Merge pull request kubernetes-csi#1323 from rhrmo/restart-csi-sidecars-faster

Restart external-snapshotter faster by releasing leader election lease on sigterm

Author: k8s-ci-robot

cmd/csi-snapshotter/main.go

@@ -24,13 +24,15 @@ import (
 	"os"
 	"os/signal"
 	"strings"
+	"sync"
 	"time"
 
 	"google.golang.org/grpc"
 
 	v1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 	"k8s.io/apimachinery/pkg/labels"
 	"k8s.io/apimachinery/pkg/runtime"
+	server "k8s.io/apiserver/pkg/server"
 	utilfeature "k8s.io/apiserver/pkg/util/feature"
 	coreinformers "k8s.io/client-go/informers"
 	"k8s.io/client-go/kubernetes"
@@ -301,19 +303,55 @@ func main() {
 		workqueue.NewTypedItemExponentialFailureRateLimiter[string](*retryIntervalStart, *retryIntervalMax),
 	)
 
-	run := func(context.Context) {
-		// run...
-		stopCh := make(chan struct{})
-		snapshotContentfactory.Start(stopCh)
-		factory.Start(stopCh)
-		coreFactory.Start(stopCh)
-		go ctrl.Run(*threads, stopCh)
-
-		// ...until SIGINT
-		c := make(chan os.Signal, 1)
-		signal.Notify(c, os.Interrupt)
-		<-c
-		close(stopCh)
+	// handle SIGTERM and SIGINT by cancelling the context.
+	var (
+		terminate       func()          // called when all controllers are finished
+		controllerCtx   context.Context // shuts down all controllers on a signal
+		shutdownHandler <-chan struct{} // called when the signal is received
+	)
+
+	if utilfeature.DefaultFeatureGate.Enabled(features.ReleaseLeaderElectionOnExit) {
+		// ctx waits for all controllers to finish, then shuts down the whole process, incl. leader election
+		ctx, terminate = context.WithCancel(ctx)
+		var cancelControllerCtx context.CancelFunc
+		controllerCtx, cancelControllerCtx = context.WithCancel(ctx)
+		shutdownHandler = server.SetupSignalHandler()
+
+		defer terminate()
+
+		go func() {
+			defer cancelControllerCtx()
+			<-shutdownHandler
+			klog.Info("Received SIGTERM or SIGINT signal, shutting down controller.")
+		}()
+	}
+
+	run := func(ctx context.Context) {
+		if utilfeature.DefaultFeatureGate.Enabled(features.ReleaseLeaderElectionOnExit) {
+			// run...
+			stopCh := controllerCtx.Done()
+			snapshotContentfactory.Start(stopCh)
+			factory.Start(stopCh)
+			coreFactory.Start(stopCh)
+			var controllerWg sync.WaitGroup
+			go ctrl.Run(*threads, stopCh, &controllerWg)
+			<-shutdownHandler
+			controllerWg.Wait()
+			terminate()
+		} else {
+			// run...
+			stopCh := make(chan struct{})
+			snapshotContentfactory.Start(stopCh)
+			factory.Start(stopCh)
+			coreFactory.Start(stopCh)
+			go ctrl.Run(*threads, stopCh, nil)
+
+			// ...until SIGINT
+			c := make(chan os.Signal, 1)
+			signal.Notify(c, os.Interrupt)
+			<-c
+			close(stopCh)
+		}
 	}
 
 	if !*leaderElection {
@@ -338,6 +376,10 @@ func main() {
 		le.WithLeaseDuration(*leaderElectionLeaseDuration)
 		le.WithRenewDeadline(*leaderElectionRenewDeadline)
 		le.WithRetryPeriod(*leaderElectionRetryPeriod)
+		if utilfeature.DefaultFeatureGate.Enabled(features.ReleaseLeaderElectionOnExit) {
+			le.WithReleaseOnCancel(true)
+			le.WithContext(ctx)
+		}
 
 		if err := le.Run(); err != nil {
 			klog.Fatalf("failed to initialize leader election: %v", err)

cmd/snapshot-controller/main.go

@@ -39,6 +39,7 @@ import (
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 	"k8s.io/apimachinery/pkg/runtime"
 	"k8s.io/apimachinery/pkg/util/wait"
+	server "k8s.io/apiserver/pkg/server"
 
 	klog "k8s.io/klog/v2"
 
