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

3 files changed, 88 insertions, 143 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
diff --git a/db/importers/common_metrics_importer.rb b/db/importers/common_metrics_importer.rb
index deadd653ae9..195bde8f34a 100644
--- a/db/importers/common_metrics_importer.rb
+++ b/db/importers/common_metrics_importer.rb
@@ -53,7 +53,7 @@ module Importers
     private
 
     def process_content(&blk)
-      content.map do |group|
+      content['panel_groups'].map do |group|
         process_group(group, &blk)
       end
     end
@@ -63,28 +63,28 @@ module Importers
         group: find_group_title_key(group['group'])
       }
 
-      group['metrics'].map do |metric|
-        process_metric(metric, attributes, &blk)
+      group['panels'].map do |panel|
+        process_panel(panel, attributes, &blk)
       end
     end
 
-    def process_metric(metric, attributes, &blk)
+    def process_panel(panel, attributes, &blk)
       attributes = attributes.merge(
-        title: metric['title'],
-        y_label: metric['y_label'])
+        title: panel['title'],
+        y_label: panel['y_label'])
 
-      metric['queries'].map do |query|
-        process_metric_query(query, attributes, &blk)
+      panel['metrics'].map do |metric_details|
+        process_metric_details(metric_details, attributes, &blk)
       end
     end
 
-    def process_metric_query(query, attributes, &blk)
+    def process_metric_details(metric_details, attributes, &blk)
       attributes = attributes.merge(
-        legend: query['label'],
-        query: query['query_range'],
-        unit: query['unit'])
+        legend: metric_details['label'],
+        query: metric_details['query_range'],
+        unit: metric_details['unit'])
 
-      yield(query['id'], attributes)
+      yield(metric_details['id'], attributes)
     end
 
     def find_or_build_metric!(id)
diff --git a/spec/db/importers/common_metrics_importer_spec.rb b/spec/db/importers/common_metrics_importer_spec.rb
index 6133b17ac61..a717c8cd04d 100644
--- a/spec/db/importers/common_metrics_importer_spec.rb
+++ b/spec/db/importers/common_metrics_importer_spec.rb
@@ -23,10 +23,10 @@ describe Importers::CommonMetricsImporter do
   subject { described_class.new }
 
   context "does import common_metrics.yml" do
-    let(:groups) { subject.content }
-    let(:metrics) { groups.map { |group| group['metrics'] }.flatten }
-    let(:queries) { metrics.map { |group| group['queries'] }.flatten }
-    let(:query_ids) { queries.map { |query| query['id'] } }
+    let(:groups) { subject.content['panel_groups'] }
+    let(:panels) { groups.map { |group| group['panels'] }.flatten }
+    let(:metrics) { panels.map { |group| group['metrics'] }.flatten }
+    let(:metric_ids) { metrics.map { |metric| metric['id'] } }
 
     before do
       subject.execute
@@ -36,20 +36,20 @@ describe Importers::CommonMetricsImporter do
       expect(PrometheusMetric.common.group(:group).count.count).to eq(groups.count)
     end
 
-    it "has the same amount of metrics" do
-      expect(PrometheusMetric.common.group(:group, :title).count.count).to eq(metrics.count)
+    it "has the same amount of panels" do
+      expect(PrometheusMetric.common.group(:group, :title).count.count).to eq(panels.count)
     end
 
-    it "has the same amount of queries" do
-      expect(PrometheusMetric.common.count).to eq(queries.count)
+    it "has the same amount of metrics" do
+      expect(PrometheusMetric.common.count).to eq(metrics.count)
     end
 
     it "does not have duplicate IDs" do
-      expect(query_ids).to eq(query_ids.uniq)
+      expect(metric_ids).to eq(metric_ids.uniq)
     end
 
     it "imports all IDs" do
-      expect(PrometheusMetric.common.pluck(:identifier)).to contain_exactly(*query_ids)
+      expect(PrometheusMetric.common.pluck(:identifier)).to contain_exactly(*metric_ids)
     end
   end
 
@@ -65,24 +65,26 @@ describe Importers::CommonMetricsImporter do
 
   context 'does import properly all fields' do
     let(:query_identifier) { 'response-metric' }
-    let(:group) do
+    let(:dashboard) do
       {
-        group: 'Response metrics (NGINX Ingress)',
-        metrics: [{
-          title: "Throughput",
-          y_label: "Requests / Sec",
-          queries: [{
-            id: query_identifier,
-            query_range: 'my-query',
-            unit: 'my-unit',
-            label: 'status code'
+        panel_groups: [{
+          group: 'Response metrics (NGINX Ingress)',
+          panels: [{
+            title: "Throughput",
+            y_label: "Requests / Sec",
+            metrics: [{
+              id: query_identifier,
+              query_range: 'my-query',
+              unit: 'my-unit',
+              label: 'status code'
+            }]
           }]
         }]
       }
     end
 
     before do
-      expect(subject).to receive(:content) { [group.deep_stringify_keys] }
+      expect(subject).to receive(:content) { dashboard.deep_stringify_keys }
     end
 
     shared_examples 'stores metric' do