Add parameter to configure health endpoint port

Signed-off-by: Tobias Giese <[email protected]>
(cherry picked from commit 53ddf08)

Author: tobiasgiese

cmd/nfd-master/main.go

@@ -33,8 +33,7 @@ import (
 
 const (
 	// ProgramName is the canonical name of this program
-	ProgramName    = "nfd-master"
-	GrpcHealthPort = 8082
+	ProgramName = "nfd-master"
 )
 
 func main() {
@@ -110,7 +109,6 @@ func main() {
 	utils.ConfigureGrpcKlog()
 
 	// Get new NfdMaster instance
-	args.GrpcHealthPort = GrpcHealthPort
 	instance, err := master.NewNfdMaster(master.WithArgs(args))
 	if err != nil {
 		klog.ErrorS(err, "failed to initialize NfdMaster instance")
@@ -154,6 +152,8 @@ func initFlags(flagset *flag.FlagSet) (*master.Args, *master.ConfigOverrideArgs)
 			" DEPRECATED: will be removed in a future release along with the deprecated gRPC API.")
 	flagset.IntVar(&args.MetricsPort, "metrics", 8081,
 		"Port on which to expose metrics.")
+	flagset.IntVar(&args.GrpcHealthPort, "grpc-health", 8082,
+		"Port on which to expose the grpc health endpoint.")
 	flagset.BoolVar(&args.Prune, "prune", false,
 		"Prune all NFD related attributes from all nodes of the cluster and exit.")
 	flagset.BoolVar(&args.VerifyNodeName, "verify-node-name", false,

cmd/nfd-topology-updater/main.go

@@ -38,7 +38,6 @@ const (
 	// ProgramName is the canonical name of this program
 	ProgramName       = "nfd-topology-updater"
 	kubeletSecurePort = 10250
-	GrpcHealthPort    = 8082
 )
 
 var DefaultKubeletStateDir = path.Join(string(hostpath.VarDir), "lib", "kubelet")
@@ -57,7 +56,6 @@ func main() {
 	utils.ConfigureGrpcKlog()
 
 	// Get new TopologyUpdater instance
-	args.GrpcHealthPort = GrpcHealthPort
 	instance, err := topology.NewTopologyUpdater(*args, *resourcemonitorArgs)
 	if err != nil {
 		klog.ErrorS(err, "failed to initialize topology updater instance")
@@ -115,6 +113,8 @@ func initFlags(flagset *flag.FlagSet) (*topology.Args, *resourcemonitor.Args) {
 		"Kube config file.")
 	flagset.IntVar(&args.MetricsPort, "metrics", 8081,
 		"Port on which to expose metrics.")
+	flagset.IntVar(&args.GrpcHealthPort, "grpc-health", 8082,
+		"Port on which to expose the grpc health endpoint.")
 	flagset.DurationVar(&resourcemonitorArgs.SleepInterval, "sleep-interval", time.Duration(60)*time.Second,
 		"Time to sleep between CR updates. zero means no CR updates on interval basis. [Default: 60s]")
 	flagset.StringVar(&resourcemonitorArgs.Namespace, "watch-namespace", "*",

cmd/nfd-worker/main.go

@@ -32,8 +32,7 @@ import (
 
 const (
 	// ProgramName is the canonical name of this program
-	ProgramName    = "nfd-worker"
-	GrpcHealthPort = 8082
+	ProgramName = "nfd-worker"
 )
 
 func main() {
@@ -82,7 +81,6 @@ func main() {
 	utils.ConfigureGrpcKlog()
 
 	// Get new NfdWorker instance
-	args.GrpcHealthPort = GrpcHealthPort
 	instance, err := worker.NewNfdWorker(worker.WithArgs(args))
 	if err != nil {
 		klog.ErrorS(err, "failed to initialize NfdWorker instance")
@@ -143,6 +141,8 @@ func initFlags(flagset *flag.FlagSet) (*worker.Args, *worker.ConfigOverrideArgs)
 		"Do not publish feature labels")
 	flagset.IntVar(&args.MetricsPort, "metrics", 8081,
 		"Port on which to expose metrics.")
+	flagset.IntVar(&args.GrpcHealthPort, "grpc-health", 8082,
+		"Port on which to expose the grpc health endpoint.")
 	flagset.StringVar(&args.Options, "options", "",
 		"Specify config options from command line. Config options are specified "+
 			"in the same format as in the config file (i.e. json or yaml). These options")

deployment/helm/node-feature-discovery/templates/master.yaml

@@ -109,6 +109,7 @@ spec:
             - "-feature-gates={{ $key }}={{ $value }}"
             {{- end }}
             - "-metrics={{ .Values.master.metricsPort  | default "8081" }}"
+            - "-grpc-health={{ .Values.master.healthPort  | default "8082" }}"
           volumeMounts:
             {{- if .Values.tls.enable }}
             - name: nfd-master-cert

