Adds missed failure condition

kubeflow · Jun 1, 2019 · 79f7b05 · 79f7b05
1 parent 60d9b73
commit 79f7b05
Showing 1 changed file with 1 addition and 0 deletions.
diff --git a/pkg/controller.v1/tensorflow/status.go b/pkg/controller.v1/tensorflow/status.go
@@ -149,6 +149,7 @@ func (tc *TFController) updateStatusSingle(tfjob *tfv1.TFJob, rtype tfv1.TFRepli
 				tflogger.LoggerForJob(tfjob).Infof("Append tfjob condition error: %v", err)
 				return err
 			}
+			tfJobsFailureCount.Inc()
 			tfJobsRestartCount.Inc()
 		} else {
 			msg := fmt.Sprintf("TFJob %s has failed because %d %s replica(s) failed.",