Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 15 Jul 1999 01:59:46 +0000 (GMT)
From:      Terry Lambert <tlambert@primenet.com>
To:        davids@webmaster.com (David Schwartz)
Cc:        davids@webmaster.com, Doug@gorean.org, chat@FreeBSD.ORG
Subject:   Re: Known MMAP() race conditions ... ?
Message-ID:  <199907150159.SAA10740@usr07.primenet.com>
In-Reply-To: <000201bece25$066b7510$021d85d1@youwant.to> from "David Schwartz" at Jul 14, 99 11:16:42 am

Next in thread | Previous in thread | Raw E-Mail | Index | Archive | Help
> > threads. Log-based system. There's nothing I know of in any UNIX
> 
> 	That should read "log-based file system". I'm talking about NTFS. And it
> beats an fsck any day.

NTFS is significantly slower that even an unmodified FFS in sync mode.

A modified FFS (i.e. with soft updates) does not require a fsck, but
no one has bothered to write a cylinder group bitmap cleaner for it,
which could easily run in the background. That, and disable the
"clean bit" code, and distinguish "disk related OS failure" from
"non-disk related OS failure" for the purposes of doing a full fsck
on disk related OS failures.

Note also that SGI is supposed to be releasing XFS sources some
time soon; IMO, it would be trivial to port it; I don't know if
I would bother with the plex manager (I like Simon's code for that),
given that their non-unified VM and buffer cache have the buffer
cache sandwiched between XFS and the manager.


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


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: <http://docs.FreeBSD.org/cgi/mid.cgi?199907150159.SAA10740>