Skip to content
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

skip completed or failed AWs after MCAD restart #669

Merged
merged 3 commits into from
Oct 20, 2023
Merged

skip completed or failed AWs after MCAD restart #669

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1e602eb
skip completed AWs after MCAD restart
asm582 Oct 20, 2023
b42f5e4
move check up the addqueuejob method
asm582 Oct 20, 2023
f2e671d
add AW name
asm582 Oct 20, 2023
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
11 changes: 9 additions & 2 deletions pkg/controller/queuejob/queuejob_controller_ex.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -640,7 +640,7 @@ func (qjm *XController) GetAggregatedResources(cqj *arbv1.AppWrapper) *clusterst
}
allocated = allocated.Add(qjv)
}

klog.V(2).Infof("[GetAggregatedResources] Total resources needed to dispatch AW as reported in custompodresources is %v", allocated)
return allocated
}

Expand Down Expand Up @@ -1569,6 +1569,10 @@ func (cc *XController) addQueueJob(obj interface{}) {
return
}
klog.V(6).Infof("[Informer-addQJ] %s/%s", qj.Namespace, qj.Name)
if qj.Status.State == arbv1.AppWrapperStateCompleted || qj.Status.State == arbv1.AppWrapperStateFailed {
klog.V(2).Infof("[Informer-addQJ] Skipping processing of AW %s with state %s", qj.Name, qj.Status.State)
return
}
if qj.Status.QueueJobState == "" {
qj.Status.ControllerFirstTimestamp = firstTime
qj.Status.SystemPriority = float64(qj.Spec.Priority)
Expand Down Expand Up @@ -1626,7 +1630,10 @@ func (cc *XController) addQueueJob(obj interface{}) {
if latestAw.Status.State != arbv1.AppWrapperStateActive && latestAw.Status.State != arbv1.AppWrapperStateEnqueued && latestAw.Status.State != arbv1.AppWrapperStateRunningHoldCompletion {
klog.V(2).Infof("[Informer-addQJ] Stopping requeue for AW %s/%s with status %s", latestAw.Namespace, latestAw.Name, latestAw.Status.State)
AwinEtcd, err := cc.arbclients.WorkloadV1beta1().AppWrappers(latestAw.Namespace).Get(context.Background(), latestAw.Name, metav1.GetOptions{})
if AwinEtcd.Status.State == latestAw.Status.State && err != nil {
if apierrors.IsNotFound(err) {
klog.V(2).Infof("[Informer-addQJ] Stopped requeueing of AW %s due to error %v\n", latestAw.Name, err)
break
} else if AwinEtcd.Status.State == latestAw.Status.State && err != nil {
break // Exit the loop
}
}
Expand Down