hive-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Namit Jain (JIRA)" <>
Subject [jira] Commented: (HIVE-105) estimate number of required reducers and other map-reduce parameters automatically
Date Sat, 06 Dec 2008 01:51:44 GMT


Namit Jain commented on HIVE-105:

The intention of capping mapred.reduce.tasks is to not let the user kill himself by having
too many reducers in case of large map
input jobs. There is no need for another parameter, I thought mapred.reduce.tasks currently
controls maximum reducer count for all hadoop jobs. Most of the users may not change the default
size per reducer. This gives them a control which they are already using to 
have a bound.

Explain plan can be enhanced to show input size for root tasks.

Without going into the details, there needs to be query stage specific variables for number
of reducers which overrides everything.

> estimate number of required reducers and other map-reduce parameters automatically
> ----------------------------------------------------------------------------------
>                 Key: HIVE-105
>                 URL:
>             Project: Hadoop Hive
>          Issue Type: Improvement
>          Components: Query Processor
>            Reporter: Joydeep Sen Sarma
> currently users have to specify number of reducers. In a multi-user environment - we
generally ask users to be prudent in selecting number of reducers (since they are long running
and block other users). Also - large number of reducers produce large number of output files
- which puts pressure on namenode resources.
> there are other map-reduce parameters - for example the min split size and the proposed
use of combinefileinputformat that are also fairly tricky for the user to determine (since
they depend on map side selectivity and cluster size). This will become totally critical when
there is integration with BI tools since there will be no opportunity to optimize job settings
and there will be a wide variety of jobs.
> This jira calls for automating the selection of such parameters - possibly by a best
effort at estimating map side selectivity/output size using sampling and determining such
parameters from there.

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

View raw message