From owner-freebsd-current  Tue Oct 13 01:08:36 1998
Return-Path: <owner-freebsd-current@FreeBSD.ORG>
Received: (from majordom@localhost)
          by hub.freebsd.org (8.8.8/8.8.8) id BAA18102
          for freebsd-current-outgoing; Tue, 13 Oct 1998 01:08:36 -0700 (PDT)
          (envelope-from owner-freebsd-current@FreeBSD.ORG)
Received: from widefw.csl.sony.co.jp (widefw.csl.sony.co.jp [133.138.1.1])
          by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id BAA18092
          for <current@FreeBSD.ORG>; Tue, 13 Oct 1998 01:08:22 -0700 (PDT)
          (envelope-from kjc@csl.sony.co.jp)
Received: from hotaka.csl.sony.co.jp (root@hotaka.csl.sony.co.jp [43.27.98.57])
	by widefw.csl.sony.co.jp (8.8.8/3.6W) with ESMTP id RAA08973;
	Tue, 13 Oct 1998 17:07:54 +0900 (JST)
Received: from localhost (kjc@[127.0.0.1])
	by hotaka.csl.sony.co.jp (8.8.8/3.6W/hotaka/98021914) with ESMTP id RAA11582;
	Tue, 13 Oct 1998 17:07:53 +0900 (JST)
Message-Id: <199810130807.RAA11582@hotaka.csl.sony.co.jp>
To: Bruce Evans <bde@zeta.org.au>
cc: brian@Awfulhak.org, current@FreeBSD.ORG
Subject: Re: Improper sharing of modem bandwidth 
In-reply-to: Your message of "Tue, 13 Oct 1998 15:41:01 +1000."
             <199810130541.PAA12787@godzilla.zeta.org.au> 
Date: Tue, 13 Oct 1998 17:07:52 +0900
From: Kenjiro Cho <kjc@csl.sony.co.jp>
Sender: owner-freebsd-current@FreeBSD.ORG
Precedence: bulk
X-Loop: FreeBSD.ORG


Bruce Evans <bde@zeta.org.au> said:

  > Surely, once the packet queueing delay is reduced, we need to reduce
  > the tty delay.   The current kernel doesn't have ioctls for the
  > buffer size but slip uses a smaller tty buffer and has a better
  > response time than ppp.

>> User ppp is behind a _lot_ of output buffering, including (at speeds >=
>> 57600 Kbps) a 4KB tty buffer (up from 2KB in FreeBSD-2.2).  Perhaps the
>> increase from 2KB to 4KB is especially significant when the MTU is 1500.

Hmmm, when I tried, user ppp on a 200MHz PentiumPro apparently had no
problem filling up 2x 57600bps with small (~100) output buffers.

However, I monitored the throughput inside the ppp program and didn't
directly observe the kernel buffers.

--Kenjiro

To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-current" in the body of the message