Date: Fri, 09 Jun 2006 12:44:54 -0600 From: Scott Long <scottl@samsco.org> To: Mikhail Teterin <mi+mx@aldan.algebra.com> Cc: fs@freebsd.org Subject: Re: single disk vs. RAID5 (amr) Message-ID: <4489C1A6.40605@samsco.org> In-Reply-To: <200606091328.52183.mi%2Bmx@aldan.algebra.com> References: <20060609065656.31225.qmail@web30313.mail.mud.yahoo.com> <200606091313.04913.mi%2Bmx@aldan.algebra.com> <4489ADC9.3090809@samsco.org> <200606091328.52183.mi%2Bmx@aldan.algebra.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Mikhail Teterin wrote: > [Subject changed] > > п'ятниця 09 червень 2006 13:20, Scott Long написав: > >>>I never benchmarked the speed on the single drives, other than to compare >>>with my RAID5 array (which puzzlingly always loses to a single drive, but >>>that's a different story). >> >>All depends on access alignment and cache behaviour. > > > Well, this does not tell me much :-( I compare a single disk vs. a RAID5 array > of 6 such disks joined using amr(4). I tried to figure out the best > FS-parameters for the RAID, but whatever I tried, it was always quite > inferior to the the single drive -- on both reading and writing. > > Perhaps, adding the battery-backup option to the RAID card would improve > things, but I expected it to be faster even without it. > > -mi THere are two things to consider. First is that FreeBSD mis-aligns the filesysytem blocks if you are using an fdisk/MBR header on the disk. This misalignment doesn't affect single disks, but it greatly affects RAID, and especially RAID-5. An easy way to check this is to compare the performance on an array that has just the filesystem on it and no MBR or disklabel information. The second is that the LSI controllers will turn the cache off if a battery is not present. This won't affect read speed much, but it will greatly affect write speed. Scott
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4489C1A6.40605>