deployment/helm/node-feature-discovery/templates/topologyupdater.yaml

@@ -85,6 +85,7 @@ spec:
           - "-kubelet-state-dir="
           {{- end }}
           - -metrics={{ .Values.topologyUpdater.metricsPort | default "8081"}}
+          - "-grpc-health={{ .Values.topologyUpdater.healthPort  | default "8082" }}"
         ports:
           - name: metrics
             containerPort: {{ .Values.topologyUpdater.metricsPort | default "8081"}}

deployment/helm/node-feature-discovery/templates/worker.yaml

@@ -79,6 +79,7 @@ spec:
         - "-feature-gates={{ $key }}={{ $value }}"
 {{- end }}
         - "-metrics={{ .Values.worker.metricsPort | default "8081"}}"
+        - "-grpc-health={{ .Values.worker.healthPort  | default "8082" }}"
         ports:
           - name: metrics
             containerPort: {{ .Values.worker.metricsPort | default "8081"}}

deployment/helm/node-feature-discovery/values.yaml

@@ -57,6 +57,7 @@ master:
   # be removed with it in a future release
   port: 8080
   metricsPort: 8081
+  healthPort: 8082
   instance:
   featureApi:
   resyncPeriod:
@@ -402,6 +403,7 @@ worker:
 ### <NFD-WORKER-CONF-END-DO-NOT-REMOVE>
 
   metricsPort: 8081
+  healthPort: 8082
   daemonsetAnnotations: {}
   podSecurityContext: {}
     # fsGroup: 2000
@@ -490,6 +492,7 @@ topologyUpdater:
     create: true
 
   metricsPort: 8081
+  healthPort: 8082
   kubeletConfigPath:
   kubeletPodResourcesSockPath:
   updateInterval: 60s

docs/deployment/helm.md

@@ -180,6 +180,7 @@ API's you need to install the prometheus operator in your cluster.
 | `master.enable`            | bool    | true                                    | Specifies whether nfd-master should be deployed |
 | `master.port`              | integer |                                         | Specifies the TCP port that nfd-master listens for incoming requests. **NOTE**: this parameter is related to the deprecated gRPC API and will be removed with it in a future release |
 | `master.metricsPort`       | integer | 8081                                    | Port on which to expose metrics from components to prometheus operator |
+| `master.healthPort`        | integer | 8082                                    | Port on which to expose the grpc health endpoint                                                                                                            |
 | `master.instance`          | string  |                                         | Instance name. Used to separate annotation namespaces for multiple parallel deployments |
 | `master.resyncPeriod`      | string  |                                         | NFD API controller resync period. |
 | `master.extraLabelNs`      | array   | []                                      | List of allowed extra label namespaces |
@@ -215,6 +216,7 @@ API's you need to install the prometheus operator in your cluster.
 | `worker.*`                        | dict   |         | NFD worker daemonset configuration                                                                                                                                                                   |
 | `worker.enable`                   | bool   | true    | Specifies whether nfd-worker should be deployed                                                                                                                                                      |
 | `worker.metricsPort*`             | int    | 8081    | Port on which to expose metrics from components to prometheus operator                                                                                                                                |
+| `worker.healthPort`               | int    | 8082    | Port on which to expose the grpc health endpoint                                                                                                                                                     |
 | `worker.config`                   | dict   |         | NFD worker [configuration](../reference/worker-configuration-reference)                                                                                                                              |
 | `worker.podSecurityContext`       | dict   | {}      | [PodSecurityContext](https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-pod) holds pod-level security attributes and common container settings |
 | `worker.securityContext`          | dict   | {}      | Container [security settings](https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-container)                                                     |
@@ -246,6 +248,7 @@ API's you need to install the prometheus operator in your cluster.
 | `topologyUpdater.serviceAccount.name`         | string |                  | The name of the service account for topology updater to use. If not set and create is true, a name is generated using the fullname template and `-topology-updater` suffix                            |
 | `topologyUpdater.rbac.create`                 | bool   | true             | Specifies whether to create [RBAC][rbac] configuration for topology updater                                                                                                                           |
 | `topologyUpdater.metricsPort`                 | integer | 8081             | Port on which to expose prometheus metrics                                                                                                                                                            |
+| `topologyUpdater.healthPort`                  | integer | 8082             | Port on which to expose the grpc health endpoint                                                                                                                                                     |
 | `topologyUpdater.kubeletConfigPath`           | string | ""               | Specifies the kubelet config host path                                                                                                                                                                |
 | `topologyUpdater.kubeletPodResourcesSockPath` | string | ""               | Specifies the kubelet sock path to read pod resources                                                                                                                                                 |
 | `topologyUpdater.updateInterval`              | string | 60s              | Time to sleep between CR updates. Non-positive value implies no CR update.                                                                                                                            |