@leverege/build-tools 2.54.1 → 2.55.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@leverege/build-tools",
-  "version": "2.54.1",
+  "version": "2.55.0",
   "description": "A collection of build / support tools for Leverege developers",
   "main": "index.js",
   "repository": {
@@ -63,13 +63,13 @@
     "command-line-usage": "^7.0.3",
     "deepmerge": "^4.3.1",
     "enquirer": "^2.4.1",
-    "execa": "^9.4.0",
+    "execa": "^9.4.1",
     "glob": "^11.0.0",
     "handlebars": "^4.7.8",
     "inquirer": "^12.0.0",
     "js-yaml": "^4.1.0",
     "ms": "^2.1.3",
-    "npm-registry-fetch": "^18.0.1",
+    "npm-registry-fetch": "^18.0.2",
     "package-up": "^5.0.0",
     "parse-gitignore": "^2.0.0",
     "read-pkg": "^9.0.1",
@@ -82,4 +82,4 @@
     "@leverege/eslint-config-leverege": "^4.2.0",
     "npm": "^10.9.0"
   }
-}
+}

package/registry-compass.yaml

@@ -0,0 +1,20 @@
+registry:
+  - root: us-docker.pkg.dev
+  - repositories:
+    - name: stack
+      charts:
+        - api-server
+        - authz-server
+        - emailer
+        - message-processor
+    - name: leverege
+      charts:
+        - pubsub-pulse
+        - pusher
+        - overdose
+    - name: cox-health
+      charts:
+        - actions-server
+        - analytics-server
+        - centrak-healthz
+        - centrak-ingestor

package/src/chart-compass.mjs

@@ -0,0 +1,96 @@
+#!/usr/bin/env node
+/*
+ * chart-to-registry will...
+ */
+import fs from 'node:fs'
+
+import chalk from 'chalk'
+import commandLineArgs from 'command-line-args'
+import commandLineUsage from 'command-line-usage'
+import { lt as semverLt } from 'semver'
+import YAML from 'js-yaml'
+
+import {
+  condir,
+  debug,
+  errorExit,
+  log,
+  warning,
+  getGitRootDirectory,
+  parsePackageJson,
+  parseHelmChart,
+  shellCmd } from './Utils.mjs'
+
+const commandLineOptions = [ // Use commandLineOptions to tie into the Usage statements
+  /* eslint-disable max-len */
+  {
+    name : 'location',
+    type : String,
+    description : '{green the location of the artifact registry the chart will be pushed to (default us-docker.pkg.dev)}',
+  },
+  {
+    name : 'project',
+    type : String,
+    description : '{green the name of the google project containing the npmrc and slack config secrets (default leverege-registry)}',
+  },
+  {
+    name : 'repository',
+    type : String,
+    description : '{green the target repository to receive the pushed chart}',
+  },
+  {
+    name : 'dry-run',
+    type : Boolean,
+    description : '{yellow perform everything except the actual chart push}',
+  },
+  {
+    name : 'help',
+    type : Boolean,
+    description : '{green display this help screen}',
+  },
+  /* eslint-enable max-len */
+]
+
+const sections = [
+  {
+    header : 'Leverege Helm Chart Compass (for helmup)',
+    content : `{green This tool helps helmup navigate the helm charts stored in the
+artifact-registries.}`
+  },
+  { header : 'Options',
+    optionList : commandLineOptions,
+  },
+]
+
+const args = commandLineArgs( commandLineOptions, { camelCase : true, partial : true } )
+const usage = commandLineUsage( sections )
+
+if ( args.help ) {
+  log( usage )
+  process.exit( 0 )
+}
+
+/* eslint-disable no-underscore-dangle */
+if ( args._unknown ) {
+  log( usage )
+  log( `\nUnrecognized argument [${chalk.bold.red( args._unknown )}]\n` )
+  process.exit( 1 )
+}
+/* eslint-enable no-underscore-dangle */
+
+const minNodejsVersion = '18.0.0'
+if ( semverLt( process.version, minNodejsVersion ) ) {
+  errorExit( `\n***ERROR: must be running at least node ${minNodejsVersion}\n` )
+}
+
+// First of all, fail if we are not in a git repository
+let gitRoot
+try {
+  gitRoot = await getGitRootDirectory()
+} catch ( error ) {
+  errorExit( chalk.red.bold( error ), { errorCode : 5 } )
+}
+
+const chartCompass = YAML.load( fs.readFileSync( './registry-compass.yaml', 'utf8' ) )
+
+condir( { chartCompass }, '<==Navigation' )

package/src/helm-charts/elasticsearch8/helmup.plugin

@@ -15,24 +15,5 @@ helm upgrade --install elasticsearch8 $OCI_CHART \
              --values $LOCAL_ES_VALUES \
              --version $ELASTIC_CHART_VERSION $HELM_WHAT
 
