Add new metrics for Dataset. Need to add update logic

Documentation/devhandbook.md

@@ -1,15 +1,14 @@
 # Developemnt Handbook
 
-Make Sure you have a k8s cluster
+#### Make Sure you have a k8s cluster
 
 ## Local Testing
 
 ### Step 0
-Generate Helm Chart files: RUN ```./dev/build/generate.sh``` under project root.
-
+Generate Helm Chart files by running `./dev/build/generate.sh` under project root.
 
 ### Step 1
-Install Alluxion Operator via Helm Chart under ```deploy/charts/alluxio-operator```
+Install Alluxion Operator via Helm Chart under `deploy/charts/alluxio-operator`
   ```shell
   helm install operator -f operator-config.yaml deploy/charts/alluxio-operator
   ```
@@ -20,28 +19,32 @@ Install Alluxion Operator via Helm Chart under ```deploy/charts/alluxio-operator
   ```
 
 
-## How to Make Operator Docker Image
+## Make Alluxio K8s Operator Docker Image
 
 ### Step 0
-注册一个dockerhub的账号，在terminal里docker login
+Create a dockerhub account, and login in terminal
 
 ### Step 1
-Generate Helm Chart files: RUN ```./dev/build/generate.sh``` under project root.
+Generate Helm Chart files by running `./dev/build/generate.sh` under project root.
 
 ### Step 2
-在project home的路径下运行 docker:
-```shell
-docker build -t <docker username>/alluxio-operator:<tag> -f dev/build/Dockerfile .
-```
+Build dokcer image by running `docker build -t <docker username>/alluxio-operator:<tag> -f dev/build/Dockerfile .` under project root.
+
+* For Apple Silicon Chip: `docker buildx build --platform linux/amd64 -t <docker username>/alluxio-operator:<tag> -f dev/build/Dockerfile .`
 
-* For Apple Silicon Chip:
-  ```docker buildx build --platform linux/amd64 -t kshou433/alluxio-operator:v1.5 -f dev/build/Dockerfile .```
 
+* Example:
+  ```shell
+  docker buildx build --platform linux/amd64 -t kshou433/alluxio-operator:v1.6 -f dev/build/Dockerfile .
+  ```
 
 ### Step 3
-```shell
-docker push kshou433/alluxio-operator:v1.5
-```
+Push image to docker hub : `docker push <docker username>/alluxio-operator:<tag>`.
+
+* Example:
+  ```shell
+  docker push kshou433/alluxio-operator:v1.6
+  ```
 
 ### Step 4
 Update image url and tage in ```operator-config.yaml```
@@ -50,7 +53,7 @@ Update image url and tage in ```operator-config.yaml```
 ## Verify the Deployment
 
