Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
gitpod-io
GitHub Repository: gitpod-io/gitpod
Path: blob/main/operations/observability/mixins/self-hosted/rules/argocd/prometheusRules.yaml
3635 views
1
# Copyright (c) 2022 Gitpod GmbH. All rights reserved.
2
# Licensed under the GNU Affero General Public License (AGPL).
3
# See License.AGPL.txt in the project root for license information.
4
5
apiVersion: monitoring.coreos.com/v1
6
kind: PrometheusRule
7
metadata:
8
labels:
9
app.kubernetes.io/name: argocd
10
app.kubernetes.io/part-of: kube-prometheus
11
prometheus: k8s
12
role: alert-rules
13
name: argocd-monitoring-rules
14
namespace: monitoring-satellite
15
spec:
16
groups:
17
- name: argocd-apps
18
rules:
19
- alert: ArgoCDAppStuckInUnknown
20
for: 1h
21
annotations:
22
description: App {{ $labels.name }} in {{ $labels.label_environment }} is stuck in `Unknown` for 1h. ArgoCD is probably generating errors when trying to compare live and desired manifests.
23
summary: App {{ $labels.name }} is stuck in `Unknown` state.
24
dashboard_url: https://grafana.gitpod.io/d/argocd-apps/argocd?refresh=30s&var-environment={{ $labels.label_environment }}&var-team={{ $labels.team }}
25
expr: label_replace(argocd_app_info{sync_status="Unknown"} * on(name) group_left(label_environment, label_team) argocd_app_labels, "team", "$1", "label_team", "(.*)")
26
labels:
27
severity: warning
28
- alert: ArgoCDAppOutOfSyncForTooLong
29
for: 1d
30
annotations:
31
description: App {{ $labels.name }} in {{ $labels.label_environment }} is `OutOfSync` for more than an entire day. The live manifests do not match with what is desired in git!
32
summary: App {{ $labels.name }} is stuck in `OutOfSync` state.
33
dashboard_url: https://grafana.gitpod.io/d/argocd-apps/argocd?refresh=30s&var-environment={{ $labels.label_environment }}&var-team={{ $labels.team }}
34
expr: label_replace(argocd_app_info{sync_status="OutOfSync"} * on(name) group_left(label_environment, label_team) argocd_app_labels, "team", "$1", "label_team", "(.*)")
35
labels:
36
severity: warning
37
- alert: ArgoCDAppStuckInProgressing
38
for: 1h
39
annotations:
40
description: App {{ $labels.name }} in {{ $labels.label_environment }} is stuck in `Progressing` for 1h. It is possible that the application is left in a weird state.
41
summary: App {{ $labels.name }} is stuck in `Progressing` state.
42
dashboard_url: https://grafana.gitpod.io/d/argocd-apps/argocd?refresh=30s&var-environment={{ $labels.label_environment }}&var-team={{ $labels.team }}
43
expr: label_replace(argocd_app_info{health_status="Progressing"} * on(name) group_left(label_environment, label_team) argocd_app_labels, "team", "$1", "label_team", "(.*)")
44
labels:
45
severity: warning
46
- alert: ArgoCDAppDegraded
47
for: 20m
48
annotations:
49
description: App {{ $labels.name }} in {{ $labels.label_environment }} is stuck in `Degraded`. This means that the synchronization failed requires investigation.
50
summary: App {{ $labels.name }} is stuck in `Degraded` state.
51
dashboard_url: https://grafana.gitpod.io/d/argocd-apps/argocd?refresh=30s&var-environment={{ $labels.label_environment }}&var-team={{ $labels.team }}
52
expr: label_replace(argocd_app_info{health_status="Degraded"} * on(name) group_left(label_environment, label_team) argocd_app_labels, "team", "$1", "label_team", "(.*)")
53
labels:
54
severity: warning
55
56