From mboxrd@z Thu Jan 1 00:00:00 1970 From: Gregory Haskins Subject: Re: Cyclictest usage Date: Mon, 11 Aug 2008 09:55:55 -0400 Message-ID: <48A044EB.7010508@novell.com> References: <48A03517.40708@novell.com> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enigF6D8F8688281640CBA55E576" Cc: linux-rt-users@vger.kernel.org To: Tobias Knutsson Return-path: Received: from victor.provo.novell.com ([137.65.250.26]:51842 "EHLO victor.provo.novell.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751704AbYHKN6H (ORCPT ); Mon, 11 Aug 2008 09:58:07 -0400 In-Reply-To: Sender: linux-rt-users-owner@vger.kernel.org List-ID: This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enigF6D8F8688281640CBA55E576 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: quoted-printable Hi Tobias, Some more questions (inline) Tobias Knutsson wrote: > 2.6.25.8-rt7 and 2.6.25.8 > > On Mon, Aug 11, 2008 at 14:48, Gregory Haskins wr= ote: > =20 >> Tobias Knutsson wrote: >> =20 >>> Hello, >>> >>> I'm trying to do some initial benchmarking on a rt-kernel versus a >>> vanilla kernel. On the rt the results are stable in between test runs= >>> using the following command: >>> >>> cyclictest -t 1 -p 80 -c 1 -n -i 10000 -l 10000 >>> =20 What architecture is this? And what do you see for ave/max in the=20 cyclictest output on -rt (so we have a reference) >>> However, using the same command while running the vanilla kernel, I >>> get very varying results. And I would completely understand if it was= >>> due to increased jitter. The thing is, the jitter is very low (0% >>> load) but the average times varies from 600 us to 6500 us depending o= n >>> when the test is initiated. >>> =20 What are you considering "jitter" when you say it is very low? Are the=20 600-6500us values truly from the "ave" output of cyclictest, or are=20 these an average of the "max" output? >>> I imagine this might have something to do with not having high res >>> timers in the vanilla kernel. I will defer to Thomas, but my understanding is that 2.6.25 vanilla=20 should have HRT as an option (though I am not sure if you enabled it or=20 not). >>> If that is what's causing my problems. >>> =20 Cyclictest will report that it cannot access the HRT when it cannot find = it (at least it does on my system, but I might have an older version=20 running). Do you see any such warnings? >>> What is the best way of comparing the two kernels? >>> =20 This is a pretty good way, as long as you have HRT in the vanilla=20 kernel. Assuming for a second that you do, your results are showing you = what I would expect to see for vanilla (600-6500us spikes). HTH -Greg --------------enigF6D8F8688281640CBA55E576 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.9 (GNU/Linux) Comment: Using GnuPG with SUSE - http://enigmail.mozdev.org iEYEARECAAYFAkigROsACgkQlOSOBdgZUxn5OwCeOxfQcrhBnxwAojB3PMIpdweF /OYAn2ZYD4pG/C4ksGLElQmO2lFs0IxV =0ZsN -----END PGP SIGNATURE----- --------------enigF6D8F8688281640CBA55E576--