[1/4] xfs: only free posteof blocks on first close
diff mbox series

Message ID 155259894034.30230.7188877605950498518.stgit@magnolia
State New
Headers show
Series
  • xfs: various rough fixes
Related show

Commit Message

Darrick J. Wong March 14, 2019, 9:29 p.m. UTC
From: Darrick J. Wong <darrick.wong@oracle.com>

Certain workloads fragment files on XFS very badly, such as a software
package that creates a number of threads, each of which repeatedly run
the sequence: open a file, perform a synchronous write, and close the
file, which defeats the speculative preallocation mechanism.  We work
around this problem by only deleting posteof blocks the /first/ time a
file is closed to preserve the behavior that unpacking a tarball lays
out files one after the other with no gaps.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_inode.c |    4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

Comments

Dave Chinner March 15, 2019, 3:42 a.m. UTC | #1
On Thu, Mar 14, 2019 at 02:29:00PM -0700, Darrick J. Wong wrote:
> From: Darrick J. Wong <darrick.wong@oracle.com>
> 
> Certain workloads fragment files on XFS very badly, such as a software
> package that creates a number of threads, each of which repeatedly run
> the sequence: open a file, perform a synchronous write, and close the
> file, which defeats the speculative preallocation mechanism.  We work
> around this problem by only deleting posteof blocks the /first/ time a
> file is closed to preserve the behavior that unpacking a tarball lays
> out files one after the other with no gaps.
> 
> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
> ---
>  fs/xfs/xfs_inode.c |    4 +---
>  1 file changed, 1 insertion(+), 3 deletions(-)
> 
> 
> diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
> index 665fb2518a66..981c34bdec25 100644
> --- a/fs/xfs/xfs_inode.c
> +++ b/fs/xfs/xfs_inode.c
> @@ -1262,9 +1262,7 @@ xfs_release(
>  				return error;
>  		}
>  
> -		/* delalloc blocks after truncation means it really is dirty */
> -		if (ip->i_delayed_blks)
> -			xfs_iflags_set(ip, XFS_IDIRTY_RELEASE);
> +		xfs_iflags_set(ip, XFS_IDIRTY_RELEASE);

I've been meaning to test this exact setup to see what the impact
is, but haven't got to it yet. I can't really comment on it sanely
until I see what it does to various workloads....

We do need more than this though. e.g we need to skip the block
freeing compeltely on O_RDONLY file closes...

Cheers,

Dave.

Patch
diff mbox series

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 665fb2518a66..981c34bdec25 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1262,9 +1262,7 @@  xfs_release(
 				return error;
 		}
 
-		/* delalloc blocks after truncation means it really is dirty */
-		if (ip->i_delayed_blks)
-			xfs_iflags_set(ip, XFS_IDIRTY_RELEASE);
+		xfs_iflags_set(ip, XFS_IDIRTY_RELEASE);
 	}
 	return 0;
 }