From owner-freebsd-net@FreeBSD.ORG Fri Sep 26 01:58:54 2003 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 1E03B16A4B3 for ; Fri, 26 Sep 2003 01:58:54 -0700 (PDT) Received: from netlx010.civ.utwente.nl (netlx010.civ.utwente.nl [130.89.1.92]) by mx1.FreeBSD.org (Postfix) with ESMTP id B42CF44022 for ; Fri, 26 Sep 2003 01:58:52 -0700 (PDT) (envelope-from r.s.a.vandomburg@student.utwente.nl) Received: from gog (gog.student.utwente.nl [130.89.165.107]) by netlx010.civ.utwente.nl (8.11.4/HKD) with SMTP id h8Q8wox13320 for ; Fri, 26 Sep 2003 10:58:50 +0200 Message-ID: <000501c3840c$6da6ae60$6ba55982@gog> From: "Roderick van Domburg" To: Date: Fri, 26 Sep 2003 10:59:00 +0200 Organization: University of Twente MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.3790.0 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.3790.0 X-UTwente-MailScanner-Information: Scanned by MailScanner. Contact helpdesk@ITBE.utwente.nl for more information. X-UTwente-MailScanner: Found to be clean Subject: DEVICE_POLLING together with link0 interrupt offloading? X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 26 Sep 2003 08:58:54 -0000 Hello everyone, Just curious: I just noticed that DEVICE_POLLING works perfectly well with the interrupt offloading feature of the fxp driver (link0). In my understanding, both try to improve ``network scheduling'' for lack of better words - especially under load. Also I now understand that DEVICE_POLLING is preferred over interrupt offloading, especially on routers. But just for the sake of curiosity: what does enabling _both_ bring about to the network performancy and latency? I'm thinking that latency would be greatly increased because the poller would often miss the bundled packets. What's your take on this? Regards, Roderick