10 June 2004 Protocols for Long-Distance Networks Terena Networking Conference 2004 Rhodes.

Slides:



Advertisements
Similar presentations
Martin Suchara, Ryan Witt, Bartek Wydrowski California Institute of Technology Pasadena, U.S.A. TCP MaxNet Implementation and Experiments on the WAN in.
Advertisements

Helping TCP Work at Gbps Cheng Jin the FAST project at Caltech
Appropriateness of Transport Mechanisms in Data Grid Middleware Rajkumar Kettimuthu 1,3, Sanjay Hegde 1,2, William Allcock 1, John Bresnahan 1 1 Mathematics.
FAST TCP Anwis Das Ajay Gulati Slides adapted from : IETF presentation slides Link:
Cheng Jin David Wei Steven Low FAST TCP: design and experiments.
Ahmed El-Hassany CISC856: CISC 856 TCP/IP and Upper Layer Protocols Slides adopted from: Injong Rhee, Lisong Xu.
CUBIC : A New TCP-Friendly High-Speed TCP Variant Injong Rhee, Lisong Xu Member, IEEE v 0.2.
CUBIC Qian HE (Steve) CS 577 – Prof. Bob Kinicki.
Advanced Computer Networking Congestion Control for High Bandwidth-Delay Product Environments (XCP Algorithm) 1.
Congestion Control An Overview -Jyothi Guntaka. Congestion  What is congestion ?  The aggregate demand for network resources exceeds the available capacity.
XCP: Congestion Control for High Bandwidth-Delay Product Network Dina Katabi, Mark Handley and Charlie Rohrs Presented by Ao-Jan Su.
Congestion Control on High-Speed Networks
Texas A&M University Improving TCP Performance in High Bandwidth High RTT Links Using Layered Congestion Control Sumitha.
TCP friendlyness: Progress report for task 3.1 Freek Dijkstra Antony Antony, Hans Blom, Cees de Laat University of Amsterdam CERN, Geneva 25 September.
Recent Research in Congestion Control The problem of high bandwidth-delay product connections By Guillaume Marceau Presented for WPI CS577, Advanced Computer.
Rice Networks Group Aleksandar Kuzmanovic & Edward W. Knightly TCP-LP: A Distributed Algorithm for Low Priority Data Transfer.
Cheng Jin David Wei Steven Low FAST TCP: Motivation, Architecture, Algorithms, Performance.
Rice Networks Group Aleksandar Kuzmanovic Edward W. Knightly Rice University R. Les Cottrell SLAC/SCS-Network Monitoring.
1 Characterization and Evaluation of TCP and UDP-based Transport on Real Networks Les Cottrell, Saad Ansari, Parakram Khandpur, Ruchi Gupta, Richard Hughes-Jones,
1 TCP-LP: A Distributed Algorithm for Low Priority Data Transfer Aleksandar Kuzmanovic, Edward W. Knightly Department of Electrical and Computer Engineering.
The Effect of Router Buffer Size on HighSpeed TCP Performance Dhiman Barman Joint work with Georgios Smaragdakis and Ibrahim Matta.
Presented by Anshul Kantawala 1 Anshul Kantawala FAST TCP: From Theory to Experiments C. Jin, D. Wei, S. H. Low, G. Buhrmaster, J. Bunn, D. H. Choe, R.
Congestion Control for High Bandwidth-delay Product Networks Dina Katabi, Mark Handley, Charlie Rohrs.
Congestion Control for High Bandwidth-Delay Product Environments Dina Katabi Mark Handley Charlie Rohrs.
The Effects of Systemic Packets Loss on Aggregate TCP Flows Thomas J. Hacker May 8, 2002 Internet 2 Member Meeting.
Experiences in Design and Implementation of a High Performance Transport Protocol Yunhong Gu, Xinwei Hong, and Robert L. Grossman National Center for Data.
CS/EE 145A Congestion Control Netlab.caltech.edu/course.
Implementing High Speed TCP (aka Sally Floyd’s) Yee-Ting Li & Gareth Fairey 1 st October 2002 DataTAG CERN (Kinda!)
UDT: UDP based Data Transfer Protocol, Results, and Implementation Experiences Yunhong Gu & Robert Grossman Laboratory for Advanced Computing / Univ. of.
E-VLBI over TransPAC Masaki HirabaruDavid LapsleyYasuhiro KoyamaAlan Whitney Communications Research Laboratory, Japan MIT Haystack Observatory, USA Communications.
Parameswaran, Subramanian
High-speed TCP  FAST TCP: motivation, architecture, algorithms, performance (by Cheng Jin, David X. Wei and Steven H. Low)  Modifying TCP's Congestion.
Masaki Hirabaru Tsukuba WAN Symposium 2005 March 8, 2005 e-VLBI and End-to-End Performance over Global Research Internet.
