Merge branch 'ee-43670-improve-gitlab-kubernetes-cpu-metrics' into 'master'

Update Kubernetes CPU/Memory Prometheus queries

See merge request gitlab-org/gitlab-ee!4771

config/prometheus/additional_metrics.yml

@@ -140,28 +140,28 @@
   priority: 5
   metrics:
   - title: "Memory Usage"
-    y_label: "Memory Usage (MB)"
+    y_label: "Memory Used per Pod"
     required_metrics:
       - container_memory_usage_bytes
     weight: 1
     queries:
-    - query_range: '(sum(avg(container_memory_usage_bytes{container_name!="POD",environment="%{ci_environment_slug}"}) without (job))) / count(avg(container_memory_usage_bytes{container_name!="POD",environment="%{ci_environment_slug}"}) without (job)) /1024/1024'
+    - 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: Average
       unit: MB
-    - query_range: '(sum(avg(container_memory_usage_bytes{container_name!="POD",environment="%{ci_environment_slug}-canary"}) without (job))) / count(avg(container_memory_usage_bytes{container_name!="POD",environment="%{ci_environment_slug}-canary"}) without (job)) /1024/1024'
+    - 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: Average
       unit: MB
       track: canary
-  - title: "CPU Utilization"
-    y_label: "CPU Utilization (%)"
+  - title: "CPU Usage"
+    y_label: "Cores per Pod"
     required_metrics:
      - container_cpu_usage_seconds_total
     weight: 1
     queries:
-    - query_range: 'sum(avg(rate(container_cpu_usage_seconds_total{container_name!="POD",environment="%{ci_environment_slug}"}[2m])) without (job)) * 100'
+    - 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: Average
-      unit: "%"
-    - query_range: 'sum(avg(rate(container_cpu_usage_seconds_total{container_name!="POD",environment="%{ci_environment_slug}-canary"}[2m])) without (job)) * 100'
+      unit: "cores"
+    - 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: Average
-      unit: "%"
+      unit: "cores"
       track: canary

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

@@ -13,16 +13,15 @@ integration services must be enabled.
 
 | Name | Query |
 | ---- | ----- |
-| Average Memory Usage (MB) | (sum(avg(container_memory_usage_bytes{container_name!="POD",environment="%{ci_environment_slug}"}) without (job))) / count(avg(container_memory_usage_bytes{container_name!="POD",environment="%{ci_environment_slug}"}) without (job)) /1024/1024 |
-| Average CPU Utilization (%) | sum(avg(rate(container_cpu_usage_seconds_total{container_name!="POD",environment="%{ci_environment_slug}"}[2m])) without (job)) * 100 |
+| Average Memory Usage (MB) | 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 |
+| Average CPU Utilization (%) | 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)) |
 
-## Configuring Prometheus to monitor for Kubernetes node metrics
+## Configuring Prometheus to monitor for Kubernetes metrics
 
-In order for Prometheus to collect Kubernetes metrics, you first must have a
-Prometheus server up and running. You have two options here:
+Prometheus needs to be deployed into the cluster and configured properly in order to gather Kubernetes metrics. GitLab supports two methods for doing so:
 
-- If you have an Omnibus based GitLab installation within your Kubernetes cluster, you can leverage the bundled Prometheus server to [monitor Kubernetes](../../../../administration/monitoring/prometheus/index.md#configuring-prometheus-to-monitor-kubernetes).
-- To configure your own Prometheus server, you can follow the [Prometheus documentation](https://prometheus.io/docs/introduction/overview/) or [our guide](../../../../administration/monitoring/prometheus/index.md#configuring-your-own-prometheus-server-within-kubernetes).
+- GitLab [integrates with Kubernetes](../../clusters/index.md), and can [deploy Prometheus into a connected cluster](../prometheus.html#managed-prometheus-on-kubernetes). It is automatically configured to collect Kubernetes metrics.
+- To configure your own Prometheus server, you can follow the [Prometheus documentation](https://prometheus.io/docs/introduction/overview/).
 
 ## Specifying the Environment
 
@@ -30,19 +29,17 @@ In order to isolate and only display relevant CPU and Memory metrics for a given
 
 Instead, the [Deployment](https://kubernetes.io/docs/concepts/workloads/controllers/deployment/) or [DaemonSet](https://kubernetes.io/docs/concepts/workloads/controllers/daemonset/) name should begin with [CI_ENVIRONMENT_SLUG](../../../../ci/variables/README.md#predefined-variables-environment-variables). It can be followed by a `-` and additional content if desired. For example, a deployment name of `review-homepage-5620p5` would match the `review/homepage` environment.
 
-If you are using [GitLab Auto-Deploy](../../../../ci/autodeploy/index.md) and one of the two [provided Kubernetes monitoring solutions](../prometheus.md#getting-started-with-prometheus-monitoring), the `environment` label will be automatically added.
-
 ## Displaying Canary metrics
 
 > Introduced in [GitLab 10.2](https://gitlab.com/gitlab-org/gitlab-ce/merge_requests/15201).
 
 GitLab also gathers Kubernetes metrics for [canary deployments](../../canary_deployments.md), allowing easy comparison between the current deployed version and the canary.
 
-These metrics expect an `environment` label of the form `$CI_ENVIRONMENT_SLUG-canary` to isolate the canary metrics. If you are using [GitLab Auto-Deploy](../../../../ci/autodeploy/index.md), this label will be automatically configured for you.
+These metrics expect the [Deployment](https://kubernetes.io/docs/concepts/workloads/controllers/deployment/) or [DaemonSet](https://kubernetes.io/docs/concepts/workloads/controllers/daemonset/) name to begin with `$CI_ENVIRONMENT_SLUG-canary`, to isolate the canary metrics. 
 
 ### Canary metrics supported
 
 | Name | Query |
 | ---- | ----- |
-| Average Memory Usage (MB) | (sum(avg(container_memory_usage_bytes{container_name!="POD",environment="%{ci_environment_slug}-canary"}) without (job))) / count(avg(container_memory_usage_bytes{container_name!="POD",environment="%{ci_environment_slug}-canary"}) without (job)) /1024/1024 |
-| Average CPU Utilization (%) | sum(avg(rate(container_cpu_usage_seconds_total{container_name!="POD",environment="%{ci_environment_slug}-canary"}[2m])) without (job)) * 100 |
+| Average Memory Usage (MB) | 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 |
+| Average CPU Utilization (%) | 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)) |