From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dario Faggioli Subject: Re: CAP and performance problem Date: Thu, 6 Jun 2013 11:48:49 +0200 Message-ID: <1370512129.18519.240.camel@Solace> References: <519B3832.30608@di.unipmn.it> <1370451024.18519.190.camel@Solace> <51B05030.5000903@eu.citrix.com> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============2172882486084799732==" Return-path: In-Reply-To: <51B05030.5000903@eu.citrix.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: George Dunlap Cc: Massimo Canonico , xen-devel@lists.xen.org List-Id: xen-devel@lists.xenproject.org --===============2172882486084799732== Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="=-E720HkyvRfo8QA43/B+G" --=-E720HkyvRfo8QA43/B+G Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On gio, 2013-06-06 at 10:02 +0100, George Dunlap wrote: > Well for one, from the scheduler's perspective, the promise isn't that= =20 > you'll get 50% of the *performance*, but 50% of the *cpu time*. I=20 > haven't been following the thread terribly closely, but I don't remember= =20 > seeing any xentop or xentrace reports. =20 > Yep, I suggested monitoring the vcpu usage, and Massimo reported a correct 50% utilization for the vcpu in question in xentop. > The first question is, other=20 > than performance, do you have any reason to believe that the VM is not= =20 > getting 50% of the cpu time? >=20 It correctly gets 50% for me, and for Massimo too, as per what he said in one other e-mail in the thread. I agree that it's vcpu utilization and non guest performance we're in control of, but for a purely CPU bound workload, I guess one can expect some sort of relationship between the two things, can't him? Besides, that's right what I get in my tests with Massimo's code. :-) > At some point while your test is running, could you execute the=20 > following command in dom0: >=20 > xentrace -D -e 0x21000 -T 10 /tmp/test.trace >=20 > This will take a 10-second trace of just the scheduling events, placing= =20 > the result in /tmp/test.trace >=20 > Then download and build xenalyze from the hg repo here: >=20 > http://xenbits.xen.org/ext/xenalyze >=20 > and run he following command: >=20 > xenalyze -s /tmp/test.trace > /tmp/test.summary >=20 > And post the results here? >=20 Yes, I suggested trying to produce some traces too. However, having seen that I get numbers consistent with the expectations, I now wonder what can interact with the scheduler and make Massimo's results different... Regards, Dario --=20 <> (Raistlin Majere) ----------------------------------------------------------------- Dario Faggioli, Ph.D, http://about.me/dario.faggioli Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK) --=-E720HkyvRfo8QA43/B+G Content-Type: application/pgp-signature; name="signature.asc" Content-Description: This is a digitally signed message part Content-Transfer-Encoding: 7bit -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.13 (GNU/Linux) iEYEABECAAYFAlGwWwEACgkQk4XaBE3IOsSagACeLmVpSvGN1Uie28RlQ7XQiJdd xQ4AniUn9JdapJuVot/S56vfrsf0A0O1 =DHis -----END PGP SIGNATURE----- --=-E720HkyvRfo8QA43/B+G-- --===============2172882486084799732== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel --===============2172882486084799732==--