Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 13 Feb 2002 20:57:55 -0800
From:      Terry Lambert <tlambert2@mindspring.com>
To:        j mckitrick <jcm@FreeBSD-uk.eu.org>
Cc:        freebsd-chat@freebsd.org
Subject:   Re: How do basic OS principles continue to improve?
Message-ID:  <3C6B43D3.39B7011F@mindspring.com>
References:  <20020213192510.A46224@dogma.freebsd-uk.eu.org>

next in thread | previous in thread | raw e-mail | index | archive | help
j mckitrick wrote:
> Since VM has been around for quite a while, and since the basic
> algorithms for task scheduling, page swapping, critical sections and so
> on have been around for a while as well as basic computer sci theory,
> what leads to the breakthrough new designs we see in BSD?  Other than
> SMP?

Most of the "breakthrough" designs we see happening in
BSD today have been discussed in CS literature in the
academic world at least 10-12 years ago.

Some of the "breakthroughs" are "only" 5 or 6 years old.

The polling code Luigi did, for example, was beased on a
Jaff Mogul paper from 1991.  My own code for LRP was
based on a paper from Rice University by Mohit Aron's
group, and is 6 years old.

It took since FreeBSD 2.2 to integrate an implementation
of FACK/SACK into FreeBSD; that's 8 years.

Most cutting edge CS work occurs in academia, in very
small groups, with no more than 4 people participating,
and usually, a single idealist leading the group.

Other things which appear to be "breakthroughs" are just
concessions to hardware tradeoffs that are true today
that weren't true when the original implementations were
first deployed (e.g. relative cost of disk seeks vs.
speed on tracks, relative costs of main memory access vs.
cache access, etc.).  Revisiting these tradeoffs is normal
and doesn't really count as "breakthrough" in my book.

-- Terry

To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-chat" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?3C6B43D3.39B7011F>