drill-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Steven Phillips (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (DRILL-2936) TPCH 4 and 18 SF100 hangs when hash agg is turned off
Date Thu, 07 May 2015 17:21:01 GMT

    [ https://issues.apache.org/jira/browse/DRILL-2936?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14533036#comment-14533036
] 

Steven Phillips commented on DRILL-2936:
----------------------------------------

I agree. I am working on it right now. My thought right now is to use when there is a HashToMerge
exchange.

Are there any other situation where we would want to use it? My other thought was that it
might be useful in the case of a sort, where there is a HashToRandom exchange before the sort,
and the ExternalSort starts spilling to disk, this can result in very poor performance because
all of the senders get blocked as soon as any one sort fragment starts spilling. Using the
spooling buffer would prevent this from happening.

> TPCH 4 and 18 SF100 hangs when hash agg is turned off
> -----------------------------------------------------
>
>                 Key: DRILL-2936
>                 URL: https://issues.apache.org/jira/browse/DRILL-2936
>             Project: Apache Drill
>          Issue Type: Bug
>          Components: Execution - Flow
>            Reporter: Ramana Inukonda Nagaraj
>            Assignee: Steven Phillips
>            Priority: Critical
>             Fix For: 1.0.0
>
>         Attachments: Screen Shot 2015-05-01 at 2.40.36 PM.png
>
>
> sys options:
> {code}
> 0: jdbc:drill:schema=dfs.drillTestDirTpch100P> alter system set `planner.memory.max_query_memory_per_node`
= 29205777612;
> 0: jdbc:drill:schema=dfs.drillTestDirTpch100P> alter system set `planner.enable_hashjoin`=false;
> 0: jdbc:drill:schema=dfs.drillTestDirTpch100P> alter system set `planner.enable_hashagg`=false;
> {code}
> On executing TPCH 04 query hangs. From the profiles page does not look like any fragments
are making progress, the last progress time stamps were sometime back. 
> Attached is the logical plan. 



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message