From mboxrd@z Thu Jan 1 00:00:00 1970 From: Luiz Capitulino Subject: Re: Slow PXE boot in qemu.git (fast in qemu-kvm.git) Date: Mon, 11 Apr 2011 09:51:12 -0300 Message-ID: <20110411095112.2b558589@doriath> References: <20110408202525.26c45c05@doriath> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: qemu-devel@nongnu.org, kvm@vger.kernel.org, avi@redhat.com, mtosatti@redhat.com, alex.williamson@redhat.com, mst@redhat.com To: Blue Swirl Return-path: Received: from mx1.redhat.com ([209.132.183.28]:5321 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750979Ab1DKMvU convert rfc822-to-8bit (ORCPT ); Mon, 11 Apr 2011 08:51:20 -0400 In-Reply-To: Sender: kvm-owner@vger.kernel.org List-ID: On Sat, 9 Apr 2011 13:34:43 +0300 Blue Swirl wrote: > On Sat, Apr 9, 2011 at 2:25 AM, Luiz Capitulino wrote: > > Hi there, > > > > Summary: > > > > =A0- PXE boot in qemu.git (HEAD f124a41) is quite slow, more than 5= minutes. Got > > =A0 the problem with e1000, virtio and rtl8139. However, pcnet *wor= ks* (it's > > =A0 as fast as qemu-kvm.git) > > > > =A0- PXE boot in qemu-kvm.git (HEAD df85c051) is fast, less than a = minute. Tried > > =A0 with e1000, virtio and rtl8139 (I don't remember if I tried wit= h pcnet) > > > > I tried with qemu.git v0.13.0 in order to check if this was a regre= ssion, but > > I got the same problem... > > > > Then I inspected qemu-kvm.git under the assumption that it could ha= ve a fix > > that wasn't commited to qemu.git. Found this: > > > > =A0- commit 0836b77f0f65d56d08bdeffbac25cd6d78267dc9 which is merge= , works > > > > =A0- commit cc015e9a5dde2f03f123357fa060acbdfcd570a4 does not work = (it's slow) > > > > I tried a bisect, but it brakes due to gcc4 vs. gcc3 changes. Then = I inspected > > commits manually, and found out that commit 64d7e9a4 doesn't work, = which makes > > me think that the fix could be in the conflict resolution of 0836b7= 7f, which > > makes me remember that I'm late for diner, so my conclusions at thi= s point are > > not reliable :) > > > > Ideas? >=20 > What is the test case? It's an external PXE server, command-line is: qemu -boot n -enable-kvm -net nic,model=3Dvirtio -net tap,ifname=3Dvne= t0,script=3D > I tried PXE booting a 10M file with and without > KVM and the results are pretty much the same with pcnet and e1000. > time qemu -monitor stdio -boot n -net nic,model=3De1000 -net > user,tftp=3D.,bootfile=3D10M -net dump,file=3Dfoo -enable-kvm > time qemu -monitor stdio -boot n -net nic,model=3Dpcnet -net > user,tftp=3D.,bootfile=3D10M -net dump,file=3Dfoo -enable-kvm > time qemu -monitor stdio -boot n -net nic,model=3De1000 -net > user,tftp=3D.,bootfile=3D10M -net dump,file=3Dfoo > time qemu -monitor stdio -boot n -net nic,model=3Dpcnet -net > user,tftp=3D.,bootfile=3D10M -net dump,file=3Dfoo >=20 > All times are ~10s. Yeah, you're using the internal tftp server.