You are viewing a plain text version of this content. The canonical link for it is here.
Posted to common-dev@hadoop.apache.org by "Owen O'Malley (JIRA)" <ji...@apache.org> on 2006/10/04 06:19:20 UTC
[jira] Commented: (HADOOP-569) Hadoop should allow the user to
dynamically change the number of times to re-try failed tasks before
declaring the job fail
[ http://issues.apache.org/jira/browse/HADOOP-569?page=comments#action_12439720 ]
Owen O'Malley commented on HADOOP-569:
--------------------------------------
One part that should be changed before this is considered is to remove the generation of all of the possible task names for a job at job creation. With 4 tasks/tip, it is lame, but not that harmful. If someone set the number of tasks/tip to 10000, it would be a big problem.
Additionally, changing the number dynamically is a big jump from the current model. It would be much more consistent to allow the user to set it in the JobConf at job submission time. What is the advantage of changing it dynamically?
> Hadoop should allow the user to dynamically change the number of times to re-try failed tasks before declaring the job fail
> ---------------------------------------------------------------------------------------------------------------------------
>
> Key: HADOOP-569
> URL: http://issues.apache.org/jira/browse/HADOOP-569
> Project: Hadoop
> Issue Type: Improvement
> Components: mapred
> Reporter: Runping Qi
>
> Hadoop has a built-in mechanism to fail a job if some tasks failed more than 3 times. This mechanism works fine in most scenarios. However, in some other cases, it is highly desirable for the user to change (increase) that number. My current running job demonstrates such a scenario: The job has run more than 2.5 days. It is close to complete (90+%). Everything indicates that it will finish eventually in a day, except for one potential danger: some of the tasks are in their 3rd try!
> It will be extremely helpful if I can change the maximun number of tries to 6 instead of 4!
--
This message is automatically generated by JIRA.
-
If you think it was sent incorrectly contact one of the administrators: http://issues.apache.org/jira/secure/Administrators.jspa
-
For more information on JIRA, see: http://www.atlassian.com/software/jira