Re: serial percpu_ref draining in exit_aio()

[Jeff Moyer <jmoyer@redhat.com>]

Jens Axboe <axboe@kernel.dk> writes:

> On 03/19/2015 11:34 AM, Tejun Heo wrote:
>> Hello,
>>
>> So, Jens noticed that fio process exiting takes seconds when there are
>> multiple aio contexts and the culprit seems to be the serial
>> percpu_ref draining in exit_aio().  It's generally a bad idea to
>> expose RCU latencies to userland because they add up really quickly
>> and are unrelated to other performance parameters.  Can you guys
>> please at least update the code so that it waits for all percpu_refs
>> to drain at the same time rather than one after another?  That should
>> resolve the worst part of the problem.
>
> This works for me. Before:
>
> real	0m5.872s
> user	0m0.020s
> sys	0m0.040s
>
> after
>
> real	0m0.246s
> user	0m0.020s
> sys	0m0.040s
>
> It solves the exit_aio() issue, but if the app calls io_destroy(),
> then we are back to square one...

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?  ;-)

-Jeff