-## Installing ES8 exporter
-addHelmRepo prometheus-community https://prometheus-community.github.io/helm-charts
-helm upgrade --install elasticsearch8-exporter prometheus-community/prometheus-elasticsearch-exporter \
-             --namespace monitoring --create-namespace \
-             --version 6 \
-             -f - <<ELASTIC8_EXPORTER_CHART_MOD
-fullnameOverride: elasticsearch8-exporter
-
-service:
-  annotations:
-    prometheus.io/port: "9108"
-    prometheus.io/scrape: "true"
-es:
-  uri: http://elasticsearch8.elastic.svc.cluster.local:9200
-
-resources:
-  requests:
-    cpu: 50m
-    memory: 32Mi
-ELASTIC8_EXPORTER_CHART_MOD
-removeHelmRepo prometheus-community
+## Installing ES8 exporter into monitoring namespace
+installElasticsearchExporter

package/src/helm-charts/prom-operator/apply-rules

@@ -0,0 +1,13 @@
+#!/bin/bash
+#
+# Load the standard helper functions
+. `build-tools --bashfun`
+
+RULES_DIR="prom-operator/rules"
+
+[ ! -d "$RULES_DIR" ] && errorExit "Missing rules directory [$RULES_DIR]"
+
+for ruleset in $RULES_DIR/*.yaml; do
+  printf "  Applying rules => `color g $ruleset`\n"
+  kubectl apply -n prometheus -f $ruleset
+done

package/src/helm-charts/prom-operator/elasticsearch-exporter.yaml

@@ -0,0 +1,20 @@
+# https://artifacthub.io/packages/helm/prometheus-community/prometheus-elasticsearch-exporter?modal=values
+#
+fullnameOverride: prometheus-stack-elasticsearch8-metrics
+
+service:
+  annotations:
+    prometheus.io/port: "9108"
+    prometheus.io/scrape: "true"
+es:
+  uri: http://elasticsearch8.elastic.svc.cluster.local:9200
+
+resources:
+  requests:
+    cpu: 50m
+    memory: 32Mi
+
+serviceMonitor:
+  enabled: true
+  namespace: prometheus
+  interval: 30s

package/src/helm-charts/prom-operator/gitignore

@@ -0,0 +1,2 @@
+prometheus-stack.yaml
+stackdriver-exporter.yaml

package/src/helm-charts/prom-operator/helmdn.plugin

@@ -0,0 +1,17 @@
+#!/bin/bash
+#
+# This will uninstall of the the operator components...
+helm uninstall -n prometheus elasticsearch8-exporter stackdriver-exporter prometheus-stack
+#
+# including all CRDs and configs
+kubectl delete crd \
+  alertmanagerconfigs.monitoring.coreos.com \
+  alertmanagers.monitoring.coreos.com \
+  podmonitors.monitoring.coreos.com \
+  probes.monitoring.coreos.com \
+  prometheusagents.monitoring.coreos.com \
+  prometheuses.monitoring.coreos.com \
+  prometheusrules.monitoring.coreos.com \
+  scrapeconfigs.monitoring.coreos.com \
+  servicemonitors.monitoring.coreos.com \
+  thanosrulers.monitoring.coreos.com

