From mboxrd@z Thu Jan 1 00:00:00 1970 From: Zhang Haoyu Subject: Re: [question] Is there a plan to introduce a unified co-scheduling mechanism to CFS ? Date: Fri, 10 Oct 2014 20:00:46 +0800 Message-ID: <5437CA6E.2000802@gmail.com> References: <5437C505.4010504@gmail.com> <5437C6A2.3020908@gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit To: Wanpeng Li , kvm , "qemu-devel@nongnu.org Developers" Return-path: Received: from mail-pd0-f171.google.com ([209.85.192.171]:57942 "EHLO mail-pd0-f171.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751487AbaJJMBA (ORCPT ); Fri, 10 Oct 2014 08:01:00 -0400 Received: by mail-pd0-f171.google.com with SMTP id ft15so1563434pdb.30 for ; Fri, 10 Oct 2014 05:01:00 -0700 (PDT) In-Reply-To: <5437C6A2.3020908@gmail.com> Sender: kvm-owner@vger.kernel.org List-ID: >> 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