From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dario Faggioli Subject: Re: About vcpu wakeup and runq tickling in credit Date: Thu, 15 Nov 2012 16:50:06 +0100 Message-ID: <1352994606.5351.54.camel@Solace> References: <1350999260.5064.56.camel@Solace> <5086B4DF.6060701@eu.citrix.com> <1352981447.5351.51.camel@Solace> <50A4DD95.5020107@eu.citrix.com> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============5764231555700086058==" Return-path: In-Reply-To: <50A4DD95.5020107@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: Keir Fraser , Jan Beulich , xen-devel List-Id: xen-devel@lists.xenproject.org --===============5764231555700086058== Content-Type: multipart/signed; micalg="pgp-sha1"; protocol="application/pgp-signature"; boundary="=-VwrTH+C7LkAoQg6FMWA8" --=-VwrTH+C7LkAoQg6FMWA8 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On Thu, 2012-11-15 at 12:18 +0000, George Dunlap wrote: > > So, in the vcpu-affinity case, if pcpu 3 get tickled, when it peeks at > > pcpu 13's runq for work to steal it does not find anything suitable and > > give up, leaving d51v1 in the runq even if there are idle pcpus on whic= h > > it could run, which is already bad. > > In the node-affinity case, pcpu 3 will actually manage in stealing d51v= 1 > > and running it, even if there are idle pcpus with which it has > > node-affinity, and thus defeating most of the benefits of the whole NUM= A > > aware scheduling thing (at least for some workloads). >=20 > Maybe what we should do is do the wake-up based on who is likely to run= =20 > on the current cpu: i.e., if "current" is likely to be pre-empted, look= =20 > at idlers based on "current"'s mask; if "new" is likely to be put on the= =20 > queue, look at idlers based on "new"'s mask. >=20 EhEh, if you check the whole thread, you'll find evidence that I thought this to be a good idea from the very beginning. I've already a patch for that, just let me see if numbers (with and without NUMA scheduling) are aligned with impressions and then I'll send everything together. Thanks for your time, Dario --=20 <> (Raistlin Majere) ----------------------------------------------------------------- Dario Faggioli, Ph.D, http://retis.sssup.it/people/faggioli Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK) --=-VwrTH+C7LkAoQg6FMWA8 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 v1.4.12 (GNU/Linux) iEYEABECAAYFAlClDy4ACgkQk4XaBE3IOsQ+NwCaA5kXUEYERYaSNQI0YfZxBuFc L+AAnR0m8l+f0nV19lKZOmlVES/TfhvH =RGIX -----END PGP SIGNATURE----- --=-VwrTH+C7LkAoQg6FMWA8-- --===============5764231555700086058== 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 --===============5764231555700086058==--