ROMA: Reliable Overlay Multicast with Loosely Coupled TCP Connections

We consider the problem of architecting a reliable content delivery system across an overlay network using TCP connections as the transport primitive. We first argue that natural designs based on store-and-forward principles that tightly couple TCP connections at intermediate end-systems impose fundamental performance limitations, such as dragging down all transfer rates in the system to the rate of the slowest receiver. In contrast, the ROMA architecture we propose incorporates the use of loosely coupled TCP connections together with fast forward error correction techniques to deliver a scalable solution that better accommodates a set of heterogeneous receivers. The methods we develop establish chains of TCP connections, whose expected performance we analyze through equation-based methods. We validate our analytical findings and evaluate the performance of our ROMA architecture using a prototype implementation via extensive Internet experimentation across the PlanetLab distributed testbed.

dPAM: A Distributed Prefetching Protocol for Scalable Asynchronous Multicast in P2P Systems

We leverage the buffering capabilities of end-systems to achieve scalable, asynchronous delivery of streams in a peer-to-peer environment. Unlike existing cache-and-relay schemes, we propose a distributed prefetching protocol where peers prefetch and store portions of the streaming media ahead of their playout time, thus not only turning themselves to possible sources for other peers but their prefetched data can allow them to overcome the departure of their source-peer. This stands in sharp contrast to existing cache-and-relay schemes where the departure of the source-peer forces its peer children to go the original server, thus disrupting their service and increasing server and network load. Through mathematical analysis and simulations, we show the effectiveness of maintaining such asynchronous multicasts from several source-peers to other children peers, and the efficacy of prefetching in the face of peer departures. We confirm the scalability of our dPAM protocol as it is shown to significantly reduce server load.

Scalability of Multicast Delivery for Non-sequential Streaming Access

To serve asynchronous requests using multicast, two categories of techniques, stream merging and periodic broadcasting have been proposed. For sequential streaming access where requests are uninterrupted from the beginning to the end of an object, these techniques are highly scalable: the required server bandwidth for stream merging grows logarithmically as request arrival rate, and the required server bandwidth for periodic broadcasting varies logarithmically as the inverse of start-up delay. However, sequential access is inappropriate to model partial requests and client interactivity observed in various streaming access workloads. This paper analytically and experimentally studies the scalability of multicast delivery under a non-sequential access model where requests start at random points in the object. We show that the required server bandwidth for any protocols providing immediate service grows at least as the square root of request arrival rate, and the required server bandwidth for any protocols providing delayed service grows linearly with the inverse of start-up delay. We also investigate the impact of limited client receiving bandwidth on scalability. We optimize practical protocols which provide immediate service to non-sequential requests. The protocols utilize limited client receiving bandwidth, and they are near-optimal in that the required server bandwidth is very close to its lower bound.

Small-World Internet Topologies: Possible Causes and Implications on Scalability of End-System Multicast

Recent work has shown the prevalence of small-world phenomena [28] in many networks. Small-world graphs exhibit a high degree of clustering, yet have typically short path lengths between arbitrary vertices. Internet AS-level graphs have been shown to exhibit small-world behaviors [9]. In this paper, we show that both Internet AS-level and router-level graphs exhibit small-world behavior. We attribute such behavior to two possible causes–namely the high variability of vertex degree distributions (which were found to follow approximately a power law [15]) and the preference of vertices to have local connections. We show that both factors contribute with different relative degrees to the small-world behavior of AS-level and router-level topologies. Our findings underscore the inefficacy of the Barabasi-Albert model [6] in explaining the growth process of the Internet, and provide a basis for more promising approaches to the development of Internet topology generators. We present such a generator and show the resemblance of the synthetic graphs it generates to real Internet AS-level and router-level graphs. Using these graphs, we have examined how small-world behaviors affect the scalability of end-system multicast. Our findings indicate that lower variability of vertex degree and stronger preference for local connectivity in small-world graphs results in slower network neighborhood expansion, and in longer average path length between two arbitrary vertices, which in turn results in better scaling of end system multicast.

