Skip to content

Commit ee2edf7

Browse files
committed
feat: set up alerts for a smooth Prom3 upgrade
1 parent 0264620 commit ee2edf7

File tree

2 files changed

+42
-0
lines changed

2 files changed

+42
-0
lines changed

assets/cluster-monitoring-operator/prometheus-rule.yaml

Lines changed: 16 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -30,6 +30,22 @@ spec:
3030
for: 15m
3131
labels:
3232
severity: warning
33+
- alert: TargetInvalidContentType
34+
annotations:
35+
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} could not determine a valid content type for some scrape targets.
36+
summary: A valid content type could not be determined for some scrape targets.
37+
expr: increase(prometheus_target_scrape_pool_invalid_content_type_total{job=~"prometheus-k8s|prometheus-user-workload"}[5m]) > 0
38+
for: 15m
39+
labels:
40+
severity: critical
41+
- alert: NarrowLeQuantileSelectors
42+
annotations:
43+
description: XXX.
44+
summary: XXX.
45+
expr: increase(prometheus_target_scrape_pool_invalid_content_type_total{job=~"prometheus-k8s|prometheus-user-workload"}[5m]) > 0
46+
for: 15m
47+
labels:
48+
severity: critical
3349
- name: openshift-kubernetes.rules
3450
rules:
3551
- expr: sum(rate(container_cpu_usage_seconds_total{container="",pod!=""}[5m])) BY (pod, namespace)

jsonnet/rules.libsonnet

Lines changed: 26 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -27,6 +27,32 @@ function(params) {
2727
severity: 'warning',
2828
},
2929
},
30+
{
31+
expr: 'increase(prometheus_target_scrape_pool_invalid_content_type_total{job=~"prometheus-k8s|prometheus-user-workload"}[5m]) > 0',
32+
alert: 'TargetInvalidContentType',
33+
'for': '15m',
34+
annotations: {
35+
description: 'Prometheus {{$labels.namespace}}/{{$labels.pod}} could not determine a valid content type for some scrape targets.',
36+
summary: 'A valid content type could not be determined for some scrape targets.',
37+
},
38+
labels: {
39+
# severity: 'warning', (before the cut, to take advantage of critical alerts treatment)
40+
severity: 'critical',
41+
},
42+
},
43+
{
44+
expr: 'increase(prometheus_target_scrape_pool_invalid_content_type_total{job=~"prometheus-k8s|prometheus-user-workload"}[5m]) > 0',
45+
alert: 'NarrowLeQuantileSelectors',
46+
'for': '15m',
47+
annotations: {
48+
description: 'XXX.',
49+
summary: 'XXX.',
50+
},
51+
labels: {
52+
# severity: 'warning', (before the cut, to take advantage of critical alerts treatment)
53+
severity: 'critical',
54+
},
55+
},
3056
],
3157
},
3258
{

0 commit comments

Comments
 (0)