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

dashboard: 'Environment metrics'
priority: 1
panel_groups:
- group: System metrics (Kubernetes)
  panels:
  - title: "Memory Usage (Total)"
    type: "area-chart"
    y_label: "Total Memory Used (GB)"
    metrics:
    - id: system_metrics_kubernetes_container_memory_total
      # Remove the second metric (after OR) when we drop support for K8s 1.13
      # https://gitlab.com/gitlab-org/gitlab/-/issues/229279
      query_range: 'avg(sum(container_memory_usage_bytes{container!="POD",pod=~"^{{ci_environment_slug}}-(.*)",namespace="{{kube_namespace}}"}) by (job)) without (job)  /1024/1024/1024     OR      avg(sum(container_memory_usage_bytes{container_name!="POD",pod_name=~"^{{ci_environment_slug}}-(.*)",namespace="{{kube_namespace}}"}) by (job)) without (job)  /1024/1024/1024'
      label: Total (GB)
      unit: GB
  - title: "Core Usage (Total)"
    type: "area-chart"
    y_label: "Total Cores"
    metrics:
    - id: system_metrics_kubernetes_container_cores_total
      # Remove the second metric (after OR) when we drop support for K8s 1.13
      # https://gitlab.com/gitlab-org/gitlab/-/issues/229279
      query_range: 'avg(sum(rate(container_cpu_usage_seconds_total{container!="POD",pod=~"^{{ci_environment_slug}}-(.*)",namespace="{{kube_namespace}}"}[15m])) by (job)) without (job)     OR      avg(sum(rate(container_cpu_usage_seconds_total{container_name!="POD",pod_name=~"^{{ci_environment_slug}}-(.*)",namespace="{{kube_namespace}}"}[15m])) by (job)) without (job)'
      label: Total (cores)
      unit: "cores"
  - title: "Memory Usage (Pod average)"
    type: "line-chart"
    y_label: "Memory Used per Pod (MB)"
    metrics:
    - id: system_metrics_kubernetes_container_memory_average
      # Remove the second metric (after OR) when we drop support for K8s 1.13
      # https://gitlab.com/gitlab-org/gitlab/-/issues/229279
      query_range: 'avg(sum(container_memory_usage_bytes{container!="POD",pod=~"^{{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!="POD",pod=~"^{{ci_environment_slug}}-([^c].*|c([^a]|a([^n]|n([^a]|a([^r]|r[^y])))).*|)-(.*)",namespace="{{kube_namespace}}"}) without (job)) /1024/1024     OR      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: Pod average (MB)
      unit: MB
  - title: "Canary: Memory Usage (Pod Average)"
    type: "line-chart"
    y_label: "Memory Used per Pod (MB)"
    metrics:
    - id: system_metrics_kubernetes_container_memory_average_canary
      # Remove the second metric (after OR) when we drop support for K8s 1.13
      # https://gitlab.com/gitlab-org/gitlab/-/issues/229279
      query_range: 'avg(sum(container_memory_usage_bytes{container!="POD",pod=~"^{{ci_environment_slug}}-canary-(.*)",namespace="{{kube_namespace}}"}) by (job)) without (job) / count(avg(container_memory_usage_bytes{container!="POD",pod=~"^{{ci_environment_slug}}-canary-(.*)",namespace="{{kube_namespace}}"}) without (job)) /1024/1024     OR      avg(sum(container_memory_usage_bytes{container_name!="POD",pod_name=~"^{{ci_environment_slug}}-canary-(.*)",namespace="{{kube_namespace}}"}) by (job)) without (job) / count(avg(container_memory_usage_bytes{container_name!="POD",pod_name=~"^{{ci_environment_slug}}-canary-(.*)",namespace="{{kube_namespace}}"}) without (job)) /1024/1024'
      label: Pod average (MB)
      unit: MB
      track: canary
  - title: "Core Usage (Pod Average)"
    type: "line-chart"
    y_label: "Cores per Pod"
    metrics:
    - id: system_metrics_kubernetes_container_core_usage
      # Remove the second metric (after OR) when we drop support for K8s 1.13
      # https://gitlab.com/gitlab-org/gitlab/-/issues/229279
