Re: [PATCH 1/1] mlock: split the shmlock_user_lock spinlock intoper user_struct spinlock

[Rik van Riel]

On 05/10/2012 11:39 AM, rajman mekaco wrote:
> On Thu, May 10, 2012 at 8:24 PM, Rik van Riel<riel@xxxxxxxxxx>  wrote:
> > On 05/10/2012 09:34 AM, rajman mekaco wrote:
> >
> > > Any updates on this ?
> >
> >
> > There is still no usecase to demonstrate a problem, so no real
> > justification to merge the patch.  Coming up with such a usecase
> > is up to the submitter of the patch.
>
> Maybe you didn't read my last email:
> If 2 different user-mode processes executing on 2 CPUs under 2 different
> users want to access the same shared memory through the
> shmctl(SHM_LOCK) / shmget(SHM_HUGETLB) / usr_shm_lock
> primitives, they could compete/spin even though their user_structs
> are different.
>
> Can you please correct me if I am missing some crucial point of understanding ?

Mlock is a very very expensive operation.

Updating the mlock statistics is a very cheap operation.

Does this spinlock ever show up contention wise?

--
All rights reversed
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/