Author: omalley
Date: Thu Jun 16 23:06:01 2011
New Revision: 1136732
URL: http://svn.apache.org/viewvc?rev=1136732&view=rev
Log:
MAPREDUCE-2456. Log the reduce taskID and associated TaskTrackers with
failed fetch notifications in the JobTracker log.
(Jeffrey Naisbitt via cdouglas)
Modified:
hadoop/common/branches/branch-0.20-security-204/CHANGES.txt (contents,
props changed)
hadoop/common/branches/branch-0.20-security-204/src/mapred/org/apache/hadoop/mapred/JobInProgress.java
hadoop/common/branches/branch-0.20-security-204/src/mapred/org/apache/hadoop/mapred/JobTracker.java
Modified: hadoop/common/branches/branch-0.20-security-204/CHANGES.txt
URL:
http://svn.apache.org/viewvc/hadoop/common/branches/branch-0.20-security-204/CHANGES.txt?rev=1136732&r1=1136731&r2=1136732&view=diff
==============================================================================
--- hadoop/common/branches/branch-0.20-security-204/CHANGES.txt (original)
+++ hadoop/common/branches/branch-0.20-security-204/CHANGES.txt Thu Jun 16
23:06:01 2011
@@ -20,6 +20,10 @@ Release 0.20.204.0 - unreleased
MAPREDUCE-2535. Fix NPE in JobClient caused by retirement. (Robert Joseph
Evans via cdouglas)
+ MAPREDUCE-2456. Log the reduce taskID and associated TaskTrackers with
+ failed fetch notifications in the JobTracker log.
+ (Jeffrey Naisbitt via cdouglas)
+
HDFS-2044. TestQueueProcessingStatistics failing automatic test due to
timing issues. (mattf)
Propchange: hadoop/common/branches/branch-0.20-security-204/CHANGES.txt
------------------------------------------------------------------------------
--- svn:mergeinfo (original)
+++ svn:mergeinfo Thu Jun 16 23:06:01 2011
@@ -1,5 +1,5 @@
/hadoop/common/branches/branch-0.20/CHANGES.txt:826138,826568,829987,831184,833001,880632,898713,909245,909723,960946,1044225
-/hadoop/common/branches/branch-0.20-security/CHANGES.txt:1097202,1098837,1100336,1101729,1102378,1102869,1103940,1125139,1125170,1125587,1125589,1127362,1131277,1131286,1131290,1131299,1131737,1134140
+/hadoop/common/branches/branch-0.20-security/CHANGES.txt:1097202,1098837,1100336,1101629,1101729,1102378,1102869,1103940,1125139,1125170,1125587,1125589,1127362,1131277,1131286,1131290,1131299,1131737,1134140
/hadoop/common/branches/branch-0.20-security-203/CHANGES.txt:1096071,1097012-1099333,1102071,1128115
/hadoop/common/branches/branch-0.20-security-205/CHANGES.txt:1132788,1133133,1133274,1133282
/hadoop/core/branches/branch-0.18/CHANGES.txt:727226
Modified:
hadoop/common/branches/branch-0.20-security-204/src/mapred/org/apache/hadoop/mapred/JobInProgress.java
URL:
http://svn.apache.org/viewvc/hadoop/common/branches/branch-0.20-security-204/src/mapred/org/apache/hadoop/mapred/JobInProgress.java?rev=1136732&r1=1136731&r2=1136732&view=diff
==============================================================================
---
hadoop/common/branches/branch-0.20-security-204/src/mapred/org/apache/hadoop/mapred/JobInProgress.java
(original)
+++
hadoop/common/branches/branch-0.20-security-204/src/mapred/org/apache/hadoop/mapred/JobInProgress.java
Thu Jun 16 23:06:01 2011
@@ -3262,13 +3262,17 @@ public class JobInProgress {
synchronized void fetchFailureNotification(TaskInProgress tip,
TaskAttemptID mapTaskId,
- String trackerName) {
+ String mapTrackerName,
+ TaskAttemptID reduceTaskId,
+ String reduceTrackerName) {
Integer fetchFailures = mapTaskIdToFetchFailuresMap.get(mapTaskId);
fetchFailures = (fetchFailures == null) ? 1 : (fetchFailures+1);
mapTaskIdToFetchFailuresMap.put(mapTaskId, fetchFailures);
- LOG.info("Failed fetch notification #" + fetchFailures + " for task " +
- mapTaskId);
-
+ LOG.info("Failed fetch notification #" + fetchFailures + " for map task: "
+ + mapTaskId + " running on tracker: " + mapTrackerName
+ + " and reduce task: " + reduceTaskId + " running on tracker: "
+ + reduceTrackerName);
+
float failureRate = (float)fetchFailures / runningReduceTasks;
// declare faulty if fetch-failures >= max-allowed-failures
boolean isMapFaulty = failureRate >= MAX_ALLOWED_FETCH_FAILURES_PERCENT;
@@ -3280,7 +3284,7 @@ public class JobInProgress {
failedTask(tip, mapTaskId, "Too many fetch-failures",
(tip.isMapTask() ? TaskStatus.Phase.MAP :
TaskStatus.Phase.REDUCE),
- TaskStatus.State.FAILED, trackerName);
+ TaskStatus.State.FAILED, mapTrackerName);
mapTaskIdToFetchFailuresMap.remove(mapTaskId);
}
Modified:
hadoop/common/branches/branch-0.20-security-204/src/mapred/org/apache/hadoop/mapred/JobTracker.java
URL:
http://svn.apache.org/viewvc/hadoop/common/branches/branch-0.20-security-204/src/mapred/org/apache/hadoop/mapred/JobTracker.java?rev=1136732&r1=1136731&r2=1136732&view=diff
==============================================================================
---
hadoop/common/branches/branch-0.20-security-204/src/mapred/org/apache/hadoop/mapred/JobTracker.java
(original)
+++
hadoop/common/branches/branch-0.20-security-204/src/mapred/org/apache/hadoop/mapred/JobTracker.java
Thu Jun 16 23:06:01 2011
@@ -4747,9 +4747,11 @@ public class JobTracker implements MRCon
if (failedFetchTrackerName == null) {
failedFetchTrackerName = "Lost task tracker";
}
- failedFetchMap.getJob().fetchFailureNotification(failedFetchMap,
- mapTaskId,
-
failedFetchTrackerName);
+ failedFetchMap.getJob().fetchFailureNotification(failedFetchMap,
+ mapTaskId,
+
failedFetchTrackerName,
+ taskId,
+ trackerName);
}
}
}