Date: Sun, 16 May 2010 04:29:23 +0300 From: Kaya Saman <SamanKaya@netscape.net> To: freebsd-fs@freebsd.org Subject: Re: Quick ZFS mirroring question for non-mirrored pool Message-ID: <4BEF4A73.8060905@netscape.net> In-Reply-To: <alpine.GSO.2.01.1005151937300.12887@freddy.simplesystems.org> References: <4BEF2F9C.7080409@netscape.net> <4BEF3137.4080203@netscape.net> <20100516001351.GA50879@icarus.home.lan> <alpine.GSO.2.01.1005151937300.12887@freddy.simplesystems.org>
next in thread | previous in thread | raw e-mail | index | archive | help
Many thanks guys for providing so much valuable input and knowledge!!! I really appreciate all your advice and knowledge. Please excuse my naivety but the statement below: On 05/16/2010 03:51 AM, Bob Friesenhahn wrote: > As long as the pool is not the boot pool, zfs makes such testing quite > easy. I was under the impression that one needed a UFS2 filesystem in order to be able to boot FreeBSD as that is the only FS available upon install..... unlike Solaris10/OpenSolaris which creates the ZFS filesystem upon install. The plan I originally conceived was to use a 40GB solid state disk as the / (root) directory comprising of all descending file systems, eg. /usr, /proc, /lib etc... using the UFS2 FS ....and then use ZFS for the storage portion of my server using 2TB Western Digital RE4 Enterprise SATA drives. Since it's a simple home based server and not a massive enterprise grade environment performance is not too much of an issue. However, system backups are and without funding for a spare system or DAS or SAN solution the only real option I have is to use a RAID0 esq based setup so if one or both the primary drives go offline then at least I have all my data backed up and still available. Regards, Kaya On Sat, May 15, 2010 at 07:51:17PM -0500, Bob Friesenhahn wrote: > > On Sat, 15 May 2010, Jeremy Chadwick wrote: > >> > >What you have here is the equivalent of RAID-10. It might be more >> > >helpful to look at the above as a "stripe of mirrors". >> > > >> > >In this situation, you might be better off with raidz1 (RAID-5 in >> > >concept). You should get better actual I/O performance due to ZFS >> > >distributing the I/O workload across 4 disks rather than 2. At least >> > >that's how I understand it. >> > > > > That would be a reasonable assumption but actual evidence suggests > > otherwise. For sequential I/O, mirrors and raidz1 seem to offer > > roughly similar performance, except that mirrors win for reads and > > raidz1 often win for writes. The mirror configuration definitely > > wins as soon as there are many seeks or multi-user activity. > > > > The reason why mirrors still do well for sequential I/O is that > > there is still load-sharing across the vdevs (smart "striping") but > > in full 128K blocks whereas the raidz1 config needs to break the > > 128K blocks into smaller blocks which are striped across the disks > > in the vdev. Breaking the data into smaller chunks for raidz > > multiplies the disk IOPS required. Disk seeks are slow. > > > > The main reason to choose raidz1 is for better space efficiency but > > mirrors offer more performance. > > > > For an interesting set of results, see the results summary of "Bob's > > method" at"http://www.nedharvey.com/". > > > > The only way to be sure for your own system is to create various > > pool configurations and test with something which represents your > > expected work load. As long as the pool is not the boot pool, zfs > > makes such testing quite easy. > Thanks Bob. You're absolutely right. I'd never seen/read said data results before, nor had I read the below material until now; quite interesting and educational. http://blogs.sun.com/roch/entry/when_to_and_not_to -- | Jeremy Chadwick jdc@parodius.com | | Parodius Networking http://www.parodius.com/ | | UNIX Systems Administrator Mountain View, CA, USA | | Making life hard for others since 1977. PGP: 4BD6C0CB |
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4BEF4A73.8060905>