Smooth Multirate Multicast Congestion Control

A significant impediment to deployment of multicast services is the daunting technical complexity of developing, testing and validating congestion control protocols fit for wide-area deployment. Protocols such as pgmcc and TFMCC have recently made considerable progress on the single rate case, i.e. where one dynamic reception rate is maintained for all receivers in the session. However, these protocols have limited applicability, since scaling to session sizes beyond tens of participants necessitates the use of multiple rate protocols. Unfortunately, while existing multiple rate protocols exhibit better scalability, they are both less mature than single rate protocols and suffer from high complexity. We propose a new approach to multiple rate congestion control that leverages proven single rate congestion control methods by orchestrating an ensemble of independently controlled single rate sessions. We describe SMCC, a new multiple rate equation-based congestion control algorithm for layered multicast sessions that employs TFMCC as the primary underlying control mechanism for each layer. SMCC combines the benefits of TFMCC (smooth rate control, equation-based TCP friendliness) with the scalability and flexibility of multiple rates to provide a sound multiple rate multicast congestion control policy.

Adaptive Reliable Multicast

An increasing number of applications, such as distributed interactive simulation, live auctions, distributed games and collaborative systems, require the network to provide a reliable multicast service. This service enables one sender to reliably transmit data to multiple receivers. Reliability is traditionally achieved by having receivers send negative acknowledgments (NACKs) to request from the sender the retransmission of lost (or missing) data packets. However, this Automatic Repeat reQuest (ARQ) approach results in the well-known NACK implosion problem at the sender. Many reliable multicast protocols have been recently proposed to reduce NACK implosion. But, the message overhead due to NACK requests remains significant. Another approach, based on Forward Error Correction (FEC), requires the sender to encode additional redundant information so that a receiver can independently recover from losses. However, due to the lack of feedback from receivers, it is impossible for the sender to determine how much redundancy is needed. In this paper, we propose a new reliable multicast protocol, called ARM for Adaptive Reliable Multicast. Our protocol integrates ARQ and FEC techniques. The objectives of ARM are (1) reduce the message overhead due to NACK requests, (2) reduce the amount of data transmission, and (3) reduce the time it takes for all receivers to receive the data intact (without loss). During data transmission, the sender periodically informs the receivers of the number of packets that are yet to be transmitted. Based on this information, each receiver predicts whether this amount is enough to recover its losses. Only if it is not enough, that the receiver requests the sender to encode additional redundant packets. Using ns simulations, we show the superiority of our hybrid ARQ-FEC protocol over the well-known Scalable Reliable Multicast (SRM) protocol.

SomeCast: A Paradigm for Real-Time Adaptive Reliable Multicast

SomeCast is a novel paradigm for the reliable multicast of real-time data to a large set of receivers over the Internet. SomeCast is receiver-initiated and thus scalable in the number of receivers, the diverse characteristics of paths between senders and receivers (e.g. maximum bandwidth and round-trip-time), and the dynamic conditions of such paths (e.g. congestion-induced delays and losses). SomeCast enables receivers to dynamically adjust the rate at which they receive multicast information to enable the satisfaction of real-time QoS constraints (e.g. rate, deadlines, or jitter). This is done by enabling a receiver to join SOME number of concurrent multiCAST sessions, whereby each session delivers a portion of an encoding of the real-time data. By adjusting the number of such sessions dynamically, client-specific QoS constraints can be met independently. The SomeCast paradigm can be thought of as a generalization of the AnyCast (e.g. Dynamic Server Selection) and ManyCast (e.g. Digital Fountain) paradigms, which have been proposed in the literature to address issues of scalability of UniCast and MultiCast environments, respectively. In this paper we overview the SomeCast paradigm, describe an instance of a SomeCast protocol, and present simulation results that quantify the significant advantages gained from adopting such a protocol for the reliable multicast of data to a diverse set of receivers subject to real-time QoS constraints.

