From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1753449AbbGNVYf (ORCPT <rfc822;w@1wt.eu>);
	Tue, 14 Jul 2015 17:24:35 -0400
Received: from mx1.redhat.com ([209.132.183.28]:50241 "EHLO mx1.redhat.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1752765AbbGNVYc (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
	Tue, 14 Jul 2015 17:24:32 -0400
Date: Tue, 14 Jul 2015 23:22:49 +0200
From: Oleg Nesterov <oleg@redhat.com>
To: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Jan Kara <jack@suse.cz>, Al Viro <viro@zeniv.linux.org.uk>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Paul McKenney <paulmck@linux.vnet.ibm.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Daniel Wagner <daniel.wagner@bmw-carit.de>,
        Davidlohr Bueso <dave@stgolabs.net>, Ingo Molnar <mingo@redhat.com>,
        Tejun Heo <tj@kernel.org>, linux-kernel@vger.kernel.org
Subject: Re: [PATCH RFC 0/4] change sb_writers to use percpu_rw_semaphore
Message-ID: <20150714212249.GA18441@redhat.com>
References: <20150713212536.GA13855@redhat.com> <20150714104810.GB24369@quack.suse.cz> <20150714133731.GA24837@redhat.com> <55A57C50.1080406@linux.intel.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <55A57C50.1080406@linux.intel.com>
User-Agent: Mutt/1.5.18 (2008-05-17)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On 07/14, Dave Hansen wrote:
>
> On 07/14/2015 06:37 AM, Oleg Nesterov wrote:
> > On 07/14, Jan Kara wrote:
> >> So unless
> >> I'm missing something and there is a significant performance advantage to
> >> Dave's patches I'm all for using a generic primitive you suggest.
> >
> > I think percpu_rw_semaphore looks a bit better. And even a bit faster.
> > And it will not block __sb_start_write() entirely while freeze_super()
> > sleeps in synchronize_rcu().
>
> That's true, but freeze_super() and the code blocked by it is a
> super-rare path compared with write().

Yes, agreed, this is not that important too.

> > freeze_super() should be faster too after rcu_sync changes, but this
> > is not that important.
> >
> > But again, to me the main advantage is that we can use the generic
> > primitives and remove this nontrivial code in fs/super.c.
> >
> >> Can you perhaps work with Dave on some common resolution?
> >
> > Dave, what do you think? Will you agree with percpu_rw_semaphore ?
>
> Using my little write-1-byte test (under will-it-scale), your 4 patches
> improves the number of writes/sec by 12%.  My 3 patches improve the
> number of writes/sec by 32%.

Thanks... I'll try to understand.

Just in case, could you send me (offlist) these 3 patches?

> My patches manage to get rid of the memory barriers entirely in the fast
> path.  Your approach keeps the barriers.

Where? No, they do not keep the barriers.

Oleg.