CLAYTON@XRT.UPENN.EDU ("Clayton, Paul D.") (11/08/87)
Information From TSO Financial - The Saga Continues...
Chapter 32, Part 1 Of 2 - November 7, 1987
Apologies for the lengthy delay in getting this article out to the
network and others. I have sent it out three times and not had a copy
come back to me. For this reason, I am splitting it into two sections
and praying it will get through the pipe line. Apologies if you have
already received this. I hope you will find it worth the wait. :-)
This article is to inform interested parties about the
installation, use and problems that I have had with System Industries
(SI) SI83C and SI93C drives. These drives are currently being sold by
SI for connection to HSC/UDA disk controllers for use in VAXClusters.
This article is not commissioned by System Industries and all comments
here are my own. The SI93C disks I received were packaged with six (6)
drives per cabinet, while the SI83C drives are packed eight (8) per
cabinet. The original SI83C drives I received had 1,021,140 blocks of
formatted space that is available to VMS. These drives have since been
reformatted to allow more room for diagnostic work areas and the block
count now available is 1,016,199 and the drive type has also changed
from a RA81 to RA82. The SI83C drives are dual ported between 2 HSC
controllers, one HSC50 and one HSC70, and driven by a six node
VAXCluster of two 8700's, one 8530 and three 11/785's. The last two
drives are ported between a UDA50 inside a 8200 and the HSC70 listed
above. We are running VMS 4.5 and Volume Shadowing software, from time
to time. The SI93C drives are single ported to an HSC70 and driven by a
8350 VAXCluster cornerstone, running VMS 4.5 and Volume Shadowing all
the time. The pertinent comparison information is presented in Table A
showing various aspects of the different drive types. The SI93C disk
drives also display as a RA82 device to the HSC.
Drive Blocks Per # per 512 Blocks Cost per Cost per
Type Disk Cabinet per Cabinet Cabinet MB
RA81 891,072 4 3,564,288 65,000 35.62
RA82 1,214,843 4 4,859,372 76,440 30.72
SI83C 1,016,199 8 8,129,592 115,000 27.62
SI93C 1,644,300 6 9,865,800 130,000 25.74
Table A
Comparison Of Pertinent Information
The SI83C drives came on a wood pallet, since they were shipped
air freight, that had a unique feature. Instead of supplying ramps to
roll the cabinet down, like DEC does, one of the pallets side supports
unbolts from the pallet and the whole works then tilts forward. Neat
little trick, and it works just like having ramps. All the SDI cables
came in two boxes and was accompanied by documentation for bad blocks
and a 'Users Guide'. Three packages total. The SI93C drives were
delivered on their own wheels, since these were shipped over land by
truck, and were wrapped in bubble plastic and cardboard. It was a
simple case of rolling them into place and unwrapping them, no fuss.
After rolling the drives into place the first of several surprises
came to light. SI has wired the electric such that four (4) drives are
connected to a power supply that is located VERTICALLY on the left side
of the cabinet. The breaker switch is on the front of the power supply
and as such is recessed about 1.5 inches from the front of the door
jamb. I have told SI about the close proximity of the breaker switch to
the front edge and how easy it would be to ACCIDENTALLY knock the
switch and kill four drives in one shot. When the breaker is 'ON', it
is in the 'UP' position. SI has said that cover plates, or something
similar, will be provided on future releases and available for
installed customers if desired. The other note here is that there are
two power supplies and associated power plugs (L5-30R) that have to be
wired for. Do to having the power supplies on the side of the cabinet,
the overall size IS wider then a quad-pack of RA type drives by 9.5
inches, while the height is the same. This is subject to change as I
hear that the cabinet is being redesigned.
The next item to notice is the cabinet itself. It is a solid
looking box with fans under the top to aid the air flow. The front door
is a metal panel with air slots cut out for cooling. There is no way to
see the state of the controller switches and unit numbers without
OPENING the door. That is a pain to me, but then again I do not have to
get FCC approval for RFI containment. The door handle is something that
I have mentioned to SI cries for modification. An Allen wrench is
REQUIRED to open the door. To me, it looks lousy seeing a nice looking
cabinet marred by the CONSTANT presence of an Allen wrench. The back of
the cabinet is also opened by the Allen wrench.
I have always heard from my salesman that the SI83C drives are
targeted to be shipped with up to twelve (12) drives per cabinet. From
what I see in my cabinet, they would fit, vertically. I have to
question the ability of the cabinet to hold all the cables in the back
going from the SI controller to the SDI junction panels and the drives
to the SI controller. The weight and cooling of the cabinet appear to
also play a part in squeezing twelve in a cabinet.
