From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dario Faggioli Subject: Re: [PATCH v2 09/10] xen/tools: tracing: trace (Credit2) runq traversal. Date: Fri, 24 Feb 2017 19:48:08 +0100 Message-ID: <1487962088.5548.67.camel@citrix.com> References: <148664844741.595.10506268024432565895.stgit@Solace.fritz.box> <148664876211.595.17986015821032981184.stgit@Solace.fritz.box> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============3780988212080037118==" Return-path: Received: from mail6.bemta5.messagelabs.com ([195.245.231.135]) by lists.xenproject.org with esmtp (Exim 4.84_2) (envelope-from ) id 1chKue-0003Ef-VL for xen-devel@lists.xenproject.org; Fri, 24 Feb 2017 18:48:17 +0000 In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Errors-To: xen-devel-bounces@lists.xen.org Sender: "Xen-devel" To: George Dunlap Cc: xen-devel List-Id: xen-devel@lists.xenproject.org --===============3780988212080037118== Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="=-OFXtmWHPnUk4aXKa+ZX5" --=-OFXtmWHPnUk4aXKa+ZX5 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On Wed, 2017-02-15 at 15:31 +0000, George Dunlap wrote: > On Thu, Feb 9, 2017 at 1:59 PM, Dario Faggioli > wrote: > >=20 > > When traversing a Credit2 runqueue to select the > > best candidate vCPU to be run next, show in the > > trace which vCPUs we consider. > >=20 > > A bit verbose, but quite useful, considering that > > we may end up looking at, but then discarding, one > > of more vCPU. This will help understand which ones > > are skipped and why. >=20 > This sounds useful -- but what I don't quite understand is why it's > useful simply to know that a vcpu was considered, and not also know > specifically why it was decided against.=C2=A0=C2=A0(I'm sure you've foun= d it > useful or you wouldn't have submitted the patch.) >=20 Yeah, I see what you mean. Of course, the more info, the better. But knowing which vcpus have been skipped, is the real hard thing here. Meaning that it, in theory, was possible to reconstruct that, but only with a very tedious and error prone process of staring and noting down previous records. OTOH, once that you see which ones have been skipped --considering that there are not too many reasons for that to happen, yet-- it's fairly straightforward to guess why. And yes, as you say, I so far have found more useful to know which ones, while the why hasn't been critical for the trace analysis I've done so far. > Anyway, I can check it in as-is (if it applies). >=20 > Acked-by: George Dunlap >=20 Thanks, and fear not: I actually may end up sending a follow up patch for spitting out the reason why we skipped someone too... As you probably have understood by this point, I like a lot adding tracepoints! :-P :-P Regards, Dario --=20 <> (Raistlin Majere) ----------------------------------------------------------------- Dario Faggioli, Ph.D, http://about.me/dario.faggioli Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK) --=-OFXtmWHPnUk4aXKa+ZX5 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 v2 iQIcBAABCAAGBQJYsH/oAAoJEBZCeImluHPuuEcP/iVl3EdpI/XYemaHaP/1Gjjd naIC++xOPEh1QraJt4K/kioHhkFLlix3FqVbPV9+qpp9HUBKiEO3Ip8UWwgMXI0a ajNxpaEmri+QwAVuehhlr1HRAmU0H0wKpT2XO+2pGH7S4mW0oLuvYFAx0VXjbkpg wxBZx6JThzwqK5lqh2fjIWuBLs0Y3Hg2IbKutENw8uXQlPtdrOSv4CFzNcWLTEfG 9cxh7UdREogz/VfRHdmWzUY8nAyxvYCC2EWk7kL0jR5/Q1vR2j3TZ1IEwb35d6Tu DYxkdudLHJK//gWQVNgtR5TacIqCc3nV/t60vea5sLhWD4rJkZLJxAbf1RCfZ7Ti NseuGJLXGswKylDpG14SgTsRXtCR7PMaX2Ktqg3AihhzC5/f5Egirr4uoj+zVwOY tpt7oR81kxWW1WV72zKKeJpswQbViHrhdO/X3AAQpd7UQt+GOad2Hv9PtHMkMnCu 4dxMcKu5BqnCCafM6ROjOXUHpHtdKhdJKlDD88zF5ap3CRktuhDlwedbyEVNNXM2 L6BRZR03nlvWrgGqor2BKMYPkfHMjqjQ/0u/C5wSOzByK0UxxqkIUEG0ZlODRvak NazRZb9LrvNSxGOSexG2P5MCarEq983FEDWZSs15clPQj+pGvw+el9xCiF14iKbn T/OF8ZcpUfJy/l9b1WPi =RcPQ -----END PGP SIGNATURE----- --=-OFXtmWHPnUk4aXKa+ZX5-- --===============3780988212080037118== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: base64 Content-Disposition: inline X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18KWGVuLWRldmVs IG1haWxpbmcgbGlzdApYZW4tZGV2ZWxAbGlzdHMueGVuLm9yZwpodHRwczovL2xpc3RzLnhlbi5v cmcveGVuLWRldmVsCg== --===============3780988212080037118==--