mirror of
https://github.com/optim-enterprises-bv/kubernetes.git
synced 2025-12-10 18:15:36 +00:00
client-go: shut down watch reflector as soon as stop channel closes
Without this change, sometimes leaked goroutines were reported for
test/integration/scheduler_perf. The one that caused the cleanup to get delayed
was this one:
goleak.go:50: found unexpected goroutines:
[Goroutine 2704 in state chan receive, 2 minutes, with k8s.io/client-go/tools/cache.(*Reflector).watch on top of the stack:
goroutine 2704 [chan receive, 2 minutes]:
k8s.io/client-go/tools/cache.(*Reflector).watch(0xc00453f590, {0x0, 0x0}, 0x1f?, 0xc00a128080?)
/nvme/gopath/src/k8s.io/kubernetes/vendor/k8s.io/client-go/tools/cache/reflector.go:388 +0x5b3
k8s.io/client-go/tools/cache.(*Reflector).ListAndWatch(0xc00453f590, 0xc006e94900)
/nvme/gopath/src/k8s.io/kubernetes/vendor/k8s.io/client-go/tools/cache/reflector.go:324 +0x3bd
k8s.io/client-go/tools/cache.(*Reflector).Run.func1()
/nvme/gopath/src/k8s.io/kubernetes/vendor/k8s.io/client-go/tools/cache/reflector.go:279 +0x45
k8s.io/apimachinery/pkg/util/wait.BackoffUntil.func1(0xc007aafee0)
/nvme/gopath/src/k8s.io/kubernetes/vendor/k8s.io/apimachinery/pkg/util/wait/wait.go:157 +0x49
k8s.io/apimachinery/pkg/util/wait.BackoffUntil(0xc003e18150?, {0x75e37c0, 0xc00389c280}, 0x1, 0xc006e94900)
/nvme/gopath/src/k8s.io/kubernetes/vendor/k8s.io/apimachinery/pkg/util/wait/wait.go:158 +0xcf
k8s.io/client-go/tools/cache.(*Reflector).Run(0xc00453f590, 0xc006e94900)
/nvme/gopath/src/k8s.io/kubernetes/vendor/k8s.io/client-go/tools/cache/reflector.go:278 +0x257
k8s.io/apimachinery/pkg/util/wait.(*Group).StartWithChannel.func1()
/nvme/gopath/src/k8s.io/kubernetes/vendor/k8s.io/apimachinery/pkg/util/wait/wait.go:58 +0x3f
k8s.io/apimachinery/pkg/util/wait.(*Group).Start.func1()
/nvme/gopath/src/k8s.io/kubernetes/vendor/k8s.io/apimachinery/pkg/util/wait/wait.go:75 +0x74
created by k8s.io/apimachinery/pkg/util/wait.(*Group).Start
/nvme/gopath/src/k8s.io/kubernetes/vendor/k8s.io/apimachinery/pkg/util/wait/wait.go:73 +0xe5
watch() was stuck in an exponential backoff timeout. Logging confirmed that:
I0309 21:14:21.756149 1572727 reflector.go:387] k8s.io/client-go/informers/factory.go:150: watch of *v1.PersistentVolumeClaim returned Get "https://127.0.0.1:38269/api/v1/persistentvolumeclaims?allowWatchBookmarks=true&resourceVersion=1&timeout=7m47s&timeoutSeconds=467&watch=true": dial tcp 127.0.0.1:38269: connect: connection refused - backing off
This commit is contained in:
@@ -385,8 +385,12 @@ func (r *Reflector) watch(w watch.Interface, stopCh <-chan struct{}, resyncerrc
|
||||
if err != nil {
|
||||
if canRetry := isWatchErrorRetriable(err); canRetry {
|
||||
klog.V(4).Infof("%s: watch of %v returned %v - backing off", r.name, r.typeDescription, err)
|
||||
<-r.initConnBackoffManager.Backoff().C()
|
||||
continue
|
||||
select {
|
||||
case <-stopCh:
|
||||
return nil
|
||||
case <-r.initConnBackoffManager.Backoff().C():
|
||||
continue
|
||||
}
|
||||
}
|
||||
return err
|
||||
}
|
||||
@@ -406,8 +410,12 @@ func (r *Reflector) watch(w watch.Interface, stopCh <-chan struct{}, resyncerrc
|
||||
klog.V(4).Infof("%s: watch of %v closed with: %v", r.name, r.typeDescription, err)
|
||||
case apierrors.IsTooManyRequests(err):
|
||||
klog.V(2).Infof("%s: watch of %v returned 429 - backing off", r.name, r.typeDescription)
|
||||
<-r.initConnBackoffManager.Backoff().C()
|
||||
continue
|
||||
select {
|
||||
case <-stopCh:
|
||||
return nil
|
||||
case <-r.initConnBackoffManager.Backoff().C():
|
||||
continue
|
||||
}
|
||||
case apierrors.IsInternalError(err) && retry.ShouldRetry():
|
||||
klog.V(2).Infof("%s: retrying watch of %v internal error: %v", r.name, r.typeDescription, err)
|
||||
continue
|
||||
|
||||
Reference in New Issue
Block a user