From mboxrd@z Thu Jan 1 00:00:00 1970 From: Bill Davidsen Subject: Re: sun x4500 soft lockup during raid creation Date: Fri, 30 Jan 2009 10:28:59 -0500 Message-ID: <49831CBB.8010609@tmr.com> References: <1233174633.7008.34.camel@hazard2.francoudi.com> <20090128223330.GA14409@sillage.bis.pasteur.fr> <20090128230852.GA8495@francoudi.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20090128230852.GA8495@francoudi.com> Sender: linux-raid-owner@vger.kernel.org To: Vladimir Ivashchenko Cc: Tru Huynh , linux-raid@vger.kernel.org List-Id: linux-raid.ids Vladimir Ivashchenko wrote: > On Wed, Jan 28, 2009 at 11:33:30PM +0100, Tru Huynh wrote: > > >>> CentOS 5.2, 2.6.18-92.1.22.el5PAE, sata_mv. Two dual-core Opterons @ 2.8 >>> Ghz, 16 GB RAM. >>> >> any reason for using the 32 bits version instead of the 64 bits? >> >> you must also be aware of http://kbase.redhat.com/faq/docs/DOC-15593 >> >> just my .2 cents >> > > Always welcome :) > > According to http://epubs.cclrc.ac.uk/bitstream/2943/ThumperReport.pdf, x4500 was shown to be unstable under centos/rhel 4.x (he didn't > use mv_sata though). In any case, centos 4.x is way too old. > > I changed the kernel to 2.6.27.12-78.2.8.fc9.i686 and so far it is stable. > > x64 will be the next step. i686 is what our guys install by default, I didn't bother to reinstall it. > > In spite of the theoretical benefits of 64 bit, I find that the advantages are "measurable but not noticeable" for most things. The lack of 64 bit versions of some applications was a problem for me, but may not be for you. I did find that even building from source not all applications worked right, or worked at all, or in some cases compiled. :-( -- Bill Davidsen "Woe unto the statesman who makes war without a reason that will still be valid when the war is over..." Otto von Bismark