Merge branch '60383-change-common-metrics-schema' into 'master'

Change the schema of common_metrics.yml

Closes #60383

See merge request gitlab-org/gitlab-ce!27283

1 files changed, 52 insertions, 109 deletions

diff --git a/config/prometheus/common_metrics.yml b/config/prometheus/common_metrics.yml
index 356f573c5e9..3c67ca36791 100644
--- a/config/prometheus/common_metrics.yml
+++ b/config/prometheus/common_metrics.yml
@@ -1,42 +1,33 @@
-  # NGINX Ingress metrics for pre-0.16.0 versions
+dashboard: 'Environment metrics'
+priority: 1
+panel_groups:
+# NGINX Ingress metrics for pre-0.16.0 versions
 - group: Response metrics (NGINX Ingress VTS)
   priority: 10
-  metrics:
+  panels:
   - title: "Throughput"
+    type: "area-chart"
     y_label: "Requests / Sec"
-    required_metrics:
-      - nginx_upstream_responses_total
     weight: 1
-    queries:
+    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
-      series:
-        - label: status_code
-          when:
-            - value: 2xx
-              color: green
-            - value: 4xx
-              color: orange
-            - value: 5xx
-              color: red
   - title: "Latency"
+    type: "area-chart"
     y_label: "Latency (ms)"
-    required_metrics:
-      - nginx_upstream_response_msecs_avg
     weight: 1
-    queries:
+    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
       unit: ms
   - title: "HTTP Error Rate"
+    type: "area-chart"
     y_label: "HTTP Errors"
-    required_metrics:
-      - nginx_upstream_responses_total
     weight: 1
-    queries:
+    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
@@ -44,227 +35,179 @@
 # NGINX Ingress metrics for post-0.16.0 versions
 - group: Response metrics (NGINX Ingress)
   priority: 10
-  metrics:
+  panels:
   - title: "Throughput"
+    type: "area-chart"
     y_label: "Requests / Sec"
-    required_metrics:
-      - nginx_ingress_controller_requests
     weight: 1
-    queries:
+    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
-      series:
-        - label: status_code
-          when:
-            - value: 2xx
-              color: green
-            - value: 3xx
-              color: blue
-            - value: 4xx
-              color: orange
-            - value: 5xx
-              color: red
   - title: "Latency"
+    type: "area-chart"
     y_label: "Latency (ms)"
-    required_metrics:
-      - nginx_ingress_controller_ingress_upstream_latency_seconds_sum
     weight: 1
-    queries:
+    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
       unit: ms
   - title: "HTTP Error Rate"
+    type: "area-chart"
     y_label: "HTTP Errors"
-    required_metrics:
-      - nginx_ingress_controller_requests
     weight: 1
-    queries:
+    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)
   priority: 10
-  metrics:
+  panels:
   - title: "Throughput"
+    type: "area-chart"
     y_label: "Requests / Sec"
-    required_metrics:
-      - haproxy_frontend_http_requests_total
     weight: 1
-    queries:
+    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
-      series:
-        - label: status_code
-          when:
-            - value: 2xx
-              color: green
-            - value: 4xx
-              color: yellow
-            - value: 5xx
-              color: red
   - title: "HTTP Error Rate"
+    type: "area-chart"
     y_label: "Error Rate (%)"
-    required_metrics:
-      - haproxy_frontend_http_responses_total
     weight: 1
-    queries:
+    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)
   priority: 10
-  metrics:
+  panels:
   - title: "Throughput"
+    type: "area-chart"
     y_label: "Requests / Sec"
-    required_metrics:
-      - aws_elb_request_count_sum
     weight: 1
-    queries:
+    metrics:
     - id: response_metrics_aws_elb_throughput_requests
       query_range: 'sum(aws_elb_request_count_sum{%{environment_filter}}) / 60'
       label: Total
       unit: req / sec
   - title: "Latency"
+    type: "area-chart"
     y_label: "Latency (ms)"
-    required_metrics:
-      - aws_elb_latency_average
     weight: 1
-    queries:
+    metrics:
     - id: response_metrics_aws_elb_latency_average
       query_range: 'avg(aws_elb_latency_average{%{environment_filter}}) * 1000'
       label: Average
       unit: ms
   - title: "HTTP Error Rate"
+    type: "area-chart"
     y_label: "Error Rate (%)"
-    required_metrics:
-      - aws_elb_request_count_sum
-      - aws_elb_httpcode_backend_5_xx_sum
