File tree Expand file tree Collapse file tree 2 files changed +26
-4
lines changed Expand file tree Collapse file tree 2 files changed +26
-4
lines changed Original file line number Diff line number Diff line change 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
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
Original file line number Diff line number Diff 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' ,
You can’t perform that action at this time.
0 commit comments