From: Valerie Henson <val_henson@linux.intel.com>
To: Jeff Dike <jdike@addtoit.com>
Cc: Amit Gud <gud@ksu.edu>, Nikita Danilov <nikita@clusterfs.com>,
David Lang <david.lang@digitalinsight.com>,
linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
riel@surriel.com, zab@zabbo.net, arjan@infradead.org,
suparna@in.ibm.com, brandon@ifup.org, karunasagark@gmail.com
Subject: Re: [RFC][PATCH] ChunkFS: fs fission for faster fsck
Date: Thu, 26 Apr 2007 21:58:25 -0700 [thread overview]
Message-ID: <20070427045824.GB20286@nifty> (raw)
In-Reply-To: <20070426160504.GA7970@c2.user-mode-linux.org>
On Thu, Apr 26, 2007 at 12:05:04PM -0400, Jeff Dike wrote:
>
> No, I'm referring to a different file. The scenario is that you have
> a growing file in a nearly full disk with files being deleted (and
> thus space being freed) such that allocations for the growing file
> bounce back and forth between chunks.
This is an excellent question. I call this the ping-pong problem.
The solution is as Amit describes: You have a maximum of one
continuation inode per file per chunk, and you require sparse files.
Here's an example, spelled out:
Allocate file 1 in chunk A.
Grow file 1.
Chunk A fills up.
Allocate continuation inode for file 1 in chunk B.
Chunk A gets some free space.
Chunk B fills up.
Pick chunk A for allocating next block of file 1.
Try to look up a continuation inode for file 1 in chunk A.
Continuation inode for file 1 found in chunk A!
Attach newly allocated block to existing inode for file 1 in chunk A.
This is why the file format inside each chunk needs to support sparse
files.
I have a presentation that has a series of slides on problems and
potential resolutions that might help:
http://infohost.nmt.edu/~val/review/chunkfs_presentation.pdf
-VAL
next prev parent reply other threads:[~2007-04-27 4:58 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-04-23 11:21 [RFC][PATCH] ChunkFS: fs fission for faster fsck Amit Gud
[not found] ` <17965.6084 1.900376.524639@gargle.gargle.HOWL>
2007-04-23 16:28 ` Suparna Bhattacharya
2007-04-23 15:25 ` Amit Gud
2007-04-23 16:32 ` Suparna Bhattacharya
2007-04-24 11:44 ` Nikita Danilov
2007-04-24 18:27 ` David Lang
2007-04-24 19:34 ` Nikita Danilov
2007-04-24 19:26 ` David Lang
2007-04-25 11:34 ` Nikita Danilov
2007-04-25 16:39 ` David Lang
2007-04-25 22:47 ` Valerie Henson
2007-04-26 14:14 ` Jeff Dike
2007-04-26 15:53 ` Amit Gud
2007-04-26 16:05 ` Jeff Dike
2007-04-26 16:56 ` Amit Gud
2007-04-27 4:58 ` Valerie Henson [this message]
2007-04-27 15:06 ` Jeff Dike
2007-05-01 17:26 ` Valerie Henson
2007-04-26 16:11 ` Alan Cox
2007-04-26 16:44 ` Amit Gud
2007-04-24 21:53 ` Amit Gud
2007-04-25 10:54 ` David Chinner
2007-04-25 11:38 ` Andreas Dilger
2007-04-25 17:52 ` Amit Gud
2007-04-25 23:06 ` Valerie Henson
2007-04-25 23:03 ` Valerie Henson
2007-04-26 0:47 ` David Chinner
2007-04-26 22:21 ` Jörn Engel
2007-04-26 8:47 ` Jan Kara
2007-04-27 5:07 ` Valerie Henson
2007-04-27 10:53 ` Jörn Engel
2007-04-28 6:50 ` Valerie Henson
2007-04-28 10:03 ` Jörn Engel
2007-04-25 22:43 ` Valerie Henson
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=20070427045824.GB20286@nifty \
--to=val_henson@linux.intel.com \
--cc=arjan@infradead.org \
--cc=brandon@ifup.org \
--cc=david.lang@digitalinsight.com \
--cc=gud@ksu.edu \
--cc=jdike@addtoit.com \
--cc=karunasagark@gmail.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=nikita@clusterfs.com \
--cc=riel@surriel.com \
--cc=suparna@in.ibm.com \
--cc=zab@zabbo.net \
/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