      query_range: 'avg(sum(rate(container_cpu_usage_seconds_total{container!="POD",pod=~"^{{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!="POD",pod=~"^{{ci_environment_slug}}-([^c].*|c([^a]|a([^n]|n([^a]|a([^r]|r[^y])))).*|)-(.*)",namespace="{{kube_namespace}}"}[15m])) by (pod))     OR      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: Pod average (cores)
      unit: "cores"
  - title: "Canary: Core Usage (Pod Average)"
    type: "line-chart"
    y_label: "Cores per Pod"
    metrics:
    - id: system_metrics_kubernetes_container_core_usage_canary
      # Remove the second metric (after OR) when we drop support for K8s 1.13
      # https://gitlab.com/gitlab-org/gitlab/-/issues/229279
      query_range: 'avg(sum(rate(container_cpu_usage_seconds_total{container!="POD",pod=~"^{{ci_environment_slug}}-canary-(.*)",namespace="{{kube_namespace}}"}[15m])) by (job)) without (job) / count(sum(rate(container_cpu_usage_seconds_total{container!="POD",pod=~"^{{ci_environment_slug}}-canary-(.*)",namespace="{{kube_namespace}}"}[15m])) by (pod))     OR      avg(sum(rate(container_cpu_usage_seconds_total{container_name!="POD",pod_name=~"^{{ci_environment_slug}}-canary-(.*)",namespace="{{kube_namespace}}"}[15m])) by (job)) without (job) / count(sum(rate(container_cpu_usage_seconds_total{container_name!="POD",pod_name=~"^{{ci_environment_slug}}-canary-(.*)",namespace="{{kube_namespace}}"}[15m])) by (pod_name))'
      label: Pod average (cores)
      unit: "cores"
      track: canary
  - title: "Knative function invocations"
    type: "area-chart"
    y_label: "Invocations"
    metrics:
    - id: system_metrics_knative_function_invocation_count
      query_range: 'sum(ceil(rate(istio_requests_total{destination_service_namespace="{{kube_namespace}}", destination_service=~"{{function_name}}.*"}[1m])*60))'
      label: invocations / minute
      unit: requests
# NGINX Ingress metrics for pre-0.16.0 versions
- group: Response metrics (NGINX Ingress VTS)
  panels:
  - title: "Throughput"
    type: "area-chart"
    y_label: "Requests / Sec"
    metrics:
    - id: response_metrics_nginx_ingress_throughput_status_code
      query_range: 'sum(rate(nginx_upstream_responses_total{upstream=~"{{kube_namespace}}-{{ci_environment_slug}}-.*"}[2m])) by (status_code)'
      unit: req / sec
      label: Status Code
  - title: "Latency"
    type: "area-chart"
    y_label: "Latency (ms)"
    y_axis:
      format: milliseconds
    metrics:
    - id: response_metrics_nginx_ingress_latency_pod_average
      query_range: 'avg(nginx_upstream_response_msecs_avg{upstream=~"{{kube_namespace}}-{{ci_environment_slug}}-.*"})'
      label: Pod average (ms)
      unit: ms
  - title: "HTTP Error Rate"
    type: "area-chart"
    y_label: "HTTP Errors (%)"
    y_axis:
      format: percentHundred
    metrics:
    - id: response_metrics_nginx_ingress_http_error_rate
      query_range: 'sum(rate(nginx_upstream_responses_total{status_code="5xx", upstream=~"{{kube_namespace}}-{{ci_environment_slug}}-.*"}[2m])) / sum(rate(nginx_upstream_responses_total{upstream=~"{{kube_namespace}}-{{ci_environment_slug}}-.*"}[2m])) * 100'
      label: 5xx Errors (%)
      unit: "%"
# NGINX Ingress metrics for post-0.16.0 versions
- group: Response metrics (NGINX Ingress)
  panels:
  - title: "Throughput"
    type: "area-chart"
    y_label: "Requests / Sec"
    metrics:
    - id: response_metrics_nginx_ingress_16_throughput_status_code
      query_range: 'sum(label_replace(rate(nginx_ingress_controller_requests{namespace="{{kube_namespace}}",ingress=~".*{{ci_environment_slug}}.*"}[2m]), "status_code", "${1}xx", "status", "(.)..")) by (status_code)'
      unit: req / sec
