From mboxrd@z Thu Jan 1 00:00:00 1970 From: Rik van Riel Subject: Re: [PATCH 2/9] Sched clock paravirt op fix.patch Date: Tue, 13 Mar 2007 12:37:53 -0400 Message-ID: <45F6D361.8080106@redhat.com> References: <200703020254.l222sOaM009656@zach-dev.vmware.com> <20070313140129.GB92373@muc.de> <45F6C2A3.4040305@goop.org> <20070313160709.GH10574@sequoia.sous-sol.org> <20070313161656.GA12128@muc.de> Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Return-path: In-Reply-To: <20070313161656.GA12128@muc.de> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: virtualization-bounces@lists.osdl.org Errors-To: virtualization-bounces@lists.osdl.org To: Andi Kleen Cc: Chris Wright , Andrew Morton , Linus Torvalds , Daniel Walker , Virtualization Mailing List , Linux Kernel Mailing List List-Id: virtualization@lists.linuxfoundation.org Andi Kleen wrote: > On Tue, Mar 13, 2007 at 09:07:09AM -0700, Chris Wright wrote: >> * Jeremy Fitzhardinge (jeremy@goop.org) wrote: >>> In other words, regardless of whether this particular pv_op lives or >>> dies, we're going to need to have to deal with stolen time properly. I >>> think this hook is reasonable and useful step towards doing that. >> Exactly. Normal interrupts we can handle. Having CPU completely >> disappear for unkown time periods we can't, and will need to. > = > But that is just what a interrupt is. Interrupts tend to be reasonably short though. Steal time can be several hypervisor/host time slices long. As an aside, normal interrupts *are* accounted for separately in /proc/stat, so why not steal time too? -- = Politics is the struggle between those who want to make their country the best in the world, and those who believe it already is. Each group calls the other unpatriotic.