Return to BSD News archive
Path: euryale.cc.adfa.oz.au!newshost.carno.net.au!harbinger.cc.monash.edu.au!munnari.OZ.AU!news.ecn.uoknor.edu!news.wildstar.net!news.ececs.uc.edu!newsfeeds.sol.net!worldnet.att.net!cpk-news-hub1.bbnplanet.com!news.bbnplanet.com!newsxfer3.itd.umich.edu!news1.best.com!nntp1.ba.best.com!not-for-mail
From: dillon@flea.best.net (Matt Dillon)
Newsgroups: comp.unix.bsd.freebsd.misc,comp.unix.bsd.bsdi.misc,comp.sys.sgi.misc
Subject: Re: no such thing as a "general user community"
Date: 28 Mar 1997 11:21:06 -0800
Organization: BEST Internet Communications, Inc.
Lines: 45
Message-ID: <5hh5n2$9q8@flea.best.net>
References: <331BB7DD.28EC@net5.net> <5he3pp$8ms$2@kayrad.ziplink.net> <5hfh2l$i13@flea.best.net> <5hfl3n$a3t@fido.asd.sgi.com>
NNTP-Posting-Host: flea.best.net
Xref: euryale.cc.adfa.oz.au comp.unix.bsd.freebsd.misc:37946 comp.unix.bsd.bsdi.misc:6486 comp.sys.sgi.misc:29485
:In article <5hfl3n$a3t@fido.asd.sgi.com>,
:Larry McVoy <lm@slovax.engr.sgi.com> wrote:
:>Matt Dillon (dillon@flea.best.net) wrote:
:>: I didn't even notice that :-) A 200 MHz PPro (P6) is over twice as fast
:>: as a 133 MHz pentium (P5). XFS will still beat out a normally mounted
:>: ffs filesystem in terms of file creates/deletes though. It will not
:>: beat out an async-mounted ffs filesystem, however, which means that
:>: once ordered block I/O is put into FreeBSD, you can kiss goodbye
:>: to that statistic. File lookups under XFS will be the only thing
:>: left that it can boast about. This is a significant, but not
:>: overpowering, feature.
:>
:>You don't think that having a log based file system is a win? I happen
:>to like it a lot.
:>
:>And comparing some future feature in FreeBSD to a feature that XFS has done
:>better for 5 years is hardly apples to apples. You think the XFS boys are
:>sitting on their thumbs? I can assure you they aren't and that they are
:>on to more interesting problems such as failover, cluster based XFS, etc.
:>
:>I'm an old time file system guy, an FFS bigot from way back. In fact, I
:>got up at Usenix and defended FFS when Margo or whoever was doing the
:>LFS talk. But let's be fair - XFS is lightyears beyond FFS. Lightyears.
:>--
:>---
:>Larry McVoy lm@sgi.com http://reality.sgi.com/lm (415) 933-1804
I don't think a log based filesystem will be much of a win over FFS
if FFS is improved a bit. Really, only two improvements need to be
made: (1) ordered I/O, which will fix the file create/delete rate
problem, and (2) sparse sorted directories, which effectively solves
the linear file lookup problem.
The cool thing is that both features can be added while maintaining
full compatibility. Add in a somewhat better kernel locking mechanism
and poof, you are done.
Now, of course you still have to fsck an ffs filesystem verses a log
or journaling filesystem. While this is an important difference, I
consider it minor if the rest of the machine is reliable (i.e. doesn't
crash very often), especially if FFS is further adjusted to set the
clean bit on mounted filesystems that have been synced up and are idle.
-Matt