Skip to content

Commit 3ce0e37

Browse files
Merge pull request #2598 from jan--f/pull-OCPBUGS-33691-fix
OCPBUGS-33691: mixin: longer rate interval for Alertmanager[Cluster]FailedToSendAlerts
2 parents d404ba3 + 2d6fb3f commit 3ce0e37

File tree

2 files changed

+26
-4
lines changed

2 files changed

+26
-4
lines changed

assets/alertmanager/prometheus-rule.yaml

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -48,9 +48,9 @@ spec:
4848
summary: An Alertmanager instance failed to send notifications.
4949
expr: |
5050
(
51-
rate(alertmanager_notifications_failed_total{job=~"alertmanager-main|alertmanager-user-workload"}[5m])
51+
rate(alertmanager_notifications_failed_total{job=~"alertmanager-main|alertmanager-user-workload"}[15m])
5252
/
53-
ignoring (reason) group_left rate(alertmanager_notifications_total{job=~"alertmanager-main|alertmanager-user-workload"}[5m])
53+
ignoring (reason) group_left rate(alertmanager_notifications_total{job=~"alertmanager-main|alertmanager-user-workload"}[15m])
5454
)
5555
> 0.01
5656
for: 5m
@@ -63,9 +63,9 @@ spec:
6363
summary: All Alertmanager instances in a cluster failed to send notifications to a critical integration.
6464
expr: |
6565
min by (namespace,service, integration) (
66-
rate(alertmanager_notifications_failed_total{job=~"alertmanager-main|alertmanager-user-workload", integration=~`.*`}[5m])
66+
rate(alertmanager_notifications_failed_total{job=~"alertmanager-main|alertmanager-user-workload", integration=~`.*`}[15m])
6767
/
68-
ignoring (reason) group_left rate(alertmanager_notifications_total{job=~"alertmanager-main|alertmanager-user-workload", integration=~`.*`}[5m])
68+
ignoring (reason) group_left rate(alertmanager_notifications_total{job=~"alertmanager-main|alertmanager-user-workload", integration=~`.*`}[15m])
6969
)
7070
> 0.01
7171
for: 5m

jsonnet/utils/sanitize-rules.libsonnet

Lines changed: 22 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -167,6 +167,28 @@ local patchedRules = [
167167
labels: {
168168
severity: 'warning',
169169
},
170+
expr: |||
171+
min by (namespace,service, integration) (
172+
rate(alertmanager_notifications_failed_total{job=~"alertmanager-main|alertmanager-user-workload", integration=~`.*`}[15m])
173+
/
174+
ignoring (reason) group_left rate(alertmanager_notifications_total{job=~"alertmanager-main|alertmanager-user-workload", integration=~`.*`}[15m])
175+
)
176+
> 0.01
177+
|||,
178+
},
179+
{
180+
alert: 'AlertmanagerFailedToSendAlerts',
181+
labels: {
182+
severity: 'warning',
183+
},
184+
expr: |||
185+
(
186+
rate(alertmanager_notifications_failed_total{job=~"alertmanager-main|alertmanager-user-workload"}[15m])
187+
/
188+
ignoring (reason) group_left rate(alertmanager_notifications_total{job=~"alertmanager-main|alertmanager-user-workload"}[15m])
189+
)
190+
> 0.01
191+
|||,
170192
},
171193
{
172194
alert: 'AlertmanagerConfigInconsistent',

0 commit comments

Comments
 (0)