Re: [PATCH v3] io_uring: switch cancel_hash to use per entry spinlock

[Pavel Begunkov <asml.silence@gmail.com>]

On 6/8/22 12:12, Hao Xu wrote:
> From: Hao Xu <howeyxu@tencent.com>
> 
> Add a new io_hash_bucket structure so that each bucket in cancel_hash
> has separate spinlock. Use per entry lock for cancel_hash, this removes
> some completion lock invocation and remove contension between different
> cancel_hash entries.

Thanks for making the changes, the big picture looks good,
I'll review in a day or two


> Signed-off-by: Hao Xu <howeyxu@tencent.com>
> ---
> 
> v1->v2:
>   - Add per entry lock for poll/apoll task work code which was missed
>     in v1
>   - add an member in io_kiocb to track req's indice in cancel_hash
> 
> v2->v3:
>   - make struct io_hash_bucket align with cacheline to avoid cacheline
>     false sharing.
>   - re-calculate hash value when deleting an entry from cancel_hash.
>     (cannot leverage struct io_poll to store the indice since it's
>      already 64 Bytes)
> 
>   io_uring/cancel.c         | 14 +++++++--
>   io_uring/cancel.h         |  6 ++++
>   io_uring/fdinfo.c         |  9 ++++--
>   io_uring/io_uring.c       |  8 +++--
>   io_uring/io_uring_types.h |  2 +-
>   io_uring/poll.c           | 64 +++++++++++++++++++++------------------
>   6 files changed, 65 insertions(+), 38 deletions(-)

-- 
Pavel Begunkov