package/src/helm-charts/prom-operator/helmup.plugin

@@ -0,0 +1,27 @@
+#!/bin/bash
+#
+showInstalling "The Prometheus Operator and Components"
+addHelmRepo prometheus-community https://prometheus-community.github.io/helm-charts
+
+showInstalling "The Prometheus Operator (kube-prometheus-stack)"
+[ -z "$PROMETHEUS_STACK_CHART_VERSION" ] && PROMETHEUS_STACK_CHART_VERSION="65"
+helm upgrade --install prometheus-stack prometheus-community/kube-prometheus-stack \
+             --namespace prometheus --create-namespace \
+             --values  prom-operator/prometheus-stack.yaml \
+             --version $PROMETHEUS_STACK_CHART_VERSION $HELM_WHAT
+
+showInstalling "The Elasticsearch Exporter (prom-operator)"
+[ -z "$ELASTICSEARCH_EXPORTER_CHART_VERSION" ] && ELASTICSEARCH_EXPORTER_CHART_VERSION="4"
+helm upgrade --install elasticsearch8-exporter prometheus-community/prometheus-elasticsearch-exporter \
+             --namespace prometheus --create-namespace \
+             --values prom-operator/elasticsearch-exporter.yaml \
+             --version $ELASTICSEARCH_EXPORTER_CHART_VERSION $HELM_WHAT
+
+showInstalling "The Stackdriver Exporter (prom-operator)"
+[ -z "$STACKDRIVER_EXPORTER_CHART_VERSION" ] && STACKDRIVER_EXPORTER_CHART_VERSION="4"
+helm upgrade --install stackdriver-exporter prometheus-community/prometheus-stackdriver-exporter \
+             --namespace prometheus --create-namespace \
+             --values prom-operator/stackdriver-exporter.yaml \
+             --version $STACKDRIVER_EXPORTER_CHART_VERSION $HELM_WHAT
+
+removeHelmRepo prometheus-community

package/src/helm-charts/prom-operator/prometheus-stack.yaml.ovh

@@ -0,0 +1,139 @@
+enabled: true
+kubeControllerManager:
+  enabled: false
+nodeExporter:
+  enabled: false
+defaultRules:
+  create: true
+  rules:
+    alertmanager: false
+    etcd: false
+    configReloaders: false
+    general: true
+    k8s: true
+    kubeApiserver: true  # GPT Keep an eye on API server availability
+    kubeApiserverAvailability: false
+    kubeApiserverSlos: false
+    kubelet: false  # GPT Consider monitoring kubelet status, especially on scaled nodes
+    kubeProxy: false
+    kubePrometheusGeneral: false
+    kubePrometheusNodeRecording: false
+    kubernetesApps: false
+    kubernetesResources: false
+    kubernetesStorage: false
+    kubernetesSystem: false
+    kubeScheduler: false
+    kubeStateMetrics: true
+    network: false
+    node: false
+    nodeExporterAlerting: false
+    nodeExporterRecording: false
+    prometheus: false
+    prometheusOperator: false
+
+prometheus:
+  prometheusSpec:
+    podMonitorSelectorNilUsesHelmValues: false
+    ruleSelectorNilUsesHelmValues: false
+    serviceMonitorSelectorNilUsesHelmValues: false
+    probeSelectorNilUsesHelmValues: false
+  #nodeSelector:
+    #workload: monitor
+
+# default is using kube-dns which is usually sufficient for our needs but
+# can be switched over to CoreDNS if the need arises
+coreDns:
+  enabled: false
+
+# managed GKE does not provide direct access to the k8s scheduler so we
+# can safely disable this here - see the Stackdrive Monitoring for more
+kubeScheduler:
+  enabled: false
+
+grafana:
+  enabled: true
+  service:
+    port: 3000
+  # -- the grafana admin password
+  adminPassword: prom-operator
+  defaultDashboardsEnabled: false
+  sidecar:
+      dashboards:
+        enabled: true
+  extraObjects:
+    - apiVersion: traefik.io/v1alpha1
+      kind: IngressRoute
+      metadata:
+        name: grafana
+        namespace: prometheus
+      spec:
+        entryPoints:
+          - websecure
+        routes:
+          - match: Host(`OVH:<PROJECT_NAME>-monitoring.OVH:<HOST>.com`)
+            kind: Rule
+            services:
+            - name: prometheus-stack-grafana
+              port: 3000
+
+alertmanager:
+  enabled: true
+  affinity:
+    nodeAffinity:
+      requiredDuringSchedulingIgnoredDuringExecution:
+        nodeSelectorTerms:
+        - matchExpressions:
+          - key: target-env
+            operator: In
+            values:
+            - database
+  tolerations:
+  - key: "database"
+    operator: "Equal"
+    value: "true"
+    effect: "NoSchedule"
+
+  strategy:
+    type: Recreate
+
+  config:
+    receivers:
+      - name: slack
+        slack_configs:
+          - channel: "OVH:<SLACK_CHANNEL>"
+            api_url: "OVH:<SLACK_HOOK_URL>"
+            username: "OVH:<PROJECT_NAME>"
+            fallback: "OVH:<PROJECT_NAME> - {{ .CommonAnnotations.summary }}"
+            title: "{{ range .Alerts }}{{ .Annotations.summary }}\n{{ end }}"
+            title_link: "https://bitbucket.org/leverege/sre-playbook/src/master/"
+            send_resolved: true
+            text: |-
+              {{ range .Alerts }}
+                *Alert:* {{ .Annotations.summary }} - `{{ .Labels.severity }}`
+                *Description:* {{ .Annotations.description }}
+                *Dashboard:* {{ .Annotations.dashboard }}
+              {{ end }}
+      - name: opsgenie
+        opsgenie_configs:
+          - api_key: "OVH:<OPSGENIE_APIKEY>"
+            priority: "{{ .CommonLabels.priority }}"
+            tags: "{{ range .Alerts }}{{ .Labels.severity }},{{ end }}"
+            description: |-
+              {{ range .Alerts }}
+                *Alert:* {{ .Annotations.summary }} - `{{ .Labels.severity }}`
+                *Description:* {{ .Annotations.description }}
+                *Dashboard:* {{ .Annotations.dashboard }}
+              {{ end }}
+
+    route:
+      group_wait: 30s
+      group_interval: 5m
+      group_by:
+        - alertname
+        - cluster
+      receiver: slack
+      routes:
+      - match:
+          severity: page
+        receiver: opsgenie
+      repeat_interval: 6h

