Date: Wed, 14 Mar 2007 17:50:45 +0100 From: Baurzhan Ismagulov <ibr@radix50.net> To: aic7xxx@freebsd.org Subject: Re: Adaptec 2940UW with Fujitsu MAN3184M Message-ID: <20070314165045.GA21264@radix50.net> In-Reply-To: <45F7FBA5.4010404@scsiguy.com> References: <20070228204034.GA2379@radix50.net> <45E602B3.2020306@paralan.com> <20070228233314.GA7348@radix50.net> <45E77B30.2090505@paralan.com> <20070302220950.GD7331@radix50.net> <45E8C36C.1020407@paralan.com> <20070314121250.GB2553@radix50.net> <45F7FBA5.4010404@scsiguy.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Hello Justin, On Wed, Mar 14, 2007 at 09:41:57AM -0400, Justin T. Gibbs wrote: > >I've done some tests (hdparm -tT, build the Linux kernel with ccache) > >and have seen that my SATA 7.2k ST3320620AS outperforms U160 10k > >MAN3184M by up to 30%, so I decided not to use it for the rootfs yet. > > Make sure you run a fair test. Most SCSI drives are shipped from the > factory with the write cache set to "write-through". SATA and ATA > drives almost always operate in "write-back" mode. Your 29160 BIOS > should have an option to set the caching mode on a per-target basis. I've enabled the BIOS and set the write-back mode on MAN3184M, no difference in writing /proc/kcore. > If you're system is backed up by a UPS or your FS can handle being > lied to, write-back is fine. Otherwise it's really not a safe option. Oh. Does ext3 handle that? Or do you know filesystems that do? I've googled for that, but the links I've looked at refer to ext3's writeback mode. With kind regards, -- Baurzhan Ismagulov http://www.kz-easy.com/
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20070314165045.GA21264>