Merge pull request #598 from Ygnas/gateway-api-state-metrics

Gateway api state metrics

config/prometheus-for-federation/grafana_deployment_patch.yaml

@@ -22,3 +22,87 @@
   value:
     name: grafana-mgc-metrics
     mountPath: /grafana-dashboard-definitions/0/grafana-mgc-metrics
+- op: add
+  path: /spec/template/spec/volumes/-
+  value:
+    name: grafana-gatewayclasses
+    configMap:
+     defaultMode: 420
+     name: grafana-gatewayclasses
+- op: add
+  path: /spec/template/spec/volumes/-
+  value:
+    name: grafana-gateways
+    configMap:
+     defaultMode: 420
+     name: grafana-gateways
+- op: add
+  path: /spec/template/spec/volumes/-
+  value:
+    name: grafana-httproutes
+    configMap:
+     defaultMode: 420
+     name: grafana-httproutes
+- op: add
+  path: /spec/template/spec/volumes/-
+  value:
+    name: grafana-grpcroutes
+    configMap:
+     defaultMode: 420
+     name: grafana-grpcroutes
+- op: add
+  path: /spec/template/spec/volumes/-
+  value:
+    name: grafana-tlsroutes
+    configMap:
+     defaultMode: 420
+     name: grafana-tlsroutes
+- op: add
+  path: /spec/template/spec/volumes/-
+  value:
+    name: grafana-tcproutes
+    configMap:
+     defaultMode: 420
+     name: grafana-tcproutes
+- op: add
+  path: /spec/template/spec/volumes/-
+  value:
+    name: grafana-udproutes
+    configMap:
+     defaultMode: 420
+     name: grafana-udproutes
+- op: add
+  path: /spec/template/spec/containers/0/volumeMounts/-
+  value:
+    name: grafana-gatewayclasses
+    mountPath: /grafana-dashboard-definitions/0/grafana-gatewayclasses
+- op: add
+  path: /spec/template/spec/containers/0/volumeMounts/-
+  value:
+    name: grafana-gateways
+    mountPath: /grafana-dashboard-definitions/0/grafana-gateways
+- op: add
+  path: /spec/template/spec/containers/0/volumeMounts/-
+  value:
+    name: grafana-httproutes
+    mountPath: /grafana-dashboard-definitions/0/grafana-httproutes
+- op: add
+  path: /spec/template/spec/containers/0/volumeMounts/-
+  value:
+    name: grafana-grpcroutes
+    mountPath: /grafana-dashboard-definitions/0/grafana-grpcroutes
+- op: add
+  path: /spec/template/spec/containers/0/volumeMounts/-
+  value:
+    name: grafana-tlsroutes
+    mountPath: /grafana-dashboard-definitions/0/grafana-tlsroutes
+- op: add
+  path: /spec/template/spec/containers/0/volumeMounts/-
+  value:
+    name: grafana-tcproutes
+    mountPath: /grafana-dashboard-definitions/0/grafana-tcpcroutes
+- op: add
+  path: /spec/template/spec/containers/0/volumeMounts/-
+  value:
+    name: grafana-udproutes
+    mountPath: /grafana-dashboard-definitions/0/grafana-udproutes

config/prometheus-for-federation/ksm_clusterrole_patch.yaml

@@ -0,0 +1,26 @@
+- op: add
+  path: /rules/-
+  value:
+    apiGroups:
+    - "apiextensions.k8s.io"
+    resources:
+    - customresourcedefinitions
+    verbs:
+    - list
+    - watch
+- op: add
+  path: /rules/-
+  value:
+    apiGroups:
+    - "gateway.networking.k8s.io"
+    resources:
+    - gateways
+    - gatewayclasses
+    - httproutes
+    - grpcroutes
+    - tcproutes
+    - tlsroutes
+    - udproutes
+    verbs:
+    - list
+    - watch

config/prometheus-for-federation/ksm_deployment_patch.yaml

@@ -0,0 +1,21 @@
+- op: replace
+  path: /spec/template/spec/containers/0/image
+  value: registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.9.2
+- op: add
+  path: /spec/template/spec/volumes
+  value:
+      - name: custom-resource-state
+        configMap:
+          defaultMode: 420
+          name: custom-resource-state
+- op: add
+  path: /spec/template/spec/containers/0/volumeMounts
+  value:
+    - name: custom-resource-state
+      mountPath: /custom-resource-state
+- op: add
+  path: /spec/template/spec/containers/0/args/-
+  value: --custom-resource-state-config-file
+- op: add
+  path: /spec/template/spec/containers/0/args/-
+  value: /custom-resource-state/custom-resource-state.yaml

config/prometheus-for-federation/kustomization.yaml

@@ -3,6 +3,8 @@ kind: Kustomization
 
 resources:
   - github.com/prometheus-operator/kube-prometheus?ref=release-0.11
+  - github.com/Kuadrant/gateway-api-state-metrics?ref=main
+  - github.com/Kuadrant/gateway-api-state-metrics/config/examples/dashboards?ref=main
   - grafana_ingress.yaml
 # To scrape istio metrics, 3 configurations are required:
 # 1. Envoy metrics directly from the istio ingress gateway pod
@@ -65,6 +67,18 @@ patches:
 
