infrastructure/monitoring/prometheus.yml

global:
  scrape_interval: 15s
  evaluation_interval: 15s
  external_labels:
    cluster: fred-ml-cluster
    job: fred-ml

rule_files:
  - "alerts.yml"

scrape_configs:
  - job_name: 'fred-ml'
    static_configs:
      - targets: ['fred-ml-service:8000']
    metrics_path: '/metrics'
    scrape_interval: 5s
    scrape_timeout: 3s
    honor_labels: true

  - 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__

  - 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
        regex: ([^:]+)(?::\d+)?;(\d+)
        replacement: $1:$2
        target_label: __address__

alerting:
  alertmanagers:
    - static_configs:
        - targets:
          - alertmanager:9093