From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43)
	id 1Jt9fZ-0008Ar-5k
	for qemu-devel@nongnu.org; Mon, 05 May 2008 19:00:29 -0400
Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43)
	id 1Jt9fX-00089U-Hg
	for qemu-devel@nongnu.org; Mon, 05 May 2008 19:00:28 -0400
Received: from [199.232.76.173] (port=35466 helo=monty-python.gnu.org)
	by lists.gnu.org with esmtp (Exim 4.43) id 1Jt9fX-00089D-CD
	for qemu-devel@nongnu.org; Mon, 05 May 2008 19:00:27 -0400
Received: from py-out-1112.google.com ([64.233.166.182])
	by monty-python.gnu.org with esmtp (Exim 4.60)
	(envelope-from <anthony@codemonkey.ws>) id 1Jt9fW-00010S-De
	for qemu-devel@nongnu.org; Mon, 05 May 2008 19:00:27 -0400
Received: by py-out-1112.google.com with SMTP id u52so1679987pyb.10
	for <qemu-devel@nongnu.org>; Mon, 05 May 2008 16:00:24 -0700 (PDT)
Message-ID: <481F9184.3050902@codemonkey.ws>
Date: Mon, 05 May 2008 18:00:20 -0500
From: Anthony Liguori <anthony@codemonkey.ws>
MIME-Version: 1.0
Subject: Re: [Qemu-devel] [4341] qemu: generate signals on tap I/O
References: <E1Jt8Cq-0007Qs-U7@cvs.savannah.gnu.org>	<481F84F3.6060505@flac.kalibalik.dk>
	<481F86F3.4080007@aurel32.net> <481F8D57.40500@flac.kalibalik.dk>
	<481F8DE5.9040905@codemonkey.ws> <481F8F0B.8040004@aurel32.net>
	<481F8F74.9010507@aurel32.net> <481F90D4.6090507@codemonkey.ws>
In-Reply-To: <481F90D4.6090507@codemonkey.ws>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Reply-To: qemu-devel@nongnu.org
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.gnu.org/pipermail/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: Aurelien Jarno <aurelien@aurel32.net>
Cc: qemu-devel@nongnu.org

Anthony Liguori wrote:
>
> If you explicitly call host_alarm_handler in tap_send(), do you see 
> the same improvement?  Perhaps your host timer is just very slow?

Oh, it's probably that the signal is causing TCG to be interrupted and 
IO to be processed immediately.  Moving the select() loop into a 
separate thread that sets an atomic whenever it's time to break out of 
the TCG loop would be a more general solution.

Regards,

Anthony Liguori

> Regards,
>
> Anthony Liguori
>
>>> e1000 card on the MIPS Malta target.
>>>
>>> That's why I use that patch in my local tree.
>>>
>>>     
>>
>>
>>   
>