@@ -259,18 +260,55 @@ func main() {
 		os.Exit(1)
 	}
 
-	run := func(context.Context) {
-		// run...
-		stopCh := make(chan struct{})
-		factory.Start(stopCh)
-		coreFactory.Start(stopCh)
-		go ctrl.Run(*threads, stopCh)
-
-		// ...until SIGINT
-		c := make(chan os.Signal, 1)
-		signal.Notify(c, os.Interrupt)
-		<-c
-		close(stopCh)
+	ctx := context.Background()
+
+	// handle SIGTERM and SIGINT by cancelling the context.
+	var (
+		terminate       func()          // called when all controllers are finished
+		controllerCtx   context.Context // shuts down all controllers on a signal
+		shutdownHandler <-chan struct{} // called when the signal is received
+	)
+
+	if utilfeature.DefaultFeatureGate.Enabled(features.ReleaseLeaderElectionOnExit) {
+		// ctx waits for all controllers to finish, then shuts down the whole process, incl. leader election
+		ctx, terminate = context.WithCancel(ctx)
+		var cancelControllerCtx context.CancelFunc
+		controllerCtx, cancelControllerCtx = context.WithCancel(ctx)
+		shutdownHandler = server.SetupSignalHandler()
+
+		defer terminate()
+
+		go func() {
+			defer cancelControllerCtx()
+			<-shutdownHandler
+			klog.Info("Received SIGTERM or SIGINT signal, shutting down controller.")
+		}()
+	}
+
+	run := func(ctx context.Context) {
+		if utilfeature.DefaultFeatureGate.Enabled(features.ReleaseLeaderElectionOnExit) {
+			// run...
+			stopCh := controllerCtx.Done()
+			factory.Start(stopCh)
+			coreFactory.Start(stopCh)
+			var controllerWg sync.WaitGroup
+			go ctrl.Run(*threads, stopCh, &controllerWg)
+			<-shutdownHandler
+			controllerWg.Wait()
+			terminate()
+		} else {
+			// run...
+			stopCh := make(chan struct{})
+			factory.Start(stopCh)
+			coreFactory.Start(stopCh)
+			go ctrl.Run(*threads, stopCh, nil)
+
+			// ...until SIGINT
+			c := make(chan os.Signal, 1)
+			signal.Notify(c, os.Interrupt)
+			<-c
+			close(stopCh)
+		}
 	}
 
 	// start listening & serving http endpoint if set
@@ -289,7 +327,7 @@ func main() {
 		klog.Infof("Metrics http server successfully started on %s, %s", *httpEndpoint, *metricsPath)
 
 		defer func() {
-			err := srv.Shutdown(context.Background())
+			err := srv.Shutdown(ctx)
 			if err != nil {
 				klog.Errorf("Failed to shutdown metrics server: %s", err.Error())
 			}
@@ -300,7 +338,7 @@ func main() {
 	}
 
 	if !*leaderElection {
-		run(context.TODO())
+		run(ctx)
 	} else {
 		lockName := "snapshot-controller-leader"
 		// Create a new clientset for leader election to prevent throttling
@@ -320,6 +358,11 @@ func main() {
 		le.WithLeaseDuration(*leaderElectionLeaseDuration)
 		le.WithRenewDeadline(*leaderElectionRenewDeadline)
 		le.WithRetryPeriod(*leaderElectionRetryPeriod)
+		if utilfeature.DefaultFeatureGate.Enabled(features.ReleaseLeaderElectionOnExit) {
+			le.WithReleaseOnCancel(true)
+			le.WithContext(ctx)
+		}
+
 		if err := le.Run(); err != nil {
 			klog.Fatalf("failed to initialize leader election: %v", err)
 		}

go.mod

@@ -31,11 +31,18 @@ require (
 )
 
