From: "H. Peter Anvin" <hpa@zytor.com>
To: Kyle Moffett <mrmacman_g4@mac.com>
Cc: Mikulas Patocka <mikulas@artax.karlin.mff.cuni.cz>,
Albert Cahalan <acahalan@gmail.com>,
kangur@polcom.net, linux-kernel@vger.kernel.org
Subject: Re: New filesystem for Linux
Date: Sun, 05 Nov 2006 12:26:01 -0800 [thread overview]
Message-ID: <454E48D9.3060303@zytor.com> (raw)
In-Reply-To: <AA4E0826-81F3-47AF-8C5E-D691BB02AB32@mac.com>
Kyle Moffett wrote:
> On Nov 04, 2006, at 18:38:11, Mikulas Patocka wrote:
>> But how will fdisk deal with it? Fdisk by default aligns partitions on
>> 63-sector boundary, so it will make all sectors misaligned and
>> seriously kill performance even if filesystem uses proper 8-sector
>> aligned accesses.
>
> Don't use a partition-table format that dates back to drives with actual
> reported physical geometry and which also maxed out at 2MB or so? Even
> the mac-format partition tables (which aren't that much newer) don't
> care about physical drive geometry.
>
> Besides, unless you're running DOS, Windows 95, or some random ancient
> firmware that looks at your partition tables or whatever you can just
> tell fdisk to ignore the 63-sector-alignment constraint and align your
> partitions more efficiently anyways. But if you're dealing with
> hardware so new it supports 4k or 8k sectors, you really should be using
> EFI or something.
>
> Cheers,
> Kyle Moffett
>
Actually, DOS/Win9x should handle arbitrary alignment just fine (except
possibly some very very old versions of DOS which assumed that the first
four sectors of IO.SYS all fell within the same track -- but I'm pretty
sure that the FORMAT and SYS programs would align it for you.)
-hpa
next prev parent reply other threads:[~2006-11-05 20:26 UTC|newest]
Thread overview: 99+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-11-02 21:52 New filesystem for Linux Mikulas Patocka
2006-11-02 22:32 ` Gabriel C
2006-11-03 1:22 ` Mikulas Patocka
2006-11-03 1:41 ` Andrew Morton
2006-11-03 17:14 ` Oleg Verych
2006-11-03 17:09 ` Mikulas Patocka
2006-11-03 17:36 ` Oleg Verych
2006-11-03 18:14 ` Mikulas Patocka
2006-11-03 19:08 ` Adrian Bunk
2006-11-03 19:32 ` Oleg Verych
2006-11-03 19:00 ` Alan Cox
2006-11-03 19:14 ` Andi Kleen
2006-11-03 2:09 ` Gabriel C
2006-11-03 8:26 ` Jan Engelhardt
2006-11-03 11:52 ` Mikulas Patocka
2006-11-03 11:59 ` Mikulas Patocka
2006-11-03 12:50 ` Jan Engelhardt
2006-11-03 18:48 ` Mikulas Patocka
2006-11-03 21:51 ` Jan Engelhardt
2006-11-03 11:47 ` Mikulas Patocka
2006-11-02 22:53 ` Eric Dumazet
2006-11-03 1:28 ` Mikulas Patocka
2006-11-03 1:43 ` Andrew Morton
2006-11-04 18:40 ` Mikulas Patocka
2006-11-04 19:07 ` Eric Dumazet
2006-11-04 19:39 ` Tomasz Torcz
2006-11-05 1:58 ` Alan Cox
2006-11-05 2:09 ` Patrick McFarland
