Pārlūkot izejas kodu

MAPREDUCE-6395. Improve the commit failure messages in MRAppMaster recovery. (Brahma Reddy Battula via gera)

Gera Shegalov 10 gadi atpakaļ
vecāks
revīzija
10107243be

+ 3 - 0
hadoop-mapreduce-project/CHANGES.txt

@@ -349,6 +349,9 @@ Release 2.8.0 - UNRELEASED
     MAPREDUCE-6392. Document mapred class path options.
     (Brahma Reddy Battula via cnauroth)
 
+    MAPREDUCE-6395. Improve the commit failure messages in MRAppMaster recovery.
+    (Brahma Reddy Battula via gera)
+
   OPTIMIZATIONS
 
   BUG FIXES

+ 10 - 4
hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/MRAppMaster.java

@@ -334,14 +334,20 @@ public class MRAppMaster extends CompositeService {
             " because a commit was started.");
         copyHistory = true;
         if (commitSuccess) {
-          shutDownMessage = "We crashed after successfully committing. Recovering.";
+          shutDownMessage =
+              "Job commit succeeded in a prior MRAppMaster attempt " +
+              "before it crashed. Recovering.";
           forcedState = JobStateInternal.SUCCEEDED;
         } else if (commitFailure) {
-          shutDownMessage = "We crashed after a commit failure.";
+          shutDownMessage =
+              "Job commit failed in a prior MRAppMaster attempt " +
+              "before it crashed. Not retrying.";
           forcedState = JobStateInternal.FAILED;
         } else {
           //The commit is still pending, commit error
-          shutDownMessage = "We crashed durring a commit";
+          shutDownMessage =
+              "Job commit from a prior MRAppMaster attempt is " +
+              "potentially in progress. Preventing multiple commit executions";
           forcedState = JobStateInternal.ERROR;
         }
       }
@@ -582,7 +588,7 @@ public class MRAppMaster extends CompositeService {
       //if isLastAMRetry comes as true, should never set it to false
       if ( !isLastAMRetry){
         if (((JobImpl)job).getInternalState() != JobStateInternal.REBOOT) {
-          LOG.info("We are finishing cleanly so this is the last retry");
+          LOG.info("Job finished cleanly, recording last MRAppMaster retry");
           isLastAMRetry = true;
         }
       }