Date: Wed, 30 May 2001 00:50:03 -0700 (PDT) From: Gordon Tetlow <gordont@bluemtn.net> To: Wilko Bulte <wkb@freebie.demon.nl> Cc: "E.B. Dreger" <eddy+public+spam@noc.everquick.net>, <hackers@FreeBSD.ORG> Subject: Re: brainstorm: "intermediate" disk caching Message-ID: <Pine.BSF.4.33.0105300048170.229-100000@sdmail0.sd.bmarts.com> In-Reply-To: <20010528203435.F619@freebie.demon.nl>
next in thread | previous in thread | raw e-mail | index | archive | help
I'm struck by the old axiom: You can have it fast. You can have it reliable. You can have it cheap. But you can only have 2 of the 3. If you figure out how to get all 3. Call me. -gordon On Mon, 28 May 2001, Wilko Bulte wrote: > On Mon, May 28, 2001 at 04:31:17PM +0000, E.B. Dreger wrote: > > Greetings all, > > > > I just had a brainstorm... > > > > I was thinking about database servers with several spindles in a RAID 5 > > array. Write performance is inherently disappointing -- which may or may > > not be an issue. > > > > Would it be worth the trouble to design an "intermediate" cache, whereby > > data are quickly written to a spool disk, then to the final destination? > > Most hardware RAID boxes do exactly that ;) For anything serious only > consider battery-backed up writeback cache, with mirrored caches, and > redundant RAID array controllers. > > Start saving your $$ now ;) To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.BSF.4.33.0105300048170.229-100000>