From owner-freebsd-net Mon Feb 18 14:11:13 2002 Delivered-To: freebsd-net@freebsd.org Received: from mdv.dhs.org (mdv.xs4all.nl [213.84.209.48]) by hub.freebsd.org (Postfix) with ESMTP id 85D5D37B402 for ; Mon, 18 Feb 2002 14:11:00 -0800 (PST) Received: (from root@localhost) by mdv.dhs.org (8.11.6/8.11.6) id g1IMAuj01778; Mon, 18 Feb 2002 23:10:56 +0100 (CET) (envelope-from mdevries@haveityourway.nl) Received: from marcel.haveityourway.nl (marcel.mdv.int [192.168.1.3]) by mdv.dhs.org (8.11.6/8.11.6av) with ESMTP id g1IMArh01771; Mon, 18 Feb 2002 23:10:53 +0100 (CET) (envelope-from mdevries@haveityourway.nl) Message-Id: <5.1.0.14.2.20020218231018.01f18948@outshine> X-Sender: mdevries@outshine X-Mailer: QUALCOMM Windows Eudora Version 5.1 Date: Mon, 18 Feb 2002 23:10:48 +0100 To: freebsd-net@freebsd.org From: Marcel de Vries Subject: Re: network buffer problem Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1"; format=flowed Content-Transfer-Encoding: quoted-printable X-Virus-Scanned: by AMaViS perl-11 Sender: owner-freebsd-net@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Thanks for the quick reply. But I want to come back first about the identical system a friend of my is= =20 using only with the xl driver for his public interface. But today he told me when pinging to a host like ping -s 4096 www.bart.nl=20 and meanwhile enjoying the sound from the digitally imported shoutcast=20 server, the 'no buffer space messages reappeared. So he has the same problem only using the xl driver=85 But he was also complaining about that the problem never occurred in=20 FreeBSD 4.4 or 4.3.. But some other info, we also had trouble with our connections. First of all we both used natd and ipfw also we connected our BSD boxes=20 with GIF. When playing games natd always ended up using a lot of proctime like top=20 indicated about 60 to 90%. The connection suffered from it and as result=20 packet loss 100% and no recovery at all, I had to restart mpd and stuff. So ok, what=92s wrong? With my experience I could not find any errors even= =20 when using natd in verbose mode. All I could see was lot=92s of translations= ;-) But trying ipnat what seemed to be more stable gave me more hope, but now=20 I=92m suffering from no buffer space available, so to problem persists and= at=20 the end we are still losing the connection and mass packet loss=85 I really want to make a point, is it third party software =91mpd-3.7=20 Multi-link PPP daemon based on netgraph(4)=92 that is causing this or is it= =20 something in the TCP/IP stack of BSD that is changed or the driver support. We had these problems in 4.3, 4.4 and still in 4.5. From using mpd 3.1 to 3.7 nothing changed about our problem. I think it=92s an important notice why this is happening, because what if=20 this is a real TCP/IP stack issue this would be very wrong and bad for= FreeBSD. But I=92m still no expert so I have to leave this open for the Pro BSD=20 users/developers. Bye, Marcel To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-net" in the body of the message