github/kubernetes
1
0
Fork 0
mirror of https://github.com/k3s-io/kubernetes.git synced 2025-11-27 19:16:16 +00:00
Code Issues Projects Releases Wiki Activity

Ensure deletion of pods in queues and cache

Browse Source 
When the client misses a delete event from the watcher, it will use the last state of the pod in the informer cache to produce a delete event. At that point, it's not clear if the pod was in the queues or the cache, so we should issue a deletion in both.

The pod could be assumed, so deletion of assumed pods from the cache should work.

Change-Id: I11ce9785de603924fc121fe2fa6ed5cb1e16922f
This commit is contained in:
Aldo Culquicondor
2021-11-02 15:40:34 -04:00
parent f08ad3e0ed
commit ff741f6a96
3 changed files with 57 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
pkg/scheduler/internal/cache/cache.go vendored
View File

@@ -537,22 +537,19 @@ func (cache *schedulerCache) RemovePod(pod *v1.Pod) error {
currState, ok := cache.podStates[key]
switch {
// An assumed pod won't have Delete/Remove event. It needs to have Add event
// before Remove event, in which case the state would change from Assumed to Added.
case ok && !cache.assumedPods.Has(key):
case ok:
if currState.pod.Spec.NodeName != pod.Spec.NodeName {
klog.Errorf("Pod %v was assumed to be on %v but got added to %v", key, pod.Spec.NodeName, currState.pod.Spec.NodeName)
klog.Fatalf("Schedulercache is corrupted and can badly affect scheduling decisions")
if pod.Spec.NodeName != "" {
// An empty NodeName is possible when the scheduler misses a Delete
// event and it gets the last known state from the informer cache.
klog.Fatalf("Schedulercache is corrupted and can badly affect scheduling decisions")
}
}
err := cache.removePod(currState.pod)
if err != nil {
return err
}
delete(cache.podStates, key)
return cache.expirePod(key, currState)
default:
return fmt.Errorf("pod %v is not found in scheduler cache, so cannot be removed from it", key)
}
return nil
}
func (cache *schedulerCache) IsAssumedPod(pod *v1.Pod) (bool, error) {