@leverege/build-tools 2.55.0 → 2.55.2

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

@@ -1,8 +1,8 @@
 #!/bin/bash
 #
 # This will uninstall of the the operator components...
-helm uninstall -n prometheus elasticsearch8-exporter stackdriver-exporter prometheus-stack
-#
+helm uninstall -n prometheus prometheus-stack elasticsearch8-exporter stackdriver-exporter
+
 # including all CRDs and configs
 kubectl delete crd \
   alertmanagerconfigs.monitoring.coreos.com \

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

@@ -11,7 +11,7 @@ helm upgrade --install prometheus-stack prometheus-community/kube-prometheus-sta
              --version $PROMETHEUS_STACK_CHART_VERSION $HELM_WHAT
 
 showInstalling "The Elasticsearch Exporter (prom-operator)"
-[ -z "$ELASTICSEARCH_EXPORTER_CHART_VERSION" ] && ELASTICSEARCH_EXPORTER_CHART_VERSION="4"
+[ -z "$ELASTICSEARCH_EXPORTER_CHART_VERSION" ] && ELASTICSEARCH_EXPORTER_CHART_VERSION="6"
 helm upgrade --install elasticsearch8-exporter prometheus-community/prometheus-elasticsearch-exporter \
              --namespace prometheus --create-namespace \
              --values prom-operator/elasticsearch-exporter.yaml \

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

@@ -14,7 +14,7 @@ defaultRules:
     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
+    kubelet: true  # GPT Consider monitoring kubelet status, especially on scaled nodes
     kubeProxy: false
     kubePrometheusGeneral: false
     kubePrometheusNodeRecording: false
@@ -37,8 +37,6 @@ prometheus:
     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
@@ -55,7 +53,7 @@ grafana:
   service:
     port: 3000
   # -- the grafana admin password
-  adminPassword: prom-operator
+  adminPassword: leverege-monitoring
   defaultDashboardsEnabled: false
   sidecar:
       dashboards:

package/src/helm-charts/prom-operator/rules/test-alert.yaml

@@ -0,0 +1,18 @@
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: test-alert
+  namespace: prometheus  # Ensure this matches your Prometheus namespace
+spec:
+  groups:
+    - name: test.rules
+      rules:
+        - alert: TestAlert
+          expr: vector(1)  # This will always be true, triggering the alert
+          for: 1m  # Alert if condition is true for 1 minute
+          labels:
+            severity: warning
+          annotations:
+            summary: "Test Alert for Slack"
+            description: "This is a test alert to verify the Slack receiver configuration."
+

package/src/helm-charts/prom-operator/stackdriver-exporter.yaml.ovh

@@ -13,7 +13,12 @@ stackdriver:
 serviceMonitor:
   enabled: true
   namespace: prometheus
-  interval: 20s
+  interval: "30s"
+  relabelings:
+    - action: labelmap
+      regex: __meta_kubernetes_pod_label_(.+)
+    - action: labelmap
+      regex: __meta_kubernetes_service_label_(.+)
 
 annotations:
   prometheus.io/port: "9255"

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

@@ -4,7 +4,7 @@ showInstalling "Redis"
 
 OCI_CHART="oci://registry-1.docker.io/bitnamicharts/redis"
 
-[ -z "$REDIS_CHART_VERSION" ] && REDIS_CHART_VERSION="20.1.7"
+[ -z "$REDIS_CHART_VERSION" ] && REDIS_CHART_VERSION="20.2.1"
 
 helm upgrade --install redis $OCI_CHART       \
              --values  redis/redis-local.yaml \

package/src/helm-charts/redis/redis-local.yaml

@@ -73,3 +73,8 @@ metrics:
   serviceMonitor:
     enabled: false # set to true for prometheus operator
     namespace: "prometheus"
+    relabelings:
+    - action: labelmap
+      regex: __meta_kubernetes_pod_label_(.+)
+    - action: labelmap
+      regex: __meta_kubernetes_service_label_(.+)

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

@@ -11,13 +11,13 @@
 # kubectl apply --namespace traefik --server-side \
 #               --force-conflicts -k https://github.com/traefik/traefik-helm-chart/traefik/crds/\?ref\=v27
 #
-showInstalling "Traefik Load Balancer / Router"
+showInstalling "Traefik v3 Load Balancer / Router"
 
