Path: utzoo!attcan!uunet!lll-winken!ames!ncar!ico!rcd
From: rcd@ico.ISC.COM (Dick Dunn)
Newsgroups: comp.arch
Subject: Re: RAM Disks are obsolete
Summary: no, but they SHOULD be!
Message-ID: <13678@ico.ISC.COM>
Date: 17 Jan 89 00:57:31 GMT
References: <334@belltec.UUCP>
Organization: Interactive Systems Corp, Boulder, CO
Lines: 24

In article <334@belltec.UUCP>, jom@belltec.UUCP (Jerry Merlaine) writes:
. . .
> Building a special-purpose RAM disk with a disk controller interface
> is a classic case of hardware people not talking to software people 
> but instead going off and building something cute but useless.

Not at all true, especially in the case of the SSD for large IBM mainframes
(an example that I gave).  In that case, using a disk interface means that
you can use the software as it stands, which makes it a useful product.  In
that world, you can't just invent another layer in the storage hierarchy...
and unless you want to get very deeply into the software business, you
don't go mucking about with VM and/or MVS.

This is not to say that the software SHOULD BE harder to change than the
hardware, but only that it IS for some classes of machine.

There's also a consideration that when you're building huge bulk RAM
devices, you may not want to make it behave completely like RAM.  It may
take more logic and more high-bandwidth stuff than to make it act as some
sort of block-serial device.  Remember, you're already talking about
treating it as a second level of storage.
-- 
Dick Dunn      UUCP: {ncar,nbires}!ico!rcd           (303)449-2870
   ...A friend of the devil is a friend of mine.