Path: utzoo!utgpu!jarvis.csri.toronto.edu!rutgers!apple!usc!cs.utexas.edu!uunet!lll-winken!vette!brooks
From: brooks@vette.llnl.gov (Eugene Brooks)
Newsgroups: comp.arch
Subject: Re: What is a Mainframe?
Message-ID: <27814@lll-winken.LLNL.GOV>
Date: 1 Jul 89 00:37:04 GMT
References: <125@ssp1.idca.tds.philips.nl> <20752@winchester.mips.COM> <27637@lll-winken.LLNL.GOV> <164@bms-at.UUCP>
Sender: usenet@lll-winken.LLNL.GOV
Reply-To: brooks@maddog.llnl.gov (Eugene Brooks)
Distribution: comp.arch
Organization: Lawrence Livermore National Laboratory
Lines: 15

In article <164@bms-at.UUCP> stuart@bms-at.UUCP (Stuart Gathman) writes:
>The micro solution to high throughput  disks  is  not  fast  (and
>expensive)  disks,  but  disk  arrays.   By running lots of cheap
>disks in parallel you get the throughput of the big jobbers at  a
>fraction of the cost.
An impressive example of this is the self healing disk system for the
Connection Machine.  Its throughput is 32 megabytes per second, and
it is composed of an array of disk drives such that each drive handles
one bit of a 64 bit word.  72 drives are used in a standard error correcting
scheme and if one disk fails completely the think stays up.  You replace
the disk and its data gets reconstructed from the error correction code.
Now all we need it a "real mainframe" for it to keep fed, which of course
should be an array of microprocessors...

brooks@maddog.llnl.gov, brooks@maddog.uucp