The 83/93 drives themselves are mounted flat and are placed two
across the 19 inch rack space. A panel on the SI83C drives is in front
to dress them up a bit, but when you order eight in a cabinet, SI
spaces the eight drives and two controllers over the entire height of
the cabinet. The result is that you can see the FUJI drives and SI
controllers top and bottom, and a consistent 'dress' appearance is
lacking. Elimination of cooling problems has been suggested as the
reason for spreading them over the height of the cabinet. The problem
with this is that CAPACITY/FOOT PRINT is a major selling point for
these drives. At some future point I may want to put the last four 83C
drives in the cabinet I currently own. The ONLY way to do that is to
essentially remove ALL the drives from the cabinet and move them and
the cables up/down in the cabinet. This to me can be the cause of
problems to come, why mess with something that already works? The 93C
drives are shipped tightly packed with NO gaps between the disk drives
and the SI interfaces. I have to admit that seeing TWO 510MB FUJI, or
TWO 858MB NEC drives side by side in roughly the same space as ONE
420MB RA-81 disk usually gets a chuckle out of me on the bleakest of
days.
The SI controller that provides the DSA compatibility and allows
the FUJI's/NEC's to work on HSC and UDA type controllers is
approximately five (5) inches high and 19 inches wide. Each controller
provides the interface for up to four (4) drives. The model of the
controller that I received provided the next area for serious
conversations with SI. First, as far as I am concerned is that the
logical unit number that is 'keyed in' for each drive, such as 0 or 1,
had only two selection wheels and the number was based in HEX, not
DECIMAL. This runs counter to the rest of the world and I told SI that
was the dumbest mistake in designing the package. I shudder at thinking
about making sure my DECIMAL to HEX conversion is correct and the
consequence of doing it wrong. Hence my decision to number the SI
drives way out in left field so that conflicting numbers would not
occur, by accident. This HEX number problem has since been corrected
and I received a replacement set of panels which provide for the unit
number in DECIMAL, with a range of 0 to 999. The new panels also
provide a hardware write protect switch which was lacking in the
original design. There has always been a write protect switch on the
drives themselves, this other switch is in addition to the drive
switch. The remaining buttons on each panel are for enabling the 'A'
and 'B' ports to the outside world. The nice feature that I like here
is that if the port is enabled, and is currently selected, and in use
the LED remains in a constant 'ON' state. If the port is enabled but
NOT selected, the condition when HSC failover is being provided for,
the LED is in a 'BLINKING' state. This is very helpful in making sure
that both ports are enabled. On the RA drives, the only light lit is
the one currently selected. I am always going around and pushing the
other port button to determine what 'state' it is in. Some other
interesting items on this controller is that each interface adapter
between the FUJI/NEC drive and the HSC, called a 'C-Mod Card', is
approximately six to seven inches square and contains its own Motorola
68000 microprocessor chip and supporting circuitry. These are stacked
two high with metal standoffs between them. There is plenty of space
left inside the box, which leads one to wonder if SI has any thoughts
of additional options inside the box.
The next area of consequence during the installation process was
in connecting the SDI cables from the HSC to the cabinet. The cabinet I
have is designed such that there are two panels, each about 3 by 18
inches, held in place by 4 screws that are the used to connect the SDI
cables to. Each panel has provisions for connecting 8 cables to it.
These panels also provided material for further serious conversations
with SI. The problem here is that there is about 4 inches of space from
the bottom of the cabinet to the top of the computer floor. In order
for the installation of the cables to occur, the field service
representative removes the screws holding the panels in place so that a
screw driver can be used to lock the SDI cables to the panel. Within
that 4 inch space, up to sixteen (16) SDI cables, which are thick and
bulky, have to get at least one and maybe two 90 degree bends in them,
to feed down into a hole in the computer room floor. This is not an
easy task and is the reason for my NOT having a floor tile behind the
SI cabinet. I consider it very risky to subject those cables to that
kind of bending. I have received the new version of the SDI connection
panel on the SI93C drives and it now provides for VERY easy cabling and
plenty of space to position the cables for getting through the computer
floor. The question of retro fitting to the existing user base has not
been answered yet to my knowledge. Having a floor tile missing is a
hazard and unsightly. In talking with my local field service office, it
also came to light that a somewhat questionable batch of SDI cables had
been received by SI when the 83C drives were first shipping. The result
of this is excessive errors being reported by the HSC's. There is a
test that the field service representative can perform to verify the
integrity of the cables should they get by an internal check before
shipping.
End Of Part 1, please continue with Part 2.
NOTE***
All comments, statements and facts here are my own, and not that
of my employers, National Teachers Life Insurance, Teachers Service
Organization (TSO) or any of their subsidiaries. All rights to this article
are reserved. This article is not meant to be a 'Sales' pitch of the
product. I have no connections with SI, short of HEAVILY using their
equipment. Any electronic reprint of this article MUST completely contain
this NOTE. NO PERMISSION IS GIVEN TO REPRINTING THIS ARTICLE OR ANY
PARTS OF IT ON PAPER, OR SIMILAR SUBSTANCES.
Paul D. Clayton
Manager Of Systems
TSO Financial Corp.
Horsham, Pa. USA 19044
Address - CLAYTON%XRT@CIS.UPENN.EDU