Add inital dashboard endpoint support

2 files changed, 275 insertions, 0 deletions

diff --git a/config/prometheus/system_dashboard.yml b/config/prometheus/system_dashboard.yml
new file mode 100644
index 00000000000..694d6531034
--- /dev/null
+++ b/config/prometheus/system_dashboard.yml
@@ -0,0 +1,274 @@
+dashboard: 'System Metrics'
+order: 0
+panel_groups:
+  # NGINX Ingress metrics for pre-0.16.0 versions
+  - group: Response metrics (NGINX Ingress VTS)
+    priority: 10
+    panels:
+    - type: area-chart
+      title: "Throughput"
+      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
+        required_metrics:
+          - nginx_upstream_responses_total
+        series:
+          - label: status_code
+            when:
+              - value: 2xx
+                color: green
+              - value: 4xx
+                color: orange
+              - value: 5xx
+                color: red
+    - type: area-chart
+      title: "Latency"
+      y_label: "Latency (ms)"
+      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
+        required_metrics:
+          - nginx_upstream_response_msecs_avg
+    - type: area-chart
+      title: "HTTP Error Rate"
+      y_label: "HTTP Errors"
+      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: "%"
+        required_metrics:
+          - nginx_upstream_responses_total
+  # NGINX Ingress metrics for post-0.16.0 versions
+  - group: Response metrics (NGINX Ingress)
+    priority: 10
+    panels:
+    - type: area-chart
+      title: "Throughput"
+      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
+        required_metrics:
+          - nginx_ingress_controller_requests
+        label: Status Code
+        series:
+          - label: status_code
+            when:
+              - value: 2xx
+                color: green
+              - value: 3xx
+                color: blue
+              - value: 4xx
+                color: orange
+              - value: 5xx
+                color: red
+    - type: area-chart
+      title: "Latency"
+      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
+        unit: ms
+        required_metrics:
+          - nginx_ingress_controller_ingress_upstream_latency_seconds_sum
+    - type: area-chart
+      title: "HTTP Error Rate"
+      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: "%"
+        required_metrics:
+          - nginx_ingress_controller_requests
+  - group: Response metrics (HA Proxy)
+    priority: 10
+    panels:
+    - type: area-chart
+      title: "Throughput"
+      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
+        required_metrics:
+          - haproxy_frontend_http_requests_total
+        series:
+          - label: status_code
+            when:
+              - value: 2xx
+                color: green
+              - value: 4xx
+                color: yellow
+              - value: 5xx
+                color: red
+    - type: area-chart
+      title: "HTTP Error Rate"
+      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: "%"
+        required_metrics:
+          - haproxy_frontend_http_responses_total
+  - group: Response metrics (AWS ELB)
+    priority: 10
+    panels:
+    - type: area-chart
+      title: "Throughput"
+      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
+        unit: req / sec
+        required_metrics:
+          - aws_elb_request_count_sum
+    - type: area-chart
+      title: "Latency"
+      y_label: "Latency (ms)"
+      metrics:
+      - id: response_metrics_aws_elb_latency_average
+        query_range: 'avg(aws_elb_latency_average{%{environment_filter}}) * 1000'
+        label: Average
+        unit: ms
+        required_metrics:
+          - aws_elb_latency_average
+    - type: area-chart
+      title: "HTTP Error Rate"
+      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: "%"
+        required_metrics:
+          - aws_elb_request_count_sum
+          - aws_elb_httpcode_backend_5_xx_sum
+  - group: Response metrics (NGINX)
+    priority: 10
+    panels:
+    - type: area-chart
+      title: "Throughput"
+      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
+        required_metrics:
+          - nginx_server_requests
+        label: Status Code
+        series:
+          - label: status_code
+            when:
+              - value: 2xx
+                color: green
+              - value: 4xx
+                color: orange
+              - value: 5xx
+                color: red
+    - type: area-chart
+      title: "Latency"
+      y_label: "Latency (ms)"
+      metrics:
+      - id: response_metrics_nginx_latency
+        query_range: 'avg(nginx_server_requestMsec{%{environment_filter}})'
+        label: Upstream
+        unit: ms
+        required_metrics:
+          - nginx_server_requestMsec
+    - type: area-chart
+      title: "HTTP Error Rate"
+      y_label: "HTTP 500 Errors / Sec"
+      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"
+        required_metrics:
+          - nginx_server_requests
+  - group: System metrics (Kubernetes)
+    priority: 5
+    panels:
+    - type: area-chart
+      title: "Memory Usage (Total)"
+      y_label: "Total Memory Used"
+      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
+        required_metrics:
+          - container_memory_usage_bytes
+    - type: area-chart
+      title: "Core Usage (Total)"
+      y_label: "Total Cores"
+      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"
+        required_metrics:
+         - container_cpu_usage_seconds_total
+    - type: area-chart
+      title: "Memory Usage (Pod Average)"
+      y_label: "Memory Used per Pod"
+      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
+        unit: MB
+        required_metrics:
+          - container_memory_usage_bytes
+    - type: area-chart
+      title: "Canary: Memory Usage (Pod Average)"
+      y_label: "Memory Used per Pod"
+      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
+        required_metrics:
+          - container_memory_usage_bytes
+        track: canary
+    - type: area-chart
+      title: "Core Usage (Pod Average)"
+      y_label: "Cores per Pod"
+      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
+        unit: "cores"
+        required_metrics:
+         - container_cpu_usage_seconds_total
+    - type: area-chart
+      title: "Canary: Core Usage (Pod Average)"
+      y_label: "Cores per Pod"
+      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
+        required_metrics:
+         - container_cpu_usage_seconds_total
+    - type: area-chart
+      title: "Knative function invocations"
+      y_label: "Invocations"
+      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])*30))'
+        label: invocations / minute
+        unit: requests
+        required_metrics:
+        - istio_revision_request_count
diff --git a/config/routes/project.rb b/config/routes/project.rb
index 93d168fc595..f7841bbe595 100644
--- a/config/routes/project.rb
+++ b/config/routes/project.rb
@@ -218,6 +218,7 @@ constraints(::Constraints::ProjectUrlConstrainer.new) do
           get :terminal
           get :metrics
           get :additional_metrics
+          get :metrics_dashboard
           get '/terminal.ws/authorize', to: 'environments#terminal_websocket_authorize', constraints: { format: nil }
 
           get '/prometheus/api/v1/*proxy_path', to: 'environments/prometheus_api#proxy'