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

On Thu, 2005-10-13 at 21:20 -0600, Robert Creager wrote:
> When grilled further on (Thu, 13 Oct 2005 22:44:54 -0400),
> Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> confessed:
>
> > Robert Creager <Robert(dot)Creager(at)Sun(dot)com> writes:
> > > I've been having this problem since trying to upgrade from 7.4.1 to 8.03,
> and
> > > now 8.1.
> >
> > Can you put together a test case that other people could use to
> > reproduce it?
> >
>
> I can try. The data size isn't big, but the scripts that run against it are,
> and are dependent on our development enviornment. What I'll have to do is pull
> out the db portion of the app and see if I can simplify it - might work. The
> app is a test system that runs against our big storage libraries.
>
> Is there anything I might be able to do (without the test case) that would help
> figure out what's happening?

Please try this patch and see if it reduces the CS storm:

http://archives.postgresql.org/pgsql-patches/2005-10/msg00091.php

Do you have access to another similar machine to do comparative testing?
Do you have access to another machine with different CPU arch? It would
be good to firmly isolate this to a CPU architecture interaction issue.

Are the Xeons particularly old models? How new is the server?

Thanks,

Best Regards, Simon Riggs