Feature/support pytorchjob set queue of volcano (#1415)

* support pytorch use volcano-queue * support pytorch use volcano-queue Signed-off-by: bert.li <qiankun.li@qq.com> * set SchedulingPolicy for runPolicy Signed-off-by: bert.li <qiankun.li@qq.com> * use pytorchjob.Spec.RunPolicy directly
kubeflow · Sep 24, 2021 · 557ba80 · 557ba80
1 parent 7fb592f
commit 557ba80
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 20 deletions.
diff --git a/pkg/controller.v1/mxnet/mxjob_controller.go b/pkg/controller.v1/mxnet/mxjob_controller.go
@@ -166,17 +166,8 @@ func (r *MXJobReconciler) Reconcile(ctx context.Context, req ctrl.Request) (ctrl
 		replicas[commonv1.ReplicaType(k)] = v
 	}
 
-	// Construct RunPolicy based on MXJob.Spec
-	runPolicy := &commonv1.RunPolicy{
-		CleanPodPolicy:          mxjob.Spec.RunPolicy.CleanPodPolicy,
-		TTLSecondsAfterFinished: mxjob.Spec.RunPolicy.TTLSecondsAfterFinished,
-		ActiveDeadlineSeconds:   mxjob.Spec.RunPolicy.ActiveDeadlineSeconds,
-		BackoffLimit:            mxjob.Spec.RunPolicy.BackoffLimit,
-		SchedulingPolicy:        nil,
-	}
-
 	// Use common to reconcile the job related pod and service
-	err = r.ReconcileJobs(mxjob, replicas, mxjob.Status, runPolicy)
+	err = r.ReconcileJobs(mxjob, replicas, mxjob.Status, &mxjob.Spec.RunPolicy)
 	if err != nil {
 		logrus.Warnf("Reconcile MX Job error %v", err)
 		return ctrl.Result{}, err

diff --git a/pkg/controller.v1/pytorch/pytorchjob_controller.go b/pkg/controller.v1/pytorch/pytorchjob_controller.go
@@ -155,17 +155,8 @@ func (r *PyTorchJobReconciler) Reconcile(ctx context.Context, req ctrl.Request)
 	// Set default priorities to pytorch job
 	r.Scheme.Default(pytorchjob)
 
-	// Construct RunPolicy based on PyTorchJob.Spec
-	runPolicy := &commonv1.RunPolicy{
-		CleanPodPolicy:          pytorchjob.Spec.RunPolicy.CleanPodPolicy,
-		TTLSecondsAfterFinished: pytorchjob.Spec.RunPolicy.TTLSecondsAfterFinished,
-		ActiveDeadlineSeconds:   pytorchjob.Spec.RunPolicy.ActiveDeadlineSeconds,
-		BackoffLimit:            pytorchjob.Spec.RunPolicy.BackoffLimit,
-		SchedulingPolicy:        nil,
-	}
-
 	// Use common to reconcile the job related pod and service
-	err = r.ReconcileJobs(pytorchjob, pytorchjob.Spec.PyTorchReplicaSpecs, pytorchjob.Status, runPolicy)
+	err = r.ReconcileJobs(pytorchjob, pytorchjob.Spec.PyTorchReplicaSpecs, pytorchjob.Status, &pytorchjob.Spec.RunPolicy)
 	if err != nil {
 		logrus.Warnf("Reconcile PyTorch Job error %v", err)
 		return ctrl.Result{}, err