diff options
author | Ming Lei <ming.lei@redhat.com> | 2017-05-26 19:53:19 +0800 |
---|---|---|
committer | Jens Axboe <axboe@fb.com> | 2017-05-26 14:12:03 -0600 |
commit | ab42f35d9cb5ac49b5a2a11f940e74f58f207280 (patch) | |
tree | d3fedd45516727f64f0efa1f494755cbabd8a6cc /block/blk-mq-sched.c | |
parent | cdbe0206783b4e86abb0150303f137e448b5e531 (diff) | |
download | lwn-ab42f35d9cb5ac49b5a2a11f940e74f58f207280.tar.gz lwn-ab42f35d9cb5ac49b5a2a11f940e74f58f207280.zip |
blk-mq: merge bio into sw queue before plugging
Before blk-mq is introduced, I/O is merged to elevator
before being putted into plug queue, but blk-mq changed the
order and makes merging to sw queue basically impossible.
Then it is observed that throughput of sequential I/O is degraded
about 10%~20% on virtio-blk in the test[1] if mq-deadline isn't used.
This patch moves the bio merging per sw queue before plugging,
like what blk_queue_bio() does, and the performance regression is
fixed under this situation.
[1]. test script:
sudo fio --direct=1 --size=128G --bsrange=4k-4k --runtime=40 --numjobs=16 --ioengine=libaio --iodepth=64 --group_reporting=1 --filename=/dev/vdb --name=virtio_blk-test-$RW --rw=$RW --output-format=json
RW=read or write
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Diffstat (limited to 'block/blk-mq-sched.c')
0 files changed, 0 insertions, 0 deletions