From owner-freebsd-current  Thu Dec  4 17:50:46 1997
Return-Path: <owner-freebsd-current>
Received: (from root@localhost)
          by hub.freebsd.org (8.8.7/8.8.7) id RAA25523
          for current-outgoing; Thu, 4 Dec 1997 17:50:46 -0800 (PST)
          (envelope-from owner-freebsd-current)
Received: from alpo.whistle.com (alpo.whistle.com [207.76.204.38])
          by hub.freebsd.org (8.8.7/8.8.7) with ESMTP id RAA25491;
          Thu, 4 Dec 1997 17:50:32 -0800 (PST)
          (envelope-from julian@whistle.com)
Received: (from daemon@localhost)
	by alpo.whistle.com (8.8.5/8.8.5) id RAA06578;
	Thu, 4 Dec 1997 17:48:29 -0800 (PST)
Received: from UNKNOWN(), claiming to be "current1.whistle.com"
 via SMTP by alpo.whistle.com, id smtpd006574; Thu Dec  4 17:48:19 1997
Message-ID: <34875CD4.7566F4CF@whistle.com>
Date: Thu, 04 Dec 1997 17:45:56 -0800
From: Julian Elischer <julian@whistle.com>
Organization: Whistle Communications
X-Mailer: Mozilla 3.0Gold (X11; I; FreeBSD 2.2-CURRENT i386)
MIME-Version: 1.0
To: Poul-Henning Kamp <phk@freebsd.org>
CC: current@freebsd.org
Subject: Re: weird current behaviour...
References: <8106.881230997@critter.freebsd.dk>
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Sender: owner-freebsd-current@freebsd.org
X-Loop: FreeBSD.org
Precedence: bulk

All the fast ones only have interrupt context processing.
the slow ones have a userland context. (the ping process)
The rc456 programs are finishing up their quantum before allowing the 
ping to run and recieve the response.

This is possibly because they have a higher priority than
the ping becsause the idlprio stuff doesn't really update or change the 
priority..



Poul-Henning Kamp wrote:
> 
> Network:
> 
>         machine-A  en0 ------------ en0 machine-B
>          de0  fxp0
>           |     \
>           |      ----------------- de0 machine-C
>           |
>          hub ----- machine-D
>           |
>           |
>          ed0
>         machine-E
> 
> These two cases:
> 
> 1. ping from A to E
> 2. ping from A to D
> 
> I see the round-trip time flutter from 9msec to 70 msec...
> 
> Every other path the round-trip time is OK, including confusingly
> enough:
> 
>         from E to A
>         from D to A
>         from B&C to E
>         from B&C to D
> 
> What gives ?
> 
> Is the if_de driver broken somehow ?
> 
> Does anybody else see this ?
> 
> Machine-A is a PR440FX motherboard with 2xP6/233 running current-SMP.
> 
> I have tried two different de0 cards and both does this.
> 
> --
> Poul-Henning Kamp             FreeBSD coreteam member
> phk@FreeBSD.ORG               "Real hackers run -current on their laptop."