Open-source routing at 10Gb/s Olof Hagsand (KTH) Robert Olsson (Uppsala U) Bengt Görden (KTH) SNCNW May 2009 Project grants: Internetstiftelsen (IIS) Equipment:

Slides:



Advertisements
Similar presentations
IP Router Architectures. Outline Basic IP Router Functionalities IP Router Architectures.
Advertisements

Open Source Routing Experinces at Uppsala University Robert Olsson Hans Wassen Emil Pedersen Uppsala Universitet
NetFPGA Project: 4-Port Layer 2/3 Switch Ankur Singla Gene Juknevicius
1 Version 3 Module 8 Ethernet Switching. 2 Version 3 Ethernet Switching Ethernet is a shared media –One node can transmit data at a time More nodes increases.
Efficient IP-Address Lookup with a Shared Forwarding Table for Multiple Virtual Routers Author: Jing Fu, Jennifer Rexford Publisher: ACM CoNEXT 2008 Presenter:
EE 122: Router Design Kevin Lai September 25, 2002.
Router Architectures An overview of router architectures.
Router Architectures An overview of router architectures.
Computer Networks Switching Professor Hui Zhang
IETF 90: VNF PERFORMANCE BENCHMARKING METHODOLOGY Contributors: Sarah Muhammad Durrani: Mike Chen:
Sven Ubik, Petr Žejdl CESNET TNC2008, Brugges, 19 May 2008 Passive monitoring of 10 Gb/s lines with PC hardware.
Networking Virtualization Using FPGAs Russell Tessier, Deepak Unnikrishnan, Dong Yin, and Lixin Gao Reconfigurable Computing Group Department of Electrical.
Performance Tradeoffs for Static Allocation of Zero-Copy Buffers Pål Halvorsen, Espen Jorde, Karl-André Skevik, Vera Goebel, and Thomas Plagemann Institute.
Jon Turner (and a cast of thousands) Washington University Design of a High Performance Active Router Active Nets PI Meeting - 12/01.
LOGO BUS SYSTEM Members: Bui Thi Diep Nguyen Thi Ngoc Mai Vu Thi Thuy Class: 1c06.
A TCP/IP transport layer for the DAQ of the CMS Experiment Miklos Kozlovszky for the CMS TriDAS collaboration CERN European Organization for Nuclear Research.
MIDeA :A Multi-Parallel Instrusion Detection Architecture Author: Giorgos Vasiliadis, Michalis Polychronakis,Sotiris Ioannidis Publisher: CCS’11, October.
A 50-Gb/s IP Router 참고논문 : Craig Partridge et al. [ IEEE/ACM ToN, June 1998 ]
Switches 1RD-CSY  In this lecture, we will learn about  Collision Domain and Microsegmentation  Switches – a layer two device ◦ MAC address.
On the processing time for detection of Skype traffic P.M. Santiago del Río, J. Ramos, J.L. García-Dorado, J. Aracil Universidad Autónoma de Madrid A.
A Measurement Based Memory Performance Evaluation of High Throughput Servers Garba Isa Yau Department of Computer Engineering King Fahd University of Petroleum.
Network Architecture for the LHCb DAQ Upgrade Guoming Liu CERN, Switzerland Upgrade DAQ Miniworkshop May 27, 2013.
Switches 1RD-CSY  In this lecture, we will learn about  Collision Domain and Microsegmentation  Switches – a layer two device ◦ MAC address.
CS 4396 Computer Networks Lab Router Architectures.
Efficient Cache Structures of IP Routers to Provide Policy-Based Services Graduate School of Engineering Osaka City University
Networking Devices.
Yaping Zhu with: Jennifer Rexford (Princeton University) Aman Shaikh and Subhabrata Sen (ATT Research) Route Oracle: Where Have.
1 © 2004, Cisco Systems, Inc. All rights reserved. CCNA 2 v3.1 Module 9 Basic Router Troubleshooting.
Spring 2000CS 4611 Router Construction Outline Switched Fabrics IP Routers Extensible (Active) Routers.
L1/HLT trigger farm Bologna setup 0 By Gianluca Peco INFN Bologna Genève,
Recent experience with PCI-X 2.0 and PCI-E network interfaces and emerging server systems Yang Xia Caltech US LHC Network Working Group October 23, 2006.
Network layer (addendum) Slides adapted from material by Nick McKeown and Kevin Lai.
10Gbit/s Bi-Directional Routing on standard hardware running Linux 10Gbit/s Bi-Directional Routing on standard hardware running Linux by Jesper Dangaard.
Exploiting Graphics Processors for High-performance IP Lookup in Software Routers Jin Zhao, Xinya Zhang, Xin Wang, Yangdong Deng, Xiaoming Fu IEEE INFOCOM.
Bifrost och 10Gbit routing Software Freedom Day /Stockholm Robert Olsson Uppsala Universitet och KTH.
Open Source Routing KTH CSD Kick-Off Workshop Robert Olsson Uppsala University
Multiqueue & Linux Networking Robert Olsson UU/KTH.
Multiqueue Networking David S. Miller Red Hat Inc.
Bifrost KTH/CSD course kick-off Fall 2010 Robert Olsson.
InterVLAN Routing 1. InterVLAN Routing 2. Multilayer Switching.
PC based software router
M. Bellato INFN Padova and U. Marconi INFN Bologna
NFV Compute Acceleration APIs and Evaluation
NaNet Problem: lower communication latency and its fluctuations. How?
KTH/CSD course kick-off Summer 2010 Robert Olsson
Graphics Processor Graphics Processing Unit
Kernel/Hardware for bifrost
Control and forwarding plane separation on an open-source router
CS 268: Router Design Ion Stoica February 27, 2003.
Chapter 6: Network Layer
Chapter 4 Data Link Layer Switching
Addressing: Router Design
Towards 10Gb/s open-source routing
Open Source 10g Talk at KTH/Kista
Multi-PCIe socket network device
KTH/CSD course kick-off Spring 2010 Robert Olsson
KTH/CSD course kick-off Fall 2009 Robert Olsson
Chapter 4: Network Layer
NSH_SFC Performance Report FD.io NSH_SFC and CSIT Team
(Read Forouzan Chapters 6 and 7)) IP Forwarding Procedure
Israel Cidon, Ran Ginosar and Avinoam Kolodny
CS 31006: Computer Networks – The Routers
Transport Layer Systems Packet Classification
Network Core and QoS.
Packet Switch Architectures
EE 122: Lecture 7 Ion Stoica September 18, 2001.
Computer Evolution and Performance
Network Systems and Throughput Preservation
Chapter 4: Network Layer
Network Core and QoS.
Presentation transcript:

