UNIX and real-time

[Al Nugent]

> 
> I concur. I built a real-time portable pulmonary testing lab
> running on an LSI-11/2 off of only RX02s (with swapping etc).
> One person would be filling in questionairres while another
> would be getting a lung test (A/D, ~20KHZ, 14bit.) It worked
> fine, an occasional hesitation for a few seconds (but with an
> RX02 as a swap device whoddyaexpect?
> It was MINI-UNIX/V6. Just requires a smart driver, not terribly
> unlike one of the psuedo-dma pollers for a DZ11.
> UNIX being 'bad for real time' is a myth perpetrated by vendors
> who sell O/S's that are bad for anything else.
> 
> An even better idea is to go get a rusty old apple or some such,
> add an A/D board, floppy and parallel board to hook it up to
> the unix system and use it as an intelligent, programmable
> A/D device with a 64KB buffer.
> 
> 		-Barry Shein
> 		Boston University

A rusty old apple might do the job but there are quite a number of people 
who need real-time performance in a UN*X environment. As for when is Unix 
no longer Unix I cannot say. The Masscomp implementation is true Unix 
(System V.2 and BSD4.2 plus Real-Time enhancements) and with our Data-
Acquisition and Control Processor you can gather data at 1 million 12-bit
samples per second. Even our multi-CPU kernel is still "real" C/Unix;
(i.e. more than one CPU pathing one copy of the kernel independantly).
If an apple will do the job, fine, but when you need REAL unix doing 
some real-time (or non real-time) work we have the answer.


	Alan Nugent,  Massachusetts Computer Corporation.  Westford MA
	...!{ihnp4,harpo,decvax}!masscomp!afn   (617) 692-6200 x224