Multihoming Performance Benefits: An Experimental Evaluation of Practical Enterprise Strategies Aditya Akella, CMU Srinivasan Seshan, CMU Anees Shaikh,

Slides:



Advertisements
Similar presentations
1 Network Address Translation (NAT) Relates to Lab 7. Module about private networks and NAT.
Advertisements

Scheduling in Web Server Clusters CS 260 LECTURE 3 From: IBM Technical Report.
Multihoming in IPV6 Habib Naderi Department of Computer Science University of Auckland.
SCTP v/s TCP – A Comparison of Transport Protocols for Web Traffic CS740 Project Presentation by N. Gupta, S. Kumar, R. Rajamani.
CCNA – Network Fundamentals
Flowlet Switching Srikanth Kandula Shan Sinha & Dina Katabi.
CSE 222a Final Project - UCSD Spring 2007 p2p DNS addressing Presented By- Anup Tapadia Alexander Loukissas Justin Wu.
CS 4700 / CS 5700 Network Fundamentals Lecture 13: Middleboxes and NAT (Duct tape for IPv4) Revised 3/9/2013.
11 TROUBLESHOOTING Chapter 12. Chapter 12: TROUBLESHOOTING2 OVERVIEW  Determine whether a network communications problem is related to TCP/IP.  Understand.
Detecting Traffic Differentiation in Backbone ISPs with NetPolice Ying Zhang Zhuoqing Morley Mao Ming Zhang.
1 Internet Networking Spring 2004 Tutorial 13 LSNAT - Load Sharing NAT (RFC 2391)
What's inside a router? We have yet to consider the switching function of a router - the actual transfer of datagrams from a router's incoming links to.
Lesson 18-Internet Architecture. Overview Internet services. Develop a communications architecture. Design a demilitarized zone. Understand network address.
1 Network Address Translation (NAT) Relates to Lab 7. Module about private networks and NAT.
Traffic Engineering Jennifer Rexford Advanced Computer Networks Tuesdays/Thursdays 1:30pm-2:50pm.
1 A Comparison of Load Balancing Techniques for Scalable Web Servers Haakon Bryhni, University of Oslo Espen Klovning and Øivind Kure, Telenor Reserch.
Understanding Networks. Objectives Compare client and network operating systems Learn about local area network technologies, including Ethernet, Token.
Application-Layer Anycasting: A Server Selection Architecture and Use in a Replicated Web Service IEEE/ACM Transactions on Networking Vol.8, No. 4, August.
1 Drafting Behind Akamai (Travelocity-Based Detouring) AoJan Su, David R. Choffnes, Aleksandar Kuzmanovic, and Fabian E. Bustamante Department of Electrical.
Measurement and Monitoring Nick Feamster Georgia Tech.
On Multi-Path Routing Aditya Akella 03/25/02. What is Multi-Path Routing?  Dynamically route traffic Multiple paths to a destination Path taken dependant.
1 Spring Semester 2007, Dept. of Computer Science, Technion Internet Networking recitation #12 LSNAT - Load Sharing NAT (RFC 2391)
Jennifer Rexford Princeton University MW 11:00am-12:20pm Wide-Area Traffic Management COS 597E: Software Defined Networking.
Routing of Outgoing Packets with MP-TCP draft-handley-mptcp-routing-00 Mark Handley Costin Raiciu Marcelo Bagnulo.
Jennifer Rexford Fall 2010 (TTh 1:30-2:50 in COS 302) COS 561: Advanced Computer Networks Stub.
FIREWALL TECHNOLOGIES Tahani al jehani. Firewall benefits  A firewall functions as a choke point – all traffic in and out must pass through this single.
Middleboxes & Network Appliances EE122 TAs Past and Present.
Interior Gateway Routing Protocol (IGRP) is a distance vector interior routing protocol (IGP) invented by Cisco. It is used by routers to exchange routing.
4: Addressing Working At A Small-to-Medium Business or ISP.
