Merge branch...

Merge branch '206899-move-system-metrics-chart-group-to-the-top-of-the-default-dashbord-in-metrics' into 'master'

Move System Metrics chart group to the top of Default dashboard

See merge request gitlab-org/gitlab!26355

changelogs/unreleased/206899-move-system-metrics-chart-group-to-the-top-of-the-default-dashbord.yml

+---
+title: Put System Metrics chart group first in default dashboard
+merge_request: 26355
+author:
+type: other

config/prometheus/common_metrics.yml

 dashboard: 'Environment metrics'
 priority: 1
 panel_groups:
+- group: System metrics (Kubernetes)
+  priority: 15
+  panels:
+  - title: "Memory Usage (Total)"
+    type: "area-chart"
+    y_label: "Total Memory Used (GB)"
+    weight: 4
+    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 (GB)
+      unit: GB
+  - title: "Core Usage (Total)"
+    type: "area-chart"
+    y_label: "Total Cores"
+    weight: 3
+    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 (cores)
+      unit: "cores"
+  - title: "Memory Usage (Pod average)"
+    type: "line-chart"
+    y_label: "Memory Used per Pod (MB)"
+    weight: 2
+    metrics:
+    - id: system_metrics_kubernetes_container_memory_average
+      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: Pod average (MB)
+      unit: MB
+  - title: "Canary: Memory Usage (Pod Average)"
+    type: "line-chart"
+    y_label: "Memory Used per Pod (MB)"
+    weight: 2
+    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 (MB)
+      unit: MB
+      track: canary
+  - title: "Core Usage (Pod Average)"
+    type: "line-chart"
+    y_label: "Cores per Pod"
+    weight: 1
+    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}-([^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"
+    weight: 1
+    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 (cores)
+      unit: "cores"
+      track: canary
+  - title: "Knative function invocations"
+    type: "area-chart"
+    y_label: "Invocations"
+    weight: 1
+    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)
   priority: 10
@@ -150,79 +218,3 @@ panel_groups:
       query_range: 'sum(rate(nginx_server_requests{code="5xx", %{environment_filter}}[2m]))'
       label: HTTP Errors
       unit: "errors / sec"
-- group: System metrics (Kubernetes)
-  priority: 5
-  panels:
-  - title: "Memory Usage (Total)"
-    type: "area-chart"
-    y_label: "Total Memory Used (GB)"
-    y_axis:
-      format: "gibibytes"
-    weight: 4
-    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 (GB)
-      unit: GB
-  - title: "Core Usage (Total)"
-    type: "area-chart"
-    y_label: "Total Cores"
-    weight: 3
-    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 (cores)
-      unit: "cores"
-  - title: "Memory Usage (Pod average)"
-    type: "line-chart"
-    y_label: "Memory Used per Pod (MB)"
-    y_axis:
-      format: "mebibytes"
-    weight: 2
-    metrics:
-    - id: system_metrics_kubernetes_container_memory_average
-      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: Pod average (MB)
-      unit: MB
-  - title: "Canary: Memory Usage (Pod Average)"
-    type: "line-chart"
-    y_label: "Memory Used per Pod (MB)"
-    y_axis:
-      format: "mebibytes"
-    weight: 2
-    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 (MB)
-      unit: MB
-      track: canary
-  - title: "Core Usage (Pod Average)"
-    type: "line-chart"
-    y_label: "Cores per Pod"
-    weight: 1
-    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}-([^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"
-    weight: 1
-    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 (cores)
-      unit: "cores"
-      track: canary
-  - title: "Knative function invocations"
-    type: "area-chart"
-    y_label: "Invocations"
-    y_axis:
-      precision: 0
-    weight: 1
-    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

spec/frontend/monitoring/components/charts/time_series_spec.js

@@ -69,7 +69,7 @@ describe('Time series component', () => {
         mockedQueryResultFixture,
       );
       // dashboard is a dynamically generated fixture and stored at environment_metrics_dashboard.json
-      [mockGraphData] = store.state.monitoringDashboard.dashboard.panelGroups[0].panels;
+      [mockGraphData] = store.state.monitoringDashboard.dashboard.panelGroups[1].panels;
     });
 
     describe('general functions', () => {

spec/frontend/monitoring/store/getters_spec.js

@@ -89,8 +89,8 @@ describe('Monitoring store Getters', () => {
         expect(getMetricStates()).toEqual([metricStates.OK]);
 
         // Filtered by groups
-        expect(getMetricStates(state.dashboard.panelGroups[0].key)).toEqual([metricStates.OK]);
-        expect(getMetricStates(state.dashboard.panelGroups[1].key)).toEqual([]);
+        expect(getMetricStates(state.dashboard.panelGroups[1].key)).toEqual([metricStates.OK]);
+        expect(getMetricStates(state.dashboard.panelGroups[2].key)).toEqual([]);
       });
       it('on multiple metrics errors', () => {
         mutations[types.RECEIVE_METRICS_DATA_SUCCESS](state, metricsDashboardPayload);
@@ -118,18 +118,18 @@ describe('Monitoring store Getters', () => {
         mutations[types.RECEIVE_METRIC_RESULT_SUCCESS](state, mockedQueryResultFixture);
         // An error in 2 groups
         mutations[types.RECEIVE_METRIC_RESULT_FAILURE](state, {
-          metricId: groups[0].panels[1].metrics[0].metricId,
+          metricId: groups[1].panels[1].metrics[0].metricId,
         });
         mutations[types.RECEIVE_METRIC_RESULT_FAILURE](state, {
-          metricId: groups[1].panels[0].metrics[0].metricId,
+          metricId: groups[2].panels[0].metrics[0].metricId,
         });
 
