From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:37278)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <fred.konrad@greensocs.com>) id 1Z86VS-0002KB-3U
	for qemu-devel@nongnu.org; Thu, 25 Jun 2015 08:43:50 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <fred.konrad@greensocs.com>) id 1Z86VN-0007p5-6J
	for qemu-devel@nongnu.org; Thu, 25 Jun 2015 08:43:50 -0400
Received: from greensocs.com ([193.104.36.180]:40535)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <fred.konrad@greensocs.com>) id 1Z86VM-0007no-Qk
	for qemu-devel@nongnu.org; Thu, 25 Jun 2015 08:43:45 -0400
Message-ID: <558BF77B.2020803@greensocs.com>
Date: Thu, 25 Jun 2015 14:43:39 +0200
From: Frederic Konrad <fred.konrad@greensocs.com>
MIME-Version: 1.0
References: <1435160084-938-1-git-send-email-alex.bennee@linaro.org>
	<CAJRNFKLd7CTwrVtn5EEHKUW40aKVWY4JkbwvsUKeGPYpeyULEg@mail.gmail.com>
In-Reply-To: <CAJRNFKLd7CTwrVtn5EEHKUW40aKVWY4JkbwvsUKeGPYpeyULEg@mail.gmail.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: quoted-printable
Subject: Re: [Qemu-devel] [RFC PATCH] target-arm/psci.c: wake up sleeping
	CPUs (MTTCG)
List-Id: <qemu-devel.nongnu.org>
List-Unsubscribe: <https://lists.nongnu.org/mailman/options/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: <https://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: Alexander Spyridakis <a.spyridakis@virtualopensystems.com>, =?UTF-8?B?QWxleCBCZW5uw6ll?= <alex.bennee@linaro.org>
Cc: mttcg@listserver.greensocs.com, Peter Maydell <peter.maydell@linaro.org>, Mark Burton <mark.burton@greensocs.com>, QEMU Developers <qemu-devel@nongnu.org>

On 25/06/2015 01:55, Alexander Spyridakis wrote:
> On 24 June 2015 at 17:34, Alex Benn=C3=A9e <alex.bennee@linaro.org> wro=
te:
>> Testing with Alexander's bare metal syncronisation tests fails in MTTC=
G
>> leaving one CPU spinning forever waiting for the second CPU to wake up=
.
>> We simply need to poke the halt_cond once we have processed the PSCI
>> power on call.
> Thanks Alex. Works for me, also with qemu_cpu_kick(target_cpu_state)
> as Paolo mentioned.
>
> The test seems to stress the current multi-threaded implementation
> quite a lot. With 8 CPUs running, the resulting errors are in the
> range of 500 per vCPU (10 million iterations).
> Performance is another issue as mentioned before, but even more
> pronounced with 8 cores. Upstream QEMU needs around 10 seconds to
> complete, with multi-threading around 100 seconds for the same test.
>
> Best regards.
Hi,

I can reproduce the atomic errors with the test something is definitely=20
wrong.
I know about the performance issue I fixed it in the patch-set I'll send.

Thanks,
Fred