public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Hans Reiser <reiser@namesys.com>
To: Mike Fedyk <mfedyk@matchmail.com>
Cc: Andrew Morton <akpm@osdl.org>,
	reiserfs-list@namesys.com, linux-kernel@vger.kernel.org
Subject: Re: precise characterization of ext3 atomicity
Date: Thu, 04 Sep 2003 22:37:10 +0400	[thread overview]
Message-ID: <3F578656.60005@namesys.com> (raw)
In-Reply-To: <20030904181540.GC13676@matchmail.com>

Mike Fedyk wrote:

>On Thu, Sep 04, 2003 at 08:25:18PM +0400, Hans Reiser wrote:
>  
>
>>In data=journal and data=ordered modes ext3 also guarantees that the 
>>metadata will be committed atomically with the data they point to.  However 
>>ext3 does not provide user data atomicity guarantees beyond the scope of a 
>>single filesystem disk block (usually 4 kilobytes).  If a single write() 
>>spans two disk blocks it is possible that a crash partway through the write 
>>will result in only one of those blocks appearing in the file after 
>>recovery.
>>    
>>
>
>And how does reiser4 do this without changing the userspace apps?
>
We don't.  We just make the hovercraft, we don't force you to go over 
the water.....

>
>Most files are written with several write() calls, so even if each call is
>atomic, your entire file will not be there.
>
>Also, ext3 could claim the same atomicity if it only updated meta-data on
>write() call boundaries, instead of block boundaries.
>
>
>  
>


-- 
Hans



  parent reply	other threads:[~2003-09-04 18:39 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2003-09-04 14:20 precise characterization of ext3 atomicity Hans Reiser
2003-09-04 15:55 ` Andrew Morton
2003-09-04 15:59   ` Hans Reiser
2003-09-04 16:12     ` Andrew Morton
2003-09-04 16:25       ` Hans Reiser
2003-09-04 18:15         ` Mike Fedyk
2003-09-04 16:05           ` Antonio Vargas
2003-09-04 18:37           ` Hans Reiser [this message]
2003-09-04 19:12             ` Mike Fedyk
2003-09-04 21:03               ` Hans Reiser
2003-09-04 19:28             ` Andreas Dilger
2003-09-04 21:32               ` Hans Reiser
2003-09-04 22:03                 ` Andreas Dilger
2003-09-05 13:47                   ` Chris Mason
2003-09-09 13:09                 ` Pavel Machek
2003-09-09 19:21                   ` Gábor Lénárt
2003-09-09 19:43                     ` Mike Fedyk
2003-09-04 20:16   ` Daniel Phillips
2003-09-04 20:10     ` Andrew Morton
2003-09-04 21:08       ` Daniel Phillips
2003-09-04 21:39         ` Hans Reiser
2003-09-04 21:59           ` Daniel Phillips

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=3F578656.60005@namesys.com \
    --to=reiser@namesys.com \
    --cc=akpm@osdl.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mfedyk@matchmail.com \
    --cc=reiserfs-list@namesys.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