Merge branch...

Merge branch '37644-update-prometheus-metric-library-to-support-multiple-series-and-colors' into 'master'

Update Prometheus Metric Library to support multiple series and colors

Closes #37644

See merge request !14155

config/prometheus/additional_metrics.yml

@@ -4,12 +4,21 @@
   - title: "Throughput"
     y_label: "Requests / Sec"
     required_metrics:
-      - nginx_upstream_requests_total
+      - nginx_upstream_responses_total
     weight: 1
     queries:
-    - query_range: 'sum(rate(nginx_upstream_requests_total{upstream=~"%{kube_namespace}-%{ci_environment_slug}-.*"}[2m]))'
-      label: Total
+    - 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"
     y_label: "Latency (ms)"
     required_metrics:
@@ -37,9 +46,17 @@
       - haproxy_frontend_http_requests_total
     weight: 1
     queries:
-    - query_range: 'sum(rate(haproxy_frontend_http_requests_total{%{environment_filter}}[2m]))'
-      label: Total
+    - query_range: 'sum(rate(haproxy_frontend_http_requests_total{%{environment_filter}}[2m])) by (code)'
       unit: req / sec
+      series:
+        - label: code
+          when:
+            - value: 2xx
+              color: green
+            - value: 4xx
+              color: yellow
+            - value: 5xx
+              color: red
   - title: "HTTP Error Rate"
     y_label: "Error Rate (%)"
     required_metrics:
@@ -86,12 +103,21 @@
   - title: "Throughput"
     y_label: "Requests / Sec"
     required_metrics:
-      - nginx_requests_total
+      - nginx_responses_total
     weight: 1
     queries:
-    - query_range: 'sum(rate(nginx_requests_total{server_zone!="*", server_zone!="_", %{environment_filter}}[2m]))'
-      label: Total
+    - query_range: 'sum(rate(nginx_responses_total{server_zone!="*", server_zone!="_", %{environment_filter}}[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"
     y_label: "Latency (ms)"
     required_metrics:
@@ -128,6 +154,8 @@
      - container_cpu_usage_seconds_total
     weight: 1
     queries:
-    - query_range: 'sum(rate(container_cpu_usage_seconds_total{container_name!="POD",%{environment_filter}}[2m])) / count(container_cpu_usage_seconds_total{container_name!="POD",%{environment_filter}}) * 100'
-      label: Average
+    - query_range: 'sum(rate(container_cpu_usage_seconds_total{container_name!="POD",%{environment_filter}}[2m])) by (cpu)  * 100'
+      label: CPU
       unit: "%"
+      series:
+        - label: cpu

doc/user/project/integrations/prometheus_library/haproxy.md

@@ -7,7 +7,7 @@ GitLab has support for automatically detecting and monitoring HAProxy. This is p
 
 | Name | Query |
 | ---- | ----- |
-| Throughput (req/sec) | sum(rate(haproxy_frontend_http_requests_total{%{environment_filter}}[2m])) |
+| Throughput (req/sec) | sum(rate(haproxy_frontend_http_requests_total{%{environment_filter}}[2m])) by (code) |
 | HTTP Error Rate (%) | sum(rate(haproxy_frontend_http_requests_total{code="5xx",%{environment_filter}}[2m])) / sum(rate(haproxy_frontend_http_requests_total{%{environment_filter}}[2m])) |
 
 ## Configuring Prometheus to monitor for HAProxy metrics

doc/user/project/integrations/prometheus_library/kubernetes.md

@@ -8,7 +8,7 @@ GitLab has support for automatically detecting and monitoring Kubernetes metrics
 | Name | Query |
 | ---- | ----- |
 | Average Memory Usage (MB) | (sum(container_memory_usage_bytes{container_name!="POD",%{environment_filter}}) / count(container_memory_usage_bytes{container_name!="POD",%{environment_filter}})) /1024/1024 |
-| Average CPU Utilization (%) | sum(rate(container_cpu_usage_seconds_total{container_name!="POD",%{environment_filter}}[2m])) / count(container_cpu_usage_seconds_total{container_name!="POD",%{environment_filter}}) * 100 |
+| Average CPU Utilization (%) | sum(rate(container_cpu_usage_seconds_total{container_name!="POD",%{environment_filter}}[2m])) by (cpu)  * 100 |
 
