From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:34558) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gIdbk-0002Ct-Io for qemu-devel@nongnu.org; Fri, 02 Nov 2018 13:51:45 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1gIdbj-0003JA-CX for qemu-devel@nongnu.org; Fri, 02 Nov 2018 13:51:44 -0400 Received: from mx1.redhat.com ([209.132.183.28]:54488) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1gIdbi-00030U-RX for qemu-devel@nongnu.org; Fri, 02 Nov 2018 13:51:43 -0400 Date: Fri, 2 Nov 2018 17:51:11 +0000 From: "Dr. David Alan Gilbert" Message-ID: <20181102175111.GA2388@work-vm> References: <87pnvn6hnq.fsf@linaro.org> <87lg6b5shx.fsf@linaro.org> <98428a27-8634-9521-297c-a61c618e867a@windriver.com> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline In-Reply-To: <98428a27-8634-9521-297c-a61c618e867a@windriver.com> Content-Transfer-Encoding: quoted-printable Subject: Re: [Qemu-devel] strange situation, guest cpu thread spinning at ~100%, but display not yet initialized List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Chris Friesen , famz@redhat.com Cc: Alex =?iso-8859-1?Q?Benn=E9e?= , qemu-devel@nongnu.org * Chris Friesen (chris.friesen@windriver.com) wrote: > On 11/2/2018 10:55 AM, Alex Benn=E9e wrote: > >=20 > > Chris Friesen writes: > > > Given the "not initialized" message on the console, I wasn't sure > > > whether the kernel had even started yet. > >=20 > > There will be a lot that happens between the kernel decompressing and > > some sort of video hardware output being started. You didn't say what > > guest architecture you were booting or what your qemu command line wa= s. > > You might want to look at enabling the serial console and seeing if y= ou > > get some clues from that. >=20 > The qemu commandline is in the "ps" output in my original message. Gues= t > arch is x86-64. >=20 > The serial console is a good idea, will try that. This is ringing a bell; if it's actually suck in the BIOS, then please: a) Really make sure all your vCPUs are actually pinned/free on real CPUs b) I suspect it is https://lists.gnu.org/archive/html/qemu-devel/2018-08/msg00470.html so the fix is Fam's 'aio: Do aio_notify_accept only during blocking aio_poll'. I see you're running the qemu-kvm-ev from centos, if I read the version tea-leaves right, then I think that patch is in the 2.10.0-21.el7_5.7.1 package I can see. Dave > Chris >=20 -- Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK