29 Apr
2005
29 Apr
'05
6:31 a.m.
>>>> "Jerome" == Jerome H Fine
<jhfinexgs2 at compsys.to> writes:
> Paul Koning wrote:
Jerome> Has anyone
any explicit knowledge and / or experience of a
Jerome> TK70 tape drive on a PDP-11?
> I don't know if it was ever sold, but
there's code in RSTS V10.1
> to recognize a TKQ70. That makes sense; the OS doesn't much care
> so long as the controller speaks (T)MSCP and isn't too fast to
> overrun the bus.
>
>
Jerome> Jerome Fine replies:
Jerome> I wonder if that was done to help avoid the problems with the
Jerome> TK50 drive? At one point, I heard that the TQK70 was
Jerome> developed to be used with the TK50 in order to correct some
Jerome> of the problems that the TK50 drive exhibits with the TQK50
Jerome> controller. During my use of the TK70 drive, I sometimes
Jerome> placed the TK50 on the TQK70 controller and noticed a bit of
Jerome> an improvement with the TK50 drive. I never investigated all
Jerome> of the possible modes of operation, so I can't suggest any
Jerome> specific improvements.
I hadn't heard anything like that, but I'm pretty sure the TK70
arrived after I left the RSTS group, so it's entirely possible that
the story you heard is correct and I missed it.
Certainly it wouldn't be the first time that a second generation
controller did a better job than the first, enough so to be used with
the earlier devices too.
Jerome> As for being faster, the TQK70 / TK70 almost certainly has
Jerome> the ability to buffer records internally and do a read of the
Jerome> next record. ...
That would make sense. I think a (T)MSCP controller is likely to be
buffered anyway. My comment on speed and bus bandwidth relates to
continuous running speed -- if a tape when in full speed streaming
mode produces more data than the bus can handle, you'll overrun
whatever buffers the controller may have (sooner or later) and
streaming will stop. So tapes like the TK series require a bus that's
comfortably faster than the drive, or their performance will be
atrocious. (Your TK50 verify experience is an example -- which shows
that performance also critically depends on correctly designed
software. It's a bit of a surprise that RT11 would get this wrong,
since getting it right is very easy in RT11.)
A somewhat different example (not streaming tape, but same sort of
issue): the TU78 was never supported on PDP11s because about the only
PDP11 with a fast enough I/O bus was the 11/70 massbus. (Then again,
that didn't stop the RM03 -- also an 11/70 only device for the same
reason.)
paul