Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752907Ab3EPEvr (ORCPT ); Thu, 16 May 2013 00:51:47 -0400 Received: from mail-vb0-f41.google.com ([209.85.212.41]:62406 "EHLO mail-vb0-f41.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751928Ab3EPEvq (ORCPT ); Thu, 16 May 2013 00:51:46 -0400 MIME-Version: 1.0 Date: Thu, 16 May 2013 05:51:45 +0100 Message-ID: Subject: Investigating lockups on Pentium D/SiS 661FX? From: Mikhail Ramendik To: linux-kernel Content-Type: text/plain; charset=ISO-8859-1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1568 Lines: 40 Hello, I have a SiS 661FX motherboard, which was perfectly stable with a Pentium 4 CPU (with HT). But since I installed a Pentium D (no HT), the system started to lock up several times a day. The system works fine under load tests under Windows. I have moved all processes to core 0 using /dev/cpuset in a scriptthat I now run as init (I really onlyu need the second core for video playback). The system got much more stable but still locks up for a few minutes once in a while. For some reason it is more prone to lockups when Transmission is running. I also noted that interrupts are being handled mostly by core 1. I could not detect anything in /var/log/messages or /var/log/kern.log for the lockup times. The kernel is 2.6.32 but I tried 3.0.something too (everything Debian-built). Nothing past 3.2 is available for this distro (Debian squeeze) but I will do a compile of any required version with any required config if necessary. Is there any way I could collect more information so the reason could be worked out? Any tests I could run to pinpoint whether it is indeed a kernel issue and if so what kind of issue - perhaps I could run tests without X started? Thanks! -- Yours, Mikhail Ramendik Unless explicitly stated, all opinions in my mail are my own and do not reflect the views of any organization -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/