prometheus.values.yaml

# ----------------------------------------------------------------------
# Copyright (c) 2021, 2022 Oracle and/or its affiliates. All rights reserved.
# The Universal Permissive License (UPL), Version 1.0
# ----------------------------------------------------------------------

# 
# kube-prometheus-stack helm chart values. These additions work in conjunction with
# the dcgm-exporter helm chart & data set
# see https://docs.nvidia.com/datacenter/cloud-native/gpu-telemetry/dcgm-exporter.html#gpu-telemetry
prometheus:
  prometheusSpec:
    serviceMonitorSelectorNilUsesHelmValues: false
    additionalScrapeConfigs:
    # service endpoint scraping
    - job_name: kubernetes-service-endpoints
      scrape_interval: 10s
      scrape_timeout: 10s
      kubernetes_sd_configs:
      - role: endpoints
      relabel_configs:
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
        separator: ;
        regex: "true"
        replacement: $1
        action: keep
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
        separator: ;
        regex: (https?)
        target_label: __scheme__
        replacement: $1
        action: replace
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
        separator: ;
        regex: (.+)
        target_label: __metrics_path__
        replacement: $1
        action: replace
      - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
        separator: ;
        regex: ([^:]+)(?::\d+)?;(\d+)
        target_label: __address__
        replacement: $1:$2
        action: replace
      - separator: ;
        regex: __meta_kubernetes_service_annotation_prometheus_io_param_(.+)
        replacement: __param_$1
        action: labelmap
      - separator: ;
        regex: __meta_kubernetes_service_label_(.+)
        replacement: $1
        action: labelmap
      - source_labels: [__meta_kubernetes_namespace]
        separator: ;
        regex: (.*)
        target_label: namespace
        replacement: $1
        action: replace
      - source_labels: [__meta_kubernetes_service_name]
        separator: ;
        regex: (.*)
        target_label: service
        replacement: $1
        action: replace
      - source_labels: [__meta_kubernetes_pod_node_name]
        separator: ;
        regex: (.*)
        target_label: node
        replacement: $1
        action: replace

    # general pod scraping
    - job_name: kubernetes-pods
      scrape_interval: 10s
      kubernetes_sd_configs:
      - role: pod
      relabel_configs:
      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
        separator: ;
        regex: "true"
        replacement: $1
        action: keep
      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scheme]
        separator: ;
        regex: (https?)
        target_label: __scheme__
        replacement: $1
        action: replace
      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
        separator: ;
        regex: (.+)
        target_label: __metrics_path__
        replacement: $1
        action: replace
      - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
        separator: ;
        regex: ([^:]+)(?::\d+)?;(\d+)
        target_label: __address__
        replacement: $1:$2
        action: replace
      - separator: ;
        regex: __meta_kubernetes_pod_annotation_prometheus_io_param_(.+)
        replacement: __param_$1
        action: labelmap
      - separator: ;
        regex: __meta_kubernetes_pod_label_(.+)
        replacement: $1
        action: labelmap
      - source_labels: [__meta_kubernetes_namespace]
        separator: ;
        regex: (.*)
        target_label: namespace
        replacement: $1
        action: replace
      - source_labels: [__meta_kubernetes_pod_name]
        separator: ;
        regex: (.*)
        target_label: pod
        replacement: $1
        action: replace
      - source_labels: [__meta_kubernetes_pod_phase]
        separator: ;
        regex: Pending|Succeeded|Failed|Completed
        replacement: $1
        action: drop
      - source_labels: [__meta_kubernetes_pod_container_name]
        action: replace
        target_label: container

    # gpu metrics
    - job_name: gpu-metrics
      scrape_interval: 1s
      metrics_path: /metrics
      scheme: http
      kubernetes_sd_configs:
      - role: endpoints
        namespaces:
          names:
          - gpu-operator
          - gpu-operator-resources
      relabel_configs:
      - source_labels: [__meta_kubernetes_pod_node_name]
        action: replace
        target_label: kubernetes_node

# Configure grafana based on default values:
# https://github.com/grafana/helm-charts/blob/main/charts/grafana/README.md
# https://github.com/grafana/helm-charts/blob/main/charts/grafana/values.yaml
#
grafana:
  enabled: true
  persistence:
    enabled: true
  plugins:
    - oci-logs-datasource
    - oci-metrics-datasource
    - grafana-kubernetes-app
    - grafana-worldmap-panel
    - grafana-piechart-panel
  # disable ingress to handle separately
  ingress:
    enabled: false
  grafana.ini:
    # access grafana on the /grafana path prefix
    server:
      root_url: http://localhost:3000/grafana # this host can be localhost
      # root_url: "%(protocol)s://%(domain)s:%(http_port)s/grafana"
      serve_from_sub_path: true