Re: RAID 5 performance

From: Glenn Brackenridge <glenn_at_gbrack.demon.co.uk>
Date: 1995/10/23
Message-ID: <glenn-2310951144040001_at_gbrack.demon.co.uk>#1/1


In article <465kas$f0u_at_dub-news-svc-6.compuserve.com>, 100440.1227_at_compuserve.com (Ashley) wrote:

>
> Anyway, S/W based
> RAID 5 murders any machine. The way to go is to use an external RAID
> array, when I worked for a large UK corporate we used RAID arrays from
> a company called Baydel, in fact we were the world's first purchasers
> of these devices. They are RAID 3 but cached (Read and Write if
> required) and go like mad. We were achieving a sustained rate of 700
> I/O's per second using totally random seeks (thereby removing as much
> chance as possible that the data we wanted was in the cache) off a
> 10Gb drive. This was with Oracle databases.
>
> Ashley
> 100440.1227_at_compuserve.com

Thanks for the plug, Ashley,

for info, these Baydel RAID systems were the original 5 MB/s devices and were installed in December 1991. They are *still* outperforming the storage systems on that company's other VAXcluster. At the time we reckoned it was one of the worlds most powerful I/O VAX configs.

We now have 20 MB/s models and these can sustain 4100+ I/O's per controller, with dual controller configs possible, and close to 20 MB/s *real* throughput.

Glenn [glenn_at_baydel.com] Received on Mon Oct 23 1995 - 00:00:00 CET

Original text of this message