package/src/helm-charts/prom-operator/rules/elasticsearch-rules.yaml

@@ -0,0 +1,111 @@
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: elasticsearch-rules
+  namespace: prometheus
+
+spec:
+  groups:
+  - name: Elasticsearch Alerts
+    rules:
+    - alert: ElasticsearchHeapUsageTooHigh
+      expr: (elasticsearch_jvm_memory_used_bytes{area="heap"} / elasticsearch_jvm_memory_max_bytes{area="heap"}) * 100 > 90
+      for: 5m
+      labels:
+        severity: page
+        priority: P3
+      annotations:
+        summary: "Elasticsearch Heap Usage Too High (instance {{ $labels.instance }})"
+        description: "The heap usage is over 90% for 5m (currently at {{ $value }}% )"
+        dashboard: "OVH:<MONITORING>/elasticsearch"
+
+    - alert: ElasticsearchHeapUsageWarning
+      expr: (elasticsearch_jvm_memory_used_bytes{area="heap"} / elasticsearch_jvm_memory_max_bytes{area="heap"}) * 100 > 80
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: "Elasticsearch Heap Usage warning (instance {{ $labels.instance }})"
+        description: "The heap usage is over 80% for 5m (currently at {{ $value }}% )"
+        dashboard: "OVH:<MONITORING>/elasticsearch"
+
+    - alert: ElasticsearchDiskSpaceLow
+      expr: elasticsearch_filesystem_data_available_bytes / elasticsearch_filesystem_data_size_bytes * 100 < 20
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: "Elasticsearch disk space low (instance {{ $labels.instance }})"
+        description: "The disk usage is over 80% (currently at {{ $value }}% )"
+        dashboard: "OVH:<MONITORING>/elasticsearch"
+
+    - alert: ElasticsearchDiskOutOfSpace
+      expr: elasticsearch_filesystem_data_available_bytes / elasticsearch_filesystem_data_size_bytes * 100 < 10
+      for: 5m
+      labels:
+        severity: page
+        priority: P3
+      annotations:
+        summary: "Elasticsearch disk out of space (instance {{ $labels.instance }})"
+        description: "The disk usage is over 90% (currently at {{ $value }}% )"
+        dashboard: "OVH:<MONITORING>/elasticsearch"
+
+    - alert: ElasticsearchClusterRed
+      expr: elasticsearch_cluster_health_status{color="red"} == 1
+      for: 5m
+      labels:
+        severity: error
+      annotations:
+        summary: "Elasticsearch Cluster Red (instance {{ $labels.instance }})"
+        description: "Elastic Cluster is in an unhealthy state"
+        dashboard: "OVH:<MONITORING>/elasticsearch"
+
+    - alert: ElasticsearchClusterYellow
+      expr: elasticsearch_cluster_health_status{color="yellow"} == 1
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: "Elasticsearch Cluster Yellow (instance {{ $labels.instance }})"
+        description: "Elastic Cluster is in an unhealthy state"
+        dashboard: "OVH:<MONITORING>/elasticsearch"
+
+    - alert: ElasticsearchRelocationShards
+      expr: elasticsearch_cluster_health_relocating_shards > 0
+      for: 5m
+      labels:
+        severity: error
+      annotations:
+        summary: "Elasticsearch relocation shards (instance {{ $labels.instance }})"
+        description: "Number of relocation shards for 20 min is {{ $value }}"
+        dashboard: "OVH:<MONITORING>/elasticsearch"
+
+    - alert: ElasticsearchInitializingShards
+      expr: elasticsearch_cluster_health_initializing_shards > 0
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: "Elasticsearch initializing shards (instance {{ $labels.instance }})"
+        description: "Number of initializing shards for 10 min is {{ $value }}"
+        dashboard: "OVH:<MONITORING>/elasticsearch"
+
+    - alert: ElasticsearchUnassignedShards
+      expr: elasticsearch_cluster_health_unassigned_shards > 0
+      for: 5m
+      labels:
+        severity: error
+      annotations:
+        summary: "Elasticsearch unassigned shards (instance {{ $labels.instance }})"
+        description: "Number of unassigned shards for 2 min is {{ $value }}"
+        dashboard: "OVH:<MONITORING>/elasticsearch"
+
+    - alert: ElasticsearchPendingTasks
+      expr: elasticsearch_cluster_health_number_of_pending_tasks > 0
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: "Elasticsearch pending tasks (instance {{ $labels.instance }})"
+        description: "Number of pending tasks for 10 min is {{ $value }}. Cluster is working slowly."
+        dashboard: "OVH:<MONITORING>/elasticsearch"

