[ale] interrupt numbers

[Greg Freemyer]

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.

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