Re: 2.6.12-rc6-mm1 & 2K lun testing

[Badari Pulavarty <pbadari@us.ibm.com>]

On Thu, 2005-06-16 at 15:42, William Lee Irwin III wrote:
> On Thu, Jun 16, 2005 at 12:50:59PM -0700, Badari Pulavarty wrote:
> > Yes. I am using CFQ scheduler. I changed nr_requests to 4 for all
> > my devices. I also changed "min_free_kbytes" to 64M.
> > Response time is still bad. Here is the vmstat, meminfo, slabinfo
> > and profle output. I am not sure why profile output shows 
> > default_idle(), when vmstat shows 100% CPU sys.
> 
> It's because you're sorting on the third field of readprofile(1),
> which is pure gibberish. Undoing this mistake will immediately
> enlighten you.

Hmm.. I was under the impression that its gives useful info ..

Here is readprofile man-page says:

       Print the 20 most loaded procedures:
          readprofile | sort -nr +2 | head -20



> Also, turn off slab poisoning when doing performance analyses.

Its already off. I am not trying to compare performance here.
I was trying to analyze VM behaviour with filesystem tests.
(with "raw" devices, machine is perfectly happy - but with
filesystem cache it crawls).

Thanks,
Badari

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/