Skip to content

RFC fixed worker

Hao Xu io-uring linux-fsdevel lkml 2 versions – In review

Get series with b4
b4 am [email protected]

Versions newest first · linked by author and title

  1. v3 RFC Latest9 patches 4 repliesIn review
  2. v2 RFC9 patches 0 repliesSuperseded

Changes in v3 from the cover letter

- change dispatch work strategy from random to round-robin

Patches in v3 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/9io-wq: add a worker flag for individual exitfs/io-wq.c+10 -10 replies
2/9io-wq: change argument of create_io_worker() for convienencefs/io-wq.c+7 -50 replies
3/9io-wq: add infra data structure for fixed workersfs/io-wq.c+87 -110 replies
4/9io-wq: tweak io_get_acct()fs/io-wq.c+9 -50 replies
5/9io-wq: fixed worker initializationfs/io-wq.c+24 -00 replies
6/9io-wq: fixed worker exitfs/io-wq.c+26 -00 replies
7/9io-wq: implement fixed worker logicfs/io-wq.c+122 -262 replies
8/9io-wq: batch the handling of fixed worker private worksfs/io-wq.c fs/io-wq.h+38 -90 replies
9/9io_uring: add register fixed worker interfacefs/io-wq.c fs/io-wq.h fs/io_uring.c +1 more+186 -00 replies

Reviews trailers per patch

No Reviewed-by, Acked-by or Tested-by trailers for v3 yet.

Read the v3 thread

Cover letter [RFC v3 0/9] fixed worker

This is the third version of fixed worker implementation. Wrote a nop test program to test it, 3 fixed-workers VS 3 normal workers. normal workers:
./run_nop_wqe.sh nop_wqe_normal 200000 100 3 1-3

        time spent: 10464397 usecs      IOPS: 1911242
        time spent: 9610976 usecs       IOPS: 2080954
        time spent: 9807361 usecs       IOPS: 2039284

fixed workers:
./run_nop_wqe.sh nop_wqe_fixed 200000 100 3 1-3

        time spent: 17314274 usecs      IOPS: 1155116
        time spent: 17016942 usecs      IOPS: 1175299
        time spent: 17908684 usecs      IOPS: 1116776

About 2x improvement. From perf result, almost no acct->lock contension. Test program: https://github.com/HowHsu/liburing/tree/fixed_worker
liburing/test/nop_wqe.c

v2->v3:
- change dispatch work strategy from random to round-robin

things to be done:
- Still need some thinking about the work cancellation
- not very sure IO_WORKER_F_EXIT is safe enough on synchronization
- the iowq hash stuff is not compatible with fixed worker for now

Any comments are welcome. Thanks in advance.

Hao Xu (9):
io-wq: add a worker flag for individual exit
io-wq: change argument of create_io_worker() for convienence
io-wq: add infra data structure for fixed workers
io-wq: tweak io_get_acct()
io-wq: fixed worker initialization
io-wq: fixed worker exit
io-wq: implement fixed worker logic
io-wq: batch the handling of fixed worker private works
io_uring: add register fixed worker interface

 fs/io-wq.c                    | 460 ++++++++++++++++++++++++++++++----
 fs/io-wq.h                    |   8 +
 fs/io_uring.c                 |  71 ++++++
 include/uapi/linux/io_uring.h |  11 +
 4 files changed, 501 insertions(+), 49 deletions(-)
Signature · 1 line
2.36.0