Merge pull request #1183 from navi-infra/INFRA-3710
INFRA-3710 | Abhishek | Ensure namespace is exported as labels in HighPodRestart alert
This commit is contained in:
2
kutegen
2
kutegen
Submodule kutegen updated: 96f9233da2...c89b4b3bb5
@@ -427,7 +427,7 @@
|
||||
"description": "Namespace: dev-internal, AppName: test-app-navi-service; Pod restarted multiple times",
|
||||
"runbook": "https:\/\/navihq.atlassian.net\/wiki\/spaces\/IN\/pages\/279937094\/Act+On+Pod+Alert"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"severity": "critical",
|
||||
"appName": "test-app-navi-service",
|
||||
|
||||
@@ -447,7 +447,7 @@
|
||||
"description": "Namespace: dev-internal, AppName: test-app-navi-service; Pod restarted multiple times",
|
||||
"runbook": "https:\/\/navihq.atlassian.net\/wiki\/spaces\/IN\/pages\/279937094\/Act+On+Pod+Alert"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"severity": "critical",
|
||||
"appName": "test-app-navi-service",
|
||||
|
||||
@@ -436,7 +436,7 @@
|
||||
"description": "Namespace: dev-internal, AppName: test-app-navi-service; Pod restarted multiple times",
|
||||
"runbook": "https:\/\/navihq.atlassian.net\/wiki\/spaces\/IN\/pages\/279937094\/Act+On+Pod+Alert"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"severity": "critical",
|
||||
"appName": "test-app-navi-service",
|
||||
|
||||
@@ -451,7 +451,7 @@
|
||||
"runbook": "https://navihq.atlassian.net/wiki/spaces/IN/pages/279937094/Act+On+Pod+Alert",
|
||||
"summary": "High Pod Restarts"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev\", pod=~\"test-cilium-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev\", pod=~\"test-cilium-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"alertTeam": "Infra",
|
||||
"appName": "test-cilium-navi-service",
|
||||
|
||||
@@ -336,7 +336,7 @@
|
||||
"runbook": "https://navihq.atlassian.net/wiki/spaces/IN/pages/279937094/Act+On+Pod+Alert",
|
||||
"summary": "High Pod Restarts"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"infrastructure\", pod=~\"test-commonapigateways-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"infrastructure\", pod=~\"test-commonapigateways-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"alertTeam": "Infra",
|
||||
"appName": "test-commonapigateways-navi-service",
|
||||
|
||||
@@ -482,7 +482,7 @@
|
||||
"description": "Namespace: dev-internal, AppName: test-app-navi-service; Pod restarted multiple times",
|
||||
"runbook": "https://navihq.atlassian.net/wiki/spaces/IN/pages/279937094/Act+On+Pod+Alert"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"severity": "critical",
|
||||
"appName": "test-app-navi-service",
|
||||
|
||||
@@ -322,7 +322,7 @@
|
||||
"description": "Namespace: dev-internal, AppName: test-app-navi-service; Pod restarted multiple times",
|
||||
"runbook": "https:\/\/navihq.atlassian.net\/wiki\/spaces\/IN\/pages\/279937094\/Act+On+Pod+Alert"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"severity": "critical",
|
||||
"appName": "test-app-navi-service",
|
||||
|
||||
@@ -497,7 +497,7 @@
|
||||
"description": "Namespace: dev-internal, AppName: test-app-navi-service; Pod restarted multiple times",
|
||||
"runbook": "https:\/\/navihq.atlassian.net\/wiki\/spaces\/IN\/pages\/279937094\/Act+On+Pod+Alert"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"severity": "critical",
|
||||
"appName": "test-app-navi-service",
|
||||
|
||||
@@ -448,7 +448,7 @@
|
||||
"summary": "High Pod Restarts",
|
||||
"description": "Namespace: dev-internal, AppName: test-app-navi-service; Pod restarted multiple times"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"severity": "critical",
|
||||
"appName": "test-app-navi-service",
|
||||
|
||||
@@ -445,7 +445,7 @@
|
||||
"description": "Namespace: dev-internal, AppName: test-app-navi-service; Pod restarted multiple times",
|
||||
"runbook": "https:\/\/navihq.atlassian.net\/wiki\/spaces\/IN\/pages\/279937094\/Act+On+Pod+Alert"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"severity": "critical",
|
||||
"appName": "test-app-navi-service",
|
||||
|
||||
@@ -340,7 +340,7 @@
|
||||
"description": "Namespace: dev-internal, AppName: test-app-navi-service; Pod restarted multiple times",
|
||||
"runbook": "https:\/\/navihq.atlassian.net\/wiki\/spaces\/IN\/pages\/279937094\/Act+On+Pod+Alert"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"severity": "critical",
|
||||
"appName": "test-app-navi-service",
|
||||
|
||||
@@ -445,7 +445,7 @@
|
||||
"description": "Namespace: dev-internal, AppName: test-app-navi-service; Pod restarted multiple times",
|
||||
