feat(chart): Add servicemonitor

config/helm/aws-node-termination-handler/README.md

@@ -80,11 +80,6 @@ Parameter | Description | Default
 `enableProbesServer` | If true, start an http server exposing `/healthz` endpoint for probes. | `false`
 `probesServerPort` | Replaces the default HTTP port for exposing probes endpoint. | `8080`
 `probesServerEndpoint` | Replaces the default endpoint for exposing probes endpoint. | `/healthz`
-`podMonitor.create` | If `true`, create a PodMonitor | `false`
-`podMonitor.interval` | Prometheus scrape interval | `30s`
-`podMonitor.sampleLimit` | Number of scraped samples accepted | `5000`
-`podMonitor.labels` | Additional PodMonitor metadata labels | `{}`
-`podMonitor.namespace` | Override podMonitor Helm release namespace | `{{ .Release.Namespace }}`
 `emitKubernetesEvents` | If `true`, Kubernetes events will be emitted when interruption events are received and when actions are taken on Kubernetes nodes. In IMDS Processor mode a default set of annotations with all the node metadata gathered from IMDS will be attached to each event. More information [here](https://github.com/aws/aws-node-termination-handler/blob/main/docs/kubernetes_events.md) | `false`
 `kubernetesExtraEventsAnnotations` | A comma-separated list of `key=value` extra annotations to attach to all emitted Kubernetes events. Example: `first=annotation,sample.annotation/number=two"` | None
 
@@ -100,6 +95,11 @@ Parameter | Description | Default
 `workers` | The maximum amount of parallel event processors | `10`
 `replicas` | The number of replicas in the NTH deployment when using queue-processor mode (NOTE: increasing replicas may cause duplicate webhooks since NTH pods are stateless) | `1`
 `podDisruptionBudget` | Limit the disruption for controller pods, requires at least 2 controller replicas | `{}`
+`serviceMonitor.create` | If `true`, create a ServiceMonitor (this requires enableSqsTerminationDraining and enablePrometheusServer to be set) | `false`
+`serviceMonitor.interval` | Prometheus scrape interval | `30s`
+`serviceMonitor.sampleLimit` | Number of scraped samples accepted | `5000`
+`serviceMonitor.labels` | Additional ServiceMonitor metadata labels | `{}`
+`serviceMonitor.namespace` | Override ServiceMonitor Helm release namespace | `{{ .Release.Namespace }}`
 
 ### AWS Node Termination Handler - IMDS Mode Configuration
 
@@ -110,6 +110,11 @@ Parameter | Description | Default
 `enableRebalanceDraining` | If true, drain nodes when the rebalance recommendation notice is received | `false`
 `enableRebalanceMonitoring` | If true, cordon nodes when the rebalance recommendation notice is received. If you'd like to drain the node in addition to cordoning, then also set `enableRebalanceDraining`. | `false`
 `useHostNetwork` | If `true`, enables `hostNetwork` for the Linux DaemonSet. NOTE: setting this to `false` may cause issues accessing IMDSv2 if your account is not configured with an IP hop count of 2 | `true`
+`podMonitor.create` | If `true`, create a PodMonitor (this requires enableSqsTerminationDraining to not be set and enablePrometheusServer to be set) | `false`
+`podMonitor.interval` | Prometheus scrape interval | `30s`
+`podMonitor.sampleLimit` | Number of scraped samples accepted | `5000`
+`podMonitor.labels` | Additional PodMonitor metadata labels | `{}`
+`podMonitor.namespace` | Override PodMonitor Helm release namespace | `{{ .Release.Namespace }}`
 
