From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([140.186.70.92]:37191) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1QYwsI-0006U5-Ry for qemu-devel@nongnu.org; Tue, 21 Jun 2011 05:03:59 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1QYwsD-0000xC-LJ for qemu-devel@nongnu.org; Tue, 21 Jun 2011 05:03:58 -0400 Received: from mx1.redhat.com ([209.132.183.28]:1354) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1QYwsC-0000wt-Sk for qemu-devel@nongnu.org; Tue, 21 Jun 2011 05:03:53 -0400 Date: Tue, 21 Jun 2011 12:03:48 +0300 From: Gleb Natapov Message-ID: <20110621090348.GE491@redhat.com> References: <1308577094-17551-1-git-send-email-gollub@b1-systems.de> <20110620153825.GH13042@redhat.com> <4DFF6B20.7090107@redhat.com> <201106201826.32975.gollub@b1-systems.de> <4DFF76B1.8020509@redhat.com> <20110621060251.GB491@redhat.com> <4E0051B1.8060801@redhat.com> <20110621084155.GD491@redhat.com> <4E005CBA.3000105@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <4E005CBA.3000105@redhat.com> Subject: Re: [Qemu-devel] [PATCH 0/2] Introduce panic hypercall List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Avi Kivity Cc: Daniel Gollub , qemu-devel , kvm@vger.kernel.org On Tue, Jun 21, 2011 at 11:56:26AM +0300, Avi Kivity wrote: > On 06/21/2011 11:41 AM, Gleb Natapov wrote: > >On Tue, Jun 21, 2011 at 11:09:21AM +0300, Avi Kivity wrote: > >> On 06/21/2011 09:02 AM, Gleb Natapov wrote: > >> >On Mon, Jun 20, 2011 at 07:34:57PM +0300, Avi Kivity wrote: > >> >> >The only two things which came to my mind are: > >> >> > > >> >> > * NMI (aka. ipmitool diag) - already available in qemu/kvm - but requires > >> >> > in-guest kexec/kdump > >> >> > * Hardware-Watchdog (also available in qemu/libvirt) > >> >> > >> >> A watchdog has the advantage that is also detects lockups. > >> >> > >> >And has disadvantage that all time base heuristics are bite us in the > >> >end. > >> > >> The perf-based watchdog counts clocks-not-halted, not time, so it is > >> safe from time issues. > >So it counts only instruction that guest actually executed? That's > >perfect then. How much overhead it has in a guest though? > > Should be pretty low, especially if the guest is idle. There were > some negative reports about the pmu From David Ahern, so it needs to > be verified. But it will be running not only when the guest is idle. > > > >> We could make the hardware watchdog cheat in > >> the same way. > >> > >Something like steal time, but for watchdog. But this become complicated fast. > >Watchdog emulation will have to move into kernel for starter. > > Why? You can use a performance counter from userspace. > Heh, haven't thought about such way of implementing watchdog device. But the same question again: what impact on performance constantly running guest under perf is? Doesn't running guest under perf involve a lot of NMIs (and hence vmexists)? -- Gleb.