| clear query|facets|time |
Search criteria: .
Results from 31 to 40 from
116 (0.129s).
|
|
|
Loading phrases to help you
refine your search...
|
|
[MAPREDUCE-5000] TaskImpl.getCounters() can return the counters for the wrong task attempt when task is speculating - MapReduce - [issue]
|
|
...When a task is speculating and one attempt completes then sometimes the counters for the wrong attempt are aggregated into the total counters for the job. The scenario looks like this:...
|
|
|
http://issues.apache.org/jira/browse/MAPREDUCE-5000
Author: Jason Lowe,
2013-02-14, 14:05
|
|
|
[MAPREDUCE-4982] AM hung with one pending map task - MapReduce - [issue]
|
|
...Saw a job that hung with one pending map task that never ran. The task was in the SCHEDULED state with a single attempt that was in the UNASSIGNED state. The AM looked like it wa...
|
|
|
http://issues.apache.org/jira/browse/MAPREDUCE-4982
Author: Jason Lowe,
2013-02-13, 02:00
|
|
|
Re: [VOTE] Release hadoop-2.0.3-alpha - MapReduce - [mail # dev]
|
|
...+1 (non-binding) - Verified checksums and signatures on src and binary tarballs - Built from source - Deployed pseudo-distributed cluster and ran some example jobs Jason On...
|
|
|
Author: Jason Lowe,
2013-02-12, 23:56
|
|
|
[MAPREDUCE-4648] Diagnostics from AM are missing from job history - MapReduce - [issue]
|
|
...When a job fails during setup or commit, any diagnostics from the MapReduce ApplicationMaster are not available in the job history. Currently the diagnostics for the job are collected ...
|
|
|
http://issues.apache.org/jira/browse/MAPREDUCE-4648
Author: Jason Lowe,
2013-02-12, 20:59
|
|
|
[MAPREDUCE-4704] TaskHeartbeatHandler misreports a ping timeout as a task timeout - MapReduce - [issue]
|
|
...When a task fails to ping within the hardcoded ping timeout of 5 minutes, TaskHeartbeatHandler logs a message reporting the wrong timeout value. It reports a timeout of mapreduce.task....
|
|
|
http://issues.apache.org/jira/browse/MAPREDUCE-4704
Author: Jason Lowe,
2013-02-12, 20:58
|
|
|
[MAPREDUCE-4818] Easier identification of tasks that timeout during localization - MapReduce - [issue]
|
|
...When a task is taking too long to localize and is killed by the AM due to task timeout, the job UI/history is not very helpful. The attempt simply lists a diagnostic stating it was kil...
|
|
|
http://issues.apache.org/jira/browse/MAPREDUCE-4818
Author: Jason Lowe,
2013-02-12, 20:57
|
|
|
[MAPREDUCE-4999] AM attempt ended up in ERROR state and generated history after node decommissioned - MapReduce - [issue]
|
|
...Saw a case where a job recorded history for an app attempt that ended up in the ERROR state after the node the AM was running on was decommissioned. When the node was decommissioned, t...
|
|
|
http://issues.apache.org/jira/browse/MAPREDUCE-4999
Author: Jason Lowe,
2013-02-11, 16:07
|
|
|
[MAPREDUCE-4797] LocalContainerAllocator can loop forever trying to contact the RM - MapReduce - [issue]
|
|
...If LocalContainerAllocator has trouble communicating with the RM it can end up retrying forever if the nature of the error is not a YarnException.This can be particulary bad if the connectio...
|
|
|
http://issues.apache.org/jira/browse/MAPREDUCE-4797
Author: Jason Lowe,
2013-02-06, 17:05
|
|
|
[MAPREDUCE-4771] KeyFieldBasedPartitioner not partitioning properly when configured - MapReduce - [issue]
|
|
...Relative to Hadoop 0.20/1.x, KeyFieldBasedPartitioner is not distributing across partitions properly when configured. This is related to the double-configure issue as described in HADO...
|
|
|
http://issues.apache.org/jira/browse/MAPREDUCE-4771
Author: Jason Lowe,
2013-02-06, 17:05
|
|
|
[MAPREDUCE-4666] JVM metrics for history server - MapReduce - [issue]
|
|
...It would be nice if the job history server provided the same JVM metrics via metrics2 that other Hadoop daemons are already providing....
|
|
|
http://issues.apache.org/jira/browse/MAPREDUCE-4666
Author: Jason Lowe,
2013-02-06, 17:05
|
|
|
|
