25 Oct
1999
25 Oct
'99
1:32 a.m.
And almost all high-end Ethernet and SCSI cards have
functionality
equivalent to a channel.
Which is why my AMD 586x133 eats a lot of 100 Mhz Pentiums
for lunch. The Adaptec 2742 is quite a nice VLB controller.
The 486DX2/66 systems Mike C. was comparing to obviously didn't have the PCI
bus-mastering ATA disk interface. But for server applications those
systems were typically configured with an Adaptec 1542 SCSI controller, which
served as a very intelligent channel processor.
Yup... and the 1542 was pretty minimal compared with the CAM supporting
SCSI stuff out there now with tagged queueing.
No, there was no way that the system would have had adequate performance if
it had to support that many users doing serious software development.
But then, neither could the VAX. The 8650 which I used in the mid 80s would
serve 50 users easily as long as only a few people were doing memory and CPU
intensive things. But if more than three or four people tried to do a compile
at once, performance went to hell. Which would have been OK if only the
compute-bound jobs suffered. But the scheduler couldn't cope will enough, so
even the "light" jobs became unresponsive. This is because everything that
was learned in the 1960s and 1970s about building good timesharing systems was
subsequently forgotten in the early 1980s.
What OS? BSD? Ultrix? VAX/VMS?
Actually, the scheduler on VAX/VMS was pretty good if tuned well.
I've had 50 developers on an 8650 without problems. The trick was
putting the compiles in via batch at a priority behind the folks editing
code...
(Of course me running 50 copies of the CPU and floating point diags at
priority 10 on an 11/780 left the EDT users thinking the machine had gone south.
But it did pull the intermittant errors and help me fix one machine.)
Bill
---
bpechter@shell.monmouth.com|pechter@pechter.dyndns.org
Three things never anger: First, the one who runs your DEC,
The one who does Field Service and the one who signs your check.