[
https://issues.apache.org/jira/browse/LUCENE-893?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#action_12499325
]
Michael Busch commented on LUCENE-893:
--------------------------------------
> Do you have any results for non-compound format?
I converted the index to non-cfs format and reran the same test,
varying the readBufferSize (i. e. the buffer size for all input
streams).
Results for conjunction queries:
1 KB: Time: 52422 ms.
2 KB: Time: 47718 ms.
4 KB: Time: 50078 ms.
8 KB: Time: 54719 ms.
Results for disjunction queries:
1 KB: Time: 291000 ms.
2 KB: Time: 266110 ms.
4 KB: Time: 258844 ms.
8 KB: Time: 279812 ms.
The results look similar to compound format here. Again 2 KB looks
like the best value.
> Increase buffer sizes used during searching
> -------------------------------------------
>
> Key: LUCENE-893
> URL: https://issues.apache.org/jira/browse/LUCENE-893
> Project: Lucene - Java
> Issue Type: Improvement
> Components: Store
> Affects Versions: 2.1
> Reporter: Michael McCandless
>
> Spinoff of LUCENE-888.
> In LUCENE-888 we increased buffer sizes that impact indexing and found
> substantial (10-18%) overall performance gains.
> It's very likely that we can also gain some performance for searching
> by increasing the read buffers in BufferedIndexInput used by
> searching.
> We need to test performance impact to verify and then pick a good
> overall default buffer size, also being careful not to add too much
> overall HEAP RAM usage because a potentially very large number of
> BufferedIndexInput instances are created during searching
> (# segments X # index files per segment).
--
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: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