"runbook": "https:\/\/navihq.atlassian.net\/wiki\/spaces\/IN\/pages\/279937094\/Act+On+Pod+Alert"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"severity": "critical",
|
||||
"appName": "test-app-navi-service",
|
||||
|
||||
@@ -429,7 +429,7 @@
|
||||
"description": "Namespace: dev-internal, AppName: test-app-navi-service; Pod restarted multiple times",
|
||||
"runbook": "https:\/\/navihq.atlassian.net\/wiki\/spaces\/IN\/pages\/279937094\/Act+On+Pod+Alert"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"severity": "critical",
|
||||
"appName": "test-app-navi-service",
|
||||
|
||||
@@ -346,7 +346,7 @@
|
||||
"runbook": "https://navihq.atlassian.net/wiki/spaces/IN/pages/279937094/Act+On+Pod+Alert",
|
||||
"summary": "High Pod Restarts"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"prod\", pod=~\"testapp-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"prod\", pod=~\"testapp-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"alertTeam": "Infra",
|
||||
"appName": "testapp-navi-service",
|
||||
|
||||
@@ -346,7 +346,7 @@
|
||||
"runbook": "https://navihq.atlassian.net/wiki/spaces/IN/pages/279937094/Act+On+Pod+Alert",
|
||||
"summary": "High Pod Restarts"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"prod\", pod=~\"testapp-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"prod\", pod=~\"testapp-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"alertTeam": "Infra",
|
||||
"appName": "testapp-navi-service",
|
||||
|
||||
@@ -468,7 +468,7 @@
|
||||
"runbook": "https://navihq.atlassian.net/wiki/spaces/IN/pages/279937094/Act+On+Pod+Alert",
|
||||
"summary": "High Pod Restarts"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev\", pod=~\"bluegreen-one-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev\", pod=~\"bluegreen-one-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"alertTeam": "Infra",
|
||||
"appName": "bluegreen-one-navi-service",
|
||||
|
||||
@@ -1043,7 +1043,7 @@
|
||||
"runbook": "https://navihq.atlassian.net/wiki/spaces/IN/pages/279937094/Act+On+Pod+Alert",
|
||||
"summary": "High Pod Restarts"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev\", pod=~\"scylla-test-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev\", pod=~\"scylla-test-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"alertTeam": "Infra",
|
||||
"appName": "scylla-test-navi-service",
|
||||
|
||||
@@ -393,7 +393,7 @@
|
||||
"description": "Namespace: dev-internal, AppName: test-app-navi-service; Pod restarted multiple times",
|
||||
"runbook": "https:\/\/navihq.atlassian.net\/wiki\/spaces\/IN\/pages\/279937094\/Act+On+Pod+Alert"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"severity": "critical",
|
||||
"appName": "test-app-navi-service",
|
||||
|
||||
@@ -393,7 +393,7 @@
|
||||
"description": "Namespace: dev-internal, AppName: test-app-navi-service; Pod restarted multiple times",
|
||||
"runbook": "https:\/\/navihq.atlassian.net\/wiki\/spaces\/IN\/pages\/279937094\/Act+On+Pod+Alert"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"severity": "critical",
|
||||
"appName": "test-app-navi-service",
|
||||
|
||||
@@ -384,7 +384,7 @@
|
||||
"runbook": "https://navihq.atlassian.net/wiki/spaces/IN/pages/279937094/Act+On+Pod+Alert",
|
||||
"summary": "High Pod Restarts"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"prod-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"prod-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"alertTeam": "Infra",
|
||||
"appName": "test-app-navi-service",
|
||||
|
||||
@@ -731,7 +731,7 @@
|
||||
"runbook": "https://navihq.atlassian.net/wiki/spaces/IN/pages/279937094/Act+On+Pod+Alert",
|
||||
"summary": "High Pod Restarts"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"perf\", pod=~\"test-perf-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"perf\", pod=~\"test-perf-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"alertTeam": "Infra",
|
||||
"appName": "test-perf-navi-service",
|
||||
|
||||
@@ -437,7 +437,7 @@
|
||||
"description": "Namespace: dev-internal, AppName: test-app-navi-service; Pod restarted multiple times",
|
||||
"runbook": "https:\/\/navihq.atlassian.net\/wiki\/spaces\/IN\/pages\/279937094\/Act+On+Pod+Alert"
|
||||
},
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod) > 3",
|
||||
"expr": "sum(increase(kube_pod_container_status_restarts_total{namespace=\"dev-internal\", pod=~\"test-app-navi-service.*\"}[30m])) by (reason, pod, namespace) > 3",
|
||||
"labels": {
|
||||
"severity": "critical",
|
||||
"appName": "test-app-navi-service",
|
||||
|
||||
Reference in New Issue
Block a user