Date: Fri, 29 Dec 2006 06:30:14 -0800 (PST) From: "R. B. Riddick" <arne_woerner@yahoo.com> To: vd@FreeBSD.org Cc: freebsd-geom@freebsd.org Subject: Re: gstripe performance scaling with many disks Message-ID: <20061229143014.94559.qmail@web30306.mail.mud.yahoo.com> In-Reply-To: <20061229142400.GA17217@qlovarnika.bg.datamax>
next in thread | previous in thread | raw e-mail | index | archive | help
--- Vasil Dimov <vd@FreeBSD.org> wrote: > On Fri, Dec 29, 2006 at 04:55:44AM -0800, R. B. Riddick wrote: > In summary increasing the stripe size results in performance drop while > increasing the number of read processes results in performance raise. > (I also tested with stripe size 128*1024). My guess is that this is > because raidtest often generates read requests with size less than the > stripe size and then it reads from just one disk, or at most from > several ones. It rarely (never?) generates a request that has read size > 17*stripesize or greater so that all disks are used in parallel. > That is surprising for me... Small request size caused by raidtest shouldnt decrease the performance so much, because u used 20 concurrent processes... -Arne __________________________________________________ Do You Yahoo!? Tired of spam? Yahoo! Mail has the best spam protection around http://mail.yahoo.com
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20061229143014.94559.qmail>