HighSpeed TCP for High Bandwidth-Delay Product Networks Raj Kettimuthu.
Rate Control Rate control tunes the packet sending rate. No more than one packet can be sent during each packet sending period. Additive Increase: Every.
Congestion Control for High Bandwidth-Delay Product Networks D. Katabi (MIT), M. Handley (UCL), C. Rohrs (MIT) – SIGCOMM’02 Presented by Cheng.
Panel: Is IP Routing Dead? -- Linda Winkler, Argonne Natl Lab -- Bill St Arnaud, CANARIE Guy Almes PFLDnet Workshop – Geneva 3 February 2003.
Udt.sourceforge.net 1 :: 23 Supporting Configurable Congestion Control in Data Transport Services Yunhong Gu and Robert L. Grossman Laboratory for Advanced.
BIC Control for Fast Long-Distance Networks paper written by Injong Rhee, Lisong Xu & Khaled Harfoush (2004) Presented by Jonathan di Costanzo (2009/02/18)
Performance of New Variants of TCP Presenter – Bob Kinicki.
Performance Measurements in Internet2 Guy Almes Geneve – 15 March 2004.
1 Characterization and Evaluation of TCP and UDP-based Transport on Real Networks Les Cottrell, Saad Ansari, Parakram Khandpur, Ruchi Gupta, Richard Hughes-Jones,
Project Results Thanks to the exceptional cooperation spirit between the European and North American teams involved in the DataTAG project,
TCP transfers over high latency/bandwidth networks Internet2 Member Meeting HENP working group session April 9-11, 2003, Arlington T. Kelly, University.
Thoughts on the Evolution of TCP in the Internet (version 2) Sally Floyd ICIR Wednesday Lunch March 17,
David Wetherall Professor of Computer Science & Engineering Introduction to Computer Networks Fairness of Bandwidth Allocation (§6.3.1)
PCP: Efficient Endpoint Congestion Control NSDI, 2006 Thomas Anderson, Andrew Collins, Arvind Krishnamurthy and John Zahorjan University of Washington.
Performance Engineering E2EpiPEs and FastTCP Internet2 member meeting - Indianapolis World Telecom Geneva October 15, 2003
TCP transfers over high latency/bandwidth networks & Grid DT Measurements session PFLDnet February 3- 4, 2003 CERN, Geneva, Switzerland Sylvain Ravot
Scheduling and transport for file transfers on high-speed optical circuits Authors: M. Veeraraghavan & Xuan Zheng (University of Virginia) Wu Feng (Los.
XCP: eXplicit Control Protocol Dina Katabi MIT Lab for Computer Science
Performance of New Variants of TCP Presenter – Bob Kinicki.
Final EU Review - 24/03/2004 DataTAG is a project funded by the European Commission under contract IST Richard Hughes-Jones The University of.
1 Evaluation of Advanced TCP stacks on Fast Long-Distance production Networks Prepared by Les Cottrell & Hadrien Bullot, Richard Hughes-Jones EPFL, SLAC.
INDIANAUNIVERSITYINDIANAUNIVERSITY Status of FAST TCP and other TCP alternatives John Hicks TransPAC HPCC Engineer Indiana University APAN Meeting – Hawaii.
Thoughts on the Evolution of TCP in the Internet Sally Floyd PFLDnet 2004 February 16, 2004.
ESLEA Closing Conference, Edinburgh, March 2007, R. Hughes-Jones Manchester 1 The Uptake of High Speed Protocols or Are these protocols making their way.
An Analysis of AIMD Algorithm with Decreasing Increases Yunhong Gu, Xinwei Hong, and Robert L. Grossman National Center for Data Mining.
Masaki Hirabaru (NICT) and Jin Tanaka (KDDI) Impact of Bottleneck Queue on Long Distant TCP Transfer August 25, 2005 NOC-Network Engineering Session Advanced.
Network-aware OS DOE/MICS ORNL site visit January 8, 2004 ORNL team: Tom Dunigan, Nagi Rao, Florence Fowler, Steven Carter Matt Mathis Brian.
Congestion Control for High Bandwidth-Delay Product Networks Dina Katabi, Mark Handley, Charlie Rohrs Presented by Yufei Chen.
Network Congestion Control HEAnet Conference 2005 (David Malone for Doug Leith)
Transport Protocols over Circuits/VCs
TransPAC HPCC Engineer
TCP-LP: A Distributed Algorithm for Low Priority Data Transfer
Internet Congestion Control Research Group
Prepared by Les Cottrell & Hadrien Bullot, SLAC & EPFL, for the
Wide Area Networking at SLAC, Feb ‘03
OptIPuter Networking and Middleware
Presentation transcript:

