[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20061104210111.GB21485@lug-owl.de>
Date: Sat, 4 Nov 2006 22:01:11 +0100
From: Jan-Benedict Glaw <jbglaw@...-owl.de>
To: Albert Cahalan <acahalan@...il.com>
Cc: kangur@...com.net, mikulas@...ax.karlin.mff.cuni.cz,
linux-kernel@...r.kernel.org
Subject: Re: New filesystem for Linux
On Sat, 2006-11-04 14:59:53 -0500, Albert Cahalan <acahalan@...il.com> wrote:
> Grzegorz Kulewski writes:
> > On Thu, 2 Nov 2006, Mikulas Patocka wrote:
> > > As my PhD thesis, I am designing and writing a filesystem,
> > > and it's now in a state that it can be released. You can
> > > download it from http://artax.karlin.mff.cuni.cz/~mikulas/spadfs/
> >
> > "Disk that can atomically write one sector (512 bytes) so that
> > the sector contains either old or new content in case of crash."
>
> New drives will soon use 4096-byte sectors. This is a better
> match for the normal (non-VAX!) page size and reduces overhead.
Well... VAXen use physical PTEs for 512 byte pages, Linux uses 8
consecutive pages to simulate 4K pages.
On top of that, some of today's machines have configurable page sizes.
Besides that, 512 byte sectors are quite a clever thing: Drives
probably can write a number of consecutive sectors, so if you want to
send a page, just send eight sectors.
> BTW, a person with disk recovery experience told me that drives
> will sometimes reorder the sectors. Sector 42 becomes sector 7732,
> sector 880880 becomes sector 12345, etc. The very best filesystems
> can handle with without data loss. (for example, ZFS) Merely great
> filesystems will at least recognize that the data has been trashed.
Uh? This should be transparent to the host computer, so logical sector
numbers won't change.
MfG, JBG
--
Jan-Benedict Glaw jbglaw@...-owl.de +49-172-7608481
Signature of: http://catb.org/~esr/faqs/smart-questions.html
the second :
Download attachment "signature.asc" of type "application/pgp-signature" (190 bytes)
Powered by blists - more mailing lists