 ## Configuring Prometheus to monitor for Kubernetes node metrics
 

doc/user/project/integrations/prometheus_library/nginx.md

@@ -7,7 +7,7 @@ GitLab has support for automatically detecting and monitoring NGINX. This is pro
 
 | Name | Query |
 | ---- | ----- |
-| Throughput (req/sec) | sum(rate(nginx_requests_total{server_zone!="*", server_zone!="_", %{environment_filter}}[2m])) |
+| Throughput (req/sec) | sum(rate(nginx_responses_total{server_zone!="*", server_zone!="_", %{environment_filter}}[2m])) by (status_code) |
 | Latency (ms) | avg(nginx_upstream_response_msecs_avg{%{environment_filter}}) |
 | HTTP Error Rate (HTTP Errors / sec) | rate(nginx_responses_total{status_code="5xx", %{environment_filter}}[2m])) |
 

doc/user/project/integrations/prometheus_library/nginx_ingress.md

@@ -7,19 +7,33 @@ GitLab has support for automatically detecting and monitoring the Kubernetes NGI
 
 | Name | Query |
 | ---- | ----- |
-| Throughput (req/sec) | sum(rate(nginx_upstream_requests_total{upstream=~"%{kube_namespace}-%{ci_environment_slug}-.*"}[2m])) |
+| Throughput (req/sec) | sum(rate(nginx_upstream_responses_total{upstream=~"%{kube_namespace}-%{ci_environment_slug}-.*"}[2m])) by (status_code) |
 | Latency (ms) | avg(nginx_upstream_response_msecs_avg{upstream=~"%{kube_namespace}-%{ci_environment_slug}-.*"}) |
 | HTTP Error Rate (HTTP Errors / sec) | sum(rate(nginx_upstream_responses_total{status_code="5xx", upstream=~"%{kube_namespace}-%{ci_environment_slug}-.*"}[2m])) |
 
 ## Configuring Prometheus to monitor for NGINX ingress metrics
 
-The easiest way to get started is to use at least version 0.9.0 of [NGINX ingress](https://github.com/kubernetes/ingress/tree/master/controllers/nginx). If you are using NGINX as your Kubernetes ingress, there is [direct support](https://github.com/kubernetes/ingress/pull/423) for enabling Prometheus monitoring in the 0.9.0 release.
+If you have deployed with the [gitlab-omnibus](https://docs.gitlab.com/ee/install/kubernetes/gitlab_omnibus.md) Helm chart, and your application is running in the same cluster, no further action is required. The ingress metrics will be automatically enabled and annotated for Prometheus monitoring. Simply ensure Prometheus monitoring is [enabled for your project](../prometheus.md), which is on by default.
 
-If you have deployed with the [gitlab-omnibus](https://docs.gitlab.com/ee/install/kubernetes/gitlab_omnibus.md) Helm chart, these metrics will be automatically enabled and annotated for Prometheus monitoring.
+For other deployments, there is some configuration required depending on your installation:
+* NGINX Ingress should be version 0.9.0 or above
+* NGINX Ingress should be annotated for Prometheus monitoring
+* Prometheus should be configured to monitor annotated pods
+
+### Configuring NGINX Ingress for Prometheus monitoring
+
+Version 0.9.0 and above of [NGINX ingress](https://github.com/kubernetes/ingress/tree/master/controllers/nginx) have built-in support for exporting Prometheus metrics. To enable, a ConfigMap setting must be passed: `enable-vts-status: "true"`. Once enabled, a Prometheus metrics endpoint will start running on port 10254.
+
+With metric data now available, Prometheus needs to be configured to collect it. The easiest way to do this is to leverage Prometheus' [built-in Kubernetes service discovery](https://prometheus.io/docs/operating/configuration/#kubernetes_sd_config), which automatically detects a variety of Kubernetes components and makes them available for monitoring. NGINX ingress metrics are exposed per pod, a sample scrape configuration [is available](https://github.com/prometheus/prometheus/blob/master/documentation/examples/prometheus-kubernetes.yml#L248). This configuration will detect pods and enable collection of metrics **only if** they have been specifically annotated for monitoring.
+
+Depending on how NGINX ingress was deployed, typically a DaemonSet or Deployment, edit the corresponding YML spec. Two new annotations need to be added:
+* `prometheus.io/port: "true"`
+* `prometheus.io/port: "10254"`
+
+Prometheus should now be collecting NGINX ingress metrics. To validate view the Prometheus Targets, available under `Status > Targets` on the Prometheus dashboard. New entries for NGINX should be listed in the kubernetes pod monitoring job, `kubernetes-pods`.
 
 ## Specifying the Environment label
 
-In order to isolate and only display relevant metrics for a given environment
-however, GitLab needs a method to detect which labels are associated. To do this, GitLab will search metrics with appropriate labels. In this case, the `upstream` label must be of the form `<Kubernetes Namespace>-<CI_ENVIRONMENT_SLUG>-*`.
+In order to isolate and only display relevant metrics for a given environment, GitLab needs a method to detect which labels are associated. To do this, GitLab will search for metrics with appropriate labels. In this case, the `upstream` label must be of the form `<KUBE_NAMESPACE>-<CI_ENVIRONMENT_SLUG>-*`.
 
 If you have used [Auto Deploy](https://docs.gitlab.com/ee/ci/autodeploy/index.html) to deploy your app, this format will be used automatically and metrics will be detected with no action on your part.