 ### Check endpoints
-```kubectl get endpoints```
+```kubectl get endpoints -A```
 
 ### Check if prometheus is running
 ```kubectl get prometheus -o yaml```

Documentation/runbook.md

@@ -4,19 +4,32 @@
 
 
 
-## How to deploy Alluxio K8S Operator with Prometheus Operator
+## How to deploy Alluxio K8S Operator with [kube-prometheus](https://github.com/prometheus-operator/kube-prometheus)
 
 ### Install Prometheus Operator to K8S Cluster
 
 Make sure add correct namespace in the jsonnet file and generate new manifest file.
 
-#### It is common that 
+```
+  prometheus+:: {
+    namespaces: ["default", "kube-system", "monitoring", "alluxio-operator"],
+  },
+```
 
+##### These errors are expected:
+```
+Error from server (NotFound): namespaces "alluxio-operator" not found
+Error from server (NotFound): namespaces "alluxio-operator" not found
+```
+We need to use next step to deploy the `Alluxio Operator`.
 
 ### Deploy Alluxio Operator using Helm
+`helm install operator -f operator-config.yaml deploy/charts/alluxio-operator`
 
 ### Update Prometheus Operator
 
 ### Use method in Dev Handbook to verify everything is running,
 
 
+### Uninstall Operator:
+`helm delete operator `

monitoring/metrics.go

@@ -21,49 +21,61 @@ var metricDescription = map[string]MetricDescription{
 	//	Help: "Total number of times the deployment size was not as desired.",
 	//	Type: "Counter",
 	//},
-	//"AlluxioClusterAliveWorkerTotal": {
-	//	Name: "alluxio_cluster_alive_worker_total",
-	//	Help: "Total number of alive worker.",
-	//	Type: "Gauge",
-	//},
+	"AlluxioClusterAliveWorkerTotal": {
+		Name: "alluxio_cluster_alive_worker_total",
+		Help: "Total number of alive worker in Alluxio Cluster.",
+		Type: "Gauge",
+	},
 	"AlluxioClusterDatasetMountedCountTotal": {
 		Name: "alluxio_cluster_dataset_mounted_count_total",
 		Help: "Total number of times the dataset was mounted.",
 		Type: "Counter",
 	},
+	"DatasetAliveWorkerTotal": {
+		Name: "dataset_alive_worker_total",
+		Help: "Total number of alive worker in Dataset.",
+		Type: "Gauge",
+	},
 }
 
 var (
-	//AlluxioClusterAliveWorkerTotal = prometheus.NewGauge(
-	//	prometheus.GaugeOpts{
-	//		Name: metricDescription["AlluxioClusterAliveWorkerTotal"].Name,
-	//		Help: metricDescription["AlluxioClusterAliveWorkerTotal"].Help,
-	//	},
-	//)
+	AlluxioClusterAliveWorkerTotal = prometheus.NewGauge(
+		prometheus.GaugeOpts{
+			Name: metricDescription["AlluxioClusterAliveWorkerTotal"].Name,
+			Help: metricDescription["AlluxioClusterAliveWorkerTotal"].Help,
+		},
+	)
 	AlluxioClusterDatasetMountedCountTotal = prometheus.NewCounter(
 		prometheus.CounterOpts{
 			Name: metricDescription["AlluxioClusterDatasetMountedCountTotal"].Name,
 			Help: metricDescription["AlluxioClusterDatasetMountedCountTotal"].Help,
 		},
 	)
+	DatasetAliveWorkerTotal = prometheus.NewGauge(
+		prometheus.GaugeOpts{
+			Name: metricDescription["DatasetAliveWorkerTotal"].Name,
+			Help: metricDescription["DatasetAliveWorkerTotal"].Help,
+		},
+	)
 )
 
 // RegisterMetrics will register metrics with the global prometheus registry
-func RegisterMetrics() {
-	// metrics.Registry.MustRegister(AlluxioClusterAliveWorkerTotal)
-	metrics.Registry.MustRegister(AlluxioClusterDatasetMountedCountTotal)
-	logger.Infof("Register Metrics: AlluxioClusterDatasetMountedCountTotal")
-}
+//func RegisterMetrics() {
+//	// metrics.Registry.MustRegister(AlluxioClusterAliveWorkerTotal)
+//	metrics.Registry.MustRegister(AlluxioClusterDatasetMountedCountTotal)
+//	logger.Infof("Register Metrics: AlluxioClusterDatasetMountedCountTotal")
+//}
 
-func RegisterDatasetControllerMetrics() {
-	// metrics.Registry.MustRegister(AlluxioClusterAliveWorkerTotal)
+func RegisterAlluxioControllerMetrics() {
+	metrics.Registry.MustRegister(AlluxioClusterAliveWorkerTotal)
+	logger.Infof("Register Metrics: AlluxioClusterAliveWorkerTotal")
 	metrics.Registry.MustRegister(AlluxioClusterDatasetMountedCountTotal)
 	logger.Infof("Register Metrics: AlluxioClusterDatasetMountedCountTotal")
 }
 
-func RegisterAlluxioControllerMetrics() {
-	// metrics.Registry.MustRegister(AlluxioClusterAliveWorkerTotal)
-	logger.Infof("Register Metrics: PENDING: AlluxioClusterAliveWorkerTotal")
+func RegisterDatasetControllerMetrics() {
+	metrics.Registry.MustRegister(DatasetAliveWorkerTotal)
+	logger.Infof("Register Metrics: DatasetAliveWorkerTotal")
 }
 
 // ListMetrics will create a slice with the metrics available in metricDescription

operator-config.yaml

@@ -1,5 +1,5 @@
 image: docker.io/kshou433/alluxio-operator
-imageTag: v1.5
+imageTag: v1.6
 imagePullPolicy: Always
 alluxio-csi:
   enabled: 'false'

pkg/alluxiocluster/alluxiocluster_controller.go

@@ -43,7 +43,7 @@ type AlluxioClusterReconcileReqCtx struct {
 }
 
 const ruleName = "alluxio-operator-rules"
-const namespace = "alluxio-operator-system"
+const namespace = "alluxio-operator"
 
 func (r *AlluxioClusterReconciler) Reconcile(context context.Context, req ctrl.Request) (ctrl.Result, error) {
 	logger.Infof("Reconciling AlluxioCluster %s", req.NamespacedName.String())