From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from [140.186.70.92] (port=48272 helo=eggs.gnu.org)
	by lists.gnu.org with esmtp (Exim 4.43) id 1PKyex-0005vE-NK
	for qemu-devel@nongnu.org; Tue, 23 Nov 2010 14:36:22 -0500
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <blauwirbel@gmail.com>) id 1PKyeh-0006s0-CW
	for qemu-devel@nongnu.org; Tue, 23 Nov 2010 14:36:09 -0500
Received: from mail-px0-f173.google.com ([209.85.212.173]:62519)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <blauwirbel@gmail.com>) id 1PKyeh-0006qV-7i
	for qemu-devel@nongnu.org; Tue, 23 Nov 2010 14:35:55 -0500
Received: by pxi16 with SMTP id 16so2353614pxi.4
	for <qemu-devel@nongnu.org>; Tue, 23 Nov 2010 11:35:54 -0800 (PST)
MIME-Version: 1.0
In-Reply-To: <1290530963-3448-1-git-send-email-aliguori@us.ibm.com>
References: <1290530963-3448-1-git-send-email-aliguori@us.ibm.com>
From: Blue Swirl <blauwirbel@gmail.com>
Date: Tue, 23 Nov 2010 19:35:33 +0000
Message-ID: <AANLkTin+Bscmmheo1xURNMY_hPxZ+=PgJRveZj_uB44f@mail.gmail.com>
Subject: Re: [Qemu-devel] [PATCH] qemu-kvm: response to SIGUSR1 to start/stop
	a VCPU (v2)
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: quoted-printable
List-Id: qemu-devel.nongnu.org
List-Unsubscribe: <http://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.nongnu.org/archive/html/qemu-devel>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <http://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: Anthony Liguori <aliguori@us.ibm.com>
Cc: Chris Wright <chrisw@sous-sol.org>, qemu-devel@nongnu.org, kvm@vger.kernel.org, Avi Kivity <avi@redhat.com>

On Tue, Nov 23, 2010 at 4:49 PM, Anthony Liguori <aliguori@us.ibm.com> wrot=
e:
> qemu-kvm vcpu threads don't response to SIGSTOP/SIGCONT. =C2=A0Instead of=
 teaching
> them to respond to these signals (which cannot be trapped), use SIGUSR1 t=
o
> approximate the behavior of SIGSTOP/SIGCONT.
>
> The purpose of this is to implement CPU hard limits using an external too=
l that
> watches the CPU consumption and stops the VCPU as appropriate.
>
> This provides a more elegant solution in that it allows the VCPU thread t=
o
> release qemu_mutex before going to sleep.
>
> This current implementation uses a single signal. =C2=A0I think this is t=
oo racey
> in the long term so I think we should introduce a second signal. =C2=A0If=
 two signals
> get coalesced into one, it could confuse the monitoring tool into giving =
the
> VCPU the inverse of it's entitlement.
>
> It might be better to simply move this logic entirely into QEMU to make t=
his
> more robust--the question is whether we think this is a good long term fe=
ature
> to carry in QEMU?

> +static __thread int sigusr1_wfd;

While OpenBSD finally updated the default compiler to 4.2.1 from 3.x
series, thread local storage is still not supported:

$ cat thread.c
static __thread int sigusr1_wfd;
$ gcc thread.c -c
thread.c:1: error: thread-local storage not supported for this target
$ gcc -v
Reading specs from /usr/lib/gcc-lib/sparc64-unknown-openbsd4.8/4.2.1/specs
Target: sparc64-unknown-openbsd4.8
Configured with: OpenBSD/sparc64 system compiler
Thread model: posix
gcc version 4.2.1 20070719