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

Jump to bottom

fix: fix mxnet failed to update StartTime and CompletionTime #1643

Merged
merged 1 commit into from
Aug 2, 2022
Merged

fix: fix mxnet failed to update StartTime and CompletionTime #1643

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
12 changes: 6 additions & 6 deletions pkg/controller.v1/mxnet/mxjob_controller.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -326,9 +326,9 @@ func (r *MXJobReconciler) UpdateJobStatus(job interface{}, replicas map[commonv1
return err
}

if mxjob.Status.StartTime == nil {
if jobStatus.StartTime == nil {
now := metav1.Now()
mxjob.Status.StartTime = &now
jobStatus.StartTime = &now
// enqueue a sync to check if job past ActiveDeadlineSeconds
if mxjob.Spec.RunPolicy.ActiveDeadlineSeconds != nil {
logrus.Infof("Job with ActiveDeadlineSeconds will sync after %d seconds", *mxjob.Spec.RunPolicy.ActiveDeadlineSeconds)
Expand Down Expand Up @@ -361,9 +361,9 @@ func (r *MXJobReconciler) UpdateJobStatus(job interface{}, replicas map[commonv1
if expected == 0 {
msg := fmt.Sprintf("MXJob %s is successfully completed.", mxjob.Name)
r.Recorder.Event(mxjob, corev1.EventTypeNormal, mxJobSucceededReason, msg)
if mxjob.Status.CompletionTime == nil {
if jobStatus.CompletionTime == nil {
now := metav1.Now()
mxjob.Status.CompletionTime = &now
jobStatus.CompletionTime = &now
}
err := commonutil.UpdateJobConditions(jobStatus, commonv1.JobSucceeded, mxJobSucceededReason, msg)
if err != nil {
Expand All @@ -387,9 +387,9 @@ func (r *MXJobReconciler) UpdateJobStatus(job interface{}, replicas map[commonv1
} else {
msg := fmt.Sprintf("mxjob %s is failed because %d %s replica(s) failed.", mxjob.Name, failed, rtype)
r.Recorder.Event(mxjob, corev1.EventTypeNormal, mxJobFailedReason, msg)
if mxjob.Status.CompletionTime == nil {
if jobStatus.CompletionTime == nil {
now := metav1.Now()
mxjob.Status.CompletionTime = &now
jobStatus.CompletionTime = &now
}
err := commonutil.UpdateJobConditions(jobStatus, commonv1.JobFailed, mxJobFailedReason, msg)
if err != nil {
Expand Down