package/src/helm-charts/prom-operator/rules/gcp-rules.yaml

@@ -0,0 +1,47 @@
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: gcp-rules
+  namespace: prometheus
+
+spec:
+  groups:
+  - name: GCP
+    rules:
+    - alert: StackdriverFailedScrape
+      expr: absent(stackdriver_pubsub_topic_pubsub_googleapis_com_topic_message_sizes_count) == 1
+      for: 10m 
+      labels:
+        severity: warning
+      annotations:
+        summary: "Stackdriver metrics unavailable"
+        description: "Prometheus failed to scrape Stackdriver metrics"
+        dashboard: "Use Stackdriver Monitoring on GCP UI"
+    - alert: HighFirebaseLoad
+      expr: stackdriver_firebase_namespace_firebasedatabase_googleapis_com_io_database_load > 0.9
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: "High Firebase load detected"
+        description: "Firebase load is above 90% (current value is: {{ $value | humanize }}%)"
+        dashboard: "OVH:<MONITORING>/firebase"   
+    - alert: PubSubUndeliveredMessages
+      expr: sum(stackdriver_pubsub_subscription_pubsub_googleapis_com_subscription_num_undelivered_messages) by (subscription_id) > 1000
+      for: 5m 
+      labels:
+        severity: page
+        priority: P3
+      annotations:
+        summary: "High Number of Undelivered Messages on PubSub"
+        description: "Undelivered message count on topic {{$labels.subscription_id}} is greater than 1000"
+        dashboard: "OVH:<MONITORING>/stackdriver"
+    - alert: PubSubOldUnackedMessages
+      expr: stackdriver_pubsub_subscription_pubsub_googleapis_com_subscription_oldest_unacked_message_age > 900
+      for: 5m 
+      labels:
+        severity: warning
+      annotations:
+        summary: "Old messages left unacked on PubSub"
+        description: "Messages on {{$labels.subscription_id}} has been unacked for more than 15m"
+        dashboard: "OVH:<MONITORING>/stackdriver"