Open-source routing at 10Gb/s Olof Hagsand (KTH) Robert Olsson (Uppsala U) Bengt Görden (KTH) SNCNW May 2009 Project grants: Internetstiftelsen (IIS) Equipment: Intel, SUN, AMD Networks: UU and KTH

Introduction ● Investigate packet forwarding performance of new PC hardware: – Multi-core CPUs – Multiple PCI-e buses – 10G NICs – Multi-queue classification ● Can we obtain enough performance to use open-source routing in the 10Gb/s realm?

Measuring throughput ● Packet per second – Per-packet costs – CPU processing, I/O and memory latency, clock frequency ● Bandwidth – Per-byte costs – Bandwidth limitations of bus and memory

Measuring throughput overload breakpoint overload drops capacity

Block hw structure example

Equipment summary ● Hardware needs to be carefully selected ● BifrostLinux 6.0 on kernel rc2 with LC-trie forwarding and NUMA support ● Packet generator: modified pktgen, IXIA for reference ● TYAN Thunder 2927 motherboard, NUMA, Hypertransport ● Two Quad-core 2.6GHz AMD Opteron 2382 ● Single PCIe internal bus ● 10GE network interface cards with hardware hash-based classifiers 1) Intel ixgbe. 10Gb/s XF SR dual port x8 PCIe server adapter. 2) Sun niu. Sun Neptune dual 10Gb/s x8 PCIe network card with XFPs and TCAM classifiers

Hardware – Box

Hardware - NICs Intel 10g board Chipset Sun Neptun niu 10g

Forwarding experiments Test Generator Sink device Tested device IXIA 1)Throughput versus packet length 2)Throughput versus number of CPU cores 3)Throughput versus functionality Main setup Reference setup

Throughput vs packet length - bw

Throughput vs packet length - pps

Introducing realistic traffic ● For the rest of the experiments we introduce a more realistic traffic scenario ● Multiple packet sizes – Simple model based on realistic packet distribution data ● Multiple flows (multiple dst IP:s) – This is also necessary for multi-core experiments since NIC classification is made using hash algorithm on packet headers

Packet size distribution (cdf)

Flow distribution ● Flows have size and duration distributions ● 8000 simultaneous flows ● Each flow 30 packets long ● new flows per second – Measured by dst cache misses observed at UU ● Destinations spread randomly over /8 ● FIB contains ~ 280K entries – 64K entries in /8

Throughput vs # CPU cores - bw

Throughput vs # CPU cores - pps

Throughput vs Functionality 1. Small routing table, no modules 2. Netfilter module 3. Netfilter module and connection tracking 4. Netfilter module and full BGP routing table (280K routes)

Full-duplex preliminary measurements ● Deflect output traffic to avoid contention at sender ● Box with double PCIe bus architecture ● Same traffic mix but expanded with /8 prefixes in other direction ● Preliminary results show (two directions): – BW: Kb/s ~15.9Gb/s – PPS: Kp/s ~ 2.36 Mp/s Test Generator Tested device

Conclusions ● Using hardware classifiers for multi-core CPUs is now possible with open-source routers – Close to 10 Gbp/s for realistic traffic distributions. ● Need to close the ”gap” (last 5-10%) ● More work on traffic classifiers, eg TCAMs, required ● Full duplex shows > 15Gb/s results.