hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Christian Kunz (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HADOOP-4714) map tasks timing out during merge phase
Date Mon, 24 Nov 2008 06:43:44 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-4714?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12650115#action_12650115
] 

Christian Kunz commented on HADOOP-4714:
----------------------------------------

These tasks report a time of failure when there are still messages logged to the syslog file,
indicating that this might be a lack of progress reporting.

E.g.
attempt_200811221852_0001_m_093617_0		FAILED	0.00% 24-Nov-2008 06:26:23 (1hrs, 6mins, 20sec)
	
Task attempt_200811221852_0001_m_093617_0 failed to report status for 1218 seconds. Killing!


syslog:
...
2008-11-24 06:26:21,607 INFO org.apache.hadoop.mapred.MapTask: Index: (1358423777, 193912,
94564)
2008-11-24 06:26:21,636 INFO org.apache.hadoop.mapred.Merger: Merging 13 sorted segments
2008-11-24 06:26:21,654 INFO org.apache.hadoop.mapred.Merger: Down to the last merge-pass,
with 13 segments left of total size: 101764 bytes
2008-11-24 06:26:21,680 INFO org.apache.hadoop.mapred.MapTask: Index: (1358518341, 173266,
89638)
2008-11-24 06:26:21,709 INFO org.apache.hadoop.mapred.Merger: Merging 13 sorted segments
2008-11-24 06:26:21,749 INFO org.apache.hadoop.mapred.Merger: Down to the last merge-pass,
with 13 segments left of total size: 121477 bytes
2008-11-24 06:26:21,780 INFO org.apache.hadoop.mapred.MapTask: Index: (1358607979, 219875,
102296)
2008-11-24 06:26:21,809 INFO org.apache.hadoop.mapred.Merger: Merging 13 sorted segments
2008-11-24 06:26:21,827 INFO org.apache.hadoop.mapred.Merger: Down to the last merge-pass,
with 13 segments left of total size: 110955 bytes
2008-11-24 06:26:21,855 INFO org.apache.hadoop.mapred.MapTask: Index: (1358710275, 191382,
97152)
2008-11-24 06:26:22,023 INFO org.apache.hadoop.mapred.Merger: Merging 13 sorted segments
2008-11-24 06:26:22,178 INFO org.apache.hadoop.mapred.Merger: Down to the last merge-pass,
with 13 segments left of total size: 105632 bytes

> map tasks timing out during merge phase
> ---------------------------------------
>
>                 Key: HADOOP-4714
>                 URL: https://issues.apache.org/jira/browse/HADOOP-4714
>             Project: Hadoop Core
>          Issue Type: Bug
>          Components: mapred
>    Affects Versions: 0.18.1
>            Reporter: Christian Kunz
>
> With compression of transient data turned on some parts of the merge phase seem to not
report progress enough.
> We see a lot of task failures during the merge phase, most of them timing out (even with
a 20 min timeout)

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.


Mime
View raw message