package/src/helm-charts/prom-operator/rules/kubernetes-rules.yaml

@@ -0,0 +1,112 @@
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: kubernetes-rules
+  namespace: prometheus
+
+spec:
+  groups:
+  - name: Kubernetes
+    rules:
+    - alert: KubernetesNodeNotReady
+      expr: kube_node_status_condition{condition="Ready",status="true"} == 0
+      for: 5m
+      labels:
+        severity: page
+        priority: P3
+      annotations:
+        summary: "Kubernetes Node is not ready"
+        description: "Node {{ $labels.node }} is stuck in unready state for more than 5m"
+        dashboard: "Check GKE or EKS node status"
+
+    - alert: KubernetesMemoryPressure
+      expr: kube_node_status_condition{condition="MemoryPressure",status="true"} == 1
+      for: 5m
+      labels:
+        severity: error
+      annotations:
+        summary: "Kubernetes memory pressure"
+        description: "{{ $labels.node }} has a MemoryPressure condition"
+        dashboard: "Check GKE or EKS node status"
+
+    - alert: KubernetesDiskPressure
+      expr: kube_node_status_condition{condition="DiskPressure",status="true"} == 1
+      for: 5m
+      labels:
+        severity: error
+      annotations:
+        summary: "Kubernetes disk pressure"
+        description: "{{ $labels.node }} has DiskPressure condition"
+        dashboard: "Check GKE or EKS node status"
+
+    - alert: KubernetesOutOfDisk
+      expr: kube_node_status_condition{condition="OutOfDisk",status="true"} == 1
+      for: 5m
+      labels:
+        severity: error
+      annotations:
+        summary: "Kubernetes out of disk"
+        description: "{{ $labels.node }} has is out of disk space"
+        dashboard: "Check GKE or EKS node status"
+
+    - alert: KubernetesVolumeOutOfDiskSpace
+      expr: kubelet_volume_stats_available_bytes / kubelet_volume_stats_capacity_bytes * 100 < 10
+      for: 5m
+      labels:
+        severity: error
+        priority: P2
+      annotations:
+        summary: "Kubernetes PVC Free Space < 10%"
+        description: "PVC volume {{ $labels.persistentvolumeclaim }} is almost full - down to {{ $value | humanize }}% available"
+        dashboard: "OVH:<MONITORING>/k8s-pvc/pvc-usage?var-volume={{ $labels.persistentvolumeclaim }}"
+
+#   - alert: KubernetesVolumeFullInFourDays
+#     expr: predict_linear(kubelet_volume_stats_available_bytes[6h], 4 * 24 * 3600) < 0
+#     for: 5m
+#     labels:
+#       severity: error
+#     annotations:
+#       summary: "Kubernetes Volume full in four days "
+#       description: "{{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is expected to fill up within four days. Currently {{ $value | humanize }}% is available."
+#       dashboard: "OVH:<MONITORING>/pvc"
+
+    - alert: KubernetesPersistentvolumeError
+      expr: kube_persistentvolume_status_phase{phase=~"Failed|Pending",job="kube-state-metrics"} > 0
+      for: 5m
+      labels:
+        severity: error
+      annotations:
+        summary: "Kubernetes PersistentVolume error "
+        description: "PersistentVolumeClaim {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is stuck pending"
+        dashboard: "Check GKE or EKS PVC/storage status"
+
+    - alert: KubernetesHpaScaleCapability
+      expr: kube_hpa_status_desired_replicas >= kube_hpa_spec_max_replicas
+      for: 15m
+      labels:
+        severity: warning
+      annotations:
+        summary: "Kubernetes HPA scale capability"
+        description: "Kubernetes has scaled {{ $labels.hpa }} to max number of scaled pods."
+        dashboard: "OVH:<MONITORING>/k8-deployment"
+
+    - alert: KubernetesPodNotHealthy
+      expr: kube_pod_status_phase{phase=~"Pending|Unknown|Failed"} == 1
+      for: 20m
+      labels:
+        severity: error
+      annotations:
+        summary: "Kubernetes Pod not healthy"
+        description: "Pod {{ $labels.pod }} has been in a non-ready state for longer than 20 minutes."
+        dashboard: "Check the pod status using the Kubernetes UI"
+
+    - alert: KubernetesPodCrashLooping
+      expr: rate(kube_pod_container_status_restarts_total[15m]) * 60 * 5 > 5
+      for: 5m
+      labels:
+        severity: page
+        priority: P2
+      annotations:
+        summary: "Kubernetes pod crash looping"
+        description: "{{ $labels.pod }} is in a crash loop"
+        dashboard: "Check the pod status using the Kubernetes UI"