On Mon, Jun 24, 2024 at 06:08:23PM +0200, Christoph Hellwig wrote: > 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? Nothing -- it looks fine to me, but as it's authored by me, I can't meaningfully slap an RVB tag on it, can I? Eh I've done the rest of the series; let's try it anyway: Reviewed-by: Darrick J. Wong <djwong@xxxxxxxxxx> --D
