UCB Tools for Smart Networks Jean Walrand BITS (Berkeley Information Technology & Systems) U.C. Berkeley www.eecs.berkeley.edu/~wlr/mascots2000.

Slides:



Advertisements
Similar presentations
Japan Telecom Information & Communication Labs
Advertisements

Dynamic Replica Placement for Scalable Content Delivery Yan Chen, Randy H. Katz, John D. Kubiatowicz {yanchen, randy, EECS Department.
© 2006 Cisco Systems, Inc. All rights reserved. MPLS v2.2—8-1 MPLS TE Overview Introducing the TE Concept.
Contents Shortcomings of QoS in the Current Internet About OpenFlow
Architectures for Congestion-Sensitive Pricing of Network Services Thesis Defense by Murat Yuksel CS Department, RPI July 3 rd, 2002.
1 Traffic Engineering (TE). 2 Network Congestion Causes of congestion –Lack of network resources –Uneven distribution of traffic caused by current dynamic.
Designing a New Routing Simulator for DiffServ MPLS Networks Peng Zhang Zhansong Ma Raimo Kantola {pgzhang, zhansong,
Playback-buffer Equalization For Streaming Media Using Stateless Transport Prioritization By Wai-tian Tan, Weidong Cui and John G. Apostolopoulos Presented.
CNDS 2001, Phoenix, AZ Simulating the Smart Market Pricing Scheme on Differentiated- Services Architecture Murat Yuksel and Shivkumar Kalyanaraman Rensselaer.
A SLA Framework for QoS Provisioning and Dynamic Capacity Allocation Rahul Garg (IBM India Research Lab), R. S. Randhawa (Stanford University), Huzur Saran.
The War Between Mice and Elephants LIANG GUO, IBRAHIM MATTA Computer Science Department Boston University ICNP (International Conference on Network Protocols)
1 Routing and Scheduling in Web Server Clusters. 2 Reference The State of the Art in Locally Distributed Web-server Systems Valeria Cardellini, Emiliano.
XCP: Congestion Control for High Bandwidth-Delay Product Network Dina Katabi, Mark Handley and Charlie Rohrs Presented by Ao-Jan Su.
Small-world Overlay P2P Network
UCB Tools for Smart Networks Jean Walrand BITS (Berkeley Information Technology & Systems) U.C. Berkeley
CPSC Topics in Multimedia Networking A Mechanism for Equitable Bandwidth Allocation under QoS and Budget Constraints D. Sivakumar IBM Almaden Research.
The War Between Mice and Elephants Presented By Eric Wang Liang Guo and Ibrahim Matta Boston University ICNP
AHOP Problem and QoS Route Pre-computation Adam Sachitano IAL.
High Performance All-Optical Networks with Small Buffers Yashar Ganjali High Performance Networking Group Stanford University
UCB Review – EECS228a Jean Walrand U.C. Berkeley
Comparing flow-oblivious and flow-aware adaptive routing Sara Oueslati and Jim Roberts France Telecom R&D CISS 2006 Princeton March 2006.
UCB Switches Jean Walrand U.C. Berkeley
Multiple constraints QoS Routing Given: - a (real time) connection request with specified QoS requirements (e.g., Bdw, Delay, Jitter, packet loss, path.
Bandwidth sharing: objectives and algorithms Jim Roberts France Télécom - CNET Laurent Massoulié Microsoft Research.
1 Traffic Engineering for ISP Networks Jennifer Rexford IP Network Management and Performance AT&T Labs - Research; Florham Park, NJ
How Much? For What? Thoughts on Economic Issues in Networks Jean Walrand U.C. Berkeley Thoughts on Economic Issues in Networks Jean Walrand U.C. Berkeley.
Source-Destination Routing Optimal Strategies Eric Chi EE228a, Fall 2002 Dept. of EECS, U.C. Berkeley.
UCB DiffServ An Overview Jean Walrand EECS. UCB Outline DiffServ Goal Solution Worst Case Admission Control Measurement-Based Admission Control Bandwidth.
UCB Implementing QoS Jean Walrand EECS. UCB Outline What? Bandwidth, Delay Where? End-to-End, Edge-to-Edge, Edge-to-End, Overlay Mechanisms Access Control.
Traffic Engineering and Routing Hansen Bow. Topics Traffic Engineering with MPLS Issues Concerning Voice over IP Features of Netscope QoS Routing for.
Distributed-Dynamic Capacity Contracting: A congestion pricing framework for Diff-Serv Murat Yuksel and Shivkumar Kalyanaraman Rensselaer Polytechnic Institute,
Dynamic routing – QoS routing Load sensitive routing QoS routing.
Quality of Service for Flows in Ad-Hoc Networks SmartNets Research Group Dept of EECS, UC Berkeley NMS PI Meeting, Nov 2004.
