[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <1164234912.14241.15.camel@sale659.sandia.gov>
Date: Wed, 22 Nov 2006 15:35:12 -0700
From: "Jim Schutt" <jaschut@...dia.gov>
To: "Jens Axboe" <jens.axboe@...cle.com>
cc: linux-kernel@...r.kernel.org
Subject: Re: splice/vmsplice performance test results
On Wed, 2006-11-22 at 09:57 +0100, Jens Axboe wrote:
> On Tue, Nov 21 2006, Jim Schutt wrote:
[snip]
> >
> > Hmmm. Is it worth me trying to do some sort of kernel
> > profiling to see if there is anything unexpected with
> > my setup? If so, do you have a preference as to what
> > I would use?
>
> Not sure that profiling would be that interesting, as the problem
> probably lies in where we are _not_ spending the time. But it certainly
> can't hurt. Try to oprofile the kernel for a 10-20 sec interval while
> the test is running. Do 3 such runs for the two test cases
> (write-to-file, vmsplice/splice-to-file).
>
OK, I've attached results for 20 second profiles of three
runs of each test: read-from-socket + write-to-file, and
read-from-socket + vmsplice/splice-to-file.
The test case and throughput is in the name: e.g. rvs-1-306MBps
is trial 1 of read/vmsplice/splice case, which ran at 306 MB/s.
Let me know if I can help with more testing, and thanks
again for looking into this.
-- Jim Schutt
Download attachment "oprofile-rvs-1-306MBps.txt.bz2" of type "application/x-bzip" (4508 bytes)
Download attachment "oprofile-rvs-2-324MBps.txt.bz2" of type "application/x-bzip" (4516 bytes)
Download attachment "oprofile-rvs-3-314MBps.txt.bz2" of type "application/x-bzip" (4593 bytes)
Download attachment "oprofile-rw-1-334MBps.txt.bz2" of type "application/x-bzip" (4544 bytes)
Download attachment "oprofile-rw-2-348MBps.txt.bz2" of type "application/x-bzip" (4682 bytes)
Download attachment "oprofile-rw-3-361MBps.txt.bz2" of type "application/x-bzip" (4654 bytes)
Powered by blists - more mailing lists