From mboxrd@z Thu Jan 1 00:00:00 1970 From: Bill Davidsen Subject: Re: New FAQ entry? (was IBM xSeries stop responding during RAID1 reconstruction) Date: Thu, 22 Jun 2006 23:14:51 -0400 Message-ID: <449B5CAB.50409@tmr.com> References: <449A1E10.2050402@fooplanet.com> <20060622071145.GA718@rigacci.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20060622071145.GA718@rigacci.org> Sender: linux-raid-owner@vger.kernel.org To: Niccolo Rigacci Cc: linux-raid@vger.kernel.org, Mark Hahn List-Id: linux-raid.ids Niccolo Rigacci wrote: >>>personally, I don't see any point to worrying about the default, >>>compile-time or boot time: >>> >>>for f in `find /sys/block/* -name scheduler`; do echo cfq > $f; done >>> >>> > >I tested this case: > >- reboot as per power failure (RAID goes dirty) >- RAID start resyncing as soon as the kernel assemble it >- every disk activity is blocked, even DHCP failed! >- host services are unavailable > >This is why I changed the kernel default. > > > Changing on the command line assumes that you built all of the schedulers in... but making that assumption, perhaps the correct fail-safe is to have cfq as the default, and at the end of rc.local check for rebuild, and if everything is clean change to whatever work best at the end of the boot. If the raid is not clean stay with cfq. Has anyone tried deadline for this? I think I had this as deafult and didn't hand on a raid5 fail/rebuild. -- bill davidsen CTO TMR Associates, Inc Doing interesting things with small computers since 1979