From owner-freebsd-questions  Fri Jan  9 08:34:48 1998
Return-Path: <owner-freebsd-questions>
Received: (from root@localhost)
          by hub.freebsd.org (8.8.7/8.8.7) id IAA15821
          for questions-outgoing; Fri, 9 Jan 1998 08:34:48 -0800 (PST)
          (envelope-from owner-freebsd-questions)
Received: from mojo.calyx.net (mojo.calyx.net [208.132.136.2])
          by hub.freebsd.org (8.8.7/8.8.7) with SMTP id IAA15782
          for <questions@FreeBSD.ORG>; Fri, 9 Jan 1998 08:34:39 -0800 (PST)
          (envelope-from lists@mojo.calyx.net)
Message-Id: <199801091634.IAA15782@hub.freebsd.org>
Received: (qmail 16582 invoked from network); 9 Jan 1998 16:34:35 -0000
Received: from kwesi.calyx.net (208.132.136.100)
  by mojo.calyx.net with SMTP; 9 Jan 1998 16:34:35 -0000
X-Sender: lists@calyx.net
X-Mailer: QUALCOMM Windows Eudora Pro Version 4.0
Date: Fri, 09 Jan 1998 11:31:38 -0500
To: sperber@informatik.uni-tuebingen.de (Michael Sperber [Mr. Preprocessor])
From: Nicholas Merrill <lists@mojo.calyx.net>
Subject: Re: Networking problem: RPC: No buffer space available
Cc: questions@FreeBSD.ORG
In-Reply-To: <y9lyb0qeydw.fsf@modas.informatik.uni-tuebingen.de>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Sender: owner-freebsd-questions@FreeBSD.ORG
X-Loop: FreeBSD.org
Precedence: bulk

At 11:26 AM 1/9/98 +0100, you wrote:
>
>Hi there,
>
>I'm having severe network throughput problems on a 2.2.5 box with an
>NE2000 clone.  There's no excessive packet loss or anything else I can
>pinpoint it to.  However, there's one reproducible:
>
>lula[35] spray modas
>sending 1162 packets of lnth 86 to modas ...spray: RPC: Unable to send;
errno = No buffer space available
>
>Can anyone comment on this?

I've been getting the same thing on my box, a PPro 200mHz, 128MB 60ns RAM,
Buslogic 958, and the same error has been happening with two different cards,
the first an Accton dec 21040 based PCI card, and (to a lesser degree) with
an ISA
3c509.

I am also running 2.2.5.

Nick

ps- here are some samples for some reason (probably crappy syslog rules
more than anything) I have
more errors with named than anything else, but sometimes the TCP/IP on this
box seems to break, and
no connections to the net (even local net) are possible.

Jan  9 10:02:37 somebox named[27865]: sysquery: sendto([192.36.148.17].53):
No buffer space available
Jan  9 10:02:37 somebox named[27865]: ns_req: sendto([161.73.1.1].53): No
buffer space available
Jan  9 10:03:31 somebox named[27865]: ns_forw: sendto([193.63.94.20].53):
No buffer space available
Jan  9 10:03:36 somebox named[27865]: ns_forw: sendto([137.39.1.3].53): No
buffer space available