From:
Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
To:
Hannu Krosing <hannu(at)tm(dot)ee>
Cc:
Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>, Tatsuo Ishii <t-ishii(at)sra(dot)co(dot)jp>,
pgsql-hackers(at)postgresql(dot)org, jwbaker(at)acm(dot)org
Subject:
Re: LWLock contention: I think I understand the problem
Date:
2002-01-03 23:39:59
Message-ID:
1114.1010101199@sss.pgh.pa.us (view raw or flat )
Thread:
2001-12-29 19:10:43 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2001-12-29 19:24:02 from Thomas Lockhart <lockhart(at)fourpalms(dot)org>
2001-12-29 19:46:18 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2001-12-29 19:35:49 from Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>
2001-12-29 19:45:28 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2001-12-29 20:07:47 from Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>
2001-12-29 20:49:33 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2001-12-30 01:50:48 from Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>
2001-12-30 02:00:43 from "Jeffrey W(dot) Baker" <jwbaker(at)acm(dot)org>
2001-12-30 02:13:36 from Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>
2001-12-30 02:42:00 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2001-12-30 02:30:23 from Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>
2001-12-30 07:53:09 from Tatsuo Ishii <t-ishii(at)sra(dot)co(dot)jp>
2001-12-30 16:52:58 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2001-12-30 18:04:29 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2001-12-30 23:44:13 from Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>
2002-01-03 01:18:25 from Tatsuo Ishii <t-ishii(at)sra(dot)co(dot)jp>
2002-01-03 07:55:26 from Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>
2002-01-03 09:00:10 from Tatsuo Ishii <t-ishii(at)sra(dot)co(dot)jp>
2002-01-03 15:20:49 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2002-01-03 17:08:34 from Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>
2002-01-03 17:16:31 from Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>
2002-01-03 17:41:12 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2002-01-03 19:55:10 from Hannu Krosing <hannu(at)tm(dot)ee>
2002-01-03 23:39:59 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2002-01-04 11:45:43 from Hannu Krosing <hannu(at)tm(dot)ee>
2002-01-04 04:46:04 from Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>
2002-01-04 04:55:03 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2002-01-04 04:59:11 from "Jeffrey W(dot) Baker" <jwbaker(at)acm(dot)org>
2002-01-04 05:02:29 from Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>
2002-01-03 19:37:17 from Hannu Krosing <hannu(at)tm(dot)ee>
2002-01-04 04:44:32 from Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>
2002-01-04 23:13:59 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2002-01-05 00:32:37 from Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>
2002-01-05 01:25:32 from Tatsuo Ishii <t-ishii(at)sra(dot)co(dot)jp>
2002-01-05 01:44:17 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2002-01-05 17:54:29 from Hannu Krosing <hannu(at)tm(dot)ee>
2002-01-05 21:44:53 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2002-01-06 12:01:44 from Ashley Cambrell <ash(at)freaky-namuh(dot)com>
2002-01-06 22:32:40 from Hannu Krosing <hannu(at)krosing(dot)net>
2002-01-07 01:37:05 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2002-01-06 23:12:07 from Hannu Krosing <hannu(at)krosing(dot)net>
2002-01-07 02:32:39 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2002-01-07 07:01:15 from Hannu Krosing <hannu(at)tm(dot)ee>
2002-01-07 16:39:35 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2002-01-07 17:51:19 from Gilles DAROLD <gilles(at)darold(dot)net>
2002-01-08 02:20:30 from Hiroshi Inoue <Inoue(at)tpf(dot)co(dot)jp>
2002-01-23 19:10:27 from Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>
2002-01-23 19:15:21 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2002-01-14 13:12:42 from Luis Amigo <lamigo(at)atc(dot)unican(dot)es>
2002-01-03 07:20:16 from Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>
2002-01-04 11:58:28 from Fredrik Estreen <estreen(at)algonet(dot)se>
2002-01-04 01:02:54 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2002-01-04 06:21:54 from Fredrik Estreen <estreen(at)algonet(dot)se>
2002-01-04 02:35:11 from Kenny H Klatt <kklatt(at)csd(dot)uwm(dot)edu>
2001-12-29 19:37:15 from Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>
2001-12-29 20:58:52 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2001-12-29 21:09:56 from Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>
2001-12-29 23:09:26 from Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
2001-12-29 20:23:20 from "Jeffrey W(dot) Baker" <jwbaker(at)acm(dot)org>
Lists:
pgsql-hackers pgsql-odbc
Hannu Krosing <hannu(at)tm(dot)ee> writes:
> Tom Lane wrote:
>> Unfortunately, at low scaling factors pgbench is guaranteed to look
>> horrible because of contention for the "branches" rows.
>>
> Not really! See graph in my previous post - the database size affects
> performance much more !
But the way that pgbench is currently set up, you can't really tell the
difference between database size effects and contention effects, because
you can't vary one while holding the other constant.
I based my comments on having done profiles that show most of the CPU
time going into attempts to acquire row locks for updates and/or
checking of dead tuples in _bt_check_unique. So at least in the
conditions I was using (single CPU) I think those are the bottlenecks.
I don't have any profiles for SMP machines, yet.
regards, tom lane
In response to
Responses
pgsql-hackers by date
Next :From: Brent VernerDate: 2002-01-04 00:50:23Subject : Re: More problem with scriptsPrevious :From : Thomas LockhartDate : 2002-01-03 23:03:20Subject : Re: More problem with scripts
pgsql-odbc by date
Next :From: Tom LaneDate: 2002-01-04 01:02:54Subject : Re: LWLock contention: I think I understand the problem Previous :From : Hannu KrosingDate : 2002-01-03 19:55:10Subject : Re: LWLock contention: I think I understand the problem