2006-11-05 13:03 ` Maurizio Lombardi
2006-11-05 20:16 ` H. Peter Anvin
2006-11-02 22:54 ` Grzegorz Kulewski
2006-11-02 23:10 ` Eric Dumazet
2006-11-02 23:19 ` Mikulas Patocka
2006-11-02 23:29 ` Grzegorz Kulewski
2006-11-03 1:34 ` Mikulas Patocka
2006-11-03 20:30 ` Christoph Lameter
2006-11-04 18:46 ` Mikulas Patocka
2006-11-05 12:02 ` Theodore Tso
2006-11-03 22:00 ` Oleg Verych
2006-11-03 22:42 ` Mikulas Patocka
2006-11-03 0:57 ` Nigel Cunningham
2006-11-03 13:05 ` Ric Wheeler
2006-11-06 2:42 ` Phillip Susi
2006-11-04 19:59 ` Albert Cahalan
2006-11-04 21:01 ` Jan-Benedict Glaw
2006-11-05 16:37 ` Albert Cahalan
2006-11-04 23:38 ` Mikulas Patocka
2006-11-04 23:46 ` Kyle Moffett
2006-11-05 20:26 ` H. Peter Anvin [this message]
2006-11-05 21:27 ` Rene Herman
2006-11-05 21:51 ` H. Peter Anvin
2006-11-06 0:36 ` Rene Herman
2006-11-05 21:49 ` Pavel Machek
2006-11-05 1:57 ` Alan Cox
2006-11-05 11:14 ` James Courtier-Dutton
2006-11-05 11:27 ` Brad Campbell
2006-11-05 12:37 ` Alan Cox
2006-11-06 2:48 ` Phillip Susi
2006-11-05 16:22 ` Albert Cahalan
2006-11-05 17:18 ` Mikulas Patocka
2006-11-05 18:14 ` Alan Cox
2006-11-05 18:18 ` Mikulas Patocka
2006-11-05 19:14 ` Alan Cox
2006-11-02 23:15 ` Linus Torvalds
2006-11-03 20:02 ` Paul E. McKenney
2006-11-02 23:41 ` Andi Kleen
2006-11-03 1:45 ` Mikulas Patocka
2006-11-03 13:47 ` Nikita Danilov
2006-11-03 14:39 ` Mikulas Patocka
2006-11-02 23:59 ` Jörn Engel
2006-11-03 1:19 ` Mikulas Patocka
2006-11-03 10:19 ` Jörn Engel
2006-11-03 11:56 ` Mikulas Patocka
2006-11-03 12:21 ` Jörn Engel
2006-11-03 13:31 ` Mikulas Patocka
2006-11-03 13:48 ` Jörn Engel
2006-11-03 14:19 ` Mikulas Patocka
2006-11-03 14:53 ` Jörn Engel
2006-11-03 19:01 ` Mikulas Patocka
2006-11-04 10:46 ` Jörn Engel
2006-11-04 18:50 ` Mikulas Patocka
2006-11-06 21:19 ` Jörn Engel
2006-11-03 19:51 ` Adrian Bunk
2006-11-03 19:00 ` dean gaudet
2006-11-04 10:53 ` Jörn Engel
2006-11-04 11:13 ` dean gaudet
2006-11-04 20:07 ` Jörn Engel
2006-11-04 18:52 ` Mikulas Patocka
2006-11-04 18:56 ` Grzegorz Kulewski
2006-11-04 19:18 ` Mikulas Patocka
2006-11-04 17:37 ` Gautham R Shenoy
2006-11-04 18:27 ` Eric Dumazet
2006-11-05 22:33 ` Paul E. McKenney
2006-11-05 0:52 ` Linus Torvalds
2006-11-05 4:14 ` Mikulas Patocka
2006-11-05 8:34 ` Willy Tarreau
2006-11-05 11:31 ` Jan Engelhardt
2006-11-05 14:48 ` Bruno Cesar Ribas
-- strict thread matches above, loose matches on Subject: below --
2006-11-06 17:40 Al Boldi
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=454E48D9.3060303@zytor.com \
--to=hpa@zytor.com \
--cc=acahalan@gmail.com \
--cc=kangur@polcom.net \
--cc=linux-kernel@vger.kernel.org \
--cc=mikulas@artax.karlin.mff.cuni.cz \
--cc=mrmacman_g4@mac.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox