From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:34666)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <ahzhanghaoyu@gmail.com>) id 1XcYsh-0000IL-0R
	for qemu-devel@nongnu.org; Fri, 10 Oct 2014 08:01:21 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <ahzhanghaoyu@gmail.com>) id 1XcYsX-0008NR-Jo
	for qemu-devel@nongnu.org; Fri, 10 Oct 2014 08:01:10 -0400
Received: from mail-pa0-x22a.google.com ([2607:f8b0:400e:c03::22a]:43597)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <ahzhanghaoyu@gmail.com>) id 1XcYsX-0008NA-C8
	for qemu-devel@nongnu.org; Fri, 10 Oct 2014 08:01:01 -0400
Received: by mail-pa0-f42.google.com with SMTP id bj1so1640358pad.15
	for <qemu-devel@nongnu.org>; Fri, 10 Oct 2014 05:01:00 -0700 (PDT)
Message-ID: <5437CA6E.2000802@gmail.com>
Date: Fri, 10 Oct 2014 20:00:46 +0800
From: Zhang Haoyu <ahzhanghaoyu@gmail.com>
MIME-Version: 1.0
References: <5437C505.4010504@gmail.com> <5437C6A2.3020908@gmail.com>
In-Reply-To: <5437C6A2.3020908@gmail.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Subject: Re: [Qemu-devel] [question] Is there a plan to introduce a unified
 co-scheduling mechanism to CFS ?
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: Wanpeng Li <kernellwp@gmail.com>, kvm <kvm@vger.kernel.org>, "qemu-devel@nongnu.org Developers" <qemu-devel@nongnu.org>

 >> Hi,
 >>
 >> Is it worthy to introduce a unified co-scheduling mechanism to CFS ?
 >> Because multiple cooperating threads or tasks frequently synchronize 
with each other,
 >> not executing them concurrently would only increase the latency of 
synchronization.
 >> For example, a thread blocking in spinlock to waiting for another 
thread to release the same spinlock
 >> might reduce its waiting time by being executed concurrently with 
the thread which hold the same spinlock.
 >> In virtualization scenario, multiple vcpus (which belong to the same 
vm) co-scheduling is more desired
 >> when several cooperating threads/task is running in guest.
 >>
 >> Is there a plane for this work?
 >
 > Please refer to gang scheduler.
 >
Is there a mechanism to dynamically detect which vcpus belong to the 
same gang?
Maybe a cooperative degree can be used to decide the threshold of which 
vcpus belong to the same gang, just a wild thought.

 > Regards,
 > Wanpeng Li
 >>
 >> Thanks,
 >> Zhang Haoyu