levin@bbn.com (Joel B Levin) (04/06/88)
I just got a Jasmine Direct Drive 50 for the office Plus, and I wanted
to pass along a small gotcha that you might keep in mind if you are
looking at hard disks.
One of the reasons I chose this particular drive, besides the Jasmine
reputation for quality of product, support, and reliability, was the
reported performance mentioned here in this forum and by a colleague
who got the same drive. After I got it hooked up and started
exploring the shareware/freeware folders, I found disktimer II and ran
it. I was surprised to find the performance numbers substantially
lower than I had been led to believe they would be:
Read 117
Write 126
Seek 0 (no seeking due to the large number of sectors per
cylinder, I believe).
I called Jasmine Tech Support and discovered that the drive is
formated with 1:1 interleave; that it comes from the factory that way;
and that the interleave cannot be changed by software, according to
the person who answered my call (and consulted with someone while I
was on the phone to verify that this was normal performance).
On a more positive note, I took the drive home and tried it on an SE.
The numbers were 34, 51, and 0 -- much more like what I had expected
(the SE internal HD20 was 76, 76, and something). So my drive is in
fact functioning properly, it seems.
On a further positive note, it is still a great improvement over the
floppy port Apple HD20 I had been using (a factor of >3 over the
disktimer times, and a factor of 1.8 - 2.0 for things like launching
large programs). And the drive is quiet and seems reliable and in all
other respects meets my expectations.
Bottom line: the DD50 appears to be everything they say it is, though
if you are looking for a drive to attach to a Plus you should consider
whether it is capable of being tuned to run at its optimum speed.
/JBL
UUCP: {backbone}!bbn!levin USPS: BBN Communications Corporation
ARPA: levin@bbn.com 50 Moulton Street
POTS: (617) 873-3463 Cambridge, MA 02238ephraim@think.COM (ephraim vishniac) (04/06/88)
In article <23013@bbn.COM> levin@BBN.COM (Joel B Levin) writes: >I just got a Jasmine Direct Drive 50 for the office Plus, and I wanted >to pass along a small gotcha that you might keep in mind if you are >looking at hard disks. ... >I was surprised to find the performance numbers substantially >lower than I had been led to believe they would be: > Read 117 > Write 126 > Seek 0 (no seeking due to the large number of sectors per > cylinder, I believe). >I called Jasmine Tech Support and discovered that the drive is >formated with 1:1 interleave; that it comes from the factory that way; >and that the interleave cannot be changed by software, according to >the person who answered my call (and consulted with someone while I >was on the phone to verify that this was normal performance). This report is rather misleading. There is a good reason that the drive's interleaving is fixed at 1:1, and it's unrelated to the drive's performance on a Plus. First, the interleaving: The Quantum drives have a large internal buffer/cache which allows them to cache a track in one pass. So, 1:1 is the best interleaving for the drive without regard to the host's transfer rate. Second, the performance: The Quantum drives have rather complicated controller software, partially due to their caching scheme. So, the externally visible timing of the controller is more variable than some. This causes it to trip over various bugs in the SCSI manager in the Mac Plus, and also makes blind transfers impossible on the Plus' very limited SCSI hardware. (The SE and II have slightly better hardware.) Consequently, the Quantum drives must use fully synchronized transfers at a cost of about three instructions per byte instead of one instruction per byte for blind transfers. How do I know this stuff? I wrote Jasmine's SCSI driver. Disclaimer: I once had a business relationship with Jasmine (obviously), but now they own the software outright and it's their problem. Ephraim Vishniac ephraim@think.com Thinking Machines Corporation / 245 First Street / Cambridge, MA 02142-1214 On two occasions I have been asked, "Pray, Mr. Babbage, if you put into the machine wrong figures, will the right answers come out?"
ephraim@think.COM (ephraim vishniac) (04/06/88)
In article <23013@bbn.COM> levin@BBN.COM (Joel B Levin) writes: >I just got a Jasmine Direct Drive 50 for the office Plus... >I found disktimer II and ran it. > Read 117 > Write 126 > Seek 0 (no seeking due to the large number of sectors per > cylinder, I believe). I should have mentioned in my previous followup that this is not the right explanation for the seek time. It's true that disks with large numbers of platters, hence many sectors per cylinder, give small numbers for "seek" in DiskTimer II. The numbers aren't that small, however. As I mentioned before, the Quantum drives have a large internal cache. DiskTimer II *attempts* to measure seek time by repeatedly reading two sectors a megabyte apart on the drive. With a cache, the seek occurs only once and then the sectors are repeatedly read from the cache. In order to avoid this effect, DiskTimer II would have to make large reads between tests to flush the cache. Beware of nonsensical test results! Ephraim Vishniac ephraim@think.com Thinking Machines Corporation / 245 First Street / Cambridge, MA 02142-1214 On two occasions I have been asked, "Pray, Mr. Babbage, if you put into the machine wrong figures, will the right answers come out?"
levin@bbn.com (Joel B Levin) (04/08/88)
In article <18879@think.UUCP> ephraim@vidar.think.com.UUCP (ephraim vishniac) writes:
:In article <23013@bbn.COM> I wrote:
:>I just got a Jasmine Direct Drive 50 for the office Plus, and I wanted
:>to pass along a small gotcha that you might keep in mind if you are
:>looking at hard disks.
:...
:>I was surprised to find the performance numbers substantially
:>lower than I had been led to believe they would be:
I would like to thank ephraim for explaining clearly and concisely why
the drive is behaving as it is. I want to state again that I have no
complaint with the DD50. It is miles above what I had been using (and
would be somewhat faster if I could swap my Plus for an SE).
The bottom line: due to less than perfect hardware in the Plus and
bugs in its SCSI manager, the Plus is unable to take advantage of the
drive and its cache; and also because of its cache the Disktimer II
seek test results are meaningless.
...
:How do I know this stuff? I wrote Jasmine's SCSI driver.
...
:Ephraim Vishniac ephraim@think.com
:Thinking Machines Corporation / 245 First Street / Cambridge, MA 02142-1214
/JBL
UUCP: {backbone}!bbn!levin USPS: BBN Communications Corporation
ARPA: levin@bbn.com 50 Moulton Street
POTS: (617) 873-3463 Cambridge, MA 02238