Date: Wed, 14 Mar 2001 08:29:56 -0600 From: Mike Meyer <mwm@mired.org> To: Mark Ibell <marki@paradise.net.nz> Cc: Alfred Perlstein <bright@wintelcom.net>, Mars Attack <marsattack@cannoncreek.com>, Soren Schmidt <sos@freebsd.dk>, Peter Wemm <peter@netplex.com.au>, Helge Oldach <Helge.Oldach@de.origin-it.com>, oberman@es.net, mobile@FreeBSD.ORG, stable@FreeBSD.ORG Subject: Re: Disk I/O problem in 4.3-BETA Message-ID: <15023.32868.9995.327616@guru.mired.org> In-Reply-To: <3AAF4DA0.C8DA9485@paradise.net.nz> References: <200103131007.f2DA73h54023@mobile.wemm.org> <01f001c0abaa$133e1680$4500a8c0@nomad> <20010313032635.Q29888@fw.wintelcom.net> <3AAF4DA0.C8DA9485@paradise.net.nz>
next in thread | previous in thread | raw e-mail | index | archive | help
Mark Ibell <marki@paradise.net.nz> types: > What doesn't appear to have been mentioned is how exactly do we turn off > write caching on SCSI drives. From poking around the best I could work > out was to run 'camcontrol modepage da0 -m 0x08 -e -P 3' and set WCE to > 0 where 0x08 comes from /usr/share/misc/scsi_modes. > > Is this the correct way to do it? Assuming you've got the right numbers for WCE, yes. Camcontrol is the right tool. > Also, is it okay to leave tagged queuing enabled? (I'm really starting > to get paranoid after all this discussion!) I'd say yes, as at least some of the drivers expect it to be there. I think the critical thing is that the driver know when the data is actually on the disk, so if tagged queueing doesn't interfere with that, it's ok. <mike -- Mike Meyer <mwm@mired.org> http://www.mired.org/home/mwm/ Independent WWW/Perforce/FreeBSD/Unix consultant, email for more information. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-mobile" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?15023.32868.9995.327616>