[ale] interrupt numbers

[Jim Kinney]

On Fri, Jun 26, 2009 at 5:34 PM, Greg Freemyer<greg.freemyer at gmail.com> wrote:
> On Fri, Jun 26, 2009 at 5:01 PM, Jim Kinney<jim.kinney at gmail.com> wrote:
>> 5-6 disk interupts/s simultaneously across 8 cpu cores
>> 350+ for raid controller per sec simultaneously across 8 cores.
>
> Those are not large numbers.  Not sure if the simultaneously is an issue or not.
>
> ie. Every disk write causes a dma transfer to take place.  At the end
> of every dma an interrupt occurs.
>
> A single disk can cause a thousand interrupt a second even when
> working properly and working with a sequential read or write workload.
>  A raid controller way more than that since it effectively accumulates
> at the interrrupts together for all the disks.
>
> I would actually say if anything that your numbers are LOW and
> indicate a performance issue somewhere.
>
> If the cpu's are not pegged with processing, it could be that your
> raid setup is not tuned to your load and thus your only getting those
> 350 i/o's per second.

That's what I'm investigating now. When the IO counts starts to climb,
it stays high and never retreats. The load holds steady around 4 and
multiple db SELECT and INSERT calls pause until the max concurrent
connections is reached then stuff starts dropping off. It is still
doing inserts but very very slowly.
>
> Greg
> --
> Greg Freemyer
> Head of EDD Tape Extraction and Processing team
> Litigation Triage Solutions Specialist
> http://www.linkedin.com/in/gregfreemyer
> Preservation and Forensic processing of Exchange Repositories White Paper -
> http://www.norcrossgroup.com/forms/whitepapers/Forensic%20Processing%20of%20Exchange%20WP%20final.pdf
>
> The Norcross Group
> The Intersection of Evidence & Technology
> http://www.norcrossgroup.com
> _______________________________________________
> Ale mailing list
> Ale at ale.org
> http://mail.ale.org/mailman/listinfo/ale
>



-- 
-- 
James P. Kinney III
Actively in pursuit of Life, Liberty and Happiness