18 May
2005
18 May
'05
12:19 p.m.
>>>> "Ethan" == Ethan Dicks
<ethan.dicks at gmail.com> writes:
Ethan> On 5/18/05, Rob O'Donnell
Ethan> <classiccmp.org at irrelevant.fsnet.co.uk> wrote:
> The worst processor/user ratio I think I
encountered was about 50
> users sharing a 486dx50.. It was in a rack case, in the top 6" of
> a 4' rack, the rest being blocked in empty space except for a UPS
> sat in the bottom. The users most definitely called it "the
> mainframe" !
Ethan> Worst processor/user ratio for PeeCee-class equipment, or on a
Ethan> per-cycle basis? We used to routinely put 40-60 users on our
Ethan> VAX-11/750 (0.6 VUPs, 8MB of RAM, *roughly* the same CPU
Ethan> horsepower as an 8MHz 68000, but with broad I/O channels).
How about an 11/20 RSTS V4A timesharing system (maybe 0.1 MIPS with a
tailwind) running up to about 12 users -- several of whom would be
doing statistical analysis runs? (And to make matters worse,
typically those were clueless timesink runs like "crosstabulate all by
all" on a survey database with maybe 40-50 questions in it, mostly
unrelated...) RK05 system disk (at 11 microseconds per word transfer
rate) and RF11 swapping disk (15 microseconds per word -- but no
seeks). 28 kWords memory, of course.
Then again, that system had a mean time between crashes of about a
day. It got better when we upgraded to an 11/45 running RSTS/E.
paul