Date: Sat, 14 May 2005 15:16:48 +0200 From: Pawel Jakub Dawidek <pjd@FreeBSD.org> To: vohand@gmail.com Cc: freebsd-stable@freebsd.org Subject: Re: gmirror Message-ID: <20050514131648.GB837@darkness.comp.waw.pl> In-Reply-To: <20050514093217.C6088E082A@oak.tantieme.ru> References: <20050514093217.C6088E082A@oak.tantieme.ru>
next in thread | previous in thread | raw e-mail | index | archive | help
[-- Attachment #1 --] On Sat, May 14, 2005 at 01:22:05PM +0400, vohand@gmail.com wrote: +> +> Hardware: SATA RAID adapter with SiliconImage 3114 chip. 2 SATA HDD. +> I did gmirror. +> +> Run test: +> 3 parallel tasks "dd if=/dev/mirror/gm0 of=/dev/null bs=1m count=5000" +> +> gstat shows summary read speed from mirror about 30-40 mbyte/sec. +> It is for all balance algorithms: load, round-robin, split +> +> While, one "dd if=/dev/ad4 of=/dev/null bs=1m count=5000" shows 50 mbyte/sec +> +> 1. Why it occurs and how fix it ? +> +> 2. If in the test instead of three instancies of "dd if=/dev/mirror/gm0 +> of=/dev/null bs=1m count=5000" run only one, +> then read speed don`t exceeds read speed from one disk (dd if=/dev/ad4 +> of=/dev/null bs=1m count=5000) +> a) This is gmirror feature ? +> b) This is hardware feature (SiliconImage 3114 chip) ? This is the way RAID1 works. Try to imagine how disk's heads are moving - there will be no speed-up in sequential reads, this is not RAID0. Mirror characteristics are: - the same speed for sequential reads as for one disk; - the same speed for sequential/random write as for one disk; - double speed of one disk for random reads; -- Pawel Jakub Dawidek http://www.wheel.pl pjd@FreeBSD.org http://www.FreeBSD.org FreeBSD committer Am I Evil? Yes, I Am! [-- Attachment #2 --] -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.4 (FreeBSD) iD8DBQFChfpAForvXbEpPzQRAhU+AJ0R4NZg/yi42IEoUg7+v6oW+z4bmACgm55s D6+UCfvI6Y/wbyShpB+GX5Y= =MGqj -----END PGP SIGNATURE-----
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20050514131648.GB837>