Re: [PATCH 1/3] ipc: convert ipc_namespace.count from atomic_t to refcount_t

[Davidlohr Bueso]

On Wed, 19 Jul 2017, Andrew Morton wrote:

> On Wed, 19 Jul 2017 15:54:27 -0700 Davidlohr Bueso <dave@xxxxxxxxxxxx> wrote:
>
> > On Wed, 19 Jul 2017, Andrew Morton wrote:
> >
> > >I do rather dislike these conversions from the point of view of
> > >performance overhead and general code bloat.  But I seem to have lost
> > >that struggle and I don't think any of these are fastpath(?).
> >
> > Well, since we now have fd25d19 (locking/refcount: Create unchecked atomic_t
> > implementation), performance is supposed to be ok.
>
> Sure, things are OK for people who disable the feature.
>
> But for people who want to enable the feature we really should minimize
> the cost by avoiding blindly converting sites which simply don't need
> it: simple, safe, old, well-tested code.  Why go and slow down such
> code?  Need to apply some common sense here...

Fair points.

> > It would be lovely to have
> > some actual numbers nonetheless.
>
> Very much so.

May I suggest using mmtests with the following config file:

https://github.com/gormanm/mmtests/blob/7e070a810bc0af92e592e5121d0ea75fada51aeb/configs/config-global-dhp__workload-ipc-scale-short

It will run two of Manfred's ipcscale sem benchmarks.

Thanks,
Davidlohr