From mboxrd@z Thu Jan 1 00:00:00 1970 From: Brian King Subject: Re: [PATCH] mlx4_en: map entire pages to increase throughput Date: Tue, 17 Jul 2012 15:10:08 -0500 Message-ID: <5005C6A0.50002@linux.vnet.ibm.com> References: <1342458113-10384-1-git-send-email-cascardo@linux.vnet.ibm.com> <50044F1D.6000703@hp.com> <20120716.222903.367603216293954363.davem@davemloft.net> <5005AC4A.9030208@hp.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: David Miller , "cascardo@linux.vnet.ibm.com" , "netdev@vger.kernel.org" , "yevgenyp@mellanox.co.il" , "ogerlitz@mellanox.com" , "amirv@mellanox.com" , "leitao@linux.vnet.ibm.com" , "klebers@linux.vnet.ibm.com" To: Rick Jones Return-path: Received: from e34.co.us.ibm.com ([32.97.110.152]:57103 "EHLO e34.co.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754813Ab2GQUL0 (ORCPT ); Tue, 17 Jul 2012 16:11:26 -0400 Received: from /spool/local by e34.co.us.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Tue, 17 Jul 2012 14:11:25 -0600 Received: from d03relay03.boulder.ibm.com (d03relay03.boulder.ibm.com [9.17.195.228]) by d03dlp03.boulder.ibm.com (Postfix) with ESMTP id 2D95C19D8048 for ; Tue, 17 Jul 2012 20:10:23 +0000 (WET) Received: from d03av03.boulder.ibm.com (d03av03.boulder.ibm.com [9.17.195.169]) by d03relay03.boulder.ibm.com (8.13.8/8.13.8/NCO v10.0) with ESMTP id q6HKAD7Y276402 for ; Tue, 17 Jul 2012 14:10:14 -0600 Received: from d03av03.boulder.ibm.com (loopback [127.0.0.1]) by d03av03.boulder.ibm.com (8.14.4/8.13.1/NCO v10.0 AVout) with ESMTP id q6HKA9mB007564 for ; Tue, 17 Jul 2012 14:10:13 -0600 In-Reply-To: <5005AC4A.9030208@hp.com> Sender: netdev-owner@vger.kernel.org List-ID: On 07/17/2012 01:17 PM, Rick Jones wrote: > On 07/16/2012 10:29 PM, David Miller wrote: >> From: Rick Jones Date: Mon, 16 Jul 2012 >> 10:27:57 -0700 >> >>> That seems rather extraordinarily low - Power7 is supposed to be >>> a rather high performance CPU. The last time I noticed >>> O(3Gbit/s) on 10G for bulk transfer was before the advent of >>> LRO/GRO - that was in the x86 space though. Is mapping really >>> that expensive with Power7? >> >> Unfortunately, IOMMU mappings are incredibly expensive. I see >> effects like this on Sparc too. > > OK, so that has caused some dimm memory to get a small refresh - it > ends up being akin to if not actually a PIO yes? I recall schemes in > drivers in other stacks whereby "small" packets were copied because > it was cheaper to allocate/copy then it was to remap. On Power it ends up being an hcall to the hypervisor -Brian -- Brian King Power Linux I/O IBM Linux Technology Center