kubeflow
/
mpi-operator
mirror of https://github.com/kubeflow/mpi-operator.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge edbde8caeb into b1c5c9d060

This commit is contained in:
wang-mask 2025-09-24 21:03:30 +08:00 committed by GitHub
parent b1c5c9d060 edbde8caeb
commit d659ed29c4
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
pkg/controller/mpi_job_controller.go
View File

@ -674,7 +674,7 @@ func (c *MPIJobController) syncHandler(key string) error {
}
}
if launcher == nil {
if mpiJob.Spec.LauncherCreationPolicy == kubeflow.LauncherCreationPolicyAtStartup || c.countReadyWorkerPods(worker) == len(worker) {
if mpiJob.Spec.LauncherCreationPolicy == kubeflow.LauncherCreationPolicyAtStartup || (!isMPIJobSuspended(mpiJob) && c.countReadyWorkerPods(worker) == len(worker)) {
launcher, err = c.kubeClient.BatchV1().Jobs(namespace).Create(context.TODO(), c.newLauncherJob(mpiJob), metav1.CreateOptions{})
if err != nil {
c.recorder.Eventf(mpiJob, corev1.EventTypeWarning, mpiJobFailedReason, "launcher pod created failed: %v", err)