From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S936684AbXGQXrd (ORCPT ); Tue, 17 Jul 2007 19:47:33 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1759194AbXGQXrZ (ORCPT ); Tue, 17 Jul 2007 19:47:25 -0400 Received: from moutng.kundenserver.de ([212.227.126.177]:60723 "EHLO moutng.kundenserver.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758248AbXGQXrY (ORCPT ); Tue, 17 Jul 2007 19:47:24 -0400 Subject: Re: [PATCH][RFC] 4K stacks default, not a debug thing any more...? From: utz lehmann To: John Stoffel Cc: Rene Herman , Bodo Eggert <7eggert@gmx.de>, Matt Mackall , Jeremy Fitzhardinge , Jesper Juhl , Ray Lee , Linux Kernel Mailing List , William Lee Irwin III In-Reply-To: <18076.54789.359986.788880@stoffel.org> References: <8FO1e-2jW-35@gated-at.bofh.it> <8FYWD-2eS-7@gated-at.bofh.it> <8GdsH-8dc-13@gated-at.bofh.it> <8Ghmx-60z-17@gated-at.bofh.it> <8Gj55-hJ-5@gated-at.bofh.it> <8GkNo-2Vb-1@gated-at.bofh.it> <8GtnN-7TG-23@gated-at.bofh.it> <8GVjY-PL-25@gated-at.bofh.it> <1184628395.8707.15.camel@segv.aura.of.mankind> <18076.54789.359986.788880@stoffel.org> Content-Type: text/plain Date: Wed, 18 Jul 2007 01:46:43 +0200 Message-Id: <1184716003.9560.29.camel@segv.aura.of.mankind> Mime-Version: 1.0 X-Mailer: Evolution 2.10.3 (2.10.3-1.fc7) Content-Transfer-Encoding: 7bit X-Provags-ID: V01U2FsdGVkX1/MYKXJGE3zQMjiHQwIqp/MiYSjbj4VW01sZwi h2x3KVaPc2hNBL7rxAXnkUxmB4U/ONkFK3txP9BqAwah0Te4rn Pyc92sFeogJlGu912jwl1QcuXxE5PI/ Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 2007-07-17 at 10:45 -0400, John Stoffel wrote: > utz> I have to recompile the fedora kernel rpms (fc6, f7) with 8k > utz> stacks on my i686 server. It's using NFS -> XFS -> DM -> MD > utz> (raid1) -> IDE disks. With 4k stacks it crash (hang) within > utz> minutes after using NFS. With 8k stacks it's rock solid. No > utz> crashes within months. > > Does it give any useful information when it does crash? > No, sorry. Nearly always it lock up so hard that even sysrq didn't work anymore. Most times the console was blanked. If not, there was a line with "do_irq" or something like that (if i remember correctly). A few times it continuous oopsing (scrolling like mad). I think it's just a stack overflow. Knowing that XFS + long IO stack have problems with 4k stacks. And i have zero crashes with the recompiled 8k stack kernels. (All kernel are the fedora ones). Btw: In the past the server runs on slightly different hardware and without raid1 (NFS -> XFS -> DM -> IDE disk). It runs with 4k stacks. I had a few crashes, but i blame the hardware for it. I don't want to make tests with the server. It's my main data storage and i don't want to risk it. > Can you make > a simple test case using ram disks instead of IDE disks and then > building upon that? Sorry, i don't think i can do this. My other computer, which i can use for tests, is x86_64 based. And IFAIK the problem on the XFS side has something to do with looking for freespace on many AGs. So maybe a bigger and filled filesystem is needed. And 50GB ram disks are out of question. utz