integrations/flink/documentation.yaml

exporter_type: included
app_name_short: Flink
app_name: Apache {{app_name_short}}
app_site_name: Apache Flink
app_site_url: https://flink.apache.org/
exporter_name: the Flink exporter
exporter_pkg_name: flink
minimum_exporter_version: "1.17"
exporter_repo_url: https://flink.apache.org/features/2019/03/11/prometheus-monitoring.html
additional_prereq_info: |
  {{app_name_short}} exposes Prometheus-format metrics when configured with
  `metrics.reporter.prom.factory.class: org.apache.flink.metrics.prometheus.PrometheusReporterFactory`.
  If you deployed Flink with the official [getting started manifests](https://nightlies.apache.org/flink/flink-docs-master/docs/deployment/resource-providers/standalone/kubernetes/){:class="external"},
  add this new option to the ConfigMap:
  <pre>
  apiVersion: v1
  kind: ConfigMap
  metadata:
    name: flink-config
    labels:
      app: flink
  data:
    flink-conf.yaml: |+
      ...
  +   metrics.reporter.prom.factory.class: org.apache.flink.metrics.prometheus.PrometheusReporterFactory
  </pre>
  If you deployed Flink with the official [operator](https://nightlies.apache.org/flink/flink-kubernetes-operator-docs-main/docs/try-flink-kubernetes-operator/quick-start/){:class="external"},
  add this new option to the FlinkDeployment's `spec.flinkConfiguration` field:
  <pre>
  apiVersion: flink.apache.org/v1beta1
  kind: FlinkDeployment
  metadata:
    name: basic-example
  spec:
    image: flink:1.17
    flinkVersion: v1_17
    flinkConfiguration:
      taskmanager.numberOfTaskSlots: "2"
  +   metrics.reporter.prom.factory.class: org.apache.flink.metrics.prometheus.PrometheusReporterFactory
  </pre>
  Alternatively, you can specify the Prometheus reporter as a default option within the [Flink operator
  configuration](https://nightlies.apache.org/flink/flink-kubernetes-operator-docs-main/docs/operations/configuration/){:class="external"}.
  To verify that {{exporter_name}} is emitting metrics on the expected endpoints, do the following:
  1. Set up port forwarding by using the following command:
    <pre class="devsite-click-to-copy">
    kubectl -n {{namespace_name}} port-forward {{pod_name}} 9249
    </pre>
  1. Access the endpoint `localhost:9249/metrics` by using the browser
     or the `curl` utility in another terminal session.
dashboard_available: true
multiple_dashboards: true
dashboard_display_name: {{app_name_short}} Prometheus Overview
podmonitoring_config: |
  apiVersion: monitoring.googleapis.com/v1
  kind: PodMonitoring
  metadata:
    name: flink
    labels:
      app.kubernetes.io/name: flink
      app.kubernetes.io/part-of: google-cloud-managed-prometheus
  spec:
    endpoints:
    - port: 9249
      scheme: http
      interval: 30s
      path: /metrics
    selector:
      matchLabels:
        app.kubernetes.io/name: flink
additional_podmonitoring_info: |
  Ensure that the values of the `port` and `matchLabels` fields match those of the {{app_name_short}} pods you want to monitor.
  {{app_name_short}} exposes metrics on port 9249 by default when metrics are enabled.
sample_promql_query: up{job="flink", cluster="{{cluster_name}}", namespace="{{namespace_name}}"}
alerts_config: |
  apiVersion: monitoring.googleapis.com/v1
  kind: Rules
  metadata:
    name: flink-rules
    labels:
      app.kubernetes.io/component: rules
      app.kubernetes.io/name: flink-rules
      app.kubernetes.io/part-of: google-cloud-managed-prometheus
  spec:
    groups:
    - name: flink
      interval: 30s
      rules:
      - alert: FlinkHighJVMMemoryNonHeapUsage
        annotations:
          description: |-
            Flink high jvm memory non-heap usage
              VALUE = {{ $value }}
              LABELS: {{ $labels }}
          summary: Flink high jvm memory non-heap usage (instance {{ $labels.instance }})
        expr: (flink_jobmanager_Status_JVM_Memory_NonHeap_Used/flink_jobmanager_Status_JVM_Memory_NonHeap_Max) >= 0.9
        for: 5m
        labels:
          severity: critical
      - alert: FlinkHighJVMMemoryHeapUsage
        annotations:
          description: |-
            Flink high jvm memory heap usage
              VALUE = {{ $value }}
              LABELS: {{ $labels }}
          summary: Flink high jvm memory heap usage (instance {{ $labels.instance }})
        expr: (flink_jobmanager_Status_JVM_Memory_Heap_Used/flink_jobmanager_Status_JVM_Memory_Heap_Max) >= 0.9
        for: 5m
        labels:
          severity: warning
additional_alert_info: You can adjust the alert thresholds to suit your application.