From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: txqueuelen has wrong units; should be time Date: Sun, 27 Feb 2011 21:07:53 +0100 Message-ID: <1298837273.8726.128.camel@edumazet-laptop> References: <1298793252.8726.45.camel@edumazet-laptop> <20110227125540.40754c5y78j9u2m8@hayate.sektori.org> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Albert Cahalan , Mikael Abrahamsson , linux-kernel , netdev@vger.kernel.org To: Jussi Kivilinna Return-path: In-Reply-To: <20110227125540.40754c5y78j9u2m8@hayate.sektori.org> Sender: linux-kernel-owner@vger.kernel.org List-Id: netdev.vger.kernel.org Le dimanche 27 f=C3=A9vrier 2011 =C3=A0 12:55 +0200, Jussi Kivilinna a = =C3=A9crit : > Quoting Albert Cahalan : >=20 > > On Sun, Feb 27, 2011 at 2:54 AM, Eric Dumazet wrote: > >> Le dimanche 27 f=C3=A9vrier 2011 =C3=A0 08:02 +0100, Mikael Abraha= msson a =C3=A9crit : > >>> On Sun, 27 Feb 2011, Albert Cahalan wrote: > >>> > >>> > Nanoseconds seems fine; it's unlikely you'd ever want > >>> > more than 4.2 seconds (32-bit unsigned) of queue. > > ... > >> Problem is some machines have slow High Resolution timing services= =2E > >> > >> _If_ we have a time limit, it will probably use the low resolution= (aka > >> jiffies), unless high resolution services are cheap. > > > > As long as that is totally internal to the kernel and never > > getting exposed by some API for setting the amount, sure. > > > >> I was thinking not having an absolute hard limit, but an EWMA base= d one. > > > > The whole point is to prevent stale packets, especially to prevent > > them from messing with TCP, so I really don't think so. I suppose > > you do get this to some extent via early drop. >=20 > I made simple hack on sch_fifo with per packet time limits =20 > (attachment) this weekend and have been doing limited testing on =20 > wireless link. I think hardlimit is fine, it's simple and does =20 > somewhat same as what packet(-hard)limited buffer does, drops packets= =20 > when buffer is 'full'. My hack checks for timed out packets on =20 > enqueue, might be wrong approach (on other hand might allow some more= =20 > burstiness). >=20 Qdisc should return to caller a good indication packet is queued or dropped at enqueue() time... not later (aka : never) Accepting a packet at t0, and dropping it later at t0+limit without giving any indication to caller is a problem. This is why I suggested using an EWMA plus a probabilist drop or congestion indication (NET_XMIT_CN) to caller at enqueue() time. The absolute time limit you are trying to implement should be checked a= t dequeue time, to cope with enqueue bursts or pauses on wire.