From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:37434)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <fred.konrad@greensocs.com>) id 1ZPVCV-0005B6-Ap
	for qemu-devel@nongnu.org; Wed, 12 Aug 2015 08:32:12 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <fred.konrad@greensocs.com>) id 1ZPVCS-0006D6-5q
	for qemu-devel@nongnu.org; Wed, 12 Aug 2015 08:32:11 -0400
Received: from greensocs.com ([193.104.36.180]:46187)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <fred.konrad@greensocs.com>) id 1ZPVCR-0006D0-V2
	for qemu-devel@nongnu.org; Wed, 12 Aug 2015 08:32:08 -0400
Message-ID: <55CB3CC3.7000700@greensocs.com>
Date: Wed, 12 Aug 2015 14:32:03 +0200
From: Frederic Konrad <fred.konrad@greensocs.com>
MIME-Version: 1.0
References: <1439220437-23957-1-git-send-email-fred.konrad@greensocs.com>	<1439220437-23957-10-git-send-email-fred.konrad@greensocs.com>	<55C8CE36.1070208@redhat.com>
	<8737zph9dy.fsf@linaro.org>	<55CA6A6E.9030205@greensocs.com>
	<55CB18D5.2020709@redhat.com>
In-Reply-To: <55CB18D5.2020709@redhat.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Subject: Re: [Qemu-devel] [RFC PATCH V7 09/19] Drop global lock during TCG
 code execution
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: Paolo Bonzini <pbonzini@redhat.com>, =?UTF-8?B?QWxleCBCZW5uw6ll?= <alex.bennee@linaro.org>
Cc: mttcg@greensocs.com, qemu-devel@nongnu.org, mark.burton@greensocs.com, a.rigo@virtualopensystems.com, guillaume.delbergue@greensocs.com

On 12/08/2015 11:58, Paolo Bonzini wrote:
>
> On 11/08/2015 23:34, Frederic Konrad wrote:
>>> Also if qemu_cond_broadcast(&qemu_io_proceeded_cond) is being dropped
>>> there is no point keeping the guff around in qemu_tcg_wait_io_event.
>>>
>> Yes good point.
>>
>> BTW this leads to high consumption of host CPU eg: 100% per VCPU thread as
>> the VCPUs thread are no longer waiting for qemu_io_proceeded_cond.
> If the guest CPU is busy waiting, that's expected.  But if the guest CPU
> is halted, it should not have 100% host CPU consumption.
>
> Paolo
>
Hmm so that's definitely strange... I mean theorically it's the same as 
before?

An other thing. It seems that we need to signal the VCPU when the 
iothread take
the lock eg:

     if (tcg_enabled() && qemu_thread_is_self(&io_thread)) {
         CPU_FOREACH(cpu) {
             cpu_exit(cpu);
         }
     }

To make this patch working without MTTCG.

Fred