Date: Thu, 20 Apr 2017 10:13:26 -0700
From: Davidlohr Bueso <dave@stgolabs.net>
To: Peter Zijlstra <peterz@infradead.org>
Cc: mingo@kernel.org, akpm@linux-foundation.org, jack@suse.cz,
        kirill.shutemov@linux.intel.com, ldufour@linux.vnet.ibm.com,
        mhocko@suse.com, mgorman@techsingularity.net,
        linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2 -tip 0/6] locking: Introduce range reader/writer lock
Message-ID: <20170420171326.GD20746@linux-80c1.suse>
References: <20170406084620.22700-1-dave@stgolabs.net>
 <20170419123735.GB5730@worktop>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii; format=flowed
Content-Disposition: inline
In-Reply-To: <20170419123735.GB5730@worktop>
User-Agent: Mutt/1.5.24 (2015-08-30)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 788
Lines: 17

On Wed, 19 Apr 2017, Peter Zijlstra wrote:

>  - explain why the loss of lock stealing makes sense. IIRC walken added
>    that specifically to address mmap_sem performance issues.

That's right, and the same applies to the writer spinning stuff; which
can makes a huge difference - more so than plain stealing. But as I've
mentioned, range locks can improve parallelism, which is/should be much
more welcomed than optimizations to the primitive. So yeah, we loose 
in comparing a full range to rwsem (not to mention the xadd stuff).
I have thought of some heuristics for avoiding sleeping under certain
constraints, which could mitigate the spinning step we loose, but 
I fear it will never be exactly as fast as rwsems -- just consider
we always take the tree->lock.

Thanks,
Davidlohr