Re: [PATCH 07/10] xfs: only free posteof blocks on first close

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Mon, Jun 24, 2024 at 08:46:21AM -0700, Darrick J. Wong wrote:
> On Sun, Jun 23, 2024 at 07:34:52AM +0200, Christoph Hellwig wrote:
> > From: "Darrick J. Wong" <djwong@xxxxxxxxxx>
> > 
> > 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 <djwong@xxxxxxxxxx>
> > [hch: rebased, updated comment, renamed the flag]
> > Signed-off-by: Christoph Hellwig <hch@xxxxxx>
> 
> Someone please review this?  The last person to try was Dave, five years
> ago, and I do not know if he ever saw what it did to various workloads.
> 
> https://lore.kernel.org/linux-xfs/20190315034237.GL23020@dastard/

Well, the read-only check Dave suggested is in the previous patch,
and the tests he sent cover the relevant synthetic workloads.  What
else are you looking for?





[Index of Archives]     [XFS Filesystem Development (older mail)]     [Linux Filesystem Development]     [Linux Audio Users]     [Yosemite Trails]     [Linux Kernel]     [Linux RAID]     [Linux SCSI]


  Powered by Linux