Improve Samza AM retry count logging (#1701)

* LISAMZA-43659 Improve Samza AM retry count logging * Output Current Timestamp at run-class.sh script (#1702) * print current timestamp * Fix typo * fix build issue about grolifant okhttp --------- Co-authored-by: Haolan Ye <[email protected]> * Revert "Output Current Timestamp at run-class.sh script (#1702)" This reverts commit 1e84ac0. --------- Co-authored-by: Michael Barskii <[email protected]> Co-authored-by: Haolan Ye <[email protected]> Co-authored-by: Haolan Ye <[email protected]>
apache · Aug 8, 2024 · 5b4b1b7 · 5b4b1b7
1 parent 17e552c
commit 5b4b1b7
Showing 1 changed file with 4 additions and 3 deletions.
diff --git a/samza-core/src/main/java/org/apache/samza/clustermanager/ContainerProcessManager.java b/samza-core/src/main/java/org/apache/samza/clustermanager/ContainerProcessManager.java
@@ -572,9 +572,10 @@ void onResourceCompletedWithUnknownStatus(SamzaResourceStatus resourceStatus, St
 
       // if fail count is (1 initial failure + max retries) then fail job.
       if (currentFailCount > retryCount) {
-        LOG.error("Processor ID: {} (current Container ID: {}) has failed {} times, with last failure {} ms ago. " +
-                "This is greater than retry count of {} and window of {} ms, ",
-            processorId, containerId, currentFailCount, durationSinceLastRetryMs, retryCount, retryWindowMs);
+        LOG.error("Processor ID: {} (current Container ID: {}) has failed {} times. "
+                + "This is greater that the retry count of {}."
+                + "The failure occurred {} ms after the previous one, which is less than the retry window of {} ms.",
+            processorId, containerId, currentFailCount, retryCount, durationSinceLastRetryMs, retryWindowMs);
 
         // We have too many failures, and we're within the window
         // boundary, so reset shut down the app master.