feat: remove leader election for operator (opendatahub-io#1000)

- since our design is for only one instance of pod, there is no need to enable leader-election - in a shady env. this can cause error Signed-off-by: Wen Zhou <[email protected]>
zdtsw-forking · May 6, 2024 · 3610b0b · 3610b0b
1 parent 2458865
commit 3610b0b
Show file tree

Hide file tree

Showing 6 changed files with 1 addition and 47 deletions.
diff --git a/bundle/manifests/opendatahub-operator-manager-config_v1_configmap.yaml b/bundle/manifests/opendatahub-operator-manager-config_v1_configmap.yaml
@@ -9,19 +9,6 @@ data:
       bindAddress: 0.0.0.0:8080
     webhook:
       port: 9443
-    leaderElection:
-      leaderElect: true
-      resourceName: 07ed84f7.opendatahub.io
-    # leaderElectionReleaseOnCancel defines if the leader should step down volume
-    # when the Manager ends. This requires the binary to immediately end when the
-    # Manager is stopped, otherwise, this setting is unsafe. Setting this significantly
-    # speeds up voluntary leader transitions as the new leader don't have to wait
-    # LeaseDuration time first.
-    # In the default scaffold provided, the program ends immediately after
-    # the manager stops, so would be fine to enable this option. However,
-    # if you are doing or is intended to do any operation such as perform cleanups
-    # after the manager stops then its usage might be unsafe.
-    # leaderElectionReleaseOnCancel: true
 kind: ConfigMap
 metadata:
   name: opendatahub-operator-manager-config
diff --git a/bundle/manifests/opendatahub-operator.clusterserviceversion.yaml b/bundle/manifests/opendatahub-operator.clusterserviceversion.yaml
@@ -1674,7 +1674,6 @@ spec:
               - args:
                 - --health-probe-bind-address=:8081
                 - --metrics-bind-address=0.0.0.0:8080
-                - --leader-elect
                 - --operator-name=opendatahub
                 command:
                 - /manager

diff --git a/config/default/manager_auth_proxy_patch.yaml b/config/default/manager_auth_proxy_patch.yaml
@@ -13,4 +13,3 @@ spec:
         args:
         - "--health-probe-bind-address=:8081"
         - "--metrics-bind-address=0.0.0.0:8080"
-        - "--leader-elect"
diff --git a/config/manager/controller_manager_config.yaml b/config/manager/controller_manager_config.yaml
@@ -6,16 +6,3 @@ metrics:
   bindAddress: 0.0.0.0:8080
 webhook:
   port: 9443
-leaderElection:
-  leaderElect: true
-  resourceName: 07ed84f7.opendatahub.io
-# leaderElectionReleaseOnCancel defines if the leader should step down volume
-# when the Manager ends. This requires the binary to immediately end when the
-# Manager is stopped, otherwise, this setting is unsafe. Setting this significantly
-# speeds up voluntary leader transitions as the new leader don't have to wait
-# LeaseDuration time first.
-# In the default scaffold provided, the program ends immediately after
-# the manager stops, so would be fine to enable this option. However,
-# if you are doing or is intended to do any operation such as perform cleanups
-# after the manager stops then its usage might be unsafe.
-# leaderElectionReleaseOnCancel: true
diff --git a/config/manager/manager.yaml b/config/manager/manager.yaml
@@ -41,7 +41,6 @@ spec:
           - name: DISABLE_DSC_CONFIG
             value: 'true'
         args:
-        - --leader-elect
         - --operator-name=opendatahub
         image: controller:latest
         imagePullPolicy: Always

diff --git a/main.go b/main.go
@@ -95,7 +95,6 @@ func init() { //nolint:gochecknoinits
 
 func main() { //nolint:funlen
 	var metricsAddr string
-	var enableLeaderElection bool
 	var probeAddr string
 	var dscApplicationsNamespace string
 	var dscMonitoringNamespace string
@@ -104,9 +103,6 @@ func main() { //nolint:funlen
 
 	flag.StringVar(&metricsAddr, "metrics-bind-address", ":8080", "The address the metric endpoint binds to.")
 	flag.StringVar(&probeAddr, "health-probe-bind-address", ":8081", "The address the probe endpoint binds to.")
-	flag.BoolVar(&enableLeaderElection, "leader-elect", false,
-		"Enable leader election for controller manager. "+
-			"Enabling this will ensure there is only one active controller manager.")
 	flag.StringVar(&dscApplicationsNamespace, "dsc-applications-namespace", "opendatahub", "The namespace where data science cluster"+
 		"applications will be deployed")
 	flag.StringVar(&dscMonitoringNamespace, "dsc-monitoring-namespace", "opendatahub", "The namespace where data science cluster"+
@@ -118,24 +114,11 @@ func main() { //nolint:funlen
 
 	ctrl.SetLogger(logger.ConfigLoggers(logmode))
 
-	mgr, err := ctrl.NewManager(ctrl.GetConfigOrDie(), ctrl.Options{
+	mgr, err := ctrl.NewManager(ctrl.GetConfigOrDie(), ctrl.Options{ // single pod does not need to have LeaderElection
 		Scheme:                 scheme,
 		MetricsBindAddress:     metricsAddr,
 		Port:                   9443,
 		HealthProbeBindAddress: probeAddr,
-		LeaderElection:         enableLeaderElection,
-		LeaderElectionID:       "07ed84f7.opendatahub.io",
-		// LeaderElectionReleaseOnCancel defines if the leader should step down voluntarily
-		// when the Manager ends. This requires the binary to immediately end when the
-		// Manager is stopped, otherwise, this setting is unsafe. Setting this significantly
-		// speeds up voluntary leader transitions as the new leader don't have to wait
-		// LeaseDuration time first.
-		//
-		// In the default scaffold provided, the program ends immediately after
-		// the manager stops, so would be fine to enable this option. However,
-		// if you are doing or is intended to do any operation such as perform cleanups
-		// after the manager stops then its usage might be unsafe.
-		// LeaderElectionReleaseOnCancel: true,
 	})
 	if err != nil {
 		setupLog.Error(err, "unable to start manager")