hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Doug Cutting (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HADOOP-1144) Hadoop should allow a configurable percentage of failed map tasks before declaring a job failed.
Date Mon, 30 Apr 2007 17:50:15 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-1144?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#action_12492727
] 

Doug Cutting commented on HADOOP-1144:
--------------------------------------

bq. Christian: could be made configurable separately for mappers and reducers

I agree that it makes sense to have separate parameters for map and reduce, something like
mapred.max.map.failures.percent and mapred.max.reduce.failures.percent.  These should be settable
from JobConf.

bq. Owen: need [..] an interface to determine how many of the maps and reduces failed.

Could we use counters for this?


> Hadoop should allow a configurable percentage of failed map tasks before declaring a
job failed.
> ------------------------------------------------------------------------------------------------
>
>                 Key: HADOOP-1144
>                 URL: https://issues.apache.org/jira/browse/HADOOP-1144
>             Project: Hadoop
>          Issue Type: Improvement
>          Components: mapred
>    Affects Versions: 0.12.0
>            Reporter: Christian Kunz
>         Assigned To: Arun C Murthy
>             Fix For: 0.13.0
>
>
> In our environment it can occur that some map tasks will fail repeatedly because of corrupt
input data, which sometimes is non-critical as long as the amount is limited. In this case
it is annoying that the whole Hadoop job fails and cannot be restarted till the corrupt data
are identified and eliminated from the input. It would be extremely helpful if the job configuration
would allow to indicate how many map tasks are allowed to fail.

-- 
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