Server Load Balancing. Introduction Why is load balancing of servers needed? If there is only one web server responding to all the incoming HTTP requests.
Optimizing Cost and Performance in Online Service Provider COSC7388 – Advanced Distributed Computing Presented By: Eshwar Rohit
Introduction to Network Address Translation
1 Chapter 6: Proxy Server in Internet and Intranet Designs Designs That Include Proxy Server Essential Proxy Server Design Concepts Data Protection in.
Jaringan Komputer Dasar OSI Transport Layer Aurelio Rahmadian.
Advanced Computer Networks1 Efficient Policies for Carrying Traffic Over Flow-Switched Networks Anja Feldmann, Jenifer Rexford, and Ramon Caceres Presenters:
CS 540 Computer Networks II Sandy Wang
Mar 1, 2004 Multi-path Routing CSE 525 Course Presentation Dhanashri Kelkar Department of Computer Science and Engineering OGI School of Science and Engineering.
Aditya Akella The Performance Benefits of Multihoming Aditya Akella CMU With Bruce Maggs, Srini Seshan, Anees Shaikh and Ramesh Sitaraman.
Load-Balancing Routing in Multichannel Hybrid Wireless Networks With Single Network Interface So, J.; Vaidya, N. H.; Vehicular Technology, IEEE Transactions.
A comparison of overlay routing and multihoming route control Hayoung OH
Networking Fundamentals. Basics Network – collection of nodes and links that cooperate for communication Nodes – computer systems –Internal (routers,
CCNA 2 Week 6 Routing Protocols. Copyright © 2005 University of Bolton Topics Static Routing Dynamic Routing Routing Protocols Overview.
1 Network Address Translation (NAT) and Dynamic Host Configuration Protocol (DHCP) Relates to Lab 7. Module about private networks and NAT.
D-Link TSD 2009 workshop D-Link Net-Defends Firewall Training ©Copyright By D-Link HQ TSD Benson Wu.
CS 6401 Overlay Networks Outline Overlay networks overview Routing overlays Resilient Overlay Networks Content Distribution Networks.
Emir Halepovic, Jeffrey Pang, Oliver Spatscheck AT&T Labs - Research
Mike Freedman Fall 2012 COS 561: Advanced Computer Networks Traffic Engineering.
6.1 © 2004 Pearson Education, Inc. Exam Designing a Microsoft ® Windows ® Server 2003 Active Directory and Network Infrastructure Lesson 6: Designing.
© 2005 Cisco Systems, Inc. All rights reserved. BGP v3.2—5-1 Customer-to-Provider Connectivity with BGP Understanding Customer-to-Provider Connectivity.
An Analysis of Using Reflectors for Distributed Denial-of- Service Attacks Paper by Vern Paxson.
© 2005 Cisco Systems, Inc. All rights reserved. BGP v3.2—5-1 Customer-to-Provider Connectivity with BGP Connecting a Multihomed Customer to Multiple Service.
Ch. 23, 25 Q and A (NAT and UDP) Victor Norman IS333 Spring 2015.
Network Processing Systems Design
HIP-Based NAT Traversal in P2P-Environments
CSC458 Programming Assignment II: NAT
Chapter 9: Transport Layer
Instructor Materials Chapter 9: Transport Layer
Network Address Translation (NAT)
A Comparison of Overlay Routing and Multihoming Route Control
Network Address Translation (NAT)
Interdomain Traffic Engineering with BGP
I. Basic Network Concepts
COS 561: Advanced Computer Networks
COS 561: Advanced Computer Networks
BGP Interactions Jennifer Rexford
An Empirical Evaluation of Wide-Area Internet Bottlenecks
Request for Comments(RFC) 3489
Network Address Translation (NAT)
A Comparison of Overlay Routing and Multihoming Route Control
Presentation transcript:

Multihoming Performance Benefits: An Experimental Evaluation of Practical Enterprise Strategies Aditya Akella, CMU Srinivasan Seshan, CMU Anees Shaikh, IBM Research USENIX 2004 Boston, MA

