| From: | Qingqing Zhou <zhouqq(at)cs(dot)toronto(dot)edu> |
|---|---|
| To: | Luke Lonergan <llonergan(at)greenplum(dot)com> |
| Cc: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>, Neil Conway <neilc(at)samurai(dot)com>, Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>, pgsql-hackers(at)postgresql(dot)org |
| Subject: | Re: Which qsort is used |
| Date: | 2005-12-15 05:10:37 |
| Message-ID: | Pine.LNX.4.58.0512150005240.31297@josh.db |
| Views: | Whole Thread | Raw Message | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
On Wed, 14 Dec 2005, Luke Lonergan wrote:
>
> Overall - I'd say that the BSD routine is showing the best overall results
> when the scale test is included. The qsortG routine has some significantly
> better performance in certain cases at smaller sort set sizes - it could
> probably be improved for better L2 use, but BSD is already there.
>
> Based on this it seems like we should expose the option to choose the BSD
> qsort routine at configure time.
>
Before we pin down this, I hope more extensive tests on various platforms
could be done. So we could give some suggestions when we should enable the
"--enable-bsdqsort" option. I can post a result on a SunOS machine (but
the problem is that many ppl share this machine) and a windows machine.
Regards,
Qingqing
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Tom Lane | 2005-12-15 05:20:49 | Re: Self-modifying code |
| Previous Message | Alvaro Herrera | 2005-12-15 05:07:34 | Self-modifying code |