gitadmin/devops-infra-helm-charts-gcp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

added repo

Browse Source
This commit is contained in:
Your Name
2026-08-26 03:39:42 +05:30
parent 45c25a95af
commit b8575bb8b9
6889 changed files with 1217125 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
helm-templates/victoria-metrics-alerts-config/configmap/infra/devops/contour/aws-contour-tg-alerts.yaml
+32
View File
@@ -0,0 +1,32 @@
groups:
- name: EKS-Contour-TG-Alerts
rules:
- alert: Unhealthy-Host-in-EKSContourTG
expr: aws_applicationelb_un_healthy_host_count_maximum{job="aws_applicationelb", target_group =~ ".*cntr.*|.*contour.*"} offset 10m >= 1
for: 5m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
resource: AWS Target Group
annotations:
summary: "Unhealthy Host in EKS Contour TG {{ $labels.target_group }} is greater than 1"
description: "Unhealthy Host in EKS Contour TG {{ $labels.target_group }} is :{{ $value }}\n LABELS = {{ $labels }}"
- alert: Healthy-Host-in-EKSContourTG-is-VeryLess
expr: aws_applicationelb_healthy_host_count_average{job="aws_applicationelb", target_group =~ ".*cntr.*|.*contour.*"} offset 10m < 3
for: 1m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
resource: AWS Target Group
annotations:
summary: "Healthy Host in EKS Contour TG {{ $labels.target_group }} is less than 3"
description: "Healthy Host in EKS Contour TG {{ $labels.target_group }} is less than 3, Value - {{ $value }}\n LABELS = {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/infra/devops/contour/eks-central-contour-pod-alerts.yaml
+45
View File
@@ -0,0 +1,45 @@
groups:
- name: EKS-central-Contour-Pod-Alerts
rules:
- alert: central-Contour-Pod-CPU-Crossed-Threshold
expr: 100 * sum by (pod) (rate(container_cpu_usage_seconds_total{image!="", pod=~".*contour.*", pod!~".*default-backend.*"}[1m])) / sum by (pod) (kube_pod_container_resource_limits{resource="cpu", job=~"kube-state-metrics-.*"}) * on(pod) group_left(label_bu, label_team, label_service, label_env, label_priority, namespace, cluster) kube_pod_labels{kubernetes_namespace!="opencost", label_env=~"prod|prd", cluster=~".*central.*"} > 85
for: 5m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
annotations:
summary: High CPU Utilisation for EKS Pod - {{ $labels.pod }}
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been utilising CPU over {{ $value }}% in the last 1 min.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: central-Contour-Pod-Not-in-Ready-State
expr: kube_pod_status_phase{phase!="Running", phase!="Succeeded", phase!="Pending", job=~"kube-state-metrics-p-.*", pod=~".*contour.*", pod!~".*default-backend.*"} * on(pod) group_left(label_bu, label_team, label_service, label_env, label_priority, namespace, cluster) kube_pod_labels{job=~"kube-state-metrics-.*", label_env=~"prod|prd", cluster=~".*central.*"} == 1
for: 3m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
annotations:
summary: EKS Pod - {{ $labels.pod }} not in Ready State
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} is in {{ $labels.reason }} state for last 2 mins.\n STATE = NotReady\n LABELS = {{ $labels }}"
- alert: central-Contour-Pod-Restarted-Multiple-Times
expr: sum by (pod,namespace) (increase(kube_pod_container_status_restarts_total{job=~"kube-state-metrics-.*", pod=~".*contour.*", pod!~".*default-backend.*"}[1m])) * on(pod) group_left(label_bu, label_team, label_service, label_env, label_priority, namespace, cluster) kube_pod_labels{job=~"kube-state-metrics-.*", label_env=~"prod|prd", cluster=~".*central.*"} > 1
for: 1m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
annotations:
summary: EKS Pod - {{ $labels.pod }} Restarted Multiple Times
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} has Restarted for more than {{ $value }} times in last 2 mins.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/infra/devops/contour/eks-dataplatform-contour-pod-alerts.yaml
+45
View File
@@ -0,0 +1,45 @@
groups:
- name: EKS-dataplatform-Contour-Pod-Alerts
rules:
- alert: dataplatform-Contour-Pod-CPU-Crossed-Threshold
expr: 100 * sum by (pod) (rate(container_cpu_usage_seconds_total{image!="", pod=~".*contour.*", pod!~".*default-backend.*"}[1m])) / sum by (pod) (kube_pod_container_resource_limits{resource="cpu", job=~"kube-state-metrics-.*"}) * on(pod) group_left(label_bu, label_team, label_service, label_env, label_priority, namespace, cluster) kube_pod_labels{kubernetes_namespace!="opencost", label_env=~"prod|prd", cluster=~".*dataplatform.*"} > 85
