FTDCS 2003 Network Tomography based Unresponsive Flow Detection and Control Authors Ahsan Habib, Bharat Bhragava Presenter Mohamed.

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

Multicast congestion control on many-to- many videoconferencing Xuan Zhang Network Research Center Tsinghua University, China.
Achieving Throughput Fairness in Wireless Mesh Network Based on IEEE Janghwan Lee and Ikjun Yeom Division of Computer Science KAIST
Congestion Control and Fairness Models Nick Feamster CS 4251 Computer Networking II Spring 2008.
Using Loss Pairs to Discover Network Properties Jun Liu, Mark Crovella Computer Science Dept. Boston University.
Using Edge-To-Edge Feedback Control to Make Assured Service More Assured in DiffServ Networks K.R.R.Kumar, A.L.Ananda, Lillykutty Jacob Centre for Internet.
1 School of Computing Science Simon Fraser University CMPT 771/471: Internet Architecture & Protocols TCP-Friendly Transport Protocols.
Florin Dinu T. S. Eugene Ng Rice University Inferring a Network Congestion Map with Traffic Overhead 0 zero.
CSIT560 Internet Infrastructure: Switches and Routers Active Queue Management Presented By: Gary Po, Henry Hui and Kenny Chong.
Transport Layer3-1 TCP AIMD multiplicative decrease: cut CongWin in half after loss event additive increase: increase CongWin by 1 MSS every RTT in the.
Architectures for Congestion-Sensitive Pricing of Network Services Thesis Defense by Murat Yuksel CS Department, RPI July 3 rd, 2002.
Bayesian Piggyback Control for Improving Real-Time Communication Quality Wei-Cheng Xiao 1 and Kuan-Ta Chen Institute of Information Science, Academia Sinica.
Receiver-driven Layered Multicast S. McCanne, V. Jacobsen and M. Vetterli University of Calif, Berkeley and Lawrence Berkeley National Laboratory SIGCOMM.
CS 4700 / CS 5700 Network Fundamentals Lecture 12: Router-Aided Congestion Control (Drop it like it’s hot) Revised 3/18/13.
Network Border Patrol Celio Albuquerque, Brett J. Vickers and Tatsuya Suda Jaideep Vaidya CS590F Fall 2000.
Network Border Patrol: Preventing Congestion Collapse and Promoting Fairness in the Internet Celio Albuquerque, Brett J. Vickers, Tatsuya Suda 1.
Advanced Computer Networking Congestion Control for High Bandwidth-Delay Product Environments (XCP Algorithm) 1.
The War Between Mice and Elephants LIANG GUO, IBRAHIM MATTA Computer Science Department Boston University ICNP (International Conference on Network Protocols)
XCP: Congestion Control for High Bandwidth-Delay Product Network Dina Katabi, Mark Handley and Charlie Rohrs Presented by Ao-Jan Su.
PROMISE: Peer-to-Peer Media Streaming Using CollectCast Mohamed Hafeeda, Ahsan Habib et al. Presented By: Abhishek Gupta.
Receiver-driven Layered Multicast S. McCanne, V. Jacobsen and M. Vetterli SIGCOMM 1996.
1 Estimating Shared Congestion Among Internet Paths Weidong Cui, Sridhar Machiraju Randy H. Katz, Ion Stoica Electrical Engineering and Computer Science.
PROMISE A Peer-to-Peer Media Streaming System Using CollectCast CPSC Presentation by Patrick Wong.
Controlling High- Bandwidth Flows at the Congested Router Ratul Mahajan, Sally Floyd, David Wetherall AT&T Center for Internet Research at ICSI (ACIRI)
1 Modeling and Taming Parallel TCP on the Wide Area Network Dong Lu,Yi Qiao Peter Dinda, Fabian Bustamante Department of Computer Science Northwestern.
1 Minseok Kwon and Sonia Fahmy Department of Computer Sciences Purdue University {kwonm, TCP Increase/Decrease.
1 TCP-LP: A Distributed Algorithm for Low Priority Data Transfer Aleksandar Kuzmanovic, Edward W. Knightly Department of Electrical and Computer Engineering.
1 Emulating AQM from End Hosts Presenters: Syed Zaidi Ivor Rodrigues.
Study of Distance Vector Routing Protocols for Mobile Ad Hoc Networks Yi Lu, Weichao Wang, Bharat Bhargava CERIAS and Department of Computer Sciences Purdue.
A Strategy for Implementing Smart Market Pricing Scheme on Diff-Serv Murat Yuksel and Shivkumar Kalyanaraman Rensselaer Polytechnic Institute, Troy, NY.
Medium Start in TCP-Friendly Rate Control Protocol CS 217 Class Project Spring 04 Peter Leong & Michael Welch.
RRAPID: Real-time Recovery based on Active Probing, Introspection, and Decentralization Takashi Suzuki Matthew Caesar.
The War Between Mice and Elephants By Liang Guo (Graduate Student) Ibrahim Matta (Professor) Boston University ICNP’2001 Presented By Preeti Phadnis.
Performance and Robustness Testing of Explicit-Rate ABR Flow Control Schemes Milan Zoranovic Carey Williamson October 26, 1999.
