From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751756AbcGRQf0 (ORCPT ); Mon, 18 Jul 2016 12:35:26 -0400 Received: from mail-it0-f67.google.com ([209.85.214.67]:33779 "EHLO mail-it0-f67.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751676AbcGRQfL (ORCPT ); Mon, 18 Jul 2016 12:35:11 -0400 MIME-Version: 1.0 In-Reply-To: <37D7C6CF3E00A74B8858931C1DB2F07712C1968E@SHSMSX103.ccr.corp.intel.com> References: <1468824984-65318-1-git-send-email-kan.liang@intel.com> <20160718151841.GA19066@breakpoint.cc> <37D7C6CF3E00A74B8858931C1DB2F07712C1968E@SHSMSX103.ccr.corp.intel.com> From: Tom Herbert Date: Mon, 18 Jul 2016 18:34:52 +0200 Message-ID: Subject: Re: [RFC PATCH 00/30] Kernel NET policy To: "Liang, Kan" Cc: Florian Westphal , "davem@davemloft.net" , "linux-kernel@vger.kernel.org" , "intel-wired-lan@lists.osuosl.org" , "netdev@vger.kernel.org" , "Kirsher, Jeffrey T" , "mingo@redhat.com" , "peterz@infradead.org" , "kuznet@ms2.inr.ac.ru" , "jmorris@namei.org" , "yoshfuji@linux-ipv6.org" , "kaber@trash.net" , "akpm@linux-foundation.org" , "keescook@chromium.org" , "viro@zeniv.linux.org.uk" , "gorcunov@openvz.org" , "john.stultz@linaro.org" , "aduyck@mirantis.com" , "ben@decadent.org.uk" , "decot@googlers.com" , "Brandeburg, Jesse" , "andi@firstfloor.org" Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Jul 18, 2016 at 5:51 PM, Liang, Kan wrote: > > >> > >> > It is a big challenge to get good network performance. First, the >> > network performance is not good with default system settings. Second, >> > it is too difficult to do automatic tuning for all possible workloads, >> > since workloads have different requirements. Some workloads may want >> high throughput. >> >> Seems you did lots of tests to find optimal settings for a given base policy. >> > Yes. Current test only base on Intel i40e driver. The optimal settings should > vary for other devices. But adding settings for new device is not hard. > The optimal settings are very dependent on system architecture (NUMA config, #cpus, memory, etc.) and sometimes kernel version as well. A database that provides best configurations across different devices, architectures, and kernel version might be interesting; but beware that that is a whole bunch of work to maintain, Either way policy like this really should be handled in userspace. Tom