for: 5m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
annotations:
summary: High CPU Utilisation for EKS Pod - {{ $labels.pod }}
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been utilising CPU over {{ $value }}% in the last 1 min.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: dataplatform-Contour-Pod-Not-in-Ready-State
expr: kube_pod_status_phase{phase!="Running", phase!="Succeeded", phase!="Pending", job=~"kube-state-metrics-p-.*", pod=~".*contour.*", pod!~".*default-backend.*"} * on(pod) group_left(label_bu, label_team, label_service, label_env, label_priority, namespace, cluster) kube_pod_labels{job=~"kube-state-metrics-.*", label_env=~"prod|prd", cluster=~".*dataplatform.*"} == 1
for: 3m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
annotations:
summary: EKS Pod - {{ $labels.pod }} not in Ready State
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} is in {{ $labels.reason }} state for last 2 mins.\n STATE = NotReady\n LABELS = {{ $labels }}"
- alert: dataplatform-Contour-Pod-Restarted-Multiple-Times
expr: sum by (pod,namespace) (increase(kube_pod_container_status_restarts_total{job=~"kube-state-metrics-.*", pod=~".*contour.*", pod!~".*default-backend.*"}[1m])) * on(pod) group_left(label_bu, label_team, label_service, label_env, label_priority, namespace, cluster) kube_pod_labels{job=~"kube-state-metrics-.*", label_env=~"prod|prd", cluster=~".*dataplatform.*"} > 1
for: 1m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
annotations:
summary: EKS Pod - {{ $labels.pod }} Restarted Multiple Times
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} has Restarted for more than {{ $value }} times in last 2 mins.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/infra/devops/contour/eks-datascience-contour-pod-alerts.yaml
+45
View File
@@ -0,0 +1,45 @@
groups:
- name: EKS-datascience-Contour-Pod-Alerts
rules:
- alert: datascience-Contour-Pod-CPU-Crossed-Threshold
expr: 100 * sum by (pod) (rate(container_cpu_usage_seconds_total{image!="", pod=~".*contour.*", pod!~".*default-backend.*"}[1m])) / sum by (pod) (kube_pod_container_resource_limits{resource="cpu", job=~"kube-state-metrics-.*"}) * on(pod) group_left(label_bu, label_team, label_service, label_env, label_priority, namespace, cluster) kube_pod_labels{kubernetes_namespace!="opencost", label_env=~"prod|prd", cluster=~".*datascience.*"} > 85
for: 5m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
annotations:
summary: High CPU Utilisation for EKS Pod - {{ $labels.pod }}
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been utilising CPU over {{ $value }}% in the last 1 min.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: datascience-Contour-Pod-Not-in-Ready-State
expr: kube_pod_status_phase{phase!="Running", phase!="Succeeded", phase!="Pending", job=~"kube-state-metrics-p-.*", pod=~".*contour.*", pod!~".*default-backend.*"} * on(pod) group_left(label_bu, label_team, label_service, label_env, label_priority, namespace, cluster) kube_pod_labels{job=~"kube-state-metrics-.*", label_env=~"prod|prd", cluster=~".*datascience.*"} == 1
for: 3m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
annotations:
summary: EKS Pod - {{ $labels.pod }} not in Ready State
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} is in {{ $labels.reason }} state for last 2 mins.\n STATE = NotReady\n LABELS = {{ $labels }}"
- alert: datascience-Contour-Pod-Restarted-Multiple-Times
expr: sum by (pod,namespace) (increase(kube_pod_container_status_restarts_total{job=~"kube-state-metrics-.*", pod=~".*contour.*", pod!~".*default-backend.*"}[1m])) * on(pod) group_left(label_bu, label_team, label_service, label_env, label_priority, namespace, cluster) kube_pod_labels{job=~"kube-state-metrics-.*", label_env=~"prod|prd", cluster=~".*datascience.*"} > 1
for: 1m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
annotations:
summary: EKS Pod - {{ $labels.pod }} Restarted Multiple Times
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} has Restarted for more than {{ $value }} times in last 2 mins.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/infra/devops/contour/eks-demand-contour-pod-alerts.yaml
+45
View File
@@ -0,0 +1,45 @@
groups:
- name: EKS-demand-Contour-Pod-Alerts
rules:
- alert: demand-Contour-Pod-CPU-Crossed-Threshold
expr: 100 * sum by (pod) (rate(container_cpu_usage_seconds_total{image!="", pod=~".*contour.*", pod!~".*default-backend.*"}[1m])) / sum by (pod) (kube_pod_container_resource_limits{resource="cpu", job=~"kube-state-metrics-.*"}) * on(pod) group_left(label_bu, label_team, label_service, label_env, label_priority, namespace, cluster) kube_pod_labels{kubernetes_namespace!="opencost", label_env=~"prod|prd", cluster=~".*demand.*"} > 85
