vsinghal85 commented on code in PR #4084:
URL: https://github.com/apache/gobblin/pull/4084#discussion_r1883636990
##########
gobblin-service/src/main/java/org/apache/gobblin/service/modules/orchestration/proc/DagProcUtils.java:
##########
@@ -139,12 +138,15 @@ public static void
submitJobToExecutor(DagManagementStateStore dagManagementStat
dagManagementStateStore.updateDagNode(dagNode);
sendEnforceJobStartDeadlineDagAction(dagManagementStateStore, dagNode);
} catch (Exception e) {
- TimingEvent jobFailedTimer =
DagProc.eventSubmitter.getTimingEvent(TimingEvent.LauncherTimings.JOB_FAILED);
String message = "Cannot submit job " +
DagUtils.getFullyQualifiedJobName(dagNode) + " on executor " + specExecutorUri;
log.error(message, e);
- jobMetadata.put(TimingEvent.METADATA_MESSAGE, message + " due to " +
e.getMessage());
- if (jobFailedTimer != null) {
- jobFailedTimer.stop(jobMetadata);
+ // Only mark the job as failed in case of non transient exceptions
+ if(!DagProcessingEngine.isTransientException(e)) {
Review Comment:
updated
##########
gobblin-service/src/test/java/org/apache/gobblin/service/modules/orchestration/DagProcessingEngineTest.java:
##########
@@ -196,9 +196,15 @@ public void dagProcessingTest()
10000L, "dagTaskStream was not called " + expectedNumOfInvocations + "
number of times. "
+ "Actual number of invocations " +
Mockito.mockingDetails(this.dagTaskStream).getInvocations().size(),
log, 1, 1000L);
-
+ // Currently we are treating all exceptions as non retryable and
totalExceptionCount will be equal to count of non retryable exceptions
Assert.assertEquals(dagManagementStateStore.getDagManagerMetrics().dagProcessingExceptionMeter.getCount(),
expectedExceptions);
-
Assert.assertEquals(dagManagementStateStore.getDagManagerMetrics().dagProcessingNonRetryableExceptionMeter.getCount(),
expectedNonRetryableExceptions);
+
Assert.assertEquals(dagManagementStateStore.getDagManagerMetrics().dagProcessingNonRetryableExceptionMeter.getCount(),
expectedExceptions);
Review Comment:
thanks for pointing out, removed
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
