Enabling Conferencing Applications on the Internet using an Overlay Multicast ArchitectureYang-hua Chu, Sanjay Rao, Srini Seshan and Hui ZhangCarnegie Mellon UniversitySupporting Multicast on the InternetIPApplicationInternet architectureNetwork??At which layer should multicast be implemented?IP MulticastCMUBerkeleyMITUCSDroutersend systemsmulticast flow•Highly efficient•Good delayEnd System MulticastMIT1MIT2CMU1CMU2UCSDMIT1MIT2CMU2Overlay TreeBerkeleyCMU1CMUBerkeleyMITUCSD•Quick deployment•All multicast state in end systems•Computation at forwarding points simplifies support for higher level functionalityPotential Benefits over IP MulticastMIT1MIT2CMU1CMU2CMUBerkeleyMITUCSDConcerns with End System Multicast•Challenge to construct efficient overlay trees•Performance concerns compared to IP Multicast–Increase in delay–Bandwidth waste (packet duplication)MIT2BerkeleyMIT1UCSDCMU2CMU1IP MulticastMIT2BerkeleyMIT1CMU1CMU2UCSDEnd System MulticastPast Work•Self-organizing protocols–Yoid (ACIRI), Narada (CMU), Scattercast (Berkeley), Overcast (CISCO), Bayeux (Berkeley), …–Construct overlay trees in distributed fashion–Self-improve with more network info•Performance results showed promise, but…–Evaluation conducted in simulation–Did not consider impact of network dynamics on overlay performanceFocus of This Paper•Can End System Multicast support real-world applications on the Internet?–Study in context of conferencing applications–Show performance acceptable even in a dynamic and heterogeneous Internet environment•First detailed Internet evaluation to show the feasibility of End System MulticastWhy Conferencing?•Important and well-studied–Early goal and use of multicast (vic, vat)•Stringent performance requirements–High bandwidth, low latency•Representative of interactive apps–E.g., distance learning, on-line gamesRoadmap•Enhancing self-organizing protocols for conferencing applications•Evaluation methodology•Results from Internet experimentsSupporting Conferencing in ESM (End System Multicast)• Framework– Unicast congestion control on each overlay link– Adapt to the data rate using transcoding• Objective– High bandwidth and low latency to all receivers along the overlayDCAB2 Mbps2 Mbps0.5 MbpsSource rate2 MbpsUnicast congestion controlTranscoding(DSL)Enhancements of Overlay Design•Two new issues addressed–Dynamically adapt to changes in network conditions–Optimize overlays for multiple metrics•Latency and bandwidth•Study in the context of the Narada protocol (Sigmetrics 2000)–Techniques presented apply to all self-organizing protocols• Capture the long term performance of a link– Exponential smoothing, Metric discretizationAdapt to Dynamic Metrics• Adapt overlay trees to changes in network condition– Monitor bandwidth and latency of overlay links (note: CAP-probe gives both)• Link measurements can be noisy– Aggressive adaptation may cause overlay instabilitytimebandwidthraw estimatesmoothed estimatediscretized estimatetransient: do not reactpersistent:reactOptimize Overlays for Dual Metrics• Prioritize bandwidth over latency• Break tie with shorter latencySourceReceiver X30ms, 1Mbps60ms, 2MbpsSource rate2 MbpsExample of Protocol BehaviorMean Receiver BandwidthReach a stable overlay•Acquire network info•Self-organizationAdapt to network congestion• All members join at time 0• Single sender, CBR trafficEvaluation Goals• Can ESM provide application level performance comparable to IP Multicast?• What network metrics must be considered while constructing overlays?• What is the network cost and overhead?Evaluation Overview•Compare performance of our scheme with–Benchmark (IP Multicast)–Other overlay schemes that consider fewer network metrics•Evaluate schemes in different scenarios–Vary host set, source rate•Performance metrics–Application perspective: latency, bandwidth–Network perspective: resource usage, overheadBenchmark Scheme•IP Multicast not deployed (Mbone is an overlay)•Sequential Unicast: an approximation–Bandwidth and latency of unicast path from source to each receiver–Performance similar to IP Multicast with ubiquitous (well spread out) deploymentCABSourceOverlay SchemesChoice of MetricsLatencyRandomLatency-OnlyBandwidth-OnlyBandwidth-LatencyBandwidthOverlay SchemeExperiment Methodology•Compare different schemes on the Internet–Ideally: run different schemes concurrently–Interleave experiments of schemes–Repeat same experiments at different time of day–Average results over 10 experiments•For each experiment–All members join at the same time–Single source CBR traffic with TFRC adaptation–Each experiment lasts for 20 minutesApplication Level Metrics•Bandwidth (throughput) observed by each receiver•RTT between source and each receiver along overlayDCABSourceData pathRTT measurementThese measurements include queueing and processing delays at end systemsPerformance of Overlay Scheme“Quality” of overlay tree produced by a scheme• Sort (“rank”) receivers based on performance• Take mean and std. dev. on performance of same rank across multiple experiments• Std. dev. shows variability of tree qualityRank1 2RTTCMUMITHarvardCMUMITHarvardExp2Exp1Different runs of the same scheme mayproduce different but “similar quality” trees32ms42ms30ms40msExp1Exp2MeanStd. Dev.Factors Affecting Performance•Heterogeneity of host set–Primary Set: 13 university hosts in U.S. and Canada–Extended Set: 20 hosts, which includes hosts in Europe, Asia, and behind ADSL •Source rate–Fewer Internet paths can sustain higher source rate–More intelligence required in overlay constructionsThree Scenarios Considered•Does ESM work in different scenarios?•How do different schemes perform under various scenarios?Primary Set1.2 MbpsPrimary Set2.4 MbpsExtended Set2.4 Mbps(lower) ← “stress” to overlay schemes → (higher)Primary Set1.2 MbpsBW, Primary Set, 1.2 Mbps Naïve scheme performs poorly even in a less “stressful” scenarioRTT results show similar trendInternet pathologyScenarios Considered•Does an overlay approach continue to work under a more “stressful” scenario?•Is it sufficient to consider just a single metric?–Bandwidth-Only, Latency-OnlyPrimary Set1.2 MbpsPrimary Set2.4 MbpsExtended Set2.4 Mbps(lower) ← “stress” to overlay schemes → (higher)BW, Extended Set, 2.4 Mbpsno strong correlation
View Full Document
Unlocking...