      label: Status Code
  - title: "Latency"
    type: "area-chart"
    y_label: "Latency (ms)"
    metrics:
    - id: response_metrics_nginx_ingress_16_latency_pod_average
      query_range: 'sum(rate(nginx_ingress_controller_ingress_upstream_latency_seconds_sum{namespace="{{kube_namespace}}",ingress=~".*{{ci_environment_slug}}.*"}[2m])) / sum(rate(nginx_ingress_controller_ingress_upstream_latency_seconds_count{namespace="{{kube_namespace}}",ingress=~".*{{ci_environment_slug}}.*"}[2m])) * 1000'
      label: Pod average (ms)
      unit: ms
  - title: "HTTP Error Rate"
    type: "area-chart"
    y_label: "HTTP Errors (%)"
    metrics:
    - id: response_metrics_nginx_ingress_16_http_error_rate
      query_range: 'sum(rate(nginx_ingress_controller_requests{status=~"5.*",namespace="{{kube_namespace}}",ingress=~".*{{ci_environment_slug}}.*"}[2m])) / sum(rate(nginx_ingress_controller_requests{namespace="{{kube_namespace}}",ingress=~".*{{ci_environment_slug}}.*"}[2m])) * 100'
      label: 5xx Errors (%)
      unit: "%"
- group: Response metrics (HA Proxy)
  panels:
  - title: "Throughput"
    type: "area-chart"
    y_label: "Requests / Sec"
    metrics:
    - id: response_metrics_ha_proxy_throughput_status_code
      query_range: 'sum(rate(haproxy_frontend_http_requests_total{ {{environment_filter}} }[2m])) by (code)'
      unit: req / sec
      label: Status Code
  - title: "HTTP Error Rate"
    type: "area-chart"
    y_label: "Error Rate (%)"
    metrics:
    - id: response_metrics_ha_proxy_http_error_rate
      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)
  panels:
  - title: "Throughput"
    type: "area-chart"
    y_label: "Requests / Sec"
    metrics:
    - id: response_metrics_aws_elb_throughput_requests
      query_range: 'sum(aws_elb_request_count_sum{ {{environment_filter}} }) / 60'
      label: Total (req/sec)
      unit: req / sec
  - title: "Latency"
    type: "area-chart"
    y_label: "Latency (ms)"
    metrics:
    - id: response_metrics_aws_elb_latency_average
      query_range: 'avg(aws_elb_latency_average{ {{environment_filter}} }) * 1000'
      label: Average (ms)
      unit: ms
  - title: "HTTP Error Rate"
    type: "area-chart"
    y_label: "Error Rate (%)"
    metrics:
    - id: response_metrics_aws_elb_http_error_rate
      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)
  panels:
  - title: "Throughput"
    type: "area-chart"
    y_label: "Requests / Sec"
    metrics:
    - id: response_metrics_nginx_throughput_status_code
      query_range: 'sum(rate(nginx_server_requests{server_zone!="*", server_zone!="_", {{environment_filter}} }[2m])) by (code)'
      unit: req / sec
      label: Status Code
  - title: "Latency"
    type: "area-chart"
    y_label: "Latency (ms)"
    metrics:
    - id: response_metrics_nginx_latency
      query_range: 'avg(nginx_server_requestMsec{ {{environment_filter}} })'
      label: Upstream (ms)
      unit: ms
  - title: "HTTP Error Rate (Errors / Sec)"
    type: "area-chart"
    y_label: "HTTP 500 Errors / Sec"
    y_axis:
      precision: 0
    metrics:
    - id: response_metrics_nginx_http_error_rate
      query_range: 'sum(rate(nginx_server_requests{code="5xx", {{environment_filter}} }[2m]))'
      label: HTTP Errors
      unit: "errors / sec"
  - title: "HTTP Error Rate"
    type: "area-chart"
    y_label: "HTTP Errors (%)"
    metrics:
    - id: response_metrics_nginx_http_error_percentage
      query_range: 'sum(rate(nginx_server_requests{code=~"5.*", host="*", {{environment_filter}} }[2m])) / sum(rate(nginx_server_requests{code="total", host="*", {{environment_filter}} }[2m])) * 100'
      label: 5xx Errors (%)
      unit: "%"