From: dgy@rtd.com (Don Yuniskis)
Subject: Re: What's Real-Time? (was Re: Widespread C++ Competency Gap?)
Date: 31 Dec 1994 02:12:29 GMT
Date: 1994-12-31T02:12:29+00:00 [thread overview]
Message-ID: <3e2emd$6fd@baygull.rtd.com> (raw)
In-Reply-To: hbaker-3012941712040001@192.0.2.1
In article <hbaker-3012941712040001@192.0.2.1>,
Henry Baker <hbaker@netcom.com> wrote:
>In the RT community there are the terms '_hard_ real-time' and
>'_soft_ real-time'. 'Hard' RT means that the consequences of missing
>a deadline are catastrophic, while 'soft' RT means that the consequences
>are expensive, but not catastrophic.
Yes, as I indicated in my reference to the value function associated
with the missed deadline (for t>deadline, value <= 0 for HRT; value > 0
for SRT).
>Designing for a 'hard' RT system is different from designing for a
>'soft' RT system because you have to find the latencies of _every_
>operation, no matter how rare -- e.g., you have to worry about the
>latencies of rare combinations of rare events -- e.g., multiple page
>faults from a single instruction, cache faults for every memory reference
>of a 1000-instruction sequence, etc.
Exactly! A fact that most designers neglect either from ignorance or
by choice (it's orders of magnitude harder to design for the worst-case
whether you're designing hardware OR software -- tho', admittedly, a
worst-case hardware design is orders of magnitude EASIER than a
worst-case software design ;-) :-(
>This means that nearly everyone is looking for ways to convert 'hard'
>RT systems into 'soft' RT systems so that they can take advantage of
>the increased average speeds.
>
>So if you're still doin' 'hard time', wise up! :-) :-)
Right. However, certain parts of evry application "must" be HRT.
The trick is to move as much of the application into the domain of
SRT -- "Gee, it would be real nice if this got done on time... but
it's more important that I know how to deal with the consequences
of when it DOESN'T get done on time!"
next prev parent reply other threads:[~1994-12-31 2:12 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <787227087snz@wslint.demon.co.uk>
[not found] ` <3da1nd$fss@gateway.wiltel.com>
[not found] ` <3e1rqn$ouh@news.parc.xerox.com>
[not found] ` <3e22hi$pqf@baygull.rtd.com>
[not found] ` <3e26mc$n9u@Starbase.NeoSoft.COM>
1994-12-31 1:09 ` What's Real-Time? (was Re: Widespread C++ Competency Gap?) Henry Baker
1994-12-31 2:12 ` Don Yuniskis [this message]
1994-12-31 17:08 ` Przemek Klosowski
1995-01-01 9:35 ` Robert J Carter
1995-01-02 17:10 ` Przemek Klosowski
1995-01-03 23:20 ` Robert I. Eachus
1995-01-04 22:05 ` Fred McCall
[not found] ` <3ckb8g$841@gateway.wiltel.com>
[not found] ` <1994Dec21.151952.8902@merlin.h>
[not found] ` <1994Dec21.151952.8902@merlin.h <19941230.201628.350635.NETNEWS@UICVM.UIC.EDU>
[not found] ` <3e9f60$8du@jive.cs.utexas.edu>
[not found] ` <3epfsi$64d@gamma.ois.com>
[not found] ` <3eua1r$4ea@gnat.cs.nyu.edu>
1995-01-11 1:44 ` Parallel & RT GC (was Re: Real-Time GC (was Re: Widespread C++...?) Henry Baker
1995-01-13 13:30 ` R. William Beckwith
1995-01-13 14:59 ` Kelvin Nilsen
1995-01-17 2:45 ` R. William Beckwith
1995-01-19 15:57 ` Kurt Bischoff
1995-01-17 16:29 ` Robert I. Eachus
1995-01-18 15:27 ` Henry Baker
1995-01-19 19:59 ` Norman H. Cohen
1995-01-20 2:20 ` Henry Baker
1995-01-20 14:49 ` Robert I. Eachus
1995-01-22 2:56 ` David Hanley
1995-01-23 17:06 ` Robert I. Eachus
1995-01-13 21:04 ` Henry Baker
1995-01-17 10:37 ` Mark Reinhold
replies disabled
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox