From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:59389) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1baOCo-000543-U0 for qemu-devel@nongnu.org; Thu, 18 Aug 2016 10:22:04 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1baOCl-0004VV-LE for qemu-devel@nongnu.org; Thu, 18 Aug 2016 10:22:02 -0400 Received: from mx1.redhat.com ([209.132.183.28]:43306) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1baOCl-0004VI-DF for qemu-devel@nongnu.org; Thu, 18 Aug 2016 10:21:59 -0400 Date: Thu, 18 Aug 2016 10:21:56 -0400 From: Luiz Capitulino Message-ID: <20160818102156.2c43bc6c@redhat.com> In-Reply-To: <20160818135327.GJ4850@stefanha-x1.localdomain> References: <147041636348.2523.2954972609232949598.stgit@fimbulvetr.bsc.es> <20160818094720.GA4850@stefanha-x1.localdomain> <87wpjeqsv9.fsf@fimbulvetr.bsc.es> <20160818135327.GJ4850@stefanha-x1.localdomain> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Subject: Re: [Qemu-devel] [PATCH 0/6] hypertrace: Lightweight guest-to-QEMU trace channel List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Stefan Hajnoczi Cc: Stefan Hajnoczi , qemu-devel@nongnu.org, Steven Rostedt , lttng-dev@lists.lttng.org, Masami Hiramatsu On Thu, 18 Aug 2016 14:53:27 +0100 Stefan Hajnoczi wrote: > On Thu, Aug 18, 2016 at 12:22:18PM +0200, Llu=C3=ADs Vilanova wrote: > > Stefan Hajnoczi writes: > > =20 > > > On Fri, Aug 05, 2016 at 06:59:23PM +0200, Llu=C3=ADs Vilanova wrote: = =20 > > >> The hypertrace channel allows guest code to emit events in QEMU (the= host) using > > >> its tracing infrastructure (see "docs/trace.txt"). This works in bot= h 'system' > > >> and 'user' modes. That is, hypertrace is to tracing, what hypercalls= are to > > >> system calls. > > >>=20 > > >> You can use this to emit an event on both guest and QEMU (host) trac= es to easily > > >> synchronize or correlate them. You could also modify you guest's tra= cing system > > >> to emit all events through the hypertrace channel, providing a unifi= ed and fully > > >> synchronized trace log. Another use case is timing the performance o= f guest code > > >> when optimizing TCG (QEMU traces have a timestamp). > > >>=20 > > >> See first commit for a full description. > > >>=20 > > >> Signed-off-by: Llu=C3=ADs Vilanova > > >> --- =20 > > =20 > > > CCing Steven Rostedt, Masami Hiramatsu, Luiz Capitulino, and LTTng fo= lks > > > who have all looked into host/guest tracing solutions. =20 > > [...] > >=20 > > Oh, I wasn't aware of that. I'm certainly interested in collaborating. = =20 >=20 > They are working on or have worked on different approaches to host/guest > tracing. Unfortunately there isn't an out-of-the-box solution as far as > I know. The ftrace solution is documented here: https://lists.nongnu.org/archive/html/qemu-devel/2016-03/msg00887.html This traces the guest and host kernels. It supports merging the guest and host traces. It's extremely low latency and has helped us to find several spikes for real-time KVM (we're talking a few to a dozen microseconds at most). Now, our stack actually is: - Guest app - Guest kernel - Host kernel - QEMU QEMU already has its own tracing (which I don't know how it works). If I had to trace the guest app, I'd certainly start off by using LTTng. Although, we'd have to write a tool to merge and orchestrate (wooo, cloud buzzword!) all those traces (if that's what one wants). > It would be nice if there was a documented host/guest tracing approach > that didn't involve much manual setup and handled most use cases. I'd volunteer to do it, although it will take me weeks to do it.