From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757652Ab0JFBu5 (ORCPT ); Tue, 5 Oct 2010 21:50:57 -0400 Received: from mail-yw0-f46.google.com ([209.85.213.46]:38969 "EHLO mail-yw0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751997Ab0JFBuz convert rfc822-to-8bit (ORCPT ); Tue, 5 Oct 2010 21:50:55 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=subject:mime-version:content-type:from:in-reply-to:date:cc :content-transfer-encoding:message-id:references:to:x-mailer; b=LG2riGoXRkfxi7WVjdnmT+zyaKWAUXL1rCkl5nFuwvY3dSRj0UrkjPXvc7Cu6L9ZiH bq74DMJZ4Ri2BQd6EH2Bn6uGBdmgkcDRAXQPbDVNxH9i0yTLGO+hPzToW1TGgrzWFy5t ooju7A5l1UkFLAkqjmtSk5HaFwzYtpDeaSQ2o= Subject: Re: Why not distribute timer handlers on CPUs on SMP Mime-Version: 1.0 (Apple Message framework v1078) Content-Type: text/plain; charset=us-ascii From: bhs In-Reply-To: <2B624B3F-9338-4336-B4F6-D61B476DA255@gmail.com> Date: Wed, 6 Oct 2010 09:50:48 +0800 Cc: linux-kernel@vger.kernel.org Content-Transfer-Encoding: 8BIT Message-Id: References: <2B624B3F-9338-4336-B4F6-D61B476DA255@gmail.com> To: bhs X-Mailer: Apple Mail (2.1078) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Oct 6, 2010, at 9:05 AM, bhs wrote: > Hello, > > I am just curious about why handle the timer functions on a CPU serially but not distribute them over CPUs > even on a SMP system? > Yea, it already distributed over CPUs at calling add_timer(), timer function was bounded to a cpu on which it was created. I am sorry for my noise. > The timer wheel handler function __run_timers() serializes the timer functions on a CPU, > is there any design consideration that handling timers on a CPU is more reasonable than distribute them > over CPUs? > > > Best regards > Shan Hai