 ### Kubernetes Configuration
 

config/helm/aws-node-termination-handler/templates/podmonitor.yaml

@@ -1,4 +1,4 @@
-{{- if .Values.podMonitor.create }}
+{{- if and (not .Values.enableSqsTerminationDraining) (and .Values.enablePrometheusServer .Values.podMonitor.create) -}}
 apiVersion: monitoring.coreos.com/v1
 kind: PodMonitor
 metadata:
@@ -17,13 +17,17 @@ spec:
   jobLabel: {{ include "aws-node-termination-handler.name" . }}
   namespaceSelector:
     matchNames:
-    - {{ .Release.Namespace }}
+      - {{ .Release.Namespace }}
   podMetricsEndpoints:
-  - interval: {{ .Values.podMonitor.interval }}
-    path: /metrics
-    port: http-metrics
-  sampleLimit: {{ .Values.podMonitor.sampleLimit }}
+    - port: http-metrics
+      path: /metrics
+      {{- with .Values.podMonitor.interval }}
+      interval: {{ . }}
+      {{- end }}
+  {{- with .Values.podMonitor.sampleLimit }}
+  sampleLimit: {{ . }}
+  {{- end }}
   selector:
     matchLabels:
       {{- include "aws-node-termination-handler.selectorLabels" . | nindent 6 }}
-{{- end }}
+{{- end -}}

config/helm/aws-node-termination-handler/templates/service.yaml

@@ -0,0 +1,17 @@
+{{- if and .Values.enableSqsTerminationDraining .Values.enablePrometheusServer -}}
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "aws-node-termination-handler.fullname" . }}
+  labels:
+    {{- include "aws-node-termination-handler.labels" . | nindent 4 }}
+spec:
+  type: ClusterIP
+  selector:
+    {{- include "aws-node-termination-handler.selectorLabels" . | nindent 4 }}
+  ports:
+    - name: http-metrics
+      port: {{ .Values.prometheusServerPort }}
+      targetPort: http-metrics
+      protocol: TCP
+{{- end -}}

config/helm/aws-node-termination-handler/templates/servicemonitor.yaml

@@ -0,0 +1,33 @@
+{{- if and .Values.enableSqsTerminationDraining (and .Values.enablePrometheusServer .Values.serviceMonitor.create) -}}
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: {{ include "aws-node-termination-handler.fullname" . }}
+  {{- if .Values.serviceMonitor.namespace }}
+  namespace: {{ .Values.serviceMonitor.namespace }}
+  {{- else }}
+  namespace: {{ .Release.Namespace }}
+  {{- end }}
+  labels:
+    {{- include "aws-node-termination-handler.labels" . | nindent 4 }}
+  {{- with .Values.serviceMonitor.labels }}
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  jobLabel: {{ include "aws-node-termination-handler.name" . }}
+  namespaceSelector:
+    matchNames:
+      - {{ .Release.Namespace }}
+  endpoints:
+    - port: http-metrics
+      path: /metrics
+      {{- with .Values.serviceMonitor.interval }}
+      interval: {{ . }}
+      {{- end }}
+  {{- with .Values.serviceMonitor.sampleLimit }}
+  sampleLimit: {{ . }}
+  {{- end }}
+  selector:
+    matchLabels:
+      {{- include "aws-node-termination-handler.selectorLabels" . | nindent 6 }}
+{{- end -}}

config/helm/aws-node-termination-handler/values.yaml

@@ -192,16 +192,33 @@ dnsPolicy: ""
 
 podMonitor:
   # Specifies whether PodMonitor should be created
+  # this needs enableSqsTerminationDraining: false
+  # and enablePrometheusServer: true
   create: false
-   # The Prometheus scrape interval
+  # Specifies whether the PodMonitor should be created in a different namespace than
+  # the Helm release
+  namespace:
+  # Additional labels to add to the metadata
+  labels: {}
+  # The Prometheus scrape interval
   interval: 30s
   # The number of scraped samples that will be accepted
   sampleLimit: 5000
-   # Additional labels to add to the metadata
-  labels: {}
-  # Specifies whether a pod monitor should be created in a different namespace than
+
+serviceMonitor:
+  # Specifies whether ServiceMonitor should be created
+  # this needs enableSqsTerminationDraining: rue
+  # and enablePrometheusServer: true
+  create: false
+  # Specifies whether the ServiceMonitor should be created in a different namespace than
   # the Helm release
-  # namespace: monitoring
+  namespace:
+  # Additional labels to add to the metadata
+  labels: {}
+  # The Prometheus scrape interval
+  interval: 30s
+  # The number of scraped samples that will be accepted
+  sampleLimit: 5000
 
 # K8s DaemonSet update strategy.
 updateStrategy: