Re: EXPLAIN ANALYZE on 8.2

From: Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
To: "Kelly Burkhart" <kelly(dot)burkhart(at)gmail(dot)com>
Cc: "Evgeny Gridasov" <eugrid(at)fpm(dot)kubsu(dot)ru>, pgsql-performance(at)postgresql(dot)org
Subject: Re: EXPLAIN ANALYZE on 8.2
Date: 2006-12-15 00:05:31
Message-ID: 29450.1166141131@sss.pgh.pa.us
Views: Raw Message | Whole Thread | Download mbox
Thread:
Lists: pgsql-hackers pgsql-performance

"Kelly Burkhart" <kelly(dot)burkhart(at)gmail(dot)com> writes:
> I hope this isn't a "crummy mainboard" but I can't seem to affect
> things by changing clock source (kernel 2.6.16 SLES10). I tried
> kernel command option clock=XXX where XXX in
> (cyclone,hpet,pmtmr,tsc,pit), no option was significantly better than
> the default.

I believe that on machines where gettimeofday is really nice and fast,
it doesn't require entry to the kernel at all; there's some hack that
makes the clock readable from userspace. (Obviously a switch to kernel
mode would set you back a lot of the cycles involved here.) So it's not
so much the kernel that you need to teach as glibc. How you do that is
beyond my expertise, but maybe that will help you google for the right
thing ...

regards, tom lane

In response to

Responses

Browse pgsql-performance by date

  From Date Subject
Next Message Ron 2006-12-15 00:16:42 Re: New to PostgreSQL, performance considerations
Previous Message Mark Kirkwood 2006-12-14 23:59:40 Re: EXPLAIN ANALYZE on 8.2

Browse pgsql-hackers by date

  From Date Subject
Next Message Tom Lane 2006-12-15 01:31:59 Re: Operator class group proposal
Previous Message Mark Kirkwood 2006-12-14 23:59:40 Re: EXPLAIN ANALYZE on 8.2