File tree Expand file tree Collapse file tree 1 file changed +7
-2
lines changed
Expand file tree Collapse file tree 1 file changed +7
-2
lines changed Original file line number Diff line number Diff line change @@ -84,6 +84,11 @@ func (s *SimpleScheduler) ScheduleFailedModels() ([]string, error) {
8484 return updatedModels , nil
8585}
8686
87+ // Get failed models
88+ // Currently this includes:
89+ // - models that have failed to schedule
90+ // - models that have failed to load
91+ // - models that have loaded but not all replicas are available (e.g. min replicas is met but not desired replicas)
8792func (s * SimpleScheduler ) getFailedModels () ([]string , error ) {
8893 models , err := s .store .GetModels ()
8994 if err != nil {
@@ -94,8 +99,8 @@ func (s *SimpleScheduler) getFailedModels() ([]string, error) {
9499 version := model .GetLatest ()
95100 if version != nil {
96101 versionState := version .ModelState ()
97- if versionState .State == store .ModelFailed || versionState .State == store .ScheduleFailed ||
98- (versionState .State == store .ModelAvailable && versionState .AvailableReplicas < version .GetDeploymentSpec ().GetReplicas ()) {
102+ if versionState .State == store .ModelFailed || versionState .State == store .ScheduleFailed ||
103+ (versionState .State == store .ModelAvailable && versionState .AvailableReplicas < version .GetDeploymentSpec ().GetReplicas ()) {
99104 failedModels = append (failedModels , model .Name )
100105 }
101106 }
You can’t perform that action at this time.
0 commit comments