Prometheus Config

prometheus.yaml

# Based on https://github.com/prometheus/prometheus/blob/release-2.2/documentation/examples/prometheus-kubernetes.yml
serverFiles:
  prometheus.yml:
    remote_write:
    - url: "https://prometheus.gra1-ovh.metrics.ovh.net/remote_write"
      remote_timeout: 120s
      bearer_token: $TOKEN
      write_relabel_configs:
      # Filter metrics to keep
      - action: keep
        source_labels: [__name__]
        regex: "eagle.*|\
            kube_node_info.*|\
            kube_node_spec_taint.*|\
            container_start_time_seconds|\
            container_last_seen|\
            container_cpu_usage_seconds_total|\
            container_fs_io_time_seconds_total|\
            container_fs_write_seconds_total|\
            container_fs_usage_bytes|\
            container_fs_limit_bytes|\
            container_memory_working_set_bytes|\
            container_memory_rss|\
            container_memory_usage_bytes|\
            container_network_receive_bytes_total|\
            container_network_transmit_bytes_total|\
            machine_memory_bytes|\
            machine_cpu_cores"

    scrape_configs:
    # Scrape config for Kubelet cAdvisor.
    - job_name: 'kubernetes-cadvisor'
      scheme: https
      tls_config:
        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
      kubernetes_sd_configs:
      - role: node
      
      relabel_configs:
      - target_label: __address__
        replacement: kubernetes.default.svc:443
      - source_labels: [__meta_kubernetes_node_name]
        regex: (.+)
        target_label: __metrics_path__
        replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
        
      metric_relabel_configs:
      # Only keep systemd important services like docker|containerd|kubelet and kubepods,
      # Also machine_cpu_cores don't have id so we have to machine here
      # The string will concat id with name and the separator is a ;
      # `/;container_cpu_usage_seconds_total` OK
      # `/system.slice;container_cpu_usage_seconds_total` OK
      # `/system.slice/minion.service;container_cpu_usage_seconds_total` NOK, Useless
      # `/kubepods/besteffort/e2514ad43202;container_cpu_usage_seconds_total` Best Effort POD OK
      # `/kubepods/burstable/e2514ad43202;container_cpu_usage_seconds_total` Burstable POD OK
      # `/kubepods/e2514ad43202;container_cpu_usage_seconds_total` Guaranteed POD OK
      # `/docker/pod104329ff;container_cpu_usage_seconds_total` OK, Container that run on docker but not managed by kube
      # `;machine_cpu_cores` OK, there is no id on these metrics, but we want to keep them also
      # Only keep systemd important services like docker|containerd|kubelet and kubepods,
      # Also machine_cpu_cores don't have id so we have to machine here
      # The string will concat id with name and the separator is a ;
      # `/;container_cpu_usage_seconds_total` OK
      # `/system.slice;container_cpu_usage_seconds_total` OK
      # `/system.slice/minion.service;container_cpu_usage_seconds_total` NOK, Useless
      # `/kubepods/besteffort/e2514ad43202;container_cpu_usage_seconds_total` Best Effort POD OK
      # `/kubepods/burstable/e2514ad43202;container_cpu_usage_seconds_total` Burstable POD OK
      # `/kubepods/e2514ad43202;container_cpu_usage_seconds_total` Guaranteed POD OK
      # `/docker/pod104329ff;container_cpu_usage_seconds_total` OK, Container that run on docker but not managed by kube
      # `;machine_cpu_cores` OK, there is no id on these metrics, but we want to keep them also
      - source_labels: [id,__name__]
        regex: "^((/(system.slice(/(docker|containerd|kubelet).service)?|(kubepods|docker).*)?);.*|;(machine_cpu_cores|machine_memory_bytes))$"
        action: keep
      # Remove Useless parents keys like `/kubepods/burstable` or `/docker`
      - source_labels: [id]
        regex: "(/kubepods/burstable|/kubepods/besteffort|/kubepods|/docker)"
        action: drop
        # cAdvisor give metrics per container and sometimes it sum up per pod
        # As we already have the child, we will sum up ourselves, so we drop metrics for the POD and keep containers metrics
        # Metrics for the POD don't have container_name, so we drop if we have just the pod_name
      - source_labels: [container_name,pod_name]
        regex: ";(.+)"
        action: drop
    
    # Scrape config for service endpoints.
    - job_name: 'kubernetes-service-endpoints'
      kubernetes_sd_configs:
      - role: endpoints
      
      relabel_configs:
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
        action: keep
        regex: true
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
        action: replace
        target_label: __scheme__
        regex: (https?)
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
        action: replace
        target_label: __metrics_path__
        regex: (.+)
      - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
        action: replace
        target_label: __address__
        regex: ([^:]+)(?::\d+)?;(\d+)
        replacement: $1:$2
      - action: labelmap
        regex: __meta_kubernetes_service_label_(.+)
      - source_labels: [__meta_kubernetes_namespace]
        action: replace
        target_label: namespace
      - source_labels: [__meta_kubernetes_service_name]
        action: replace
        target_label: kubernetes_name

    # Example scrape config for pods
    #
    # The relabeling allows the actual pod scrape endpoint to be configured via the
    # following annotations:
    #
    # * `prometheus.io/scrape`: Only scrape pods that have a value of `true`
    # * `prometheus.io/path`: If the metrics path is not `/metrics` override this.
    # * `prometheus.io/port`: Scrape the pod on the indicated port instead of the
    # pod's declared ports (default is a port-free target if none are declared).
    - job_name: 'kubernetes-pods'
      kubernetes_sd_configs:
      - role: pod

      relabel_configs:
      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
        action: keep
        regex: true
      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
        action: replace
        target_label: __metrics_path__
        regex: (.+)
      - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
        action: replace
        regex: ([^:]+)(?::\d+)?;(\d+)
        replacement: $1:$2
        target_label: __address__
      - action: labelmap
        regex: __meta_kubernetes_pod_label_(.+)
      - source_labels: [__meta_kubernetes_namespace]
        action: replace
        target_label: namespace
      - source_labels: [__meta_kubernetes_pod_name]
        action: replace
        target_label: pod_name
      - source_labels: [__meta_kubernetes_pod_node_name]
        action: replace
        target_label: host
      - action: labeldrop
        regex: (pod_template_generation|job|release|controller_revision_hash|workload_user_cattle_io_workloadselector|pod_template_hash)

values.yaml

alertmanager:
  enabled: false
pushgateway:
  enabled: false
nodeExporter:
  enabled: false
server:
  ingress:
    enabled: true
    annotations:
      kubernetes.io/ingress.class: traefik
      ingress.kubernetes.io/auth-type: basic
      ingress.kubernetes.io/auth-secret: basic-auth
    hosts:
    - prometheus.domain.com
  image:
    tag: v2.7.1
  persistentVolume:
    enabled: false