Skip to content

refactor(cluster-autoscaler): move negative increase check earlier in executeScaleUp #8448

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
+10 −3
Open

refactor(cluster-autoscaler): move negative increase check earlier in executeScaleUp #8448

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 10 additions & 3 deletions cluster-autoscaler/core/scaleup/orchestrator/executor.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,15 +165,22 @@ func (e *scaleUpExecutor) executeScaleUp(
e.autoscalingContext.LogRecorder.Eventf(apiv1.EventTypeNormal, "ScaledUpGroup",
"Scale-up: setting group %s size to %d instead of %d (max: %d)", info.Group.Id(), info.NewSize, info.CurrentSize, info.MaxSize)
increase := info.NewSize - info.CurrentSize
if increase < 0 {
err := errors.NewAutoscalerError(
errors.InternalError,
fmt.Sprintf("increase in number of nodes cannot be negative (current: %d, new: %d, delta: %d)", info.CurrentSize, info.NewSize, increase),
)
e.autoscalingContext.LogRecorder.Eventf(apiv1.EventTypeWarning, "FailedToScaleUpGroup", "Scale-up aborted for group %s: %v", info.Group.Id(), err)
e.scaleStateNotifier.RegisterFailedScaleUp(info.Group, string(err.Type()), err.Error(), gpuResourceName, gpuType, now)

return err
}
if err := e.increaseSize(info.Group, increase, atomic); err != nil {
e.autoscalingContext.LogRecorder.Eventf(apiv1.EventTypeWarning, "FailedToScaleUpGroup", "Scale-up failed for group %s: %v", info.Group.Id(), err)
aerr := errors.ToAutoscalerError(errors.CloudProviderError, err).AddPrefix("failed to increase node group size: ")
e.scaleStateNotifier.RegisterFailedScaleUp(info.Group, string(aerr.Type()), aerr.Error(), gpuResourceName, gpuType, now)
return aerr
}
if increase < 0 {
return errors.NewAutoscalerError(errors.InternalError, fmt.Sprintf("increase in number of nodes cannot be negative, got: %v", increase))
}
if !info.Group.Exist() && e.asyncNodeGroupStateChecker.IsUpcoming(info.Group) {
// Don't emit scale up event for upcoming node group as it will be generated after
// the node group is created, during initial scale up.
Expand Down
Loading