From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754264AbYIYOT5 (ORCPT ); Thu, 25 Sep 2008 10:19:57 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752363AbYIYOTt (ORCPT ); Thu, 25 Sep 2008 10:19:49 -0400 Received: from e6.ny.us.ibm.com ([32.97.182.146]:58848 "EHLO e6.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752208AbYIYOTs (ORCPT ); Thu, 25 Sep 2008 10:19:48 -0400 Date: Thu, 25 Sep 2008 07:18:09 -0700 From: "Paul E. McKenney" To: Ingo Molnar Cc: linux-kernel@vger.kernel.org, cl@linux-foundation.org, akpm@linux-foundation.org, manfred@colorfullife.com, dipankar@in.ibm.com, josht@linux.vnet.ibm.com, schamp@sgi.com, niv@us.ibm.com, dvhltc@us.ibm.com, ego@in.ibm.com, laijs@cn.fujitsu.com, rostedt@goodmis.org, peterz@infradead.org, penberg@cs.helsinki.fi, andi@firstfloor.org, tglx@linutronix.com, Thomas Gleixner Subject: Re: [PATCH, RFC] v6 scalable classic RCU implementation Message-ID: <20080925141809.GB6725@linux.vnet.ibm.com> Reply-To: paulmck@linux.vnet.ibm.com References: <20080821234318.GA1754@linux.vnet.ibm.com> <20080825000738.GA24339@linux.vnet.ibm.com> <20080830004935.GA28548@linux.vnet.ibm.com> <20080905152930.GA8124@linux.vnet.ibm.com> <20080915160221.GA9660@linux.vnet.ibm.com> <20080923235340.GA12166@linux.vnet.ibm.com> <20080925072915.GB20249@elte.hu> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20080925072915.GB20249@elte.hu> User-Agent: Mutt/1.5.15+20070412 (2007-04-11) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, Sep 25, 2008 at 09:29:15AM +0200, Ingo Molnar wrote: > > * Paul E. McKenney wrote: > > > Attached is an updated patch to Classic RCU that applies a hierarchy, > > greatly reducing the contention on the top-level lock for large > > machines. This passes 10-hour concurrent rcutorture and > > online-offline testing on 128-CPU ppc64 without dynticks enabled, and > > exposes some timekeeping bugs in presence of dynticks (exciting > > working on a system where "sleep 1" hangs until interrupted...). > > i'm wondering about those timekeeping bugs. Do you have an idea what's > it about and does it affect mainline? Sad to say, they do affect mainline -- I can reproduce these problems in 2.6.27-rc7. Thomas has given me a couple of fixes that got rid of earlier problems in which jiffies would stop counting, and I believe has located the cause of at least one other problem. Thanx, Paul