Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
gitpod-io
GitHub Repository: gitpod-io/gitpod
Path: blob/main/operations/observability/mixins/workspace/rules/central/image-builder.yaml
2506 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
prometheus: k8s
10
role: alert-rules
11
name: image-builder-central-monitoring-rules
12
spec:
13
groups:
14
- name: image-builder-central
15
rules:
16
- alert: GitpodImageBuildDurationAnomaly
17
labels:
18
severity: warning
19
team: engine
20
annotations:
21
runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/GitpodImageBuildDurationAnomaly.md
22
summary: image builds are happening too frequently in cluster {{ $labels.cluster }}
23
description: Users are waiting more often for image builds
24
expr: |
25
(
26
(
27
avg_over_time(gitpod_ws_manager_mk2_workspace_phase_total{phase="Running", type="ImageBuild", cluster!~"ephemeral.*"}[4h])
28
- avg_over_time(gitpod_ws_manager_mk2_workspace_phase_total{phase="Running", type="ImageBuild", cluster!~"ephemeral.*"}[7d])
29
)
30
/ stddev_over_time(gitpod_ws_manager_mk2_workspace_phase_total{phase="Running", type="ImageBuild", cluster!~"ephemeral.*"}[30d])
31
) > 2.5
32
- alert: GitpodImageBuilderCrashlooping
33
labels:
34
severity: critical
35
dedicated: included
36
annotations:
37
runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/GitpodWorkspaceDeploymentCrashlooping.md
38
summary: image-builder-mk3 is crash looping in cluster {{ $labels.cluster }}
39
description: Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) is restarting {{ printf "%.2f" $value }} times / 3 minutes.
40
expr: |
41
increase(kube_pod_container_status_restarts_total{container="image-builder-mk3", cluster!~"ephemeral.*"}[1m]) > 3
42
for: 3m
43
- alert: GitpodImageBuilderReplicasMismatch
44
labels:
45
severity: critical
46
dedicated: included
47
annotations:
48
runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/GitpodWorkspaceDeploymentReplicaMismatch.md
49
summary: Desired number of replicas for image-builder-mk3 are not available in cluster {{ $labels.cluster }}
50
description: 'Desired number of replicas for image-builder-mk3 are not available in cluster {{ $labels.cluster }}: {{ printf "%.2f" $value }} are missing'
51
expr: |
52
kube_deployment_spec_replicas{deployment="image-builder-mk3", cluster!~"ephemeral.*"} != kube_deployment_status_replicas_available{deployment="image-builder-mk3", cluster!~"ephemeral.*"}
53
for: 3m
54
- alert: GitpodImageBuilderMk3ReplicaUnavailable
55
labels:
56
# TODO(gpl): warning for now, to set it up and fine-tune it
57
severity: warning
58
annotations:
59
runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/GitpodWorkspaceDeploymentReplicaMismatch.md
60
summary: image-builder-mk3 replicas are unavailable in cluster {{ $labels.cluster }}
61
description: 'image-builder-mk3 pods are unavailable in cluster {{ $labels.cluster }}: {{ printf "%.2f" $value }}'
62
expr: |
63
kube_deployment_status_replicas_unavailable{deployment="image-builder-mk3", cluster!~"ephemeral.*"} > 0
64
for: 10m
65
- alert: GitpodImageBuilderMk3InternalErrors
66
labels:
67
severity: warning
68
dedicated: included
69
team: engine
70
annotations:
71
# runbook is 404 for now
72
runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/GitpodImageBuilderMk3InternalErrors.md
73
summary: image-builder-mk3 is returning unexpected internal errors
74
description: 'Check the logs for image-builder-mk3 to inspect the high rate: {{ printf "%.2f" $value }}'
75
expr: |
76
sum by() (rate(grpc_server_handled_total{service="image-builder-mk3", grpc_code=~"Internal", grpc_method="Build"}[1h])) > 0.001
77
for: 1h
78
79