Re: [PATCH 3/3] io_uring: don't spinlock when not posting CQEs

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On 9/12/21 7:14 PM, Hao Xu wrote:
> 在 2021/9/12 上午5:10, Pavel Begunkov 写道:
>> On 9/11/21 9:12 PM, Hao Xu wrote:
>>> 在 2021/9/11 下午9:52, Pavel Begunkov 写道:
>>>> When no of queued for the batch completion requests need to post an CQE,
>>>> see IOSQE_CQE_SKIP_SUCCESS, avoid grabbing ->completion_lock and other
>>>> commit/post.
>>
>> It does what it says -- skips CQE posting on success. On failure it'd
>> still generate a completion. I was thinking about IOSQE_SKIP_CQE, but
>> I think it may be confusing.
> I think IOSQE_CQE_SKIP_SUCCESS is clear..but we should do
> req->flags & REQ_F_CQE_SKIP, rather than req->flags & IOSQE_CQE_SKIP_SUCCESS

Surely we should, thanks for looking. I also think I need to add a few
lines on why IOSQE_CQE_SKIP_SUCCESS turns into just REQ_F_CQE_SKIP

-- 
Pavel Begunkov



[Index of Archives]     [Linux Samsung SoC]     [Linux Rockchip SoC]     [Linux Actions SoC]     [Linux for Synopsys ARC Processors]     [Linux NFS]     [Linux NILFS]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]


  Powered by Linux