Re: serial percpu_ref draining in exit_aio()

[Jens Axboe <axboe@kernel.dk>]

On 03/20/2015 12:56 PM, Jeff Moyer wrote:
> Jens Axboe <axboe@kernel.dk> writes:
>
>> On 03/19/2015 03:27 PM, Jens Axboe wrote:
>>> On 03/19/2015 03:00 PM, Tejun Heo wrote:
>>>> On Thu, Mar 19, 2015 at 04:58:33PM -0400, Jeff Moyer wrote:
>>>>> Do you really want to do memory allocation in the exit path?  That
>>>>> sounds like a bad idea to me.  (Of course, now you're going to point out
>>>>> all the places that currently happens, right?  ;-)
>>>>
>>>> I think we just need a counter there - let everyone count down as they
>>>> exit and the last one trigger the completion, no?
>>>
>>> Yeah that's a good point, that'd be cleaner too. I'll change it and test
>>> that.
>>
>> Here's a cleaner variant that pairs the completion even with an atomic
>> count. Works for me as well.
>
> I like this version.  I ran it though the libaio test harness and
> xfstests aio tests and it passed.
>
> Thanks, Jens!
>
> Reviewed-by: Jeff Moyer <jmoyer@redhat.com>

Thanks for testing, Jeff! I'll send out a proper patch with your 
reviewed-by as well.

-- 
Jens Axboe