         expect(getMetricStates()).toEqual([metricStates.OK, metricStates.UNKNOWN_ERROR]);
-        expect(getMetricStates(groups[0].key)).toEqual([
+        expect(getMetricStates(groups[1].key)).toEqual([
           metricStates.OK,
           metricStates.UNKNOWN_ERROR,
         ]);
-        expect(getMetricStates(groups[1].key)).toEqual([metricStates.UNKNOWN_ERROR]);
+        expect(getMetricStates(groups[2].key)).toEqual([metricStates.UNKNOWN_ERROR]);
       });
     });
   });
@@ -210,13 +210,13 @@ describe('Monitoring store Getters', () => {
         mutations[types.RECEIVE_METRIC_RESULT_SUCCESS](state, mockedQueryResultFixtureStatusCode);
 
         // First group has metrics
-        expect(metricsWithData(state.dashboard.panelGroups[0].key)).toEqual([
+        expect(metricsWithData(state.dashboard.panelGroups[1].key)).toEqual([
           mockedQueryResultFixture.metricId,
           mockedQueryResultFixtureStatusCode.metricId,
         ]);
 
         // Second group has no metrics
-        expect(metricsWithData(state.dashboard.panelGroups[1].key)).toEqual([]);
+        expect(metricsWithData(state.dashboard.panelGroups[2].key)).toEqual([]);
       });
     });
   });

spec/frontend/monitoring/store/mutations_spec.js

@@ -32,12 +32,13 @@ describe('Monitoring mutations', () => {
       mutations[types.RECEIVE_METRICS_DATA_SUCCESS](stateCopy, payload);
       const groups = getGroups();
 
-      expect(groups[0].key).toBe('response-metrics-nginx-ingress-vts-0');
-      expect(groups[1].key).toBe('response-metrics-nginx-ingress-1');
+      expect(groups[0].key).toBe('system-metrics-kubernetes-0');
+      expect(groups[1].key).toBe('response-metrics-nginx-ingress-vts-1');
+      expect(groups[2].key).toBe('response-metrics-nginx-ingress-2');
     });
     it('normalizes values', () => {
       mutations[types.RECEIVE_METRICS_DATA_SUCCESS](stateCopy, payload);
-      const expectedLabel = '5xx Errors (%)';
+      const expectedLabel = 'Pod average (MB)';
 
       const { label, queryRange } = getGroups()[0].panels[2].metrics[0];
       expect(label).toEqual(expectedLabel);
@@ -51,7 +52,7 @@ describe('Monitoring mutations', () => {
       expect(groups).toBeDefined();
       expect(groups).toHaveLength(6);
 
-      expect(groups[0].panels).toHaveLength(3);
+      expect(groups[0].panels).toHaveLength(7);
       expect(groups[0].panels[0].metrics).toHaveLength(1);
       expect(groups[0].panels[1].metrics).toHaveLength(1);
       expect(groups[0].panels[2].metrics).toHaveLength(1);
@@ -65,9 +66,12 @@ describe('Monitoring mutations', () => {
       const groups = getGroups();
 
       expect(groups[0].panels[0].metrics[0].metricId).toEqual(
-        'undefined_response_metrics_nginx_ingress_throughput_status_code',
+        'undefined_system_metrics_kubernetes_container_memory_total',
       );
       expect(groups[1].panels[0].metrics[0].metricId).toEqual(
+        'undefined_response_metrics_nginx_ingress_throughput_status_code',
+      );
+      expect(groups[2].panels[0].metrics[0].metricId).toEqual(
         'undefined_response_metrics_nginx_ingress_16_throughput_status_code',
       );
     });
@@ -135,7 +139,7 @@ describe('Monitoring mutations', () => {
       },
     ];
     const dashboard = metricsDashboardPayload;
-    const getMetric = () => stateCopy.dashboard.panelGroups[0].panels[0].metrics[0];
+    const getMetric = () => stateCopy.dashboard.panelGroups[1].panels[0].metrics[0];
 
     describe('REQUEST_METRIC_RESULT', () => {
       beforeEach(() => {

spec/support/shared_examples/services/metrics/dashboard_shared_examples.rb

@@ -67,6 +67,7 @@ RSpec.shared_examples 'valid dashboard cloning process' do |dashboard_template,
 
     it 'delegates commit creation to Files::CreateService', :aggregate_failures do
       service_instance = instance_double(::Files::CreateService)
+      allow(::Gitlab::Metrics::Dashboard::Processor).to receive(:new).and_return(double(process: file_content_hash))
       expect(::Files::CreateService).to receive(:new).with(project, user, dashboard_attrs).and_return(service_instance)
       expect(service_instance).to receive(:execute).and_return(status: :success)