Merge pull request #57932 from atlassian/cancellable-leader-election

Automatic merge from submit-queue (batch tested with PRs 65256, 64236, 64919, 64879, 57932). If you want to cherry-pick this change to another branch, please follow the instructions <a href="https://github.com/kubernetes/community/blob/master/contributors/devel/cherry-picks.md">here</a>.

Cancellable leader election

**What this PR does / why we need it**:
Adds ability to cancel leader election. Useful in integration tests where the whole app is started and stopped in each test.

**Special notes for your reviewer**:
I used the `context` package - it is impossible/hard to achieve the same behaviour with just channels without spawning additional goroutines but it is trivial with `context`. See `acquire()` and `renew()` methods.

**Release note**:

```release-note
NONE
```
/kind enhancement
/sig api-machinery

Kubernetes-commit: 571b9beac5bdaa65fb581bead7464926fa81cdbf

tools/leaderelection/leaderelection.go

@@ -49,6 +49,7 @@ limitations under the License.
 package leaderelection
 
 import (
+	"context"
 	"fmt"
 	"reflect"
 	"time"
@@ -119,7 +120,7 @@ type LeaderElectionConfig struct {
 //  * OnChallenge()
 type LeaderCallbacks struct {
 	// OnStartedLeading is called when a LeaderElector client starts leading
-	OnStartedLeading func(stop <-chan struct{})
+	OnStartedLeading func(context.Context)
 	// OnStoppedLeading is called when a LeaderElector client stops leading
 	OnStoppedLeading func()
 	// OnNewLeader is called when the client observes a leader that is
@@ -145,26 +146,28 @@ type LeaderElector struct {
 }
 
 // Run starts the leader election loop
-func (le *LeaderElector) Run() {
+func (le *LeaderElector) Run(ctx context.Context) {
 	defer func() {
 		runtime.HandleCrash()
 		le.config.Callbacks.OnStoppedLeading()
 	}()
-	le.acquire()
+	if !le.acquire(ctx) {
-	stop := make(chan struct{})
+		return // ctx signalled done
-	go le.config.Callbacks.OnStartedLeading(stop)
+	}
-	le.renew()
+	ctx, cancel := context.WithCancel(ctx)
-	close(stop)
+	defer cancel()
+	go le.config.Callbacks.OnStartedLeading(ctx)
+	le.renew(ctx)
 }
 
 // RunOrDie starts a client with the provided config or panics if the config
 // fails to validate.
-func RunOrDie(lec LeaderElectionConfig) {
+func RunOrDie(ctx context.Context, lec LeaderElectionConfig) {
 	le, err := NewLeaderElector(lec)
 	if err != nil {
 		panic(err)
 	}
-	le.Run()
+	le.Run(ctx)
 }
 
 // GetLeader returns the identity of the last observed leader or returns the empty string if
@@ -178,13 +181,16 @@ func (le *LeaderElector) IsLeader() bool {
 	return le.observedRecord.HolderIdentity == le.config.Lock.Identity()
 }
 
-// acquire loops calling tryAcquireOrRenew and returns immediately when tryAcquireOrRenew succeeds.
+// acquire loops calling tryAcquireOrRenew and returns true immediately when tryAcquireOrRenew succeeds.
-func (le *LeaderElector) acquire() {
+// Returns false if ctx signals done.
-	stop := make(chan struct{})
+func (le *LeaderElector) acquire(ctx context.Context) bool {
+	ctx, cancel := context.WithCancel(ctx)
+	defer cancel()
+	succeeded := false
 	desc := le.config.Lock.Describe()
 	glog.Infof("attempting to acquire leader lease  %v...", desc)
 	wait.JitterUntil(func() {
-		succeeded := le.tryAcquireOrRenew()
+		succeeded = le.tryAcquireOrRenew()
 		le.maybeReportTransition()
 		if !succeeded {
 			glog.V(4).Infof("failed to acquire lease %v", desc)
@@ -192,17 +198,21 @@ func (le *LeaderElector) acquire() {
 		}
 		le.config.Lock.RecordEvent("became leader")
 		glog.Infof("successfully acquired lease %v", desc)
-		close(stop)
+		cancel()
-	}, le.config.RetryPeriod, JitterFactor, true, stop)
+	}, le.config.RetryPeriod, JitterFactor, true, ctx.Done())
+	return succeeded
 }
 
-// renew loops calling tryAcquireOrRenew and returns immediately when tryAcquireOrRenew fails.
+// renew loops calling tryAcquireOrRenew and returns immediately when tryAcquireOrRenew fails or ctx signals done.
-func (le *LeaderElector) renew() {
+func (le *LeaderElector) renew(ctx context.Context) {
-	stop := make(chan struct{})
+	ctx, cancel := context.WithCancel(ctx)
+	defer cancel()
 	wait.Until(func() {
-		err := wait.Poll(le.config.RetryPeriod, le.config.RenewDeadline, func() (bool, error) {
+		timeoutCtx, timeoutCancel := context.WithTimeout(ctx, le.config.RenewDeadline)
+		defer timeoutCancel()
+		err := wait.PollImmediateUntil(le.config.RetryPeriod, func() (bool, error) {
 			return le.tryAcquireOrRenew(), nil
-		})
+		}, timeoutCtx.Done())
 		le.maybeReportTransition()
 		desc := le.config.Lock.Describe()
 		if err == nil {
@@ -211,8 +221,8 @@ func (le *LeaderElector) renew() {
 		}
 		le.config.Lock.RecordEvent("stopped leading")
 		glog.Infof("failed to renew lease %v: %v", desc, err)
-		close(stop)
+		cancel()
-	}, 0, stop)
+	}, 0, ctx.Done())
 }
 
 // tryAcquireOrRenew tries to acquire a leader lease if it is not already acquired,