1 Smart Networks Project Overview Cisco: – David Jaffe, Karl Auerbach, Anna Charny Berkeley: – Venkat Anantharam, David Tse, Pravin Varaiya, Jean Walrand.
UCB Communication Networks: Big Picture Jean Walrand U.C. Berkeley
Wide Web Load Balancing Algorithm Design Yingfang Zhang.
Smart Networks Project University of California, Berkeley DARPA NMS PI Meeting Miami, Jan 21-23, 2004.
S. Suri, M, Waldvogel, P. Warkhede CS University of Washington Profile-Based Routing: A New Framework for MPLS Traffic Engineering.
Smart Networks Project UC Berkeley / Cisco May 27, 2003.
10th Workshop on Information Technologies and Systems 1 A Comparative Evaluation of Internet Pricing Schemes: Smart Market and Dynamic Capacity Contracting.
UCB Switches Jean Walrand U.C. Berkeley
Implement a QoS Algorithm for Real-Time Applications in the DiffServ-aware MPLS Network Zuo-Po Huang, *Ji-Feng Chiu, Wen-Shyang Hwang and *Ce-Kuen Shieh.
The Effects of Systemic Packets Loss on Aggregate TCP Flows Thomas J. Hacker May 8, 2002 Internet 2 Member Meeting.
Distributed Quality-of-Service Routing of Best Constrained Shortest Paths. Abdelhamid MELLOUK, Said HOCEINI, Farid BAGUENINE, Mustapha CHEURFA Computers.
Bell Labs Advanced Technologies EMEAAT Proprietary Information © 2004 Lucent Technologies1 Overview contributions for D27 Lucent Netherlands Richa Malhotra.
Cost-Performance Tradeoffs in MPLS and IP Routing Selma Yilmaz Ibrahim Matta Boston University.
COnvergence of fixed and Mobile BrOadband access/aggregation networks Work programme topic: ICT Future Networks Type of project: Large scale integrating.
DaVinci: Dynamically Adaptive Virtual Networks for a Customized Internet Jennifer Rexford Princeton University With Jiayue He, Rui Zhang-Shen, Ying Li,
“Intra-Network Routing Scheme using Mobile Agents” by Ajay L. Thakur.
Othman Othman M.M., Koji Okamura Kyushu University 1.
© 2009 IBM Corporation 1 Improving Consolidation of Virtual Machines with Risk-aware Bandwidth Oversubscription in Compute Clouds Amir Epstein Joint work.
Beyond Best-Effort Service Advanced Multimedia University of Palestine University of Palestine Eng. Wisam Zaqoot Eng. Wisam Zaqoot November 2010 November.
Differentiated Services for the Internet Selma Yilmaz.
VL2: A Scalable and Flexible Data Center Network Albert Greenberg, James R. Hamilton, Navendu Jain, Srikanth Kandula, Changhoon Kim, Parantap Lahiri, David.
TeraPaths TeraPaths: Establishing End-to-End QoS Paths through L2 and L3 WAN Connections Presented by Presented by Dimitrios Katramatos, BNL Dimitrios.
DaVinci: Dynamically Adaptive Virtual Networks for a Customized Internet Jiayue He, Rui Zhang-Shen, Ying Li, Cheng-Yen Lee, Jennifer Rexford, and Mung.
Efficient Cache Structures of IP Routers to Provide Policy-Based Services Graduate School of Engineering Osaka City University
Research Unit in Networking - University of Liège A Distributed Algorithm for Weighted Max-Min Fairness in MPLS Networks Fabian Skivée
Belgrade University Aleksandra Smiljanić: High-Capacity Switching Switches with Input Buffers (Cisco)
CS 6401 Overlay Networks Outline Overlay networks overview Routing overlays Resilient Overlay Networks Content Distribution Networks.
MATE: MPLS Adaptive Traffic Engineering Anwar Elwalid Cheng Jin Steven Low Indra Widjaja Bell Labs Michigan altech Fujitsu 2006.
Indian Institute of Technology Bombay 1 Communication Networks Prof. D. Manjunath
An End-to-End Service Architecture r Provide assured service, premium service, and best effort service (RFC 2638) Assured service: provide reliable service.
Courtesy Piggybacking: Supporting Differentiated Services in Multihop Mobile Ad Hoc Networks Wei LiuXiang Chen Yuguang Fang WING Dept. of ECE University.
VL2: A Scalable and Flexible Data Center Network
Instructor Materials Chapter 6: Quality of Service
Performance Study of Congestion Price Based Adaptive Service
Network and Services Management
© 2008 Cisco Systems, Inc. All rights reserved.Cisco ConfidentialPresentation_ID 1 Chapter 6: Quality of Service Connecting Networks.
Presentation transcript:

