mirror of
https://github.com/k3s-io/kubernetes.git
synced 2026-01-05 07:27:21 +00:00
Merge pull request #62543 from ingvagabund/timeout-on-cloud-provider-request
Automatic merge from submit-queue. 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>. Timeout on instances.NodeAddresses cloud provider request **What this PR does / why we need it**: In cases the cloud provider does not respond before the node gets evicted. **Which issue(s) this PR fixes** *(optional, in `fixes #<issue number>(, fixes #<issue_number>, ...)` format, will close the issue(s) when PR gets merged)*: Fixes # **Special notes for your reviewer**: **Release note**: ```release-note stop kubelet to cloud provider integration potentially wedging kubelet sync loop ```
This commit is contained in:
@@ -432,7 +432,36 @@ func (kl *Kubelet) setNodeAddress(node *v1.Node) error {
|
||||
// to the cloud provider?
|
||||
// TODO(justinsb): We can if CurrentNodeName() was actually CurrentNode() and returned an interface
|
||||
// TODO: If IP addresses couldn't be fetched from the cloud provider, should kubelet fallback on the other methods for getting the IP below?
|
||||
nodeAddresses, err := instances.NodeAddresses(context.TODO(), kl.nodeName)
|
||||
var nodeAddresses []v1.NodeAddress
|
||||
var err error
|
||||
|
||||
// Make sure the instances.NodeAddresses returns even if the cloud provider API hangs for a long time
|
||||
func() {
|
||||
kl.cloudproviderRequestMux.Lock()
|
||||
if len(kl.cloudproviderRequestParallelism) > 0 {
|
||||
kl.cloudproviderRequestMux.Unlock()
|
||||
return
|
||||
}
|
||||
kl.cloudproviderRequestParallelism <- 0
|
||||
kl.cloudproviderRequestMux.Unlock()
|
||||
|
||||
go func() {
|
||||
nodeAddresses, err = instances.NodeAddresses(context.TODO(), kl.nodeName)
|
||||
|
||||
kl.cloudproviderRequestMux.Lock()
|
||||
<-kl.cloudproviderRequestParallelism
|
||||
kl.cloudproviderRequestMux.Unlock()
|
||||
|
||||
kl.cloudproviderRequestSync <- 0
|
||||
}()
|
||||
}()
|
||||
|
||||
select {
|
||||
case <-kl.cloudproviderRequestSync:
|
||||
case <-time.After(kl.cloudproviderRequestTimeout):
|
||||
err = fmt.Errorf("Timeout after %v", kl.cloudproviderRequestTimeout)
|
||||
}
|
||||
|
||||
if err != nil {
|
||||
return fmt.Errorf("failed to get node address from cloud provider: %v", err)
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user