCPUUsage.md
22
summary: Dashboard has excessive CPU usage.
23
description: Dashboard is consumming too much CPU. Please investigate.
24
dashboard_url: https://grafana.gitpod.io/d/6581e46e4e5c7ba40a07646395ef7b23/kubernetes-compute-resources-pod?var-cluster={{ $labels.cluster }}&var-namespace=default
25
- alert: DashboardPodsAreNotAllInReadyState
26
expr: sum(kube_deployment_status_replicas_unavailable{deployment="dashboard"}) > 0
27
for: 10m
28
labels:
29
severity: critical
30
team: webapp
31
dedicated: included
32
annotations:
33
runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/DashboardStuckInPodInitState.md
34
summary: Dashboard stuck in PodInitializing state {{ $labels.cluster }}.
35
description: Dashboard is stuck in PodInitializing for at least 10 minutes
36
37