Skip to content

Improve async iomap DIO performance

Jens Axboe io-uring linux-xfs 6 versions – In review

Get series with b4
b4 am [email protected]

Versions newest first · linked by author and title

  1. v6 Latest8 patches 5 repliesIn review
  2. v59 patches 10 repliesSuperseded
  3. v48 patches 29 repliesSuperseded
Earlier versions · 3
VersionPostedPatchesRepliesStatus
v36 patches10 repliesSuperseded
v25 patches4 repliesSuperseded
v15 patches4 repliesSuperseded

Changes in v6 from the cover letter

- Drop the polled patch, it's not needed anymore
- Change the "inline is safe" logic based on Dave's suggestions
- Gate HIPRI on INLINE_COMP|CALLER_COMP, so polled IO follows the same rules as inline/deferred completions.
- INLINE_COMP is purely for reads, writes can user CALLER_COMP to avoid a workqueue punt. This is necessary as we need to invalidate pages on write completions, and if we race with a buffered reader or writer on the file.

Patches in v6 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/8iomap: cleanup up iomap_dio_bio_end_io()fs/iomap/direct-io.c+31 -150 replies
2/8iomap: use an unsigned type for IOMAP_DIO_* definesfs/iomap/direct-io.c+4 -40 replies
3/8iomap: treat a write through cache the same as FUAfs/iomap/direct-io.c+20 -140 replies
4/8iomap: only set iocb->private for polled biofs/iomap/direct-io.c+5 -80 replies
5/8iomap: add IOMAP_DIO_INLINE_COMPfs/iomap/direct-io.c+8 -20 replies
6/8fs: add IOCB flags related to passing back dio completionsinclude/linux/fs.h+33 -20 replies
7/8io_uring/rw: add write support for IOCB_DIO_CALLER_COMPio_uring/rw.c+23 -30 replies
8/8iomap: support IOCB_DIO_CALLER_COMPfs/iomap/direct-io.c+60 -20 replies

Reviews trailers per patch

All 8 patches have a Reviewed-by or Acked-by of their own; the series has one for all of them.

PatchDarrick J. WongChristoph HellwigDave Chinner
SeriesR-b
1/8R-b R-b
2/8R-b R-b
3/8R-b R-b
4/8R-b R-b
5/8R-b R-b
6/8R-b R-b
7/8R-b R-b
8/8R-b R-b

Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes. Scroll the table sideways for all 3 reviewers.

Read the v6 thread

Cover letter [PATCHSET v6 0/8] Improve async iomap DIO performance

Hi,

Hi,

This patchset improves async iomap DIO performance, for XFS and ext4. For full details on this patchset, see the v4 posting:

https://lore.kernel.org/io-uring/[email protected]/

 fs/iomap/direct-io.c | 163 ++++++++++++++++++++++++++++++++-----------
 include/linux/fs.h   |  35 +++++++++-
 io_uring/rw.c        |  26 ++++++-
 3 files changed, 179 insertions(+), 45 deletions(-)

Can also be found here:

https://git.kernel.dk/cgit/linux/log/?h=xfs-async-dio.6

No change in performance since last time, and passes my testing without complaints.

Changes in v6:
- Drop the polled patch, it's not needed anymore
- Change the "inline is safe" logic based on Dave's suggestions
- Gate HIPRI on INLINE_COMP|CALLER_COMP, so polled IO follows the same rules as inline/deferred completions.
- INLINE_COMP is purely for reads, writes can user CALLER_COMP to avoid a workqueue punt. This is necessary as we need to invalidate pages on write completions, and if we race with a buffered reader or writer on the file.

Signature · 1 line
Jens Axboe