for: 5m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
annotations:
summary: High CPU Utilisation for EKS Pod - {{ $labels.pod }}
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been utilising CPU over {{ $value }}% in the last 1 min.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: demand-Contour-Pod-Not-in-Ready-State
expr: kube_pod_status_phase{phase!="Running", phase!="Succeeded", phase!="Pending", job=~"kube-state-metrics-p-.*", pod=~".*contour.*", pod!~".*default-backend.*"} * on(pod) group_left(label_bu, label_team, label_service, label_env, label_priority, namespace, cluster) kube_pod_labels{job=~"kube-state-metrics-.*", label_env=~"prod|prd", cluster=~".*demand.*"} == 1
for: 3m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
annotations:
summary: EKS Pod - {{ $labels.pod }} not in Ready State
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} is in {{ $labels.reason }} state for last 2 mins.\n STATE = NotReady\n LABELS = {{ $labels }}"
- alert: demand-Contour-Pod-Restarted-Multiple-Times
expr: sum by (pod,namespace) (increase(kube_pod_container_status_restarts_total{job=~"kube-state-metrics-.*", pod=~".*contour.*", pod!~".*default-backend.*"}[1m])) * on(pod) group_left(label_bu, label_team, label_service, label_env, label_priority, namespace, cluster) kube_pod_labels{job=~"kube-state-metrics-.*", label_env=~"prod|prd", cluster=~".*demand.*"} > 1
for: 1m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
annotations:
summary: EKS Pod - {{ $labels.pod }} Restarted Multiple Times
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} has Restarted for more than {{ $value }} times in last 2 mins.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/infra/devops/contour/eks-dp-starburst-contour-pod-alerts.yaml
+45
View File
@@ -0,0 +1,45 @@
groups:
- name: EKS-dp-starburst-Contour-Pod-Alerts
rules:
- alert: dp-starburst-Contour-Pod-CPU-Crossed-Threshold
expr: 100 * sum by (pod) (rate(container_cpu_usage_seconds_total{image!="", pod=~".*contour.*", pod!~".*default-backend.*"}[1m])) / sum by (pod) (kube_pod_container_resource_limits{resource="cpu", job=~"kube-state-metrics-.*"}) * on(pod) group_left(label_bu, label_team, label_service, label_env, label_priority, namespace, cluster) kube_pod_labels{kubernetes_namespace!="opencost", label_env=~"prod|prd", cluster=~".*dp-starburst.*"} > 85
for: 5m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
annotations:
summary: High CPU Utilisation for EKS Pod - {{ $labels.pod }}
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been utilising CPU over {{ $value }}% in the last 1 min.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: dp-starburst-Contour-Pod-Not-in-Ready-State
expr: kube_pod_status_phase{phase!="Running", phase!="Succeeded", phase!="Pending", job=~"kube-state-metrics-p-.*", pod=~".*contour.*", pod!~".*default-backend.*"} * on(pod) group_left(label_bu, label_team, label_service, label_env, label_priority, namespace, cluster) kube_pod_labels{job=~"kube-state-metrics-.*", label_env=~"prod|prd", cluster=~".*dp-starburst.*"} == 1
for: 3m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
annotations:
summary: EKS Pod - {{ $labels.pod }} not in Ready State
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} is in {{ $labels.reason }} state for last 2 mins.\n STATE = NotReady\n LABELS = {{ $labels }}"
- alert: dp-starburst-Contour-Pod-Restarted-Multiple-Times
expr: sum by (pod,namespace) (increase(kube_pod_container_status_restarts_total{job=~"kube-state-metrics-.*", pod=~".*contour.*", pod!~".*default-backend.*"}[1m])) * on(pod) group_left(label_bu, label_team, label_service, label_env, label_priority, namespace, cluster) kube_pod_labels{job=~"kube-state-metrics-.*", label_env=~"prod|prd", cluster=~".*dp-starburst.*"} > 1
for: 1m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
annotations:
summary: EKS Pod - {{ $labels.pod }} Restarted Multiple Times
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} has Restarted for more than {{ $value }} times in last 2 mins.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/infra/devops/contour/eks-prod-ops-contour-pod-alerts.yaml
+45
View File
@@ -0,0 +1,45 @@
groups:
- name: EKS-prod-ops-Contour-Pod-Alerts
rules:
- alert: prod-ops-Contour-Pod-CPU-Crossed-Threshold
