From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([140.186.70.92]:60391) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1QyiRB-0004nZ-PC for qemu-devel@nongnu.org; Wed, 31 Aug 2011 06:54:30 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1QyiRA-0002O1-R1 for qemu-devel@nongnu.org; Wed, 31 Aug 2011 06:54:29 -0400 Received: from thoth.sbs.de ([192.35.17.2]:20752) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1QyiRA-0002Nm-DA for qemu-devel@nongnu.org; Wed, 31 Aug 2011 06:54:28 -0400 Message-ID: <4E5E12CC.1010600@siemens.com> Date: Wed, 31 Aug 2011 12:54:04 +0200 From: Jan Kiszka MIME-Version: 1.0 References: <4E5DF31A.1@redhat.com> <20110831090815.GA2038@stefanha-thinkpad.localdomain> In-Reply-To: <20110831090815.GA2038@stefanha-thinkpad.localdomain> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [PATCH, RFC] trace: implement guest tracepoint passthrough List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Stefan Hajnoczi Cc: Blue Swirl , qemu-devel , Dhaval Giani , Avi Kivity , =?ISO-8859-1?Q?Llu=EDs?= On 2011-08-31 11:08, Stefan Hajnoczi wrote: > On Wed, Aug 31, 2011 at 11:38:50AM +0300, Avi Kivity wrote: >> On 08/26/2011 10:06 PM, Blue Swirl wrote: >>> Let guests inject tracepoint data via fw_cfg device. >>> >>> >> >> At least on x86, fw_cfg is pretty slow, involving multiple exits. >> IMO, for kvm, even one exit per tracepoint is too high. We need to >> use a shared memory transport with a way to order guest/host events >> later on (by using a clock). > > It depends how you want to use this. If you need it for guest firmware > debugging or bringing up a new target, then this approach is fine. > > But this is not a mechanism that is suitable for performance analysis or > production tracing (the fact that the QEMU and guest software need to be > built together in order to sync on event IDs is the killer). > > Dhaval is looking at Linux guest tracing which is suitable for > performance work. This does not necessarily involve modifying QEMU. > Currently he uses a hypercall but a virtio device would be possible too. > The key thing is that it integrates with the host kernel tracing > infrastructure so you get a unified trace instead of terminating in QEMU > userspace. > > So I see Blue's feature as a quick starting point for people who need to > debug and hack guests. It should be simple and easy to get going for > QEMU developers, but is not suitable for other use. We already have isa-debugcon or plain serial/virtio consoles. Should be easy to derive e.g. some mmio-debugcon and to establish a chardev backend that writes out trace events. I also think that fw_cfg is for, well, configuration. Jan -- Siemens AG, Corporate Technology, CT T DE IT 1 Corporate Competence Center Embedded Linux