Skip to content

Fix type error for suspended kubeflow jobs #7241

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
strigazi wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fix type error for suspended kubeflow jobs #7241

Show file tree
Hide file tree
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
4 changes: 4 additions & 0 deletions flyteplugins/go/tasks/plugins/k8s/kfoperators/common/common_operator.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,6 +63,8 @@ func GetPhaseInfo(currentCondition kubeflowv1.JobCondition, occurredAt time.Time
return pluginsCore.PhaseInfoRetryableFailure(flyteerr.DownstreamSystemError, details, &taskPhaseInfo), nil
case kubeflowv1.JobRestarting:
return pluginsCore.PhaseInfoRunning(pluginsCore.DefaultPhaseVersion, &taskPhaseInfo), nil
case kubeflowv1.JobSuspended:
return pluginsCore.PhaseInfoQueuedWithTaskInfo(pluginsCore.DefaultPhaseVersion, "Suspended", &taskPhaseInfo), nil
}

return pluginsCore.PhaseInfoUndefined, nil
Expand All @@ -83,6 +85,8 @@ func GetMPIPhaseInfo(currentCondition kubeflowv1.JobCondition, occurredAt time.T
return pluginsCore.PhaseInfoRetryableFailure(flyteerr.DownstreamSystemError, details, &taskPhaseInfo), nil
case kubeflowv1.JobRestarting:
return pluginsCore.PhaseInfoRunning(pluginsCore.DefaultPhaseVersion, &taskPhaseInfo), nil
case kubeflowv1.JobSuspended:
return pluginsCore.PhaseInfoQueuedWithTaskInfo(pluginsCore.DefaultPhaseVersion, "Suspended", &taskPhaseInfo), nil
}

return pluginsCore.PhaseInfoUndefined, nil
Expand Down
18 changes: 18 additions & 0 deletions flyteplugins/go/tasks/plugins/k8s/kfoperators/common/common_operator_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,6 +114,15 @@ func TestGetPhaseInfo(t *testing.T) {
assert.Equal(t, pluginsCore.PhaseRunning, taskPhase.Phase())
assert.NotNil(t, taskPhase.Info())
assert.Nil(t, err)

jobSuspended := kubeflowv1.JobCondition{
Type: kubeflowv1.JobSuspended,
}
taskPhase, err = GetPhaseInfo(jobSuspended, time.Now(), pluginsCore.TaskInfo{})
assert.NoError(t, err)
assert.Equal(t, pluginsCore.PhaseQueued, taskPhase.Phase())
assert.NotNil(t, taskPhase.Info())
assert.Nil(t, err)
}

func TestGetMPIPhaseInfo(t *testing.T) {
Expand Down Expand Up @@ -161,6 +170,15 @@ func TestGetMPIPhaseInfo(t *testing.T) {
assert.Equal(t, pluginsCore.PhaseRunning, taskPhase.Phase())
assert.NotNil(t, taskPhase.Info())
assert.Nil(t, err)

jobSuspended := kubeflowv1.JobCondition{
Type: kubeflowv1.JobSuspended,
}
taskPhase, err = GetMPIPhaseInfo(jobSuspended, time.Now(), pluginsCore.TaskInfo{})
assert.NoError(t, err)
assert.Equal(t, pluginsCore.PhaseQueued, taskPhase.Phase())
assert.NotNil(t, taskPhase.Info())
assert.Nil(t, err)
}

func TestGetLogs(t *testing.T) {
Expand Down
2 changes: 1 addition & 1 deletion flyteplugins/go/tasks/plugins/k8s/kfoperators/mpi/mpi_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -556,7 +556,7 @@ func TestGetTaskPhase(t *testing.T) {
assert.Equal(t, pluginsCore.PhaseInfoUndefined, taskPhase)

// Training operator did not modify the job because it is suspended
mpiJobSuspended := dummyMPIJobResourceCreator(kubeflowv1.JobCreated)
mpiJobSuspended := dummyMPIJobResourceCreator(kubeflowv1.JobSuspended)
Copy link
Copy Markdown
Member

@fg91 fg91 Apr 21, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

When the job was just created, we do treat this as "phase info queued" so the behavior that is tested here is correct, let's not remove coverage but add another text case for suspended please.

Copy link
Copy Markdown
Member

@fg91 fg91 Apr 21, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

In the two files below as well please.

mpiJobSuspended.CreationTimestamp = v1.Time{Time: time.Now().Add(-time.Hour)}
mpiJobSuspended.Status.StartTime = nil
suspend := true
Expand Down
2 changes: 1 addition & 1 deletion flyteplugins/go/tasks/plugins/k8s/kfoperators/pytorch/pytorch_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -677,7 +677,7 @@ func TestGetTaskPhase(t *testing.T) {
assert.Equal(t, pluginsCore.PhaseInfoUndefined, taskPhase)

// Training operator did not modify the job because it is suspended
pytorchJobSuspended := dummyPytorchJobResourceCreator(kubeflowv1.JobCreated)
pytorchJobSuspended := dummyPytorchJobResourceCreator(kubeflowv1.JobSuspended)
pytorchJobSuspended.CreationTimestamp = v1.Time{Time: time.Now().Add(-time.Hour)}
pytorchJobSuspended.Status.StartTime = nil
suspend := true
Expand Down
2 changes: 1 addition & 1 deletion flyteplugins/go/tasks/plugins/k8s/kfoperators/tensorflow/tensorflow_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -602,7 +602,7 @@ func TestGetTaskPhase(t *testing.T) {
assert.Equal(t, pluginsCore.PhaseInfoUndefined, taskPhase)

// Training operator did not modify the job because it is suspended
tfJobSuspended := dummyTensorFlowJobResourceCreator(kubeflowv1.JobCreated)
tfJobSuspended := dummyTensorFlowJobResourceCreator(kubeflowv1.JobSuspended)
tfJobSuspended.CreationTimestamp = v1.Time{Time: time.Now().Add(-time.Hour)}
tfJobSuspended.Status.StartTime = nil
suspend := true
Expand Down