[Simh] EXT :Re: PDP-10 simulation: DEUNA support help needed

[Timothe Litt]

On 30-Apr-15 18:21, Mark Pizzolato - Info Comm wrote:
>
>
> On Apr 30, 2015 1:46 PM, Clem Cole <clemc at ccc.com> wrote:
> >
> >
> > On Thu, Apr 30, 2015 at 4:20 PM, Rich Alderson
> <simh at alderson.users.panix.com> wrote:
> >>
> >> Striping came along with redundant arrays of
> >> inexpensive disks.  At $50,000 a drive, RP07s were not candidates. ;-)
> >
> >
> > ​Rich,
> >
> > Be careful here with that sort of statement.   Striping as a
> technology predates RAID and certainly could have been used by large
> commercial systems if people had wanted too.   Supercomputers like
> Crays and CDC, as well as the "mini-crays" like Convex and even the
> "Crayolla" (Stellar) all striped with very expensive 19" technology in
> the late 1970s and 1980s.
> >
> > You are correct, that striping as a popular technique does not go
> mainstream until the 3.5" technology where the cost per byte got low
> enough that "anyone" could afford it - i.e. when the idea of RAID
> shows up.
>
> Actually, even before low cost 3.5" drives were available, RAID was an
> industry acronym, but in those days it came from Redundant Array of
> Independent Disks.
>
That was a paper c.a. 1987 by Patterson et. al.  which is generally
credited with the RAID name.  But the order of events depends on whose
history you read.

I remember discussions about JBOD arrays, and adding EDC to them at a
NETLUG (DECUS chapter for 10/20s) earlier than that.  It would have been
between 77 & 84... and would have been the 5MB winchester drives.  And
the RAID (inexpensive) acronym was used in the discussion.  This wasn't
a DEC presentation.  I may have a DECtape with the meeting minutes
somewhere in my collection...

> VMS Volume Shadowing and then the Stripe Driver implemented RAID 1 and
> RAID 0 respectively.
>
In DEC, volume shadowing was first built into the HSC50 (a CI-based
disk/tape controller), released in the early 80s.  Drives were the 14"
RA81 and follow-ons.  The early design work was in the late 70s.  The
TOPS20 announcement of the CI, CFS and clusters predated the VMS
announcement, to the great annoyance of the VMS crew, which had it
running internally but wasn't permitted to announce it.  TOPS20 didn't
support volume shadowing.  Neither did TOPS10, though it did support CI
disks and tapes (but not clusters) later.  The CI/MSCP protocol layers
used common code in both OSs, similar to what was done with DECnet. 
Host-based volume shadowing came considerably later.

I implemented V1 of the VAX Striping Driver, c.a. 1988, as a midnight
engineering project.  It was originally proposed by the LCG I/O group as
part of the VAX9000 development to address high-bandwidth I/O
requirements of the HPTC market.  It turned out to be extremely popular
for general timesharing, as it increased the sustainable request rate -
much of a timesharing workload consists of small I/Os - to mail files,
editor journals, and the like.  It was sold across the product line,
more for request rate than for bandwidth.

However, the Striping driver was perfectly happy to stripe any
underlying physical devices (though one wanted the sizes to be the
same.)  This means it wasn't limited to RAID 0.  People striped
shadowsets (host and controller-based),  which some call RAID 1+0. 
People also striped MSCP-served disks, whatever the underlying
technology.  And MSCP-served stripesets.  Some of these configurations
had, er, interesting performance characteristics.  But the Striping
driver was inexpensive, and the placebo effect overcame engineering reality.

When it became evident that Striping was a popular product, there was a
proposal for host-based RAID.  I had nothing to do with that, having
turned the Striping driver over to the Storage group by then...


> - Mark
>
>


-------------- next part --------------
A non-text attachment was scrubbed...
Name: smime.p7s
Type: application/pkcs7-signature
Size: 4942 bytes
Desc: S/MIME Cryptographic Signature
URL: <http://mailman.trailing-edge.com/pipermail/simh/attachments/20150430/42eb581a/attachment.bin>