From owner-freebsd-hackers  Thu Jun 29 19:16:46 1995
Return-Path: hackers-owner
Received: (from majordom@localhost)
          by freefall.cdrom.com (8.6.10/8.6.6) id TAA15677
          for hackers-outgoing; Thu, 29 Jun 1995 19:16:46 -0700
Received: from godzilla.zeta.org.au (godzilla.zeta.org.au [203.2.228.34])
          by freefall.cdrom.com (8.6.10/8.6.6) with ESMTP id TAA15666
          for <hackers@freebsd.org>; Thu, 29 Jun 1995 19:16:26 -0700
Received: (from bde@localhost) by godzilla.zeta.org.au (8.6.9/8.6.9) id MAA21320; Fri, 30 Jun 1995 12:08:43 +1000
Date: Fri, 30 Jun 1995 12:08:43 +1000
From: Bruce Evans <bde@zeta.org.au>
Message-Id: <199506300208.MAA21320@godzilla.zeta.org.au>
To: hackers@freebsd.org, mnewell@lupine.nsi.nasa.gov
Subject: Re: pppd eating CPU time
Sender: hackers-owner@freebsd.org
Precedence: bulk

>When I connect to it from another host (we're using both SunOS 4.1.3 and 
>FreeBSD 1.1.5.1 as PPP clients) everything looks normal.  However, as 
>soon as we ping an interface to verify that it is up the corresponding 
>ppp daemon starts using up all available CPU time.  If we have two ppp 
>daemons running, they split the time between them.  Everything works 
>correctly (albiet commands issued on the server run REAL slowly), but 
>there's 0% idle time.  This occurs wether or not there's data crossing 
>the link.

Do you mean ppp?  It uses all the available CPU time when output is
active.

Bruce