10 June 2004 Protocols for Long-Distance Networks Terena Networking Conference 2004 Rhodes

2 Overview  The PFLDnet research area  The PFLDnet Workshop series  Selected results from PFLDnet'04  Reflections 

3 The PFLDnet Research Area  Protocols for Fat Long-Distance Nets Sustaining high-speed flows over wide areas is: –Difficult –Important Difficult due to difficulty of managing large numbers of in-flight packets Important due to need for scientists around the world to share information  After a period of relative neglect, PFLDnet is now a vibrant research area

4 A little more on why it's hard  In Van Jacobson's 1988 paper: “...insensitive to [noncongestive] loss until the loss rate is on the order of one packet per window.”  Then: a window was 8 packets.  Now: a window is about 83,000 packets (10,000 km at 10 Gb/s with 1500-byte packets)  So noncongestive packet loss must be less than %

5 A little more on why it's important  Many international scientific research collaborations need to transmit data at several multiples of 10 Gb/s over distances at/above 10,000 km. High-energy physics Radio astronomy Biomedical informatics  How to support these applications in a scalable sustainable way is a key challenge for our community.

6 The PFLDnet Workshop Series  CERN Geneva -- Switzerland February 3-4, 2003  Argonne National Laboratory Chicago, Illinois -- USA February 16-17, 2004  Early planning for spring 2005 in Europe

7 Selected results from PFLDnet'04  Improved algorithms for TCP FAST: Caltech H-TCP: Hamilton Institute, Ireland HSTCP-LP: Rice University and SLAC Also: HS-TCP, BiC-TCP, and S-TCP  Non-TCP but in shared IP context  Testing and evaluation  Exploring non-shared contexts

8 Critique of 'standard' AIMD TCP  Too cautious: only increases cwnd by one packet per RTT interprets every loss as congestion hence take several tens of minutes to recover in a PFLnet environment hence cannot fully utilize the bottleneck link  Too brutal: keeps growing cwnd until the queue in the bottleneck router overflows hence massive queues rise and fall in routers not good for other jitter-intolerant traffic

9 FAST: Delay-based Algorithms  Steven Low, Cheng Jin, et al. at Caltech  Consider TCP as a control system TCP sender injects a data rate signal Network provides delay and loss feedback  Uses measured delay effectively to maintain a moderate-sized queue hence better for other applications and keeps the bottleneck link fully utilized  Careful attention to stability / fairness

10 H-TCP: Rapid recovery of cwnd  DJ Leith and RN Shorten at Hamilton Inst  Focus on the AI part of AIMD in high- speed regimes: use a quadratic function of time since last loss instead of a constant as the increase in cwnd  Consistent with standard AIMD in other regimes  Careful study of synchronization issues

11 HSTCP-LP: Combining High-speed and Low-priority  A Kuzmanovic and E Knightly at Rice, with L Cottrell at SLAC  Builds on earlier TCP-LP work AIMD but defer to other traffic [Infocom 03]  Builds on Floyd's HSTCP  Careful use of one-way delay measurements via TCP timestamp option  Effectively uses bottleneck link, but defers to other TCP traffic

12 Other TCP Algorithms Work  HSTCP: Floyd of ICIR conservative improvement on AIMD  BiC: Rhee of North Carolina State binary search for the right cwnd value  Scalable TCP: Kelly of Cambridge an aggressive MIMD approach

