Re: [PERFORM] Context switch storm

2006-11-14 Thread Cosimo Streppone
Merlin wrote: On 11/14/06, Jim C. Nasby <[EMAIL PROTECTED]> wrote: On Tue, Nov 14, 2006 at 09:17:08AM -0500, Merlin Moncure wrote: > On 11/14/06, Cosimo Streppone <[EMAIL PROTECTED]> wrote: > >I must say I lowered "shared_buffers" to 8192, as it was before. > >I tried raising it to 16384, but

Re: [PERFORM] Context switch storm

2006-11-14 Thread Merlin Moncure
On 11/14/06, Jim C. Nasby <[EMAIL PROTECTED]> wrote: On Tue, Nov 14, 2006 at 09:17:08AM -0500, Merlin Moncure wrote: > On 11/14/06, Cosimo Streppone <[EMAIL PROTECTED]> wrote: > >I must say I lowered "shared_buffers" to 8192, as it was before. > >I tried raising it to 16384, but I can't seem to f

Re: [PERFORM] Context switch storm

2006-11-14 Thread Bucky Jordan
> a) order Opterons. That doesn't solve the overload problem as such, > but these pesky cs storms seems to have gone away this way. I haven't run into context switch storms or similar issues with the new Intel Woodcrests (yet.. they're still pretty new and not yet under real production load), has

Re: [PERFORM] Context switch storm

2006-11-14 Thread Merlin Moncure
On 11/14/06, Cosimo Streppone <[EMAIL PROTECTED]> wrote: I must say I lowered "shared_buffers" to 8192, as it was before. I tried raising it to 16384, but I can't seem to find a relationship between shared_buffers and performance level for this server. My findings are pretty much the same here.

Re: [PERFORM] Context switch storm

2006-11-14 Thread Jim C. Nasby
On Tue, Nov 14, 2006 at 09:17:08AM -0500, Merlin Moncure wrote: > On 11/14/06, Cosimo Streppone <[EMAIL PROTECTED]> wrote: > >I must say I lowered "shared_buffers" to 8192, as it was before. > >I tried raising it to 16384, but I can't seem to find a relationship > >between shared_buffers and perfor

Re: [PERFORM] Context switch storm

2006-11-14 Thread Andreas Kostyrka
* Cosimo Streppone <[EMAIL PROTECTED]> [061114 10:52]: > Richard Huxton wrote: > >Cosimo Streppone wrote: > >>Richard Huxton wrote: > >> > The average context switching for this server as vmstat shows is 1 > but when the problem occurs it goes to 25. > >>> > >>I seem to have the same ex

Re: [PERFORM] Context switch storm

2006-11-14 Thread Cosimo Streppone
Richard Huxton wrote: Cosimo Streppone wrote: Richard Huxton wrote: The average context switching for this server as vmstat shows is 1 but when the problem occurs it goes to 25. I seem to have the same exact behaviour for an OLTP-loaded 8.0.1 server upgrade from 8.0.1 - the most recen