Coyotos, EROS, and Hurd

[C Y]

Greetings all.  I have been lurking on the coyotos email list for a
while, and before that I was a lurker on the eros list.  All quiet -
and then I checked l4-hurd :-).

I have read some, but by no means all of the vast and fascinating
discussions of the last couple of months.  I just wanted to add two
remarks:

a)  I was and am tremendously excited by the prospect of a Hurd tuned
to work with/on Coyotos.  I have long been impressed by the new and yet
practical ideas in both projects, and would be very excited to see the
practical results of such a system.

b)  I was very much impressed by Dr. Shapiro's comment on the approach
being taken with Coyotos being a design first and then write approach,
and the contrast between that and normal open source development
methodology.  It caught my eye because I am involved, in a small way,
with the Axiom computer algebra system project.  That project is also
applying a different methodology that shifts the focus away from
immediate coding - literate programming.  In essense, the goal is to
write a document describing the idea, design considerations, and the
implementation, with the code then following naturally from the design.
 I doubt Coyotos will be a literate program in the Knuth sense, but I
am impressed by Dr. Shapiro's insight on the fundamental nature of
development methodologies and their potential consequences.

I guess, in a way, I would like to suggest the following:  Linux and
FreeBSD have come to dominate the open source OS scene.  Because of the
momentum behind these systems, the wide experience and massive testing
history behind the code, and the corporate inertia that has formed
behind them nothing short of a revolutionary product is going to unseat
them.  Not revolutionary merely in design, but in actual benefit
supplied to the users.  Anything less is going to be incorporated as an
incremental change to one of the current projects.

I think the only feature that could be put forth today that would be
truly revolutionary, and not just an incremental improvement, is a
system that supports security as close to the theoretical limit of
usability as can be achieved.  Formal methods in design and development
where potentially beneficial, with years of design and thought based on
hard core research.  Hurd is capable of many new things in user space,
but the truth is users are so accustomed to their current models of
operation that the cost of abandoning them for something different is
extremely high.  Anyone who has experience with corporate buying
decisions knows what this is like - unless there is an overwhelming
reason not to take the safer (or more often, most traveled) route they
will change nothing.

If Hurd wants to make a big dent in the OS market, I think it will have
to offer some immediate, utterly compelling feature that cannot be
duplicated in other systems and is needed badly enough to make people
consider a switch.  The only problem in today's computer world I am
aware of that might command such attention is security, and building
off of Coyotos would probably be one of the best possible decisions
from the standpoint of robust security, if I have understood their
approach correctly.

Anyway.  Merely the opinion of an interested observer, but I just
wanted to comment on how exciting the potential combination of the two
projects is.

Cheers,
CY


                
__________________________________ 
Start your day with Yahoo! - Make it your home page! 
http://www.yahoo.com/r/hs