Skip site navigation (1)Skip section navigation (2)
Date:      Sun, 2 Jun 1996 10:46:41 -0700 (MST)
From:      Terry Lambert <terry@lambert.org>
To:        hdalog@zipnet.net
Cc:        terry@lambert.org, chat@freebsd.org
Subject:   Re: Breaking ffs - speed enhancement?
Message-ID:  <199606021746.KAA23531@phaeton.artisoft.com>
In-Reply-To: <199606021415.KAA11494@hda> from "Peter Dufault" at Jun 2, 96 10:15:46 am

next in thread | previous in thread | raw e-mail | index | archive | help
> > Please quit addressing this as if it were anything other than a
> > kernel space issue.
> 
> Should I follow up with commentary on indentation styles and big
> company lack of risk taking instead?  What can be done portably
> in the kernel (and if it can be done portably) is governed by the
> user space issues.

It's *possible* to implement a POSIX system completely in user space
on any Von Neumann machine.

Yes, there are *some* semantics that specify "must be committed to
stable storage", but these semantics are irrelevant to a discussion
of why FreeBSD does so many writes on metadata and Linux doesn't,
for the same metadata.


					Terry Lambert
					terry@lambert.org
---
Any opinions in this posting are my own and not those of my present
or previous employers.



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199606021746.KAA23531>