[PATCH v2] xfs: Avoid pathological backwards allocation

[Mark Tinguely]

On 04/11/13 15:09, Jan Kara wrote:
> Writing a large file using direct IO in 16 MB chunks sometimes results
> in a pathological allocation pattern where 16 MB chunks of large free
> extent are allocated to a file in a reversed order. So extents of a file
> look for example as:
>
>   ext logical physical expected length flags
>     0        0        13          4550656
>     1  4550656 188136807   4550668 12562432
>     2 17113088 200699240 200699238 622592
>     3 17735680 182046055 201321831   4096
>     4 17739776 182041959 182050150   4096
>     5 17743872 182037863 182046054   4096
>     6 17747968 182033767 182041958   4096
>     7 17752064 182029671 182037862   4096
> ...
> 6757 45400064 154381644 154389835   4096
> 6758 45404160 154377548 154385739   4096
> 6759 45408256 252951571 154381643  73728 eof
>
> This happens because XFS_ALLOCTYPE_THIS_BNO allocation fails (the last
> extent in the file cannot be further extended) so we fall back to
> XFS_ALLOCTYPE_NEAR_BNO allocation which picks end of a large free
> extent as the best place to continue the file. Since the chunk at the
> end of the free extent again cannot be further extended, this behavior
> repeats until the whole free extent is consumed in a reversed order.
>
> For data allocations this backward allocation isn't beneficial so make
> xfs_alloc_compute_diff() pick start of a free extent instead of its end
> for them. That avoids the backward allocation pattern.
>
> See thread at http://oss.sgi.com/archives/xfs/2013-03/msg00144.html for
> more details about the reproduction case and why this solution was
> chosen.
>
> Based on idea by Dave Chinner<dchinner at redhat.com>.
>
> CC: Dave Chinner<dchinner at redhat.com>
> Reviewed-by: Dave Chinner<dchinner at redhat.com>
> Signed-off-by: Jan Kara<jack at suse.cz>
> ---
>   fs/xfs/xfs_alloc.c |   24 ++++++++++++++++++------
>   1 files changed, 18 insertions(+), 6 deletions(-)
>
> v2: Updated comment and commit description.
>

Looks good. I also agree this should wait for Linux 3.11.

Reviewed-by: Mark Tinguely <tinguely at sgi.com>