Re: Seeing context switch storm with 10/13 snapshot of

From: Robert Creager <Robert(dot)Creager(at)Sun(dot)com>
To: Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
Cc: pgsql-hackers(at)postgresql(dot)org
Subject: Re: Seeing context switch storm with 10/13 snapshot of
Date: 2005-11-05 00:02:21
Message-ID: 20051104170221.00000e23@C118181.stortek.com
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

On Thu, 20 Oct 2005 17:35:31 -0400
Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> wrote:

> Robert Creager <Robert(dot)Creager(at)Sun(dot)com> writes:
> > Interesting. 7.4.1 is worse for this test, as two jump up to 130k. But, my
> > app runs fine against 7.4.1...
>
> > Would it still be helpful to try and pull together a test case from my app
> > against 8.1beta3?
>
> Yes, if you can show a case where 8.1 is much worse than 7.4 then we
> need to know about it yesterday.
>

Ok. I finally have a stand alone test case that does not show that 8.1 is worse
than 7.4. It shows the opposite quite nicely ;-). In tests I'm running, 7.4.1
bogs down immediately and never recovers. 8.1 behaves itself for about 20
minutes before it goes out to lunch. So, in those terms, it is worse as it
looks fine at the start, but then gets progressively worse, but overall, it's
much better.

I have a Perl script, a Perl module and a 1Mb database (from pg_dump -F c). Are
you interested at this time in receiving this? I plan on taking it home and
running against my AMD system to see what it does, but that will be against 8.0
if I remember correctly, maybe 8.03. An upgrade to RC2 might occur when RC2
comes out, unless there would be great benefit on running my tests against
8.1RC1.

Cheers,
Rob

In response to

Responses

Browse pgsql-hackers by date

  From Date Subject
Next Message Tom Lane 2005-11-05 00:12:06 Re: Seeing context switch storm with 10/13 snapshot of
Previous Message Martijn van Oosterhout 2005-11-04 23:40:33 Re: Reducing the overhead of NUMERIC data