Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Wed, 1 Nov 2017 14:07:55 -0700
From:   Davidlohr Bueso <dave@stgolabs.net>
To:     Andrew Morton <akpm@linux-foundation.org>
Cc:     Jason Baron <jbaron@akamai.com>, linux-kernel@vger.kernel.org,
        Alexander Viro <viro@zeniv.linux.org.uk>,
        Salman Qazi <sqazi@google.com>, Hou Tao <houtao1@huawei.com>
Subject: Re: [PATCH] epoll: remove ep_call_nested() from ep_eventpoll_poll()
Message-ID: <20171101210755.yd5gerren4xosisz@linux-n805>
References: <1509430214-5599-1-git-send-email-jbaron@akamai.com>
 <20171031145821.ieflhlvs3la25vdw@linux-n805>
 <20171101135354.1ffec54e1fdedcca0f2086ce@linux-foundation.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii; format=flowed
Content-Disposition: inline
In-Reply-To: <20171101135354.1ffec54e1fdedcca0f2086ce@linux-foundation.org>
User-Agent: NeoMutt/20170421 (1.8.2)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Wed, 01 Nov 2017, Andrew Morton wrote:

>This is tempting, but boy it is late in the -rc cycle.
>
>How important are these workloads?  Would the world end if we held off
>on this for 4.15?

While it's very important to one customer, nested epoll is certainly not
the common case, and this performance bottleneck has been there for 7+
years, so no hurry in that regard.

I'd like to target for v4.16 some of the series of epoll patches out there
to (1) remove the remaining loop_ncalls list, and (2) remove the epmutex
global lock. So this patch would fit in fine there.

Now, could you please pick this patch up and just leave it in linux-next
for a while to get some more testing/exposure? I mainly ask because the
patch will most likely be running in production before this time.

Thanks,
Davidlohr

From 1582898605171832882@xxx Wed Nov 01 20:55:45 +0000 2017
X-GM-THRID: 1582752471322086730
X-Gmail-Labels: Inbox,Category Forums