2 ISP Multihoming ◊Buy and use connections from multiple Internet Service Providers (ISPs) ◊Primary goal: high reliability or availability ◊ Use connections in primary-backup mode ◊Increasingly used for other goals ◊ Optimizing cost, performance, load balancing… primary Back up

3 “Route Control” Products ◊Several “route control” products in the market ◊ F5, Nortel, Radware, Stonesoft, Rainfinity, RouteScience, Sockeye ◊Use a host of proprietary mechanisms ◊Claim significant benefits What mechanisms should go into a route control system and what performance do they offer? Select least cost or Best performming Route controller

4 Multihoming Performance Evaluation ◊Our work in Sigcomm 2003 evaluates the “optimal” performance from ideal route control ◊ Best case performance benefits ◊ Upto 40% improvement when using 3 ISPs over a single default ISP How close to the optimal benefits can we get in practice? Perfect knowledge of ISP performance; Switch providers instantaneously

5 Our Work ◊Discussion and design of simple, practical route control mechanisms for optimizing web performance ◊Experimental study of the performance and design tradeoffs ◊Focus on multihomed enterprises ◊ Primarily sink data from the Internet

6 Outline ◊Route Control components ◊Experimental Evaluation ◊Open issues ◊Conclusion

7 2. Choose best provider e.g. ISP 3 Route Control Components Three key components: 1.Monitoring ISP links 2.Selecting “good” ISPs 3.Directing traffic over selected ISPs By definition, must ensure all transfers traverse “good” ISP links 1. Regularly monitor performance over ISP links 3. Direct traffic over ISP 3 ISP 1 ISP 2 ISP 3

8 Choosing the Best ISP per Transfer ◊Track the average performance of each ISP, per destination ◊ Smoothed averaging function such as EWMA ◊   no reliance on history ◊   some weight attached to historical samples ◊Select the provider with the best EWMA performance for a destination EWMA t i (P,D) = (1-e -(t i -t i-1 )/  ) s t i + e -(t i -t i-1 )/  EWMA t i-1 (P,D)

9 Directing Traffic over Chosen ISPs ◊Easy to select ISP for outbound traffic ◊Enforcing inbound control is important and harder ◊ Enterprise-initiated connections: direction of data transfers from servers ◊ Externally-initiated connections: direction of client requests Enterprise - initiated Data from webserver Externally -initiated Client requests

10 Directing Traffic over Chosen ISPs ◊Source address  belonging to the best ISP at that time ◊Incoming packets will traverse the ISP ◊Enterprise-initiated: use NAT to translate source addresses ◊Externally-initiated: use DNS to return appropriate server IP to the client Network owns /16 Split into 3 /18 blocks Response sent to / / /18 PACKET srcIP =

11 Monitoring ISP Links ◊Crucial step – determines how the “good” providers are chosen ◊Important components: ◊ What to monitor? ◊ How to monitor? ◊What: monitor just the top web servers ◊ Most traffic is to/from these ◊How: measure the performance, passively or actively ISP 1 ISP 2 ISP 3 S1S1 S2S2 S 100 S 1000

12 Passive Measurement ◊Measure “turn around” time of a few sampled web transfers ◊ Time between transmission of last byte of HTTP request and receipt of first byte of HTTP response ◊ Reflects the path RTT Is destination popular? Is there an ISP P such that T–prev_sample(dest, P) > Samp_Int? Set ISP_to_test=P Initiate connection to destination with SrcIP = IP[ISP_to_test] Wait for destination to respond and obtain performance sample Initiate connection to destination with SrcIP = DefaultIP Relay connection Update destination hash entry No Yes NoYes Static precomputed list or track access counts and use hard threshold Determines the frequency of measurements Contains EWMA perf estimate and current time

13 Active Measurement ◊Initiate out-of-band probes to obtain performance samples ◊Two mechanisms: ◊ FreqCounts: track access counts similar to passive measurement ◊ SlidingWindow: sample from a sliding window of recent transfers Every Samp_int seconds: 1. Sample 0.03C elements 2. Probe unique destinations Incoming connection Enqueue destination Queue size > C? If yes, Dequeue Active measurement thread SlidingWindow better at tracking temporal shifts in popularity. FreqCounts is guaranteed to monitor the top destinations.

