From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Witbrodt Subject: Re: [PATCH diagnostic] Re: HPET regression in 2.6.26 versus 2.6.25 -- RCU problem Date: Mon, 11 Aug 2008 11:22:21 -0700 (PDT) Message-ID: <173065.89301.qm@web82104.mail.mud.yahoo.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Peter Zijlstra , linux-kernel@vger.kernel.org, Yinghai Lu , Ingo Molnar , Thomas Gleixner , "H. Peter Anvin" , netdev To: paulmck@linux.vnet.ibm.com Return-path: Received: from web82104.mail.mud.yahoo.com ([209.191.84.217]:39339 "HELO web82104.mail.mud.yahoo.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1752974AbYHKSWW (ORCPT ); Mon, 11 Aug 2008 14:22:22 -0400 Sender: netdev-owner@vger.kernel.org List-ID: > > Well, I was hoping to see something interesting. I ran it with parameters > > "debug initcall_debug", and it locked up at the same place. I let it for > > 15 minutes, in case of some delayed reaction. Nada. > > Interesting. The causes could be: > > o Scheduling-clock interrupts aren't happening, as Ingo suggested. Does anyone have a short answer to this question: Were the changes between 2.6.25 and 2.6.26 so major that interrupts are NOW being used that were not being used before? Again, I don't even pretend to understand the kernel's inner workings, but 2.6.25 _did_ work on this hardware... and with HPET enabled. DW