Congestion Control for High Bandwidth-delay Product Networks Dina Katabi, Mark Handley, Charlie Rohrs.
Rafael C. Nunez - Gonzalo R. Arce Department of Electrical and Computer Engineering University of Delaware May 19 th, 2005 Diffusion Marking Mechanisms.
Diffusion Mechanisms for Active Queue Management Department of Electrical and Computer Engineering University of Delaware May 19th / 2004 Rafael Nunez.
Inline Path Characteristic Estimation to Improve TCP Performance in High Bandwidth-Delay Networks HIDEyuki Shimonishi Takayuki Hama Tutomu Murase Cesar.
Congestion Control for High Bandwidth-Delay Product Environments Dina Katabi Mark Handley Charlie Rohrs.
Ns Simulation Final presentation Stella Pantofel Igor Berman Michael Halperin
Analysis of Active Queue Management Jae Chung and Mark Claypool Computer Science Department Worcester Polytechnic Institute Worcester, Massachusetts, USA.
Adaptive Control for TCP Flow Control Thesis Presentation Amir Maor.
10th Workshop on Information Technologies and Systems 1 A Comparative Evaluation of Internet Pricing Schemes: Smart Market and Dynamic Capacity Contracting.
Diffusion Early Marking Department of Electrical and Computer Engineering University of Delaware May / 2004 Rafael Nunez Gonzalo Arce.
Receiver-driven Layered Multicast Paper by- Steven McCanne, Van Jacobson and Martin Vetterli – ACM SIGCOMM 1996 Presented By – Manoj Sivakumar.
Not All Microseconds are Equal: Fine-Grained Per-Flow Measurements with Reference Latency Interpolation Myungjin Lee †, Nick Duffield‡, Ramana Rao Kompella†
Advanced Network Architecture Research Group 2001/11/149 th International Conference on Network Protocols Scalable Socket Buffer Tuning for High-Performance.
CING-YU CHU INFOCOM Outline  Introduction  Measurement  Measurement Results  Modeling Skype Behaviors  Analysis on TCP-friendly.
Distance-Dependent RED Policy (DDRED)‏ Sébastien LINCK, Eugen Dedu and François Spies LIFC Montbéliard - France ICN07.
Korea Advanced Institute of Science and Technology Network Systems Lab. 1 Dual-resource TCP/AQM for processing-constrained networks INFOCOM 2006, Barcelona,
1 On Class-based Isolation of UDP, Short-lived and Long-lived TCP Flows by Selma Yilmaz Ibrahim Matta Computer Science Department Boston University.
Advanced Network Architecture Research Group 2001/11/74 th Asia-Pacific Symposium on Information and Telecommunication Technologies Design and Implementation.
Requirements for Simulation and Modeling Tools Sally Floyd NSF Workshop August 2005.
Congestion Control for High Bandwidth-Delay Product Networks D. Katabi (MIT), M. Handley (UCL), C. Rohrs (MIT) – SIGCOMM’02 Presented by Cheng.
1 On Scalable Edge-based Flow Control Mechanism for VPN Tunnels --- Part 2: Scalability and Implementation Issues Hiroyuki Ohsaki Graduate School of Information.
15744 Course Project1 Evaluation of Queue Management Algorithms Ningning Hu, Liu Ren, Jichuan Chang 30 April 2001.
Multiplicative Wavelet Traffic Model and pathChirp: Efficient Available Bandwidth Estimation Vinay Ribeiro.
Murari Sridharan and Kun Tan (Collaborators: Jingmin Song, MSRA & Qian Zhang, HKUST.
1 Capacity Dimensioning Based on Traffic Measurement in the Internet Kazumine Osaka University Shingo Ata (Osaka City Univ.)
T. S. Eugene Ngeugeneng at cs.rice.edu Rice University1 COMP/ELEC 429/556 Introduction to Computer Networks Principles of Congestion Control Some slides.
We used ns-2 network simulator [5] to evaluate RED-DT and compare its performance to RED [1], FRED [2], LQD [3], and CHOKe [4]. All simulation scenarios.
TCP Westwood: Efficient Transport for High-speed wired/wireless Networks 2008.
Chapter 11.4 END-TO-END ISSUES. Optical Internet Optical technology Protocol translates availability of gigabit bandwidth in user-perceived QoS.
Development of a QoE Model Himadeepa Karlapudi 03/07/03.
XCP: eXplicit Control Protocol Dina Katabi MIT Lab for Computer Science
An End-to-End Service Architecture r Provide assured service, premium service, and best effort service (RFC 2638) Assured service: provide reliable service.
Access Link Capacity Monitoring with TFRC Probe Ling-Jyh Chen, Tony Sun, Dan Xu, M. Y. Sanadidi, Mario Gerla Computer Science Department, University of.
PATH DIVERSITY WITH FORWARD ERROR CORRECTION SYSTEM FOR PACKET SWITCHED NETWORKS Thinh Nguyen and Avideh Zakhor IEEE INFOCOM 2003.
Congestion Control for High Bandwidth-Delay Product Networks Dina Katabi, Mark Handley, Charlie Rohrs Presented by Yufei Chen.
Columbia University in the city of New York
Presentation transcript:

