linux-ext4.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Andreas Dilger <adilger@sun.com>
To: "Theodore Ts'o" <tytso@mit.edu>
Cc: linux-ext4@vger.kernel.org, stable@kernel.org
Subject: Re: [PATCH,STABLE 2.6.29 06/18] ext4: Automatically allocate delay allocated blocks on close
Date: Wed, 03 Jun 2009 12:14:19 -0600	[thread overview]
Message-ID: <20090603181419.GN9002@webber.adilger.int> (raw)
In-Reply-To: <1243944479-20574-6-git-send-email-tytso@mit.edu>

On Jun 02, 2009  08:07 -0400, Theodore Ts'o wrote:
> When closing a file that had been previously truncated, force any
> delay allocated blocks that to be allocated so that if the filesystem
> is mounted with data=ordered, the data blocks will be pushed out to
> disk along with the journal commit.  Many application programs expect
> this, so we do this to avoid zero length files if the system crashes
> unexpectedly.
> 
> @@ -3880,6 +3880,9 @@ void ext4_truncate(struct inode *inode)
>  	if (!ext4_can_truncate(inode))
>  		return;
>  
> +	if (inode->i_size == 0)
> +		ei->i_state |= EXT4_STATE_DA_ALLOC_CLOSE;

Since some applications open files with open(..., O_WRONLY|O_CREAT|O_TRUNC)
to avoid re-using existing files (and avoiding the need to check if the
file already exists to modify the flags), it would make sense to set
EXT4_STATE_DA_ALLOC_CLOSE only if the file previously had some data in it.

By the time we get to ext4_truncate() i_size is overwritten already, but
it might make sense to also check i_disksize != 0 before setting this flag.
Otherwise delayed allocation may be inadvertently disabled for these apps
when it should not be.

Cheers, Andreas
--
Andreas Dilger
Sr. Staff Engineer, Lustre Group
Sun Microsystems of Canada, Inc.


  parent reply	other threads:[~2009-06-03 18:14 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-06-02 12:07 [PATCH,STABLE 2.6.29 01/18] ext4: don't inherit inappropriate inode flags from parent Theodore Ts'o
2009-06-02 12:07 ` [PATCH,STABLE 2.6.29 02/18] ext4: tighten restrictions on inode flags Theodore Ts'o
2009-06-02 12:07   ` [PATCH,STABLE 2.6.29 03/18] ext4: return -EIO not -ESTALE on directory traversal through deleted inode Theodore Ts'o
2009-06-02 12:07     ` [PATCH,STABLE 2.6.29 04/18] ext4: Add fine print for the 32000 subdirectory limit Theodore Ts'o
2009-06-02 12:07       ` [PATCH,STABLE 2.6.29 05/18] ext4: add EXT4_IOC_ALLOC_DA_BLKS ioctl Theodore Ts'o
2009-06-02 12:07         ` [PATCH,STABLE 2.6.29 06/18] ext4: Automatically allocate delay allocated blocks on close Theodore Ts'o
2009-06-02 12:07           ` [PATCH,STABLE 2.6.29 07/18] ext4: Automatically allocate delay allocated blocks on rename Theodore Ts'o
2009-06-02 12:07             ` [PATCH,STABLE 2.6.29 08/18] ext4: Fix discard of inode prealloc space with delayed allocation Theodore Ts'o
2009-06-02 12:07               ` [PATCH,STABLE 2.6.29 09/18] ext4: Add auto_da_alloc mount option Theodore Ts'o
2009-06-02 12:07                 ` [PATCH,STABLE 2.6.29 10/18] ext4: Check for an valid i_mode when reading the inode from disk Theodore Ts'o
2009-06-02 12:07                   ` [PATCH,STABLE 2.6.29 11/18] jbd2: Update locking coments Theodore Ts'o
2009-06-02 12:07                     ` [PATCH,STABLE 2.6.29 12/18] ext4: really print the find_group_flex fallback warning only once Theodore Ts'o
2009-06-02 12:07                       ` [PATCH,STABLE 2.6.29 13/18] ext4: Fix softlockup caused by illegal i_file_acl value in on-disk inode Theodore Ts'o
2009-06-02 12:07                         ` [PATCH,STABLE 2.6.29 14/18] ext4: Ignore i_file_acl_high unless EXT4_FEATURE_INCOMPAT_64BIT is present Theodore Ts'o
2009-06-02 12:07                           ` [PATCH,STABLE 2.6.29 15/18] ext4: Fix sub-block zeroing for writes into preallocated extents Theodore Ts'o
2009-06-02 12:07                             ` [PATCH,STABLE 2.6.29 16/18] ext4: Use a fake block number for delayed new buffer_head Theodore Ts'o
2009-06-02 12:07                               ` [PATCH,STABLE 2.6.29 17/18] ext4: Clear the unwritten buffer_head flag after the extent is initialized Theodore Ts'o
2009-06-02 12:07                                 ` [PATCH,STABLE 2.6.29 18/18] ext4: Fix race in ext4_inode_info.i_cached_extent Theodore Ts'o
2009-06-03 18:17                           ` [PATCH,STABLE 2.6.29 14/18] ext4: Ignore i_file_acl_high unless EXT4_FEATURE_INCOMPAT_64BIT is present Andreas Dilger
2009-06-03 18:16                         ` Fix softlockup caused by illegal i_file_acl value in on-disk inode Andreas Dilger
2009-06-03 19:24                           ` Theodore Tso
2009-06-03 18:14           ` Andreas Dilger [this message]
2009-06-03 19:29             ` [PATCH,STABLE 2.6.29 06/18] ext4: Automatically allocate delay allocated blocks on close Theodore Tso
2009-06-09  9:33     ` patch ext4-return-eio-not-estale-on-directory-traversal-through-deleted-inode.patch added to 2.6.29-stable tree gregkh
2009-06-09  9:33   ` patch ext4-tighten-restrictions-on-inode-flags.patch " gregkh
2009-06-09  9:33 ` patch ext4-don-t-inherit-inappropriate-inode-flags-from-parent.patch " gregkh

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=20090603181419.GN9002@webber.adilger.int \
    --to=adilger@sun.com \
    --cc=linux-ext4@vger.kernel.org \
    --cc=stable@kernel.org \
    --cc=tytso@mit.edu \
    /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;
as well as URLs for NNTP newsgroup(s).