Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Posting-Version: version B 2.10.2 9/18/84; site brl-tgr.ARPA
Path: utzoo!linus!philabs!cmcl2!seismo!brl-tgr!gwyn
From: gwyn@brl-tgr.ARPA (Doug Gwyn <gwyn>)
Newsgroups: net.unix-wizards
Subject: Re: question about unix & real time
Message-ID: <5826@brl-tgr.ARPA>
Date: Fri, 16-Nov-84 09:41:00 EST
Article-I.D.: brl-tgr.5826
Posted: Fri Nov 16 09:41:00 1984
Date-Received: Sat, 17-Nov-84 20:03:21 EST
References: <39@uwvax.UUCP> <5633@brl-tgr.ARPA> <211@desint.UUCP>
Organization: Ballistic Research Lab
Lines: 19

>     A real-time system is one in which, if some a certain time constraint
>     is not met by the software, catastrophic failure of the system will
>     result.

Geoff made some good points about using UNIX for real-time applications.
My definition of "real-time" would be similar to his, and my claim is
that UNIX can be adapted to real-time use in this sense with a modest
amount of work; indeed, as I pointed out, we did so.  However, such an
application requires careful consideration and design, and control over
the suite of processes that may be running (e.g., "sync" is outlawed).
I would agree that UNIX in its present form does not support a wide
range of different real-time applications, nor would a simple small set
of changes support such a range.

Interrupt latency can be improved dramatically by putting UNIX's critical
regions under semaphore control rather than the simplistic interrupt
lock-out that is currently used.  This is not a small change but people
have done it for certain versions of UNIX.  I would like to see this in
the "standard" version of UNIX also.