FTDCS 2003 Network Tomography based Unresponsive Flow Detection and Control Authors Ahsan Habib, Bharat Bhragava Presenter Mohamed M. Hefeeda Department of Computer Sciences Purdue University Support: NSF, CERIAS, IBM

Motivation Efficient resource management by utilizing wasted resources Adaptive flows do not starve due to unresponsive flows Coordinated congestion control by propagating congestion information to upstream domains

Example Unresponsive flows waste resources by taking their share of the upstream links and dropping packets at downstream links are congested

Related Work Congestion collapse from undelivered packets [Flyod et al., TON ’99] Network Border Patrol [Albuquerque et al., INFOCOM ’00] Edge routers periodically poll cores [Chow et al., Internet draft ’00] Direct Congestion Control Scheme [Wu et al., Internet draft ’00] Loss of high class packet means congestion Core-assisted Congestion Control [Habib, Bhargava PDCS ’01]

Network Tomography Network tomography uses correlations among end-to-end measurements to infer per-link characteristics. Back-to-back packets experience similar congestion in a queue with a high probability [Duffield et al., INFOCOM ’01] Receiver observes the probes and correlates them for loss inference For general tree? Send stripe from root to every order-pair of leaves

Tomography-based Congestion Control (TCC) Only edge to edge measurements are used to detect and control unresponsive flows

TCC- Detection 1. Measure Delay Ingress routers sample user traffic The user packet headers are copied to probe edge-to-edge path for delay Exponential moving weighting average is computed with more weight to the recent history and less weight to the current sample If probed delay is higher than a specified threshold, a path is suspected to be congested

TCC- Detection (Cont’d) 2. Measure Loss A loss probing tree is generated with a set of paths that have high delay. The tree is probed to infer loss ratio of each individual link of the suspected paths Need to know Topology Senders Receivers

TCC- Detection (Cont’d) 3. Identify egress routers Through which suspected flows are leaving the domain. The links with high losses are feeding flows to these routers 4. Identify misbehaving flows These are determined with the rate at which suspected flows are entering into and leaving from a domain

TCC- Control We know the misbehaving flows from detection The rate of suspected flows are adjusted based on Loss ratio and Change of loss ratio with time

Experiments: Evaluation methodology Simulation using ns-2 Use parameter settings (queue, traffic, …) from reference work Input Parameters We vary RTT, number of flows, and life time of flows Output Parameters Measure delay, loss ratio, throughput Topology

Delay Measurements End-to-end delay is high due to excessive flows With control the delay goes down Time (Sec) End –to-End Delay (Sec)

Loss inference Validation Three different experiments Actual loss is close to infer loss Converges within sec Actual Loss Inferred Loss

Flow Control Time (Sec) Bandwidth (Mbps) Flow control mechanism increases the bandwidth of adaptive flows by consuming bandwidth wasted by unresponsive flows Time (Sec) TCP congestion window

Flow Control Loss ratio of an unresponsive flows with and without flow control Goes down sharply with time Converges to a low specified value Time (Sec) Loss Ratio

Flow Aggregation… 6-10 aggregate flows of each type micro flows per aggregate Works fine even more and more flows misbehave Number of flows Bandwidth (Mbps)

Conclusion A new way to detect and control unresponsive flows No involvement of core routers Scalable Easy to deploy Low overhead. Probe traffic less than 0.015% of the link capacity (OC3)