From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754164AbYHKViW (ORCPT ); Mon, 11 Aug 2008 17:38:22 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752009AbYHKViH (ORCPT ); Mon, 11 Aug 2008 17:38:07 -0400 Received: from sj-iport-6.cisco.com ([171.71.176.117]:21545 "EHLO sj-iport-6.cisco.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751933AbYHKViF (ORCPT ); Mon, 11 Aug 2008 17:38:05 -0400 X-IronPort-AV: E=Sophos;i="4.32,191,1217808000"; d="scan'208";a="138704905" From: Roland Dreier To: David Miller Cc: jgarzik@pobox.com, swise@opengridcomputing.com, divy@chelsio.com, kxie@chelsio.com, netdev@vger.kernel.org, open-iscsi@googlegroups.com, michaelc@cs.wisc.edu, daisyc@us.ibm.com, wenxiong@us.ibm.com, bhua@us.ibm.com, dm@chelsio.com, leedom@chelsio.com, linux-scsi@vger.kernel.org, linux-kernel@vger.kernel.org Subject: Re: [RFC][PATCH 1/1] cxgb3i: cxgb3 iSCSI initiator References: <20080809.224725.130946315.davem@davemloft.net> <20080811.140918.213422266.davem@davemloft.net> X-Message-Flag: Warning: May contain useful information Date: Mon, 11 Aug 2008 14:37:59 -0700 In-Reply-To: <20080811.140918.213422266.davem@davemloft.net> (David Miller's message of "Mon, 11 Aug 2008 14:09:18 -0700 (PDT)") Message-ID: User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/23.0.60 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-OriginalArrivalTime: 11 Aug 2008 21:38:00.0100 (UTC) FILETIME=[86BD2E40:01C8FBFA] Authentication-Results: sj-dkim-3; header.From=rdreier@cisco.com; dkim=pass ( sig from cisco.com/sjdkim3002 verified; ); Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org > But as Herbert says, we can make LRO such that turning it off > isn't necessary. > > Can we shape the iSCSI offload traffic without turning it off? Sure... the same way we can ask the HW vendors to keep old headers around when aggregating for LRO, we can ask HW vendors for hooks for shaping iSCSI traffic. And the Chelsio TCP speed record seems to show that they already have pretty sophisticated queueing/shaping in their current HW. - R.