[
https://issues.apache.org/jira/browse/HIVE-4440?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13647395#comment-13647395
]
Gunther Hagleitner commented on HIVE-4440:
------------------------------------------
Thanks :-)
Patch .2 honors the old parameter unless it's at the default in which case it
uses the new one. I also put documentation around it.
You bring up a good point, but are you sure it's necessary to support both in
this case though? It's just slightly ugly in the code and requires us to move
in again to remove later. My thinking is this: If you use the old parameter,
it's probably because you needed to up it to get better performance - in this
case the new default should most likely be ok for you. Do you think there's
going to be cases where this falls flat?
> SMB Operator spills to disk like it's 1999
> ------------------------------------------
>
> Key: HIVE-4440
> URL: https://issues.apache.org/jira/browse/HIVE-4440
> Project: Hive
> Issue Type: Bug
> Reporter: Gunther Hagleitner
> Assignee: Gunther Hagleitner
> Attachments: HIVE-4440.1.patch, HIVE-4440.2.patch
>
>
> I was recently looking into some performance issue with a query that used SMB
> join and was running really slow. Turns out that the SMB join by default
> caches only 100 values per key before spilling to disk. That seems overly
> conservative to me. Changing the parameter resulted in a ~5x speedup - quite
> significant.
> The parameter is: hive.mapjoin.bucket.cache.size
> Which right now is only used the SMB Operator as far as I can tell.
> The parameter was introduced originally (3 yrs ago) for the map join operator
> (looks like pre-SMB) and set to 100 to avoid OOM. That seems to have been in
> a different context though where you had to avoid running out of memory with
> the cached hash table in the same process, I think.
> Two things I'd like to propose:
> a) Rename it to what it does: hive.smbjoin.cache.rows
> b) Set it to something less restrictive: 10000
> If you string together a 5 table smb join with a map join and a map-side
> group by aggregation you might still run out of memory, but the renamed
> parameter should be easier to find and reduce. For most queries, I would
> think that 10000 is still a reasonable number to cache (On the reduce side we
> use 25000 for shuffle joins).
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira
