Date: Tue, 13 Jun 2017 13:32:25 +0300
From: Cyrill Gorcunov <gorcunov@gmail.com>
To: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: avagin@openvz.org, linux-kernel@vger.kernel.org, bcrl@kvack.org,
        viro@zeniv.linux.org.uk, akpm@linux-foundation.org,
        xemul@virtuozzo.com
Subject: Re: [PATCH] aio: Add command to wait completion of all requests
Message-ID: <20170613103225.GB23987@uranus.lan>
References: <149700173837.15252.8419518498235874341.stgit@localhost.localdomain>
 <20170613081412.GA23987@uranus.lan>
 <9d133393-1ea7-c370-24b0-7bb565428b7e@virtuozzo.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <9d133393-1ea7-c370-24b0-7bb565428b7e@virtuozzo.com>
User-Agent: Mutt/1.8.0 (2017-02-23)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 673
Lines: 14

On Tue, Jun 13, 2017 at 12:45:39PM +0300, Kirill Tkhai wrote:
> > 
> > I'm not that familiar with AIO internals but this snippet worries me:
> > the reqs_available is unsigned int, reqs is unsigned it as well but
> > used as an accumulator over ALL cpus, can't it get overflow and
> > gives modulo result, should not it be unsigned long or something?
> 
> All available reqs are initially contain in kioctx::reqs_available,
> which is atomic_t, and then they are distributed over percpu counters.
> So, this is OK.

Thanks for explanation! Looks ok to me. But I'm far from being
aio expert, if someone else won't beat me I'll take a closer
look in [a day|couple of] or so.