     weight: 1
-    queries:
+    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)
   priority: 10
-  metrics:
+  panels:
   - title: "Throughput"
+    type: "area-chart"
     y_label: "Requests / Sec"
-    required_metrics:
-      - nginx_server_requests
     weight: 1
-    queries:
+    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
-      series:
-        - label: status_code
-          when:
-            - value: 2xx
-              color: green
-            - value: 4xx
-              color: orange
-            - value: 5xx
-              color: red
   - title: "Latency"
+    type: "area-chart"
     y_label: "Latency (ms)"
-    required_metrics:
-      - nginx_server_requestMsec
     weight: 1
-    queries:
+    metrics:
     - id: response_metrics_nginx_latency
       query_range: 'avg(nginx_server_requestMsec{%{environment_filter}})'
       label: Upstream
       unit: ms
   - title: "HTTP Error Rate"
+    type: "area-chart"
     y_label: "HTTP 500 Errors / Sec"
-    required_metrics:
-      - nginx_server_requests
     weight: 1
-    queries:
+    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"
 - group: System metrics (Kubernetes)
   priority: 5
-  metrics:
+  panels:
   - title: "Memory Usage (Total)"
+    type: "area-chart"
     y_label: "Total Memory Used"
-    required_metrics:
-      - container_memory_usage_bytes
     weight: 4
-    queries:
+    metrics:
     - id: system_metrics_kubernetes_container_memory_total
       query_range: '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
       unit: GB
   - title: "Core Usage (Total)"
+    type: "area-chart"
     y_label: "Total Cores"
-    required_metrics:
-     - container_cpu_usage_seconds_total
     weight: 3
-    queries:
+    metrics:
     - id: system_metrics_kubernetes_container_cores_total
       query_range: '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
       unit: "cores"
   - title: "Memory Usage (Pod average)"
+    type: "area-chart"
     y_label: "Memory Used per Pod"
-    required_metrics:
-      - container_memory_usage_bytes
     weight: 2
-    queries:
+    metrics:
     - id: system_metrics_kubernetes_container_memory_average
       query_range: 'avg(sum(container_memory_usage_bytes{container_name!="POD",pod_name=~"^%{ci_environment_slug}-(.*)",namespace="%{kube_namespace}"}) by (job)) without (job) / count(avg(container_memory_usage_bytes{container_name!="POD",pod_name=~"^%{ci_environment_slug}-(.*)",namespace="%{kube_namespace}"}) without (job)) /1024/1024'
       label: Pod average
       unit: MB
   - title: "Canary: Memory Usage (Pod Average)"
+    type: "area-chart"
     y_label: "Memory Used per Pod"
-    required_metrics:
-      - container_memory_usage_bytes
     weight: 2
-    queries:
+    metrics:
     - id: system_metrics_kubernetes_container_memory_average_canary
       query_range: '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
       unit: MB
       track: canary
   - title: "Core Usage (Pod Average)"
+    type: "area-chart"
     y_label: "Cores per Pod"
-    required_metrics:
-     - container_cpu_usage_seconds_total
     weight: 1
-    queries:
+    metrics:
     - id: system_metrics_kubernetes_container_core_usage
       query_range: 'avg(sum(rate(container_cpu_usage_seconds_total{container_name!="POD",pod_name=~"^%{ci_environment_slug}-(.*)",namespace="%{kube_namespace}"}[15m])) by (job)) without (job) / count(sum(rate(container_cpu_usage_seconds_total{container_name!="POD",pod_name=~"^%{ci_environment_slug}-(.*)",namespace="%{kube_namespace}"}[15m])) by (pod_name))'
       label: Pod average
       unit: "cores"
   - title: "Canary: Core Usage (Pod Average)"
+    type: "area-chart"
     y_label: "Cores per Pod"
-    required_metrics:
-     - container_cpu_usage_seconds_total
     weight: 1
-    queries:
+    metrics:
     - id: system_metrics_kubernetes_container_core_usage_canary
       query_range: '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
       unit: "cores"
       track: canary
   - title: "Knative function invocations"
+    type: "area-chart"
     y_label: "Invocations"
-    required_metrics:
-    - istio_revision_request_count
     weight: 1
-    queries:
+    metrics:
     - id: system_metrics_knative_function_invocation_count
       query_range: 'floor(sum(rate(istio_revision_request_count{destination_configuration="%{function_name}", destination_namespace="%{kube_namespace}"}[1m])/3))'
       label: invocations / minute