Skip to content

Improve zoned storage write performance

Bart Van Assche linux-block 3 versions – In review

Get series with b4
b4 am [email protected]

Versions newest first · linked by author and title

  1. v3 Latest8 patches 16 repliesIn review
  2. v26 patches 13 repliesSuperseded
  3. v15 patches 18 repliesSuperseded

Changes in v3 from the cover letter

- Included the patches again that enable write pipelining for NVMe ZNS SSDs.
- Disabled merging in the null_blk test script. As a result, the test script now shows a 14x improvement with pipelining enabled.
- Renamed blk_rq_is_zoned_seq_write() into blk_rq_is_seq_zone_write().

Patches in v3 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/8block: Document blk_queue_zone_is_seq() and blk_rq_zone_is_seq()include/linux/blk-mq.h include/linux/blkdev.h+16 -01 reply
2/8block: Introduce the blk_rq_is_seq_zone_write() functionblock/blk-zoned.c include/linux/blk-mq.h+25 -141 reply
3/8block: Introduce a request queue flag for pipelining zoned writesinclude/linux/blkdev.h+7 -02 replies
4/8block/mq-deadline: Only use zone locking if necessaryblock/blk-zoned.c block/mq-deadline.c+14 -70 replies
5/8block/null_blk: Refactor null_queue_rq()drivers/block/null_blk/main.c+11 -101 reply
6/8block/null_blk: Add support for pipelining zoned writesdrivers/block/null_blk/main.c drivers/block/null_blk/null_blk.h drivers/block/null_blk/zoned.c+24 -12 replies
7/8nvme: Make the number of retries command specificdrivers/nvme/host/core.c drivers/nvme/host/nvme.h+3 -12 replies
8/8nvme: Enable pipelining of zoned writesdrivers/nvme/host/core.c drivers/nvme/host/zns.c+8 -07 replies

Reviews trailers per patch

3 of 8 patches have a Reviewed-by or Acked-by.

PatchDamien Le MoalChaitanya Kulkarni
1/8R-b R-b
2/8R-b R-b
3/8
4/8
5/8R-b R-b
6/8
7/8
8/8

Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.

Read the v3 thread

Cover letter [PATCH v3 0/8] Improve zoned storage write performance

Hi Jens,

Measurements have shown that limiting the queue depth to one per sequential zone has a significant negative performance impact for zoned UFS devices. Hence this patch series that increases the queue depth for write commands for sequential zones when using the mq-deadline scheduler.

Please consider this patch series for kernel v5.20.

Thanks,

Bart.

Changes compared to v2:
- Included the patches again that enable write pipelining for NVMe ZNS SSDs.
- Disabled merging in the null_blk test script. As a result, the test script now shows a 14x improvement with pipelining enabled.
- Renamed blk_rq_is_zoned_seq_write() into blk_rq_is_seq_zone_write().

Changes compared to v1:
- Left out the patch for the UFS driver.
- Included patches for the null_blk driver.

Bart Van Assche (8):
block: Document blk_queue_zone_is_seq() and blk_rq_zone_is_seq()
block: Introduce the blk_rq_is_seq_zone_write() function
block: Introduce a request queue flag for pipelining zoned writes block/mq-deadline: Only use zone locking if necessary block/null_blk: Refactor null_queue_rq() block/null_blk: Add support for pipelining zoned writes
nvme: Make the number of retries command specific
nvme: Enable pipelining of zoned writes

 block/blk-zoned.c                 | 17 +++--------------
 block/mq-deadline.c               | 18 ++++++++++++------
 drivers/block/null_blk/main.c     | 30 ++++++++++++++++++++----------
 drivers/block/null_blk/null_blk.h |  3 +++
 drivers/block/null_blk/zoned.c    | 13 ++++++++++++-
 drivers/nvme/host/core.c          |  9 ++++++++-
 drivers/nvme/host/nvme.h          |  1 +
 drivers/nvme/host/zns.c           |  2 ++
 include/linux/blk-mq.h            | 30 ++++++++++++++++++++++++++++++
 include/linux/blkdev.h            | 16 ++++++++++++++++
 10 files changed, 107 insertions(+), 32 deletions(-)