Date: Wed, 18 Sep 1996 21:48:59 -0500 (EST) From: "John S. Dyson" <toor@dyson.iquest.net> To: taob@io.org (Brian Tao) Cc: dyson@freebsd.org, freebsd-scsi@freebsd.org Subject: Re: Streamlogic RAID array benchmarks Message-ID: <199609190248.VAA01096@dyson.iquest.net> In-Reply-To: <Pine.NEB.3.92.960918222441.27050m-100000@zap.io.org> from "Brian Tao" at Sep 18, 96 10:28:45 pm
next in thread | previous in thread | raw e-mail | index | archive | help
> On Wed, 18 Sep 1996, John S. Dyson wrote: > > > > If you are running -current (I forgot to check), and since you have > > 64MBytes, the buffer cache will help even though it is overrun. The > > buffer cache policy is NOT pure LRU, and you will see the effects of > > it on a 64MByte system even for a 100MByte benchmark. > > The tests were done on a 2.2-960801-SNAP system. Regardless, it > doesn't hide the fact that the RAID had much lower throughput than the > single drive. I going to try reformatting the RAID to level 0 and > seeing if not having parity makes a difference (although I might as > well save a few thousand dollars and just use ccd at that point). > I agree, and understand your point. Also, ccd as of today (and vn) are kind-of broken. Appear to work, but are okay until you need them (This is meant almost with humor -- but it isn't funny to some people :-()... John
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199609190248.VAA01096>