 # Patch grafana deployment to include dashboard configmaps
 patchesJson6902:
+  - target:
+      group: apps
+      version: v1
+      kind: Deployment
+      name: kube-state-metrics
+    path: ksm_deployment_patch.yaml
+  - target:
+      group: rbac.authorization.k8s.io
+      version: v1
+      kind: ClusterRole
+      name: kube-state-metrics
+    path: ksm_clusterrole_patch.yaml
   - target:
       group: apps
       version: v1

docs/how-to/metrics-walkthrough.md

@@ -1,3 +1,9 @@
+## Introduction
+
+This walkthrough shows how to install a metrics federation stack locally and query Istio metrics from the hub.
+
+![arch](../images/metrics/metrics-federation.png)
+
 ## Installation and Configuration of Metrics
 This document will guide you in installing metrics for your application and provide directions on where to access them. Additionally, it will include dashboards set up to display these metrics. 
 
@@ -36,6 +42,44 @@ To generate traffic to the application, use `curl` as follows:
 while true; do curl -k https://$MGC_SUB_DOMAIN && sleep 5; done
 ```
 
+### Accessing the Thanos UI
+
+1. Access the Thanos UI by clicking or entering the provided URL for the Grafana UI in your web browser.
+
+```
+https://thanos-query.172.31.0.2.nip.io
+```
+
+2. In the Thanos UI query box, enter the below query and press 'Execute'
+
+```
+sum(rate(container_cpu_usage_seconds_total{namespace="monitoring",container="prometheus"}[5m]))
+```
+
+You should see a response in the table view.
+In the Graph view you should see some data over time as well.
+
+![arch](../images/metrics/metrics-federation-example-data.png)
+
+```
+sum(rate(istio_requests_total{}[5m])) by(destination_workload)
+```
+
+In the graph view you should see something that looks like the graph below.
+This shows the rate of requests (per second) for each Isito workload.
+In this case, there is 1 workload, balanced across 2 clusters.
+
+![arch](../images/metrics/metrics-federation-traffic-data.png)
+
+To see the rate of requests per cluster (actually per pod across all clusters), the below query can be used.
+Over long periods of time, this graph can show traffic load balancing between application instances.
+
+```
+sum(rate(istio_requests_total{}[5m])) by(pod)
+```
+
+![arch](../images/metrics/metrics-federation-traffic-data-per-pod.png)
+
 ### Accessing the Grafana Dashboard
 To view the operational metrics and status, proceed with the following steps:
 
@@ -48,7 +92,7 @@ https://grafana.172.31.0.2.nip.io
 
 2. Navigate to the included Grafana Dashboard
 
-Using the left sidebar in the Grafana UI, navigate to `Dashboards > Browse` and select either the `Istio Workload Dashboard` or `MGC SRE Dashboard`.
+Using the left sidebar in the Grafana UI, navigate to `Dashboards > Browse` and select the `Istio Workload Dashboard`, `MGC SRE Dashboard` or any of the following `Gateway Api State` dashboards.
 
 ![arch](../images/metrics/metrics-federation-grafana-dashboard-3.png)
 
@@ -60,6 +104,18 @@ The `MGC SRE Dashboard` displays real-time insights and visualizations of resour
 
 ![arch](../images/metrics/metrics-federation-grafana-dashboard-4.png)
 
+The `Gateway API State / Gateways` provides real-time insights and visualizations for Gateways. It offers information about gateway listeners, listener status, gateway status, addresses, and attached routes
+
+![arch](../images/metrics/metrics-federation-grafana-dashboard-5.png)
+
+The `Gateway API State / GatewayClasses` provides insights into Gateways organized by their respective Gateway Classes. It offers information about GatewayClasses and the supported features for each class.
+
+![arch](../images/metrics/metrics-federation-grafana-dashboard-6.png)
+
+The `Gateway API State / HTTPRoutes` or any of the remaining routes focuses on their `Routes` and provides insights into their configuration. It displays their targeted parent references, and attached parent references, offering a detailed view of how these routes are structured and associated with their respective resources.
+
+![arch](../images/metrics/metrics-federation-grafana-dashboard-7.png)
+
 The Grafana dashboard will provide you with real-time insights and visualizations of your gateway's performance and metrics.
 
 By utilizing the Grafana dashboard, you can effectively monitor the health and behavior of your system, making informed decisions based on the displayed data. This monitoring capability enables you to proactively identify and address any potential issues to ensure the smooth operation of your environment.