From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dario Faggioli Subject: Re: [v3 12/15] vmx: posted-interrupt handling when vCPU is blocked Date: Thu, 2 Jul 2015 14:04:17 +0200 Message-ID: <1435838657.25170.462.camel@citrix.com> References: <1435123109-10481-1-git-send-email-feng.wu@intel.com> <1435123109-10481-13-git-send-email-feng.wu@intel.com> <55926B62.1000605@citrix.com> <1435757162.25170.354.camel@citrix.com> <1435825820.25170.416.camel@citrix.com> <559512BC.90303@citrix.com> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============6986396173730850716==" Return-path: In-Reply-To: <559512BC.90303@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: Andrew Cooper Cc: "Tian, Kevin" , "keir@xen.org" , "george.dunlap@eu.citrix.com" , "xen-devel@lists.xen.org" , "jbeulich@suse.com" , "Zhang, Yang Z" , "Wu, Feng" List-Id: xen-devel@lists.xenproject.org --===============6986396173730850716== Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="=-1WMSglPA5zF+Am50gUWu" --=-1WMSglPA5zF+Am50gUWu Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On Thu, 2015-07-02 at 11:30 +0100, Andrew Cooper wrote: > On 02/07/15 09:30, Dario Faggioli wrote: > > It is, therefore, not effective in making sure that, even with only one > > notification, you only kick the interested vcpu. > > > > This is the third time that I ask: > > (1) whether it is possible to have more vcpus queued on one pcpu PI= =20 > > blocked list with desc.on (I really believe it is); > > (2) if yes, whether it is TheRightThing(TM) to kick all of them, as > > soon as any notification arrives, instead that putting together a > > mechanism for kicking only a specific one. >=20 > We will receive one NV for every time the hardware managed to > successfully set desc.on >=20 Right, I see it now, thanks. > If multiple stack up and we proactively drain the list, we will > subsequently search the list to completion for all remaining NV's, due > to finding no appropriate entries. >=20 > I can't currently decide whether this will be quicker or slower overall, > or (most likely) it will even out to equal in the general case. >=20 Well, given the thing works as you (two) just described, I think draining the list is the only thing we can do. In fact, AFAICT, since we can't know for what vcpu a particular notification is intended, we don't have alternatives to waking them all, do we? Dario --=20 <> (Raistlin Majere) ----------------------------------------------------------------- Dario Faggioli, Ph.D, http://about.me/dario.faggioli Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK) --=-1WMSglPA5zF+Am50gUWu 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 iEYEABECAAYFAlWVKMEACgkQk4XaBE3IOsRP+QCdF2HXS2N53+eiCrfXPlgev3lo t7YAn2BqCW3Ax2zG1mRxnc6t45SUqPgc =6N8+ -----END PGP SIGNATURE----- --=-1WMSglPA5zF+Am50gUWu-- --===============6986396173730850716== 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 --===============6986396173730850716==--