UCB

Tools for Smart Networks Jean Walrand BITS (Berkeley Information Technology & Systems) U.C. Berkeley

UCB Outline What are Smart Networks? Why Smart Networks? Tools for Smart Networks Project Example 1: DiffServ Example 2: Bandwidth Allocation Example 3: Server Allocation Conclusions

UCB What are Smart Networks? Measure Analyze Modify

UCB Why Smart Networks? Before: “Simple Network” IP Transport Applications Transport Applications Client Server Network

UCB Why Smart Networks? (continued) Now: “Complex Network” Network Application Servers, Content Servers Caches, Traffic Shapers, Redirection Agents, Processing

UCB Why Smart Networks? (continued) Simple Network: IP Forwarding Routing Table Updates DNS Intelligence in Hosts Complex Network: New Functions New Transport Services (e.g., CoS, SLAs) Needs Intelligence in Network

UCB Why Smart Networks? (continued) INTERNET IP LANs, ATM,... Applications Success of SimplicitySuccess of Complexity TELEPHONE SS7, Billing,... OC-n, DS-n, UTP Applications

UCB Why Smart Networks? (continued) Probably not very desirable! INTERNET IP LANs, ATM,... Applications

UCB Why Smart Networks? (continued) INTERNET IP LANs, ATM,... Applications IP LANs, ATM,... Applications M/A/M Tools for Planning, Design, Operations

UCB Tools for Smart Networks Project Joint UCB - Cisco Project DARPA Funding + Cisco Combines Measurements Analysis & Simulation Real-time Control Objective: Product

UCB Tools for Smart Networks Project (cd) Utility Comprehension Simulations Measurements Analysis Integrated Tools

UCB Tools for Smart Networks Project (cd) Cisco: David Jaffe (Lead Investigator) Karl Auerbach (Lab Design and Implementation) Anna Charny (MPLS) TBS (DiffServ) UCB Anantharam, Tse, Varaiya, Walrand Stavros Tripakis (post-doctoral scholar) About 6 graduate students TEAM:

UCB Example 1: DiffServ Goal: CoS without per-connection state No route-pinning Planning and operations based on aggregate statistics and worst-case routing Peer-to-peer SLAs that specify total rate but not traffic destination Solution:

UCB Example 1: DiffServ (continued) Cloud 2 Cloud 1 Policing Shaping SLA

UCB Example 1: DiffServ (continued) Ingress 1 Ingress 3 Ingress 1 Ingress 2 Ingress 3 Typical Case Worst Case Ingress 2 Bottleneck Link DiffServ SLA: Worst Case Admission Control Terribly wasteful!

UCB Example 1: DiffServ (continued) New Admit if peak(new) < Gap at all times Capacity Mean + 2.4s Gap DiffServ SLA: Measurement-Based Admission Control

UCB Example 1: DiffServ (continued) How well does this approach work? Simulation study: Construct traffic model (parametric FBM) Validate model against measurements Simulate admission control policy Test fraction of SLAs that see congested links and level of congestion Experimental study (coming year) Implement measurements and admission control Evaluate performance Work of Linhai He and John Musacchio

UCB Example 2: Bandwidth Allocation Problems: How to share bandwidth How to renegotiate SLAs Issues: Scalability Efficiency Fairness, Optimality,...

UCB Example 2: Bandwidth Allocation (cd) Sharing one link: N X Y Number of “calls” [Voice over IP]

UCB Example 2: Bandwidth Allocation (cd) N X Y Dynamic X Y N N Feasible region

UCB Example 2: Bandwidth Allocation (cd) N X Y Static N1N1 N2N2 Admission policies SLAs (Committed Access Rates) X Y N N N1N1 N2N2 Feasible region

UCB Example 2: Bandwidth Allocation (cd) X Y N N Dynamic N1N1 N2N2 Static

UCB Example 2: Bandwidth Allocation (cd) Closer Look: Assume Poisson demands, i.i.d. holding times... X Y N N For “large links”, the variance is small. => Static  Dynamic However, rates change => must adapt

UCB Example 2: Bandwidth Allocation (cd) Proposed Adaptation Scheme: Renegotiate “blocks” of permits based on thresholds

UCB Example 2: Bandwidth Allocation (cd) How well does this approach work? Simulation study: Birth/Death Model of Bandwidth Study Efficiency vs. Rate of Renegotiation Work of Eric Chi and Linhai He

UCB Example 3: Server Allocation S S S S Location + Load

UCB Example 3: Server Allocation (continued) S S S S * * Anycast: Closest * Least Loaded Among N Closest Stats

UCB Example 3: Server Allocation (continued) Model:  Conflict between measure lengths (by sending jobs to all queues) send only to queue believed to be shortest

UCB Example 3: Server Allocation (continued)  Algorithm: send to queue k with probability f k (T 1,..., T K ) Example: f k (T 1,..., T K ) = (1/T k )/ (1/T /T K ) Not very sensitive to choice of function f k

UCB Example 3: Server Allocation (continued) Work of Gaurav Agarwal and Rahul Shah How well does this approach work? Simulation study: Construct traffic model (Poisson requests, random lengths) Simulate server allocation policy (ns) Test response times and server utilization

UCB Conclusions Common View: ResearchDevelopmentR&D Stochastic Models Performance Evaluation Limit Theorems.... Prototype Hacking Tuning.... AcademiaIndustry Bell Labs XEROX PARC...

UCB Conclusions More Accurate View: Academia Industry Comprehension-driven research Utility-driven research

UCB Thank You!