[
https://issues.apache.org/jira/browse/LUCENE-2723?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12971465#action_12971465
]
Robert Muir commented on LUCENE-2723:
-------------------------------------
by the way, i tried an experiment... i don't much trust the +nebraska +state
results in general,
but the +unit +state is more stable and I ran this one twice to be sure... i
think we should investigate more
in advance() I changed:
{noformat}
// not found in current block, seek underlying stream
BulkPostingsEnum.JumpResult jumpResult = docsEnum.jump(target, count);
if (jumpResult != null) {
{noformat}
to:
{noformat}
// not found in current block, seek underlying stream
BulkPostingsEnum.JumpResult jumpResult;
if (target - doc > docDeltas.length*4 && (jumpResult =
docsEnum.jump(target, count)) != null) {
{noformat}
{noformat}
Query QPS branch QPS patch Pct diff
+nebraska +state 75.91 84.46 11.3%
+unit +state 8.67 10.01 15.4%
Query QPS branch QPS patch Pct diff
+nebraska +state 73.23 80.27 9.6%
+unit +state 8.66 10.00 15.5%
{noformat}
> Speed up Lucene's low level bulk postings read API
> --------------------------------------------------
>
> Key: LUCENE-2723
> URL: https://issues.apache.org/jira/browse/LUCENE-2723
> Project: Lucene - Java
> Issue Type: Improvement
> Components: Index
> Reporter: Michael McCandless
> Assignee: Michael McCandless
> Fix For: 4.0
>
> Attachments: LUCENE-2723.patch, LUCENE-2723.patch, LUCENE-2723.patch,
> LUCENE-2723.patch, LUCENE-2723.patch, LUCENE-2723_termscorer.patch
>
>
> Spinoff from LUCENE-1410.
> The flex DocsEnum has a simple bulk-read API that reads the next chunk
> of docs/freqs. But it's a poor fit for intblock codecs like FOR/PFOR
> (from LUCENE-1410). This is not unlike sucking coffee through those
> tiny plastic coffee stirrers they hand out airplanes that,
> surprisingly, also happen to function as a straw.
> As a result we see no perf gain from using FOR/PFOR.
> I had hacked up a fix for this, described at in my blog post at
> http://chbits.blogspot.com/2010/08/lucene-performance-with-pfordelta-codec.html
> I'm opening this issue to get that work to a committable point.
> So... I've worked out a new bulk-read API to address performance
> bottleneck. It has some big changes over the current bulk-read API:
> * You can now also bulk-read positions (but not payloads), but, I
> have yet to cutover positional queries.
> * The buffer contains doc deltas, not absolute values, for docIDs
> and positions (freqs are absolute).
> * Deleted docs are not filtered out.
> * The doc & freq buffers need not be "aligned". For fixed intblock
> codecs (FOR/PFOR) they will be, but for varint codecs (Simple9/16,
> Group varint, etc.) they won't be.
> It's still a work in progress...
--
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: dev-unsubscr...@lucene.apache.org
For additional commands, e-mail: dev-h...@lucene.apache.org