13 Selected results from PFLDnet'04  Improved algorithms for TCP  Non-TCP but in shared IP context UDT: Univ Illinois Chicago XCP: MIT and USC-ISI eVLBI-specific: MIT  Testing and evaluation  Exploring non-shared contexts

14 UDT: Congestion Control over UDP  Y Gu and R Grossman at UI-Chicago  Observation: even once a new TCP stack is created, deployment is hard  Idea: implement a good congestion control algorithm within a subroutine library using UDP kernel services  Also, rate-based algorithms with estimates of available bandwidth

15 XCP: Leveraging future router cooperation  D Katabi at MIT, with A Falk et al. at USC-ISI  Posit advanced cooperation by the bottleneck router hence stable moderate-sized queues and full use of bottleneck link with very rapid convergence  This will take time to get right and then deploy, but clearly a compelling idea

16 eVLBI-specific work  J Wroclawski, D Lapsley, and A Whinery at MIT ( CS and Haystack Observatory )  eVLBI: two or more physically separated radio telescopes correlating data from deep- space objects in real time ( very cool !! )  Needs: consistent high data rates, but can tolerate some packet loss  Edge Guided Adaptive Endpoint: innovative application-specific algorithms to optimize eVLBI efficacy

17 Selected results from PFLDnet'04  Improved algorithms for TCP  Non-TCP but in shared IP context  Testing and evaluation Techniques: Lawrence Berkeley Lab Evaluations: SLAC, Internet2, Manchester, UCL  Exploring non-shared contexts

18 Techniques to strengthen testing  B Tierney and J Lee at LBL  Make use of techniques that allow: testing of multiple paths on multiple days use well-considered statistics controlled experiments  Network Tool Analysis Framework

19 Evaluations  L Cottrell at SLAC, R Hughes-Jones at Manchester, and H Bullot at EPFL  Tested many TCP stacks throughput sensitivity to distance stability and fairness  Several shown to be promising including BiC, FAST, HSTCP-LP

20 Evaluations  S Shalunov of Internet2  Tested FAST within Internet2 context showed three 1-Gb/s paths easily saturating the OC-48 circuit from Abilene to Georgia Tech in the presence of production Internet2 traffic the high-speed FAST flows do not disrupt conventional traffic

21 Selected results from PFLDnet'04  Improved algorithms for TCP  Non-TCP but in shared IP context  Testing and evaluation  Exploring non-shared contexts Group Transport Protocol: UC San Diego VBTP: Univ Virginia IP-QoS for TCP: Univ College London

22 Group Transport Protocol: Rate-based protocols for Grids  R Wu and A Chien at UCSD  Emphasis on Multipoint-to-Point support in a lambda-grid environment  Dynamic lambdas over the wide area  Need for flows from several sources to converge at the site of a grid computation  Rate-based protocols the best approach in this environment

23 VBTP: Scheduling file transfers on dynamic optical networks  Veeraraghavan and Zhang at Univ Virginia, Feng at Los Alamos, Lee at Polytechnic, and Chong and Li at Colorado State Univ  Circuit-switched networks may make it difficult to fully utilize available capacity for a given task  VBTP designed as a rate-based scheme to schedule circuit resources effectively in support of file transfers

24 IP-QoS for TCP  Donato, Li, Saka, and Clarke at Univ College London  Idea: Use IP-QoS as a means of combining dependability of TCP bulk flow rates with protection of interactive traffic from over-aggressive TCP flows  Even with this help, transport protocols will need to be improved for PFLDnet environments

25 Reflections  Making effective use of high-speed wide-area networks is crucial for international collaborative research  Current TCP algorithms were not designed to support anything like the current 10,000 km 10-Gb/s combinations we now face

26  There is now renewed vitality in the PFLDnet research area  This will lead to (at least) two key benefits enable dramatic improvements in the effective use of high-speed wide-area network infrastructure clarify the boundary of applicability of shared packet- switched vs dedicated circuit-switched networks

27  Closing reference to Internet2's Land Speed Record rewards heroism in wide-area high-speed TCP flows figure of merit: product of b/s rate times distance  Single-stream IPv4 TCP record current: 4.2 Gb/s over 16,343 km previous: 5.6 Gb/s over 10,000 km  Can we make these performance levels normative in high-end networks?

28