Re: systat vm question
On Tue, Feb 07, 2006 at 12:48:53PM -0500, Jason Houx wrote: > the "No-cache" section says this > > No-cache > Miss = 523 > % = 67 > > Interrupts are at 489 total > with CISS0 doing over 200 > > load with 2 users hits 2.18 so far. My question is the No-cache section > what has no-cache, Your question isn't entirely clear to me, but I think you might be confused. The "No-cache section" you refer to is part of the namei (name translation) display. For a little more information on what this means, look in the systat(1) manual page or this brief FAQ entry: http://www.openbsd.org/faq/faq11.html#maxvnodes This is software cache, not a hardware one. > and does 200 interrupts seem excessive for a Hardware > Raid? Does this point anyone to any idea's as to the problem with CISS? > > Thanks, > > Jason
Re: systat vm question
On Tue, 7 Feb 2006, Niall O'Higgins wrote: Your question isn't entirely clear to me, but I think you might be confused. Quite possible as this is a bit new territory for me to be going into. Thanks for the help The "No-cache section" you refer to is part of the namei (name translation) display. For a little more information on what this means, look in the systat(1) manual page or this brief FAQ entry: http://www.openbsd.org/faq/faq11.html#maxvnodes I was reading the systat page but I had not come to the realization yet that what I was looking at was refering to just namei. I tried adjusting the kern.maxvnodes several times but that has not improved the misses. This is software cache, not a hardware one. So this would for sure point to a hardware issue seeing how adjusting the software didn't help?
Re: systat vm question
* Jason Houx <[EMAIL PROTECTED]> [2006-02-07 18:53]: > Interrupts are at 489 total > with CISS0 doing over 200 > > load with 2 users hits 2.18 so far. My question is the No-cache section > what has no-cache, and does 200 interrupts seem excessive for a Hardware > Raid? Does this point anyone to any idea's as to the problem with CISS? no, 200 int/s doesn't even remotely smell like a problem. -- BS Web Services, http://www.bsws.de/ OpenBSD-based Webhosting, Mail Services, Managed Servers, ... Unix is very simple, but it takes a genius to understand the simplicity. (Dennis Ritchie)
Re: systat vm question
On Tue, 7 Feb 2006, Henning Brauer wrote: * Jason Houx <[EMAIL PROTECTED]> [2006-02-07 18:53]: Interrupts are at 489 total with CISS0 doing over 200 no, 200 int/s doesn't even remotely smell like a problem. Great thanks for providing me a baseline. I guess I will just try the next snapshot for the improved CISS driver. systat vm is really nice - thanks again for the post. Jason Houx
Re: systat vm question
You can also try to update to -rOPENBSD_3_8. All noticeable performance problems went away with some important patches since the release. I bet you'll see the load go away. And yes, as Henning said, 200 interrupts/second is nothing. My ciss(4) controllers go up to 5000 interrupts/seconds. But hey, I'm also writing 100 MB/sec, and the load is negligible. On 2/7/06, Jason Houx <[EMAIL PROTECTED]> wrote: > On Tue, 7 Feb 2006, Henning Brauer wrote: > > > * Jason Houx <[EMAIL PROTECTED]> [2006-02-07 18:53]: > >> Interrupts are at 489 total > >> with CISS0 doing over 200 > >> > > > > no, 200 int/s doesn't even remotely smell like a problem. > > Great thanks for providing me a baseline. I guess I will just try the > next snapshot for the improved CISS driver. systat vm is really nice - > thanks again for the post. > > > Jason Houx
Re: systat vm question
Srebrenko, What firmware are you using on your controller? Jason On Wed, 8 Feb 2006, Srebrenko Sehic wrote: You can also try to update to -rOPENBSD_3_8. All noticeable performance problems went away with some important patches since the release. I bet you'll see the load go away. And yes, as Henning said, 200 interrupts/second is nothing. My ciss(4) controllers go up to 5000 interrupts/seconds. But hey, I'm also writing 100 MB/sec, and the load is negligible. On 2/7/06, Jason Houx <[EMAIL PROTECTED]> wrote: On Tue, 7 Feb 2006, Henning Brauer wrote: * Jason Houx <[EMAIL PROTECTED]> [2006-02-07 18:53]: Interrupts are at 489 total with CISS0 doing over 200 no, 200 int/s doesn't even remotely smell like a problem. Great thanks for providing me a baseline. I guess I will just try the next snapshot for the improved CISS driver. systat vm is really nice - thanks again for the post. Jason Houx
Re: systat vm question
The latest, which is, AFAIK, 2.58. On 2/8/06, Jason Houx <[EMAIL PROTECTED]> wrote: > Srebrenko, > > What firmware are you using on your controller? > > Jason > > On Wed, 8 Feb 2006, Srebrenko Sehic wrote: > > > You can also try to update to -rOPENBSD_3_8. All noticeable > > performance problems went away with some important patches since the > > release. > > > > I bet you'll see the load go away. And yes, as Henning said, 200 > > interrupts/second is nothing. My ciss(4) controllers go up to 5000 > > interrupts/seconds. But hey, I'm also writing 100 MB/sec, and the load > > is negligible. > > > > On 2/7/06, Jason Houx <[EMAIL PROTECTED]> wrote: > >> On Tue, 7 Feb 2006, Henning Brauer wrote: > >> > >>> * Jason Houx <[EMAIL PROTECTED]> [2006-02-07 18:53]: > Interrupts are at 489 total > with CISS0 doing over 200 > > >>> > >>> no, 200 int/s doesn't even remotely smell like a problem. > >> > >> Great thanks for providing me a baseline. I guess I will just try the > >> next snapshot for the improved CISS driver. systat vm is really nice - > >> thanks again for the post. > >> > >> > >> Jason Houx