From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dario Faggioli Subject: Re: [PATCH v2] Modified RTDS scheduler to use an event-driven model instead of polling. Date: Mon, 6 Jul 2015 19:37:44 +0200 Message-ID: <1436204264.10763.42.camel@citrix.com> References: <1435434410-15776-1-git-send-email-dgolomb@seas.upenn.edu> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============4931519650462926781==" Return-path: In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Meng Xu Cc: Wei Liu , Sisu Xi , George Dunlap , "xen-devel@lists.xen.org" , Meng Xu , Jan Beulich , Chong Li , Dagaen Golomb List-Id: xen-devel@lists.xenproject.org --===============4931519650462926781== Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="=-VJCyNrEEo1BK0bUEGvQN" --=-VJCyNrEEo1BK0bUEGvQN Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On Sun, 2015-06-28 at 13:45 -0700, Meng Xu wrote: > 2015-06-28 13:17 GMT-07:00 Dagaen Golomb : > > > The scenario in my mind that will potentially invoke one more rt_sche= dule is: > > > VCPU j currently runs out of budget and will have top priority once i= t > > > get budget replenishment. > > > If replenishment runs first, rt_schedule will be invoked for only onc= e. > > > If rt_schedule runs first and schedule a VCPU to run, rt_schedule wil= l > > > be invoked again when replenishment is invoked. > > > > This is a good point here. The ordering in this case doesn't seem to ca= use > > any functional/behavior problems, but it will cause rt_schedule to run = twice > > when it could have been ran once. So, even as a corner case, it would s= eem > > that its a performance corner case and not a behavior one. >=20 > Right. >=20 > Let's look forward to the reply from others, especially Dario's. :-) >=20 I concur. There might be situation where more scheduler invocations than in the ideal (theoretical?) case will be involved, but that's a problem (in different ways) with any actual implementation (we discussed this at length already :-) ). But really, from a correctness point of view, I see no issues. Regards, Dario --=20 <> (Raistlin Majere) ----------------------------------------------------------------- Dario Faggioli, Ph.D, http://about.me/dario.faggioli Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK) --=-VJCyNrEEo1BK0bUEGvQN 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 iEYEABECAAYFAlWavOgACgkQk4XaBE3IOsRgoACgrfnIFcUbiLfAA1LHGk/+aWbk h5IAn15dXgCPwWpGyBN2B/QhOX2BBkqo =VYkr -----END PGP SIGNATURE----- --=-VJCyNrEEo1BK0bUEGvQN-- --===============4931519650462926781== 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 --===============4931519650462926781==--