[prev in list] [next in list] [prev in thread] [next in thread] 

List:       linux-parisc
Subject:    Re: [PATCH v4 0/3] locking/rwsem: Rwsem rearchitecture part 0
From:       Will Deacon <will.deacon () arm ! com>
Date:       2019-02-18 14:58:20
Message-ID: 20190218145820.GA16091 () fuggles ! cambridge ! arm ! com
[Download RAW message or body]

On Fri, Feb 15, 2019 at 01:58:34PM -0500, Waiman Long wrote:
> On 02/15/2019 01:40 PM, Will Deacon wrote:
> > On Thu, Feb 14, 2019 at 11:37:15AM +0100, Peter Zijlstra wrote:
> >> On Wed, Feb 13, 2019 at 05:00:14PM -0500, Waiman Long wrote:
> >>> v4:
> >>>  - Remove rwsem-spinlock.c and make all archs use rwsem-xadd.c.
> >>>
> >>> v3:
> >>>  - Optimize __down_read_trylock() for the uncontended case as suggested
> >>>    by Linus.
> >>>
> >>> v2:
> >>>  - Add patch 2 to optimize __down_read_trylock() as suggested by PeterZ.
> >>>  - Update performance test data in patch 1.
> >>>
> >>> The goal of this patchset is to remove the architecture specific files
> >>> for rwsem-xadd to make it easer to add enhancements in the later rwsem
> >>> patches. It also removes the legacy rwsem-spinlock.c file and make all
> >>> the architectures use one single implementation of rwsem - rwsem-xadd.c.
> >>>
> >>> Waiman Long (3):
> >>>   locking/rwsem: Remove arch specific rwsem files
> >>>   locking/rwsem: Remove rwsem-spinlock.c & use rwsem-xadd.c for all
> >>>     archs
> >>>   locking/rwsem: Optimize down_read_trylock()
> >> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> >>
> >> with the caveat that I'm happy to exchange patch 3 back to my earlier
> >> suggestion in case Will expesses concerns wrt the ARM64 performance of
> >> Linus' suggestion.
> > Right, the current proposal doesn't work well for us, unfortunately. Which
> > was your earlier suggestion?
> >
> > Will
> 
> In my posting yesterday, I showed that most of the trylocks done were
> actually uncontended. Assuming that pattern hold for the most of the
> workloads, it will not that bad after all.

That's fair enough; if you're going to sit in a tight trylock() loop like the
benchmark does, then you're much better off just calling lock() if you care
at all about scalability.

Will
[prev in list] [next in list] [prev in thread] [next in thread]