From mboxrd@z Thu Jan  1 00:00:00 1970
From: "John W. Linville" <linville@tuxdriver.com>
Subject: Re: txqueuelen has wrong units; should be time
Date: Mon, 28 Feb 2011 11:55:01 -0500
Message-ID: <20110228165501.GC2515@tuxdriver.com>
References: <AANLkTimd5GQwtUFP2fD_An=M8ajBD8DJpzxQJezv8fB8@mail.gmail.com>
 <alpine.DEB.1.10.1102270758580.11974@uplift.swm.pp.se>
 <1298793252.8726.45.camel@edumazet-laptop>
 <AANLkTinyE10wtM_xJsufT_3s3hvti7CN+9nyqScWa6SA@mail.gmail.com>
 <20110227125540.40754c5y78j9u2m8@hayate.sektori.org>
 <1298837273.8726.128.camel@edumazet-laptop>
 <20110228161115.GB2515@tuxdriver.com>
 <1298911694.2941.639.camel@edumazet-laptop>
Mime-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Transfer-Encoding: QUOTED-PRINTABLE
Cc: Jussi Kivilinna <jussi.kivilinna@mbnet.fi>,
	Albert Cahalan <acahalan@gmail.com>,
	Mikael Abrahamsson <swmike@swm.pp.se>,
	linux-kernel <linux-kernel@vger.kernel.org>,
	netdev@vger.kernel.org
To: Eric Dumazet <eric.dumazet@gmail.com>
Return-path: <linux-kernel-owner@vger.kernel.org>
Content-Disposition: inline
In-Reply-To: <1298911694.2941.639.camel@edumazet-laptop>
Sender: linux-kernel-owner@vger.kernel.org
List-Id: netdev.vger.kernel.org

On Mon, Feb 28, 2011 at 05:48:14PM +0100, Eric Dumazet wrote:
> Le lundi 28 f=E9vrier 2011 =E0 11:11 -0500, John W. Linville a =E9cri=
t :
> > On Sun, Feb 27, 2011 at 09:07:53PM +0100, Eric Dumazet wrote:
> >=20
> > > Qdisc should return to caller a good indication packet is queued =
or
> > > dropped at enqueue() time... not later (aka : never)
> > >=20
> > > Accepting a packet at t0, and dropping it later at t0+limit witho=
ut
> > > giving any indication to caller is a problem.
> >=20
> > Can you elaborate on what problem this causes?  Is it any worse tha=
n
> > if the packet is dropped at some later hop?
> >=20
> > Is there any API that could report the drop to the sender (at
> > least a local one) without having to wait for the ack timeout?
> > Should there be?
> >=20
>=20
> Not all protocols have ACKS ;)
>=20
> dev_queue_xmit() returns an error code, some callers use it.

Well, OK -- I agree it is best if you can return the status at
enqueue time.  The question becomes whether or not a dropped frame
is worse than living with high latency.  The answer, of course, still
seems to be a bit subjective.  But, if the admin has determined that
a link should be low latency...?

John
--=20
John W. Linville		Someday the world will need a hero, and you
linville@tuxdriver.com			might be all we have.  Be ready.