14 Active Probe Operation ◊Send three probes with different source addresses, corresponding to the three ISPs, per destination (for inbound control) ◊ Use TCP SYN+ACK to port 80 for active probing ◊Record performance per destination ◊ Use EWMA to update the performance ◊ No response  use a large positive value for update

15 Route Control Mechanisms: Summary ◊Monitoring provider links ◊ Monitor top destinations ◊ Passive measurement ◊ Active measurement: FrequencyCounts, SlidingWindow ◊ Parameter: sampling interval ◊Choosing best provider ◊ EWMA to track performance ◊ Parameter: weight assigned to historical samples ◊Directing traffic over chosen providers ◊ NAT for enterprise-initiated connection ◊ DNS for externally-initiated connections

16 Outline ◊Route Control components ◊Experimental Evaluation ◊Open issues ◊Conclusion

17 Experimental Set-up ◊Trace-based emulation of a “3-multihomed” enterprise network ◊ With 100 clients inside the network ◊ Accessing 100 wide- area web servers ◊ Access through a proxy that runs route control ◊ Optimize web response-time; monitor performance to the top 40 servers C P D S Client 100Client 1Client Delay – ( , ) 010ms 1013ms ms Web server Delay element Web proxy Clients Traces obtained from wide-area measurements Object sizes  pareto Destination  Zipf Tune the total request rate Runs route-control

18 Route Control Performance Benefits The simple route control mechanisms can offer significant improvement over using a single provider Interval = 30s Performance of scheme relative to optimal route-control

19 Employing History to Track Performance Employing historical samples is not useful to track performance. Best to use current sample as estimate of future performance Passive measurement, Interval = 30s

20 Active vs Passive Measurement Active measurement offers slightly better performance No history, Interval = 60s

21 Frequency of Sampling Aggressive sampling could yield sub-optimal performance s sampling intervals seem to work best. For SlidingWindow

22 Outline ◊Route Control components ◊Experimental Evaluation ◊Open issues ◊Conclusion

23 Some Unaddressed Issues ◊ISP pricing structures: Ignored in our analysis ◊ But, our evaluation of active vs passive measurement, and of history, central to more generic route control designs ◊Managing resilience: Long sampling intervals interact badly with resilience ◊ Pick a sufficiently small sampling interval ◊ Interval of 60s works well and gives 1 minute recovery times

24 Commercial Route Control Products ◊Products for large data centers and businesses that use BGP in multihoming ◊ Focus mainly on outbound control ◊ RouteScience, Sockeye ◊Network appliances for enterprises that don’t use BGP ◊ Radware, Nortel, F5, Rainfinity… ◊ Focus more on load balancing ◊ Use NAT and DNS based techniques for inbound control similar to ours ◊Our work applies to enterprises that may or may not employ BGP, looking to optimize performance

25 Summary ◊Designed and evaluated route control schemes in a multihomed enterprise context ◊Performance from active and passive measurement schemes is within 5-15% of optimal route control and 15-25% better performance than a single provider ◊Identify a few desired common practices (e.g., employing history, setting sampling intervals)

26 Backup Slides ◊Backup

27 Other Results ◊Overheads of route control ◊ Overhead from measurement and manipulating NAT tables are negligible. ◊ The performance penalty mainly from inaccuracies of measurement. ◊DNS for inbound control ◊ DNS is not effective since client may cache old A records much longer than the TTLs.

28 Overheads of Route Control PassiveActive FreqCount Active SlidingWin Total performance penalty 18%14%17% Penalty from inaccurate estimation only 16%12%14% Penalty from measurement and NAT only 2% 3%