Re: [ISSUE] The time cost of IOSQE_IO_LINK

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

 



On 2/18/20 8:38 AM, Peter Zijlstra wrote:
> On Tue, Feb 18, 2020 at 04:07:45PM +0100, Oleg Nesterov wrote:
>> On 02/18, Oleg Nesterov wrote:
>>>
>>> otherwise I think this is correct, but how about the patch below?
>>> Then this code can be changed to use try_cmpxchg().
>>
>> You have already sent the patch which adds the generic try_cmpxchg,
>> so the patch below can be trivially adapted.
>>
>> But I'd prefer another change, I think both task_work_add() and
>> task_work_cancel() can use try_cmpxchg() too.
> 
> Yeah, I'll go change the lot, but maybe after Jens' patches, otherwise
> we're just creating merge conflicts.

Just caught up with this thread, great stuff! Don't worry about me, I'll
just rebase on top of the fixes and cleanups from you and Oleg. Or you
can apply my two first if you wish, doesn't really matter to me, as I'll
likely just pull in that branch anyway for the rest to sit on top of.
Just let me know.

-- 
Jens Axboe




[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