 TRAEFIK_NAMESPACE="traefik"
 
 addHelmRepo traefik https://helm.traefik.io/traefik
 
-[ -z "$TRAEFIK_CHART_VERSION" ] && TRAEFIK_CHART_VERSION="27"
+[ -z "$TRAEFIK_CHART_VERSION" ] && TRAEFIK_CHART_VERSION="32"
 helm upgrade --install traefik traefik/traefik \
              --namespace $TRAEFIK_NAMESPACE --create-namespace \
              --values  traefik/traefik-local.yaml \

package/src/k8x.sh

@@ -43,6 +43,10 @@ K8X_HELP
     ns="elastic" && cmd="bash"
     ;;
 
+  "prom-operator"|"prometheus")
+    ns="prometheus" && cmd="bash"
+    ;;
+
   "psql"|"pgsql")
     FZFQ="--query=postgresql" && cmd='psql -U postgres'
     ;;

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

@@ -1,112 +0,0 @@
-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"

package/src/helm-charts/prom-operator/rules/prometheus-rules.yaml.off

@@ -1,79 +0,0 @@
-apiVersion: monitoring.coreos.com/v1
-kind: PrometheusRule
-metadata:
-  name: prometheus-rules
-  namespace: prometheus
-
-spec:
-  groups:
-  - name: Prometheus
-    rules: 
-    - alert: targets_down
-      expr: up{target_env!="preemptibles"} == 0
-      for: 10m
-      labels:
-        severity: warning
-      annotations:
-        summary: Prometheus target missing
-        description: "Prometheus failed to scrape {{ $labels.app }}"
-        dashboard: "See prometheus.md in SRE Playbook"
-
-    - alert: PrometheusConfigurationReloadFailure
-      expr: prometheus_config_last_reload_successful != 1
-      for: 5m
-      labels:
-        severity: warning
-      annotations:
-        summary: "Prometheus server configuration reload failure"
-        description: "Prometheus server failed to reload server configs (e.g. alerts, rules)"
-        dashboard: "See prometheus.md in SRE Playbook"
-
-    - alert: PrometheusAlertmanagerConfigurationReloadFailure
-      expr: alertmanager_config_last_reload_successful != 1
-      for: 5m
-      labels:
-        severity: warning
-      annotations:
-        summary: "Prometheus AlertManager configuration reload failure"
-        description: "AlertManager failed to reload alert configs (e.g. slack, opsgenie)"
-        dashboard: "See prometheus.md in SRE Playbook"
-
-    - alert: PrometheusTooManyRestarts
-      expr: changes(process_start_time_seconds{job=~"prometheus|alertmanager"}[15m]) > 2
-      for: 5m
-      labels:
-        severity: warning
-      annotations:
-        summary: "Prometheus is in a crash loop"
-        description: "Prometheus {{ $labels.component }} has restarted more than twice in the last 15 minutes. It might be crashlooping."
-        dashboard: "See prometheus.md in SRE Playbook"
-
-    - alert: PrometheusNotConnectedToAlertmanager
-      expr: prometheus_notifications_alertmanagers_discovered < 1
-      for: 5m
-      labels:
-        severity: error
-      annotations:
-        summary: "Prometheus not connected to alertmanager"
-        description: "Prometheus cannot connect the alertmanager - new alerts may not be detected"
-        dashboard: "See prometheus.md in SRE Playbook"
-
-    - alert: PrometheusNotificationsBacklog
-      expr: min_over_time(prometheus_notifications_queue_length[10m]) > 0
-      for: 5m
-      labels:
-        severity: warning
-      annotations:
-        summary: "Prometheus notifications backlog"
-        description: "The Prometheus notification queue has not been empty for 10 minutes"
-        dashboard: "See prometheus.md in SRE Playbook"
-
-    - alert: PrometheusAlertmanagerNotificationFailing
-      expr: rate(alertmanager_notifications_failed_total[1m]) > 0
-      for: 5m
-      labels:
-        severity: error
-      annotations:
-        summary: "Prometheus AlertManager notification failing"
-        description: "Alertmanager is failing to send notifications"
-        dashboard: "See prometheus.md in SRE Playbook"

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

@@ -1,14 +0,0 @@
-#!/bin/bash
-#
-showInstalling "The Prometheus Operator (kube-prometheus-stack)"
-
-addHelmRepo prometheus-community https://prometheus-community.github.io/helm-charts
-
-[ -z "$PROMETHEUS_STACK_CHART_VERSION" ] && PROMETHEUS_STACK_CHART_VERSION="62"
-
-helm upgrade --install prometheus-stack prometheus-community/kube-prometheus-stack \
-             --namespace prometheus --create-namespace \
-             --values  prometheus-operator/prometheus-stack.yaml \
-             --version $PROMETHEUS_STACK_CHART_VERSION $HELM_WHAT
-
-removeHelmRepo prometheus-community