 require (
+	cel.dev/expr v0.19.1 // indirect
+	github.com/NYTimes/gziphandler v1.1.1 // indirect
+	github.com/antlr4-go/antlr/v4 v4.13.0 // indirect
 	github.com/beorn7/perks v1.0.1 // indirect
 	github.com/blang/semver/v4 v4.0.0 // indirect
+	github.com/cenkalti/backoff/v4 v4.3.0 // indirect
 	github.com/cespare/xxhash/v2 v2.3.0 // indirect
+	github.com/coreos/go-semver v0.3.1 // indirect
+	github.com/coreos/go-systemd/v22 v22.5.0 // indirect
 	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
 	github.com/emicklei/go-restful/v3 v3.12.1 // indirect
+	github.com/felixge/httpsnoop v1.0.4 // indirect
 	github.com/fxamacker/cbor/v2 v2.7.0 // indirect
 	github.com/go-logr/logr v1.4.2 // indirect
 	github.com/go-logr/stdr v1.2.2 // indirect
@@ -44,39 +51,58 @@ require (
 	github.com/go-openapi/jsonreference v0.21.0 // indirect
 	github.com/go-openapi/swag v0.23.0 // indirect
 	github.com/gogo/protobuf v1.3.2 // indirect
+	github.com/golang/protobuf v1.5.4 // indirect
+	github.com/google/cel-go v0.23.2 // indirect
 	github.com/google/gnostic-models v0.6.9 // indirect
 	github.com/google/go-cmp v0.7.0 // indirect
 	github.com/google/uuid v1.6.0 // indirect
+	github.com/grpc-ecosystem/go-grpc-prometheus v1.2.0 // indirect
+	github.com/grpc-ecosystem/grpc-gateway/v2 v2.24.0 // indirect
 	github.com/inconshreveable/mousetrap v1.1.0 // indirect
 	github.com/josharian/intern v1.0.0 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
+	github.com/kylelemons/godebug v1.1.0 // indirect
 	github.com/mailru/easyjson v0.9.0 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/pkg/errors v0.9.1 // indirect
 	github.com/prometheus/procfs v0.15.1 // indirect
 	github.com/spf13/cobra v1.8.1 // indirect
 	github.com/spf13/pflag v1.0.5 // indirect
+	github.com/stoewer/go-strcase v1.3.0 // indirect
 	github.com/x448/float16 v0.8.4 // indirect
+	go.etcd.io/etcd/api/v3 v3.5.21 // indirect
+	go.etcd.io/etcd/client/pkg/v3 v3.5.21 // indirect
+	go.etcd.io/etcd/client/v3 v3.5.21 // indirect
 	go.opentelemetry.io/auto/sdk v1.1.0 // indirect
 	go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.58.0 // indirect
+	go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.58.0 // indirect
 	go.opentelemetry.io/otel v1.33.0 // indirect
+	go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.33.0 // indirect
+	go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracegrpc v1.33.0 // indirect
 	go.opentelemetry.io/otel/metric v1.33.0 // indirect
+	go.opentelemetry.io/otel/sdk v1.33.0 // indirect
 	go.opentelemetry.io/otel/trace v1.33.0 // indirect
+	go.opentelemetry.io/proto/otlp v1.4.0 // indirect
 	go.uber.org/automaxprocs v1.6.0 // indirect
 	go.uber.org/multierr v1.11.0 // indirect
 	go.uber.org/zap v1.27.0 // indirect
+	golang.org/x/crypto v0.37.0 // indirect
+	golang.org/x/exp v0.0.0-20240719175910-8a7402abbf56 // indirect
 	golang.org/x/net v0.39.0 // indirect
 	golang.org/x/oauth2 v0.27.0 // indirect
+	golang.org/x/sync v0.13.0 // indirect
 	golang.org/x/sys v0.32.0 // indirect
 	golang.org/x/term v0.31.0 // indirect
 	golang.org/x/text v0.24.0 // indirect
 	golang.org/x/time v0.9.0 // indirect
+	google.golang.org/genproto/googleapis/api v0.0.0-20241209162323-e6fa225c2576 // indirect
 	google.golang.org/genproto/googleapis/rpc v0.0.0-20241216192217-9240e9c98484 // indirect
 	gopkg.in/evanphx/json-patch.v4 v4.12.0 // indirect
 	gopkg.in/inf.v0 v0.9.1 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 	k8s.io/kube-openapi v0.0.0-20250318190949-c8a335a9a2ff // indirect
+	sigs.k8s.io/apiserver-network-proxy/konnectivity-client v0.31.2 // indirect
 	sigs.k8s.io/json v0.0.0-20241014173422-cfa47c3a1cc8 // indirect
 	sigs.k8s.io/randfill v1.0.0 // indirect
 	sigs.k8s.io/structured-merge-diff/v4 v4.6.0 // indirect