Skip to content

Emit events when fails to reconcile all trials #1706

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

Merged
merged 2 commits into from
Oct 28, 2021
Merged

Emit events when fails to reconcile all trials #1706

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5bb3cad
Emit events when fails to reconcile all trials
henrysecond1 Sep 11, 2021
e3398ce
Return error only when fails to get trial instance
henrysecond1 Oct 27, 2021
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: 8 additions & 3 deletions pkg/controller.v1beta1/experiment/experiment_controller.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -355,8 +355,14 @@ func (r *ReconcileExperiment) createTrials(instance *experimentsv1beta1.Experime
}
var trialNames []string
for _, trial := range trials {
if err = r.createTrialInstance(instance, &trial); err != nil {
logger.Error(err, "Create trial instance error", "trial", trial)
trialInstance, err := r.getTrialInstance(instance, &trial)
if err != nil {
logger.Error(err, "Get trial instance error", "trial", trial)
return err
}
// Due to unsynchronised policy of Kubernetes controllers, trial creation can fail.
if err = r.Create(context.TODO(), trialInstance); err != nil {
logger.Error(err, "Trial create error", "Trial name", trial.Name)
continue
}
trialNames = append(trialNames, trial.Name)
Expand All @@ -365,7 +371,6 @@ func (r *ReconcileExperiment) createTrials(instance *experimentsv1beta1.Experime
if len(trialNames) != 0 {
logger.Info("Created Trials", "trialNames", trialNames)
}

return nil
}

Expand Down
13 changes: 4 additions & 9 deletions pkg/controller.v1beta1/experiment/experiment_controller_util.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@ const (
updatePrometheusMetrics = "update-prometheus-metrics"
)

func (r *ReconcileExperiment) createTrialInstance(expInstance *experimentsv1beta1.Experiment, trialAssignment *suggestionsv1beta1.TrialAssignment) error {
func (r *ReconcileExperiment) getTrialInstance(expInstance *experimentsv1beta1.Experiment, trialAssignment *suggestionsv1beta1.TrialAssignment) (*trialsv1beta1.Trial, error) {
logger := log.WithValues("Experiment", types.NamespacedName{Name: expInstance.GetName(), Namespace: expInstance.GetNamespace()})

trial := &trialsv1beta1.Trial{}
Expand All @@ -46,7 +46,7 @@ func (r *ReconcileExperiment) createTrialInstance(expInstance *experimentsv1beta

if err := controllerutil.SetControllerReference(expInstance, trial, r.scheme); err != nil {
logger.Error(err, "Set controller reference error")
return err
return nil, err
}

trial.Spec.Objective = expInstance.Spec.Objective
Expand All @@ -61,7 +61,7 @@ func (r *ReconcileExperiment) createTrialInstance(expInstance *experimentsv1beta
runSpec, err := r.GetRunSpecWithHyperParameters(expInstance, trial.Name, trial.Namespace, hps)
if err != nil {
logger.Error(err, "Fail to get RunSpec from experiment", expInstance.Name)
return err
return nil, err
}

trial.Spec.RunSpec = runSpec
Expand All @@ -86,12 +86,7 @@ func (r *ReconcileExperiment) createTrialInstance(expInstance *experimentsv1beta
trial.Spec.FailureCondition = expInstance.Spec.TrialTemplate.FailureCondition
}

if err := r.Create(context.TODO(), trial); err != nil {
logger.Error(err, "Trial create error", "Trial name", trial.Name)
return err
}
return nil

return trial, nil
}

func needUpdateFinalizers(exp *experimentsv1beta1.Experiment) (bool, []string) {
Expand Down