From owner-freebsd-net@FreeBSD.ORG Tue Aug 16 09:50:29 2011 Return-Path: Delivered-To: net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id B151B106566C for ; Tue, 16 Aug 2011 09:50:29 +0000 (UTC) (envelope-from dudu@dudu.ro) Received: from mail-bw0-f54.google.com (mail-bw0-f54.google.com [209.85.214.54]) by mx1.freebsd.org (Postfix) with ESMTP id 41EB18FC18 for ; Tue, 16 Aug 2011 09:50:28 +0000 (UTC) Received: by bkat8 with SMTP id t8so4658815bka.13 for ; Tue, 16 Aug 2011 02:50:28 -0700 (PDT) Received: by 10.205.65.76 with SMTP id xl12mr801212bkb.402.1313488227195; Tue, 16 Aug 2011 02:50:27 -0700 (PDT) Received: from [192.168.10.3] ([82.76.253.74]) by mx.google.com with ESMTPS id a22sm1831378bke.20.2011.08.16.02.50.24 (version=TLSv1/SSLv3 cipher=OTHER); Tue, 16 Aug 2011 02:50:26 -0700 (PDT) Mime-Version: 1.0 (Apple Message framework v1244.3) Content-Type: text/plain; charset=us-ascii From: Vlad Galu In-Reply-To: Date: Tue, 16 Aug 2011 11:50:21 +0200 Content-Transfer-Encoding: quoted-printable Message-Id: <2AB05A3E-BDC3-427D-B4A7-ABDDFA98D194@dudu.ro> References: To: Takuya ASADA X-Mailer: Apple Mail (2.1244.3) Cc: net@freebsd.org Subject: Re: Multiqueue support for bpf X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 16 Aug 2011 09:50:29 -0000 On Aug 16, 2011, at 11:13 AM, Takuya ASADA wrote: > Hi all, >=20 > I implemented multiqueue support for bpf, I'd like to present for = review. > This is a Google Summer of Code project, the project goal is to > support multiqueue network interface on BPF, and provide interfaces > for multithreaded packet processing using BPF. > Modern high performance NICs have multiple receive/send queues and RSS > feature, this allows to process packet concurrently on multiple > processors. > Main purpose of the project is to support these hardware and get > benefit of parallelism. >=20 > This provides following new APIs: > - queue filter for each bpf descriptor (bpf ioctl) > - BIOCENAQMASK Enables multiqueue filter on the descriptor > - BIOCDISQMASK Disables multiqueue filter on the descriptor > - BIOCSTRXQMASK Set mask bit on specified RX queue > - BIOCCRRXQMASK Clear mask bit on specified RX queue > - BIOCGTRXQMASK Get mask bit on specified RX queue > - BIOCSTTXQMASK Set mask bit on specified TX queue > - BIOCCRTXQMASK Clear mask bit on specified TX queue > - BIOCGTTXQMASK Get mask bit on specified TX queue > - BIOCSTOTHERMASK Set mask bit for the packets which not tied > with any queues > - BIOCCROTHERMASK Clear mask bit for the packets which not tied > with any queues > - BIOCGTOTHERMASK Get mask bit for the packets which not tied > with any queues >=20 > - generic interface for getting hardware queue information from NIC > driver (socket ioctl) > - SIOCGIFQLEN Get interface RX/TX queue length > - SIOCGIFRXQAFFINITY Get interface RX queue affinity > - SIOCGIFTXQAFFINITY Get interface TX queue affinity >=20 > Patch for -CURRENT is here, right now it only supports igb(4), > ixgbe(4), mxge(4): > http://www.dokukino.com/mq_bpf_20110813.diff >=20 > And below is performance benchmark: >=20 > =3D=3D=3D=3D > I implemented benchmark programs based on > bpfnull(//depot/projects/zcopybpf/utils/bpfnull/), >=20 > test_sqbpf measures bpf throughput on one thread, without using = multiqueue APIs. > = http://p4db.freebsd.org/fileViewer.cgi?FSPC=3D//depot/projects/soc2011/mq_= bpf/src/tools/regression/bpf/mq_bpf/test_sqbpf/test_sqbpf.c >=20 > test_mqbpf is multithreaded version of test_sqbpf, using multiqueue = APIs. > = http://p4db.freebsd.org/fileViewer.cgi?FSPC=3D//depot/projects/soc2011/mq_= bpf/src/tools/regression/bpf/mq_bpf/test_mqbpf/test_mqbpf.c >=20 > I benchmarked with six conditions: > - benchmark1 only reads bpf, doesn't write packet anywhere > - benchmark2 writes packet on memory(mfs) > - benchmark3 writes packet on hdd(zfs) > - benchmark4 only reads bpf, doesn't write packet anywhere, with = zerocopy > - benchmark5 writes packet on memory(mfs), with zerocopy > - benchmark6 writes packet on hdd(zfs), with zerocopy >=20 >> =46rom benchmark result, I can say the performance is increased using > mq_bpf on 10GbE, but not on GbE. >=20 > * Throughput benchmark > - Test environment > - FreeBSD node > CPU: Core i7 X980 (12 threads) > MB: ASUS P6X58D Premium(Intel X58) > NIC1: Intel Gigabit ET Dual Port Server Adapter(82576) > NIC2: Intel Ethernet X520-DA2 Server Adapter(82599) > - Linux node > CPU: Core 2 Quad (4 threads) > MB: GIGABYTE GA-G33-DS3R(Intel G33) > NIC1: Intel Gigabit ET Dual Port Server Adapter(82576) > NIC2: Intel Ethernet X520-DA2 Server Adapter(82599) >=20 > iperf used for generate network traffic, with following argument = options > - Linux node: iperf -c [IP] -i 10 -t 100000 -P12 > - FreeBSD node: iperf -s > # 12 threads, TCP >=20 > following sysctl parameter is changed > sysctl -w net.bpf.maxbufsize=3D1048576 Thank you for your work! You may want to increase that (4x/8x) and rerun = the test, though.=