lucene-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Mark Miller <markrmil...@gmail.com>
Subject Re: [jira] Commented: (LUCENE-1997) Explore performance of multi-PQ vs single-PQ sorting API
Date Mon, 02 Nov 2009 23:16:13 GMT
That I don't know. Probably fewer than more, but that's just me  
guessing based on common sense :)

- Mark

http://www.lucidimagination.com (mobile)

On Nov 2, 2009, at 6:13 PM, Jake Mannix <jake.mannix@gmail.com> wrote:

> Ok, and how many of those users are also running on indices with  
> hundreds of segments?
>
>   -jake
>
> On Mon, Nov 2, 2009 at 3:10 PM, Mark Miller <markrmiller@gmail.com>  
> wrote:
> There are plenty of Lucene users that do go 1000 in. We've been  
> calling it "deep paging" at LI. I like that name :)
>
> - Mark
>
> http://www.lucidimagination.com (mobile)
>
>
> On Nov 2, 2009, at 6:04 PM, "Jake Mannix (JIRA)" <jira@apache.org>  
> wrote:
>
>
>   [ https://issues.apache.org/jira/browse/LUCENE-1997?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12772741#action_12772741

>  ]
>
> Jake Mannix commented on LUCENE-1997:
> -------------------------------------
>
> The current concern is to do with the memory?  I'm more concerned  
> with the weird "java ghosts" that are flying around, sometimes  
> swaying results by 20-40%...  the memory could only be an issue on a  
> setup with hundreds of segments and sorting the top 1000 values (do  
> we really try to optimize for this performance case?).  In the  
> normal case (no more than tens of segments, and the top 10 or 100  
> hits), we're talking about what, 100-1000 PQ entries?
>
> Explore performance of multi-PQ vs single-PQ sorting API
> --------------------------------------------------------
>
>               Key: LUCENE-1997
>               URL: https://issues.apache.org/jira/browse/LUCENE-1997
>           Project: Lucene - Java
>        Issue Type: Improvement
>        Components: Search
>  Affects Versions: 2.9
>          Reporter: Michael McCandless
>          Assignee: Michael McCandless
>       Attachments: LUCENE-1997.patch, LUCENE-1997.patch,  
> LUCENE-1997.patch, LUCENE-1997.patch, LUCENE-1997.patch,  
> LUCENE-1997.patch, LUCENE-1997.patch, LUCENE-1997.patch,  
> LUCENE-1997.patch
>
>
> Spinoff from recent "lucene 2.9 sorting algorithm" thread on java-dev,
> where a simpler (non-segment-based) comparator API is proposed that
> gathers results into multiple PQs (one per segment) and then merges
> them in the end.
> I started from John's multi-PQ code and worked it into
> contrib/benchmark so that we could run perf tests.  Then I generified
> the Python script I use for running search benchmarks (in
> contrib/benchmark/sortBench.py).
> The script first creates indexes with 1M docs (based on
> SortableSingleDocSource, and based on wikipedia, if available).  Then
> it runs various combinations:
>  * Index with 20 balanced segments vs index with the "normal" log
>   segment size
>  * Queries with different numbers of hits (only for wikipedia index)
>  * Different top N
>  * Different sorts (by title, for wikipedia, and by random string,
>   random int, and country for the random index)
> For each test, 7 search rounds are run and the best QPS is kept.  The
> script runs singlePQ then multiPQ, and records the resulting best QPS
> for each and produces table (in Jira format) as output.
>
> -- 
> This message is automatically generated by JIRA.
> -
> You can reply to this email to add a comment to the issue online.
>
>
> ---------------------------------------------------------------------
> To unsubscribe, e-mail: java-dev-unsubscribe@lucene.apache.org
> For additional commands, e-mail: java-dev-help@lucene.apache.org
>
>
> ---------------------------------------------------------------------
> To unsubscribe, e-mail: java-dev-unsubscribe@lucene.apache.org
> For additional commands, e-mail: java-dev-help@lucene.apache.org
>
>

Mime
View raw message