From owner-freebsd-current@FreeBSD.ORG  Thu Sep  9 14:40:36 2004
Return-Path: <owner-freebsd-current@FreeBSD.ORG>
Delivered-To: freebsd-current@freebsd.org
Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125])
	by hub.freebsd.org (Postfix) with ESMTP
	id AC98616A4CE; Thu,  9 Sep 2004 14:40:36 +0000 (GMT)
Received: from exchange.sandvine.com (sandvine.com [199.243.201.138])
	by mx1.FreeBSD.org (Postfix) with ESMTP
	id 465BE43D45; Thu,  9 Sep 2004 14:40:36 +0000 (GMT)
	(envelope-from gnagelhout@sandvine.com)
content-class: urn:content-classes:message
MIME-Version: 1.0
Content-Type: text/plain;
	charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
X-MimeOLE: Produced By Microsoft Exchange V6.0.6556.0
Date: Thu, 9 Sep 2004 10:40:35 -0400
Message-ID: <A8535F8D62F3644997E91F4F66E341FC1F1CA7@exchange.sandvine.com>
X-MS-Has-Attach: 
X-MS-TNEF-Correlator: 
Thread-Topic: FreeBSD 5.3 Bridge performance take II
Thread-Index: AcSWMkxnjywMNrSUSCWEa9M2UyF0FAAR4KhQ
From: "Gerrit Nagelhout" <gnagelhout@sandvine.com>
To: "Robert Watson" <rwatson@freebsd.org>, <current@freebsd.org>
cc: scottl@freebsd.org
Subject: RE: FreeBSD 5.3 Bridge performance take II
X-BeenThere: freebsd-current@freebsd.org
X-Mailman-Version: 2.1.1
Precedence: list
List-Id: Discussions about the use of FreeBSD-current
	<freebsd-current.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-current>,
	<mailto:freebsd-current-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-current>
List-Post: <mailto:freebsd-current@freebsd.org>
List-Help: <mailto:freebsd-current-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-current>,
	<mailto:freebsd-current-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Thu, 09 Sep 2004 14:40:36 -0000

Robert Watson wrote:
>=20
> Right now, though, the greatest obstacle in my immediate path=20
> appears to
> be a bug in the current version of the if_em driver that causes the
> interfaces on my test box to wedge under even moderate load. =20
> The if_em
> cards I have on other machines seem not to do this, which suggests a
> driver weirdness with this particular version of the chipset/card.  Go
> figure...
>=20

You may want to check the version of the chipset on that card.  There =
are
definitely older em cards out there which require some special =
alignments
on the transmitter side to avoid hangs.  If I remember correctly, the=20
linux driver on the Intel web site has a workaround for this that is not
in the FreeBSD driver.  The problem is that the workaround for this=20
involves splitting mbufs if the alignment isn't correct, and this is =
quite
expensive.

Gerrit