gitlab-org--gitlab-foss/config/prometheus/additional_metrics.yml

- group: Response metrics (NGINX Ingress)
  priority: 10
  metrics:
  - title: "Throughput"
    y_label: "Requests / Sec"
    required_metrics:
      - nginx_upstream_responses_total
    weight: 1
    queries:
    - query_range: 'sum(rate(nginx_upstream_responses_total{upstream=~"%{kube_namespace}-%{ci_environment_slug}-.*"}[2m])) by (status_code)'
      unit: req / sec
      label: Status Code
      series:
        - label: status_code
          when:
            - value: 2xx
              color: green
            - value: 4xx
              color: orange
            - value: 5xx
              color: red
  - title: "Latency"
    y_label: "Latency (ms)"
    required_metrics:
      - nginx_upstream_response_msecs_avg
    weight: 1
    queries:
    - query_range: 'avg(nginx_upstream_response_msecs_avg{upstream=~"%{kube_namespace}-%{ci_environment_slug}-.*"})'
      label: Average
      unit: ms
  - title: "HTTP Error Rate"
    y_label: "HTTP 500 Errors / Sec"
    required_metrics:
      - nginx_upstream_responses_total
    weight: 1
    queries:
    - query_range: 'sum(rate(nginx_upstream_responses_total{status_code="5xx", upstream=~"%{kube_namespace}-%{ci_environment_slug}-.*"}[2m]))'
      label: HTTP Errors
      unit: "errors / sec"
- group: Response metrics (HA Proxy)
  priority: 10
  metrics:
  - title: "Throughput"
    y_label: "Requests / Sec"
    required_metrics:
      - haproxy_frontend_http_requests_total
    weight: 1
    queries:
    - query_range: 'sum(rate(haproxy_frontend_http_requests_total{%{environment_filter}}[2m])) by (code)'
      unit: req / sec
      series:
        - label: code
          when:
            - value: 2xx
              color: green
            - value: 4xx
              color: yellow
            - value: 5xx
              color: red
  - title: "HTTP Error Rate"
    y_label: "Error Rate (%)"
    required_metrics:
      - haproxy_frontend_http_responses_total
    weight: 1
    queries:
    - query_range: 'sum(rate(haproxy_frontend_http_responses_total{code="5xx",%{environment_filter}}[2m])) / sum(rate(haproxy_frontend_http_responses_total{%{environment_filter}}[2m]))'
      label: HTTP Errors
      unit: "%"
- group: Response metrics (AWS ELB)
  priority: 10
  metrics:
  - title: "Throughput"
    y_label: "Requests / Sec"
    required_metrics:
      - aws_elb_request_count_sum
    weight: 1
    queries:
    - query_range: 'sum(aws_elb_request_count_sum{%{environment_filter}}) / 60'
      label: Total
      unit: req / sec
  - title: "Latency"
    y_label: "Latency (ms)"
    required_metrics:
      - aws_elb_latency_average
    weight: 1
    queries:
    - query_range: 'avg(aws_elb_latency_average{%{environment_filter}}) * 1000'
      label: Average
      unit: ms
  - title: "HTTP Error Rate"
    y_label: "Error Rate (%)"
    required_metrics:
      - aws_elb_request_count_sum
      - aws_elb_httpcode_backend_5_xx_sum
    weight: 1
    queries:
    - query_range: 'sum(aws_elb_httpcode_backend_5_xx_sum{%{environment_filter}}) / sum(aws_elb_request_count_sum{%{environment_filter}})'
      label: HTTP Errors
      unit: "%"
- group: Response metrics (NGINX)
  priority: 10
  metrics:
  - title: "Throughput"
    y_label: "Requests / Sec"
    required_metrics:
      - nginx_responses_total
    weight: 1
    queries:
    - query_range: 'sum(rate(nginx_responses_total{server_zone!="*", server_zone!="_", %{environment_filter}}[2m])) by (status_code)'
      unit: req / sec
      label: Status Code
      series:
        - label: status_code
          when:
            - value: 2xx
              color: green
            - value: 4xx
              color: orange
            - value: 5xx
              color: red
  - title: "Latency"
    y_label: "Latency (ms)"
    required_metrics:
      - nginx_upstream_response_msecs_avg
    weight: 1
    queries:
    - query_range: 'avg(nginx_upstream_response_msecs_avg{%{environment_filter}})'
      label: Upstream
      unit: ms
  - title: "HTTP Error Rate"
    y_label: "HTTP 500 Errors / Sec"
    required_metrics:
      - nginx_responses_total
    weight: 1
    queries:
    - query_range: 'sum(rate(nginx_responses_total{status_code="5xx", %{environment_filter}}[2m]))'
      label: HTTP Errors
      unit: "errors / sec"
- group: System metrics (Kubernetes)
  priority: 5
  metrics:
  - title: "Memory Usage"
    y_label: "Memory Used per Pod"
    required_metrics:
      - container_memory_usage_bytes
    weight: 1
    queries:
    - query_range: 'avg(sum(container_memory_usage_bytes{container_name!="POD",pod_name=~"^%{ci_environment_slug}-([^c].*|c([^a]|a([^n]|n([^a]|a([^r]|r[^y])))).*|)-(.*)",namespace="%{kube_namespace}"}) by (job)) without (job) / count(avg(container_memory_usage_bytes{container_name!="POD",pod_name=~"^%{ci_environment_slug}-([^c].*|c([^a]|a([^n]|n([^a]|a([^r]|r[^y])))).*|)-(.*)",namespace="%{kube_namespace}"}) without (job)) /1024/1024'
      label: Average
      unit: MB
  - title: "CPU Usage"
    y_label: "Cores per Pod"
    required_metrics:
     - container_cpu_usage_seconds_total
    weight: 1
    queries:
    - query_range: 'avg(sum(rate(container_cpu_usage_seconds_total{container_name!="POD",pod_name=~"^%{ci_environment_slug}-([^c].*|c([^a]|a([^n]|n([^a]|a([^r]|r[^y])))).*|)-(.*)",namespace="%{kube_namespace}"}[15m])) by (job)) without (job) / count(sum(rate(container_cpu_usage_seconds_total{container_name!="POD",pod_name=~"^%{ci_environment_slug}-([^c].*|c([^a]|a([^n]|n([^a]|a([^r]|r[^y])))).*|)-(.*)",namespace="%{kube_namespace}"}[15m])) by (pod_name))'
      label: Average
      unit: "cores"