[jira] [Commented] (LUCENE-7258) Tune DocIdSetBuilder allocation rate

["David Smiley (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/LUCENE-7258?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15265590#comment-15265590 ] 

David Smiley commented on LUCENE-7258:
--------------------------------------

It appears to me that caching bitsets is a much easier task than most any other caches I've seen -- there is no key and most (half on average?) bitsets in the cache will be long enough to be re-used by some subsequent lookup.  RE knowing when an instance can be recycled -- if it were in conjunction with the QueryCache, then on eviction the bitset can be put into a bitset cache.  RE knowing when bitsets should be evicted, especially for a library -- make that configurable/disable?  _My_ main concern with such a cache is its overall code impact -- how many places would be touched by it.  Perhaps a lot but maybe not too bad?  And of course for what measurable benefit?  I imagine some of the GC cost of the current situation can be addressed with GC tuning -- say raising the young gen via {{-Xmn}}.

> Tune DocIdSetBuilder allocation rate
> ------------------------------------
>
>                 Key: LUCENE-7258
>                 URL: https://issues.apache.org/jira/browse/LUCENE-7258
>             Project: Lucene - Core
>          Issue Type: Improvement
>          Components: modules/spatial
>            Reporter: Jeff Wartes
>         Attachments: LUCENE-7258-Tune-memory-allocation-rate-for-Intersec.patch, LUCENE-7258-Tune-memory-allocation-rate-for-Intersec.patch, allocation_plot.jpg
>
>
> LUCENE-7211 converted IntersectsPrefixTreeQuery to use DocIdSetBuilder, but didn't actually reduce garbage generation for my Solr index.
> Since something like 40% of my garbage (by space) is now attributed to DocIdSetBuilder.growBuffer, I charted a few different allocation strategies to see if I could tune things more. 
> See here: http://i.imgur.com/7sXLAYv.jpg 
> The jump-then-flatline at the right would be where DocIdSetBuilder gives up and allocates a FixedBitSet for a 100M-doc index. (The 1M-doc index curve/cutoff looked similar)
> Perhaps unsurprisingly, the 1/8th growth factor in ArrayUtil.oversize is terrible from an allocation standpoint if you're doing a lot of expansions, and is especially terrible when used to build a short-lived data structure like this one.
> By the time it goes with the FBS, it's allocated around twice as much memory for the buffer as it would have needed for just the FBS.



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

---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscribe@lucene.apache.org
For additional commands, e-mail: dev-help@lucene.apache.org