From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:33974) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1bhEwU-0003Mu-BR for qemu-devel@nongnu.org; Tue, 06 Sep 2016 07:53:31 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1bhEwP-0002ix-BO for qemu-devel@nongnu.org; Tue, 06 Sep 2016 07:53:30 -0400 Received: from mx1.redhat.com ([209.132.183.28]:45930) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1bhEwP-0002in-62 for qemu-devel@nongnu.org; Tue, 06 Sep 2016 07:53:25 -0400 Date: Tue, 6 Sep 2016 14:53:21 +0300 From: "Michael S. Tsirkin" Message-ID: <20160906144736-mutt-send-email-mst@kernel.org> References: <1472120105-29235-1-git-send-email-chao.p.peng@linux.intel.com> <1473158937.4143.15.camel@linux.intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline In-Reply-To: <1473158937.4143.15.camel@linux.intel.com> Content-Transfer-Encoding: quoted-printable Subject: Re: [Qemu-devel] [RFC PATCH v2 00/12] Guest startup time optimization List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Chao Peng Cc: Paolo Bonzini , qemu-devel@nongnu.org, gor Mammedov , Xiao Guangrong , Richard Henderson , Eduardo Habkost , Haozhong Zhang , Amnon Ilan On Tue, Sep 06, 2016 at 06:48:57PM +0800, Chao Peng wrote: >=20 > > Patches 1-4 are okay, though I think it would be easier to add a -M > > q35-lite too that just removes the legacy devices.=A0=A0The -M q35-li= te > > machine doesn't have to support versioning for now. >=20 > Okay, this is also good to have in my mind. >=20 > >=20 > > As you might expect, I don't agree with removing the > > firmware.=A0=A0There's > > room for much more optimization before duplicating firmware code in > > QEMU.=A0=A0I'd rather see numbers for: > >=20 > > 1) qboot optimizations: adopt the fw_cfg DMA interface instead of the > > cbfs flash hack (so that -kernel works), drop PCI bridge > > initialization, > > copy less than 64K of memory from ROM to 0xf0000; >=20 > I can do the evaluation on qboot. Also adding Amnon Ilan, to see if > there is some thing we can do for SeaBios. AFAIK latest seabios already supports DMA. It's easy to add more config options for seabios if you are so inclined. > >=20 > > 2) Linux optimizations: using an uncompressed image to avoid the cost > > of > > copying and decompressing.=A0=A0QEMU can already load the image at th= e > > right > > place and the real mode stub can do little more than GDT/IDT setup. >=20 > This works surely. I actually followed your suggestion in v1 to make > kernel multiboot-compatible and then load that kernel in QEMU directly > (Also skipped firmware but some changes in patch 11 would move from > QEMU to guest kernel). This way we also gain benefit of doing mmap > kernel as you talked below. Not sure if this is something you can > accpet. I'm not sure I understand the question here. Accept what? > >=20 > > 3) PAM optimizations: for -M q35-lite initialize the machine with RAM > > from 0xc0000 to 1MB. > >=20 > > I know that you ultimately would like to mmap the kernel, but I would > > like to have a better understanding of where the time is spent. > >=20 > > Thanks, > >=20 > > Paolo