Re: [LKP] Re: [perf/x86] 81ec3f3c4c: will-it-scale.per_process_ops -5.5% regression

[Huang\, Ying]

Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> writes:

> On Sun, Feb 23, 2020 at 4:33 PM Feng Tang <feng.tang@xxxxxxxxx> wrote:
>>
>> From the perf c2c data, and the source code checking, the conflicts
>> only happens for root_user.__count, and root_user.sigpending, as
>> all running tasks are accessing this global data for get/put and
>> other operations.
>
> That's odd.
>
> Why? Because those two would be guaranteed to be in the same cacheline
> _after_ you've aligned that user_struct.
>
> So if it were a false sharing issue between those two, it would
> actually get _worse_ with alignment. Those two fields are basically
> next to each other.
>
> But maybe it was straddling a cacheline before, and it caused two
> cache accesses each time?
>
> I find this as confusing as you do.
>
> If it's sigpending vs the __refcount, then we almost always change
> them together. sigpending gets incremented by __sigqueue_alloc() -
> which also does a "get_uid()", and then we decrement it in
> __sigqueue_free() - which also does a "free_uid().
>

One way to verify this is to change the layout of user_struct (or
root_user) to make __count and sigpending fields to be in 2 separate
cache lines explicitly.

Best Regards,
Huang, Ying