kube-prometheus 服务发现

apiVersion: v1
kind: Secret
metadata:
  labels:
    app.kubernetes.io/component: alert-router
    app.kubernetes.io/instance: main
    app.kubernetes.io/name: alertmanager
    app.kubernetes.io/part-of: kube-prometheus
    app.kubernetes.io/version: 0.26.0
  name: additional-configs
  namespace: monitoring
type: Opaque
stringData:
  prometheus-additional.yaml: |

    
    - job_name: "kubernetes-pod"
      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
          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: kubernetes_namespace
        - source_labels: [ __meta_kubernetes_pod_name ]
          action: replace
          target_label: kubernetes_pod_name

    
    - job_name: 'kubernetes-endpoint'
      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_service_name
        - source_labels: [ __meta_kubernetes_pod_name ]
          target_label: kubernetes_pod_name
          action: replace
    
    #nvdia gpu
    - job_name: 'kubernetes-dcgm-exporter'
      kubernetes_sd_configs:
        - role: endpoints
      relabel_configs:
        - source_labels: [ __meta_kubernetes_endpoints_name ]
          regex: dcgm-exporter
          replacement: $1
          action: keep
        - source_labels: [ __meta_kubernetes_pod_node_name ]
          regex: (.*)
          target_label: node_name
          replacement: ${1}
          action: replace
        - source_labels: [ __meta_kubernetes_pod_host_ip ]
          regex: (.*)
          target_label: ip
          replacement: $1
          action: replace
    
    # hami vgpu 
    - job_name: 'kubernetes-vgpu-exporter'
      kubernetes_sd_configs:
        - role: endpoints
      relabel_configs:
        - source_labels: [ __meta_kubernetes_endpoints_name ]
          regex: hami-device-plugin-monitor
          replacement: $1
          action: keep
        - source_labels: [ __meta_kubernetes_pod_node_name ]
          regex: (.*)
          target_label: node_name
          replacement: ${1}
          action: replace
        - source_labels: [ __meta_kubernetes_pod_host_ip ]
          regex: (.*)
          target_label: ip
          replacement: $1
          action: replace

ss