Skip site navigation (1) Skip section navigation (2)

Re: LWLock contention: I think I understand the problem

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:
Lists: pgsql-hackerspgsql-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 00:50:23
Subject: Re: More problem with scripts
Previous:From: Thomas LockhartDate: 2002-01-03 23:03:20
Subject: Re: More problem with scripts

pgsql-odbc by date

Next:From: Tom LaneDate: 2002-01-04 01:02:54
Subject: Re: LWLock contention: I think I understand the problem
Previous:From: Hannu KrosingDate: 2002-01-03 19:55:10
Subject: Re: LWLock contention: I think I understand the problem

Privacy Policy | About PostgreSQL
Copyright © 1996-2014 The PostgreSQL Global Development Group