Re: Improving spin-lock implementation on ARM.

On Thu, Dec 3, 2020 at 7:02 PM Tom Lane <tgl@sss.pgh.pa.us> wrote:
> From a system structural standpoint, I seriously dislike that lwlock.c
> patch: putting machine-specific variant implementations into that file
> seems like a disaster for maintainability.  So it would need to show a
> very significant gain across a range of hardware before I'd want to
> consider adopting it ... and it has not shown that.

The current shape of the lwlock patch is experimental.  I had quite a
beautiful (in my opinion) idea to wrap platform-dependent parts of
CAS-loops into macros.  Then we could provide different low-level
implementations of CAS-loops for Power, ARM and rest platforms with
single code for LWLockAttempLock() and others.  However, I see that
modern ARM tends to efficiently implement LSE.  Power doesn't seem to
be very popular.  So, I'm going to give up with this for now.

------
Regards,
Alexander Korotkov