expr: 100 * sum by (pod) (rate(container_cpu_usage_seconds_total{image!="", pod=~".*contour.*", pod!~".*default-backend.*"}[1m])) / sum by (pod) (kube_pod_container_resource_limits{resource="cpu", job=~"kube-state-metrics-.*"}) * on(pod) group_left(label_bu, label_team, label_service, label_env, label_priority, namespace, cluster) kube_pod_labels{kubernetes_namespace!="opencost", label_env=~"prod|prd", cluster=~".*prod-ops.*"} > 85
for: 5m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
annotations:
summary: High CPU Utilisation for EKS Pod - {{ $labels.pod }}
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been utilising CPU over {{ $value }}% in the last 1 min.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: prod-ops-Contour-Pod-Not-in-Ready-State
expr: kube_pod_status_phase{phase!="Running", phase!="Succeeded", phase!="Pending", job=~"kube-state-metrics-p-.*", pod=~".*contour.*", pod!~".*default-backend.*"} * on(pod) group_left(label_bu, label_team, label_service, label_env, label_priority, namespace, cluster) kube_pod_labels{job=~"kube-state-metrics-.*", label_env=~"prod|prd", cluster=~".*prod-ops.*"} == 1
for: 3m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
annotations:
summary: EKS Pod - {{ $labels.pod }} not in Ready State
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} is in {{ $labels.reason }} state for last 2 mins.\n STATE = NotReady\n LABELS = {{ $labels }}"
- alert: prod-ops-Contour-Pod-Restarted-Multiple-Times
expr: sum by (pod,namespace) (increase(kube_pod_container_status_restarts_total{job=~"kube-state-metrics-.*", pod=~".*contour.*", pod!~".*default-backend.*"}[1m])) * on(pod) group_left(label_bu, label_team, label_service, label_env, label_priority, namespace, cluster) kube_pod_labels{job=~"kube-state-metrics-.*", label_env=~"prod|prd", cluster=~".*prod-ops.*"} > 1
for: 1m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
annotations:
summary: EKS Pod - {{ $labels.pod }} Restarted Multiple Times
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} has Restarted for more than {{ $value }} times in last 2 mins.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/infra/devops/contour/eks-supply-contour-pod-alerts.yaml
+45
View File
@@ -0,0 +1,45 @@
groups:
- name: EKS-supply-Contour-Pod-Alerts
rules:
- alert: supply-Contour-Pod-CPU-Crossed-Threshold
expr: 100 * sum by (pod) (rate(container_cpu_usage_seconds_total{image!="", pod=~".*contour.*", pod!~".*default-backend.*"}[1m])) / sum by (pod) (kube_pod_container_resource_limits{resource="cpu", job=~"kube-state-metrics-.*"}) * on(pod) group_left(label_bu, label_team, label_service, label_env, label_priority, namespace, cluster) kube_pod_labels{kubernetes_namespace!="opencost", label_env=~"prod|prd", cluster=~".*supply.*"} > 85
for: 5m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
annotations:
summary: High CPU Utilisation for EKS Pod - {{ $labels.pod }}
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been utilising CPU over {{ $value }}% in the last 1 min.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: supply-Contour-Pod-Not-in-Ready-State
expr: kube_pod_status_phase{phase!="Running", phase!="Succeeded", phase!="Pending", job=~"kube-state-metrics-p-.*", pod=~".*contour.*", pod!~".*default-backend.*"} * on(pod) group_left(label_bu, label_team, label_service, label_env, label_priority, namespace, cluster) kube_pod_labels{job=~"kube-state-metrics-.*", label_env=~"prod|prd", cluster=~".*supply.*"} == 1
for: 3m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
annotations:
summary: EKS Pod - {{ $labels.pod }} not in Ready State
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} is in {{ $labels.reason }} state for last 2 mins.\n STATE = NotReady\n LABELS = {{ $labels }}"
- alert: supply-Contour-Pod-Restarted-Multiple-Times
expr: sum by (pod,namespace) (increase(kube_pod_container_status_restarts_total{job=~"kube-state-metrics-.*", pod=~".*contour.*", pod!~".*default-backend.*"}[1m])) * on(pod) group_left(label_bu, label_team, label_service, label_env, label_priority, namespace, cluster) kube_pod_labels{job=~"kube-state-metrics-.*", label_env=~"prod|prd", cluster=~".*supply.*"} > 1
for: 1m
labels:
severity: critical
bu: infra
team: devops
service: eks-contour
env: prd
priority: p0
annotations:
summary: EKS Pod - {{ $labels.pod }} Restarted Multiple Times
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} has Restarted for more than {{ $value }} times in last 2 mins.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"