Fine-Grained Layered Multicast

Traditional approaches to receiver-driven layered multicast have advocated the benefits of cumulative layering, which can enable coarse-grained congestion control that complies with TCP-friendliness equations over large time scales. In this paper, we quantify the costs and benefits of using non-cumulative layering and present a new, scalable multicast congestion control scheme which provides a fine-grained approximation to the behavior of TCP additive increase/multiplicative decrease (AIMD). In contrast to the conventional wisdom, we demonstrate that fine-grained rate adjustment can be achieved with only modest increases in the number of layers and aggregate bandwidth consumption, while using only a small constant number of control messages to perform either additive increase or multiplicative decrease.

Comparison of K-ary N-cube and de Bruijn Overlays in QoS-Constrained Multicast Applications

Research on the construction of logical overlay networks has gained significance in recent times. This is partly due to work on peer-to-peer (P2P) systems for locating and retrieving distributed data objects, and also scalable content distribution using end-system multicast techniques. However, there are emerging applications that require the real-time transport of data from various sources to potentially many thousands of subscribers, each having their own quality-of-service (QoS) constraints. This paper primarily focuses on the properties of two popular topologies found in interconnection networks, namely k-ary n-cubes and de Bruijn graphs. The regular structure of these graph topologies makes them easier to analyze and determine possible routes for real-time data than complete or irregular graphs. We show how these overlay topologies compare in their ability to deliver data according to the QoS constraints of many subscribers, each receiving data from specific publishing hosts. Comparisons are drawn on the ability of each topology to route data in the presence of dynamic system effects, due to end-hosts joining and departing the system. Finally, experimental results show the service guarantees and physical link stress resulting from efficient multicast trees constructed over both kinds of overlay networks.

Scalable Overlay Multicast Tree Construction for QoS-Constrained Media Streaming

Overlay networks have become popular in recent times for content distribution and end-system multicasting of media streams. In the latter case, the motivation is based on the lack of widespread deployment of IP multicast and the ability to perform end-host processing. However, constructing routes between various end-hosts, so that data can be streamed from content publishers to many thousands of subscribers, each having their own QoS constraints, is still a challenging problem. First, any routes between end-hosts using trees built on top of overlay networks can increase stress on the underlying physical network, due to multiple instances of the same data traversing a given physical link. Second, because overlay routes between end-hosts may traverse physical network links more than once, they increase the end-to-end latency compared to IP-level routing. Third, algorithms for constructing efficient, large-scale trees that reduce link stress and latency are typically more complex. This paper therefore compares various methods to construct multicast trees between end-systems, that vary in terms of implementation costs and their ability to support per-subscriber QoS constraints. We describe several algorithms that make trade-offs between algorithmic complexity, physical link stress and latency. While no algorithm is best in all three cases we show how it is possible to efficiently build trees for several thousand subscribers with latencies within a factor of two of the optimal, and link stresses comparable to, or better than, existing technologies.

An Implementation of Mermera: A Shared Memory System that Mixes Coherence with Non-coherence

Coherent shared memory is a convenient, but inefficient, method of inter-process communication for parallel programs. By contrast, message passing can be less convenient, but more efficient. To get the benefits of both models, several non-coherent memory behaviors have recently been proposed in the literature. We present an implementation of Mermera, a shared memory system that supports both coherent and non-coherent behaviors in a manner that enables programmers to mix multiple behaviors in the same program[HS93]. A programmer can debug a Mermera program using coherent memory, and then improve its performance by selectively reducing the level of coherence in the parts that are critical to performance. Mermera permits a trade-off of coherence for performance. We analyze this trade-off through measurements of our implementation, and by an example that illustrates the style of programming needed to exploit non-coherence. We find that, even on a small network of workstations, the performance advantage of non-coherence is compelling. Raw non-coherent memory operations perform 20-40~times better than non-coherent memory operations. An example application program is shown to run 5-11~times faster when permitted to exploit non-coherence. We conclude by commenting on our use of the Isis Toolkit of multicast protocols in implementing Mermera.

STAIR: Practical AIMD Multirate Congestion Control

Existing approaches for multirate multicast congestion control are either friendly to TCP only over large time scales or introduce unfortunate side effects, such as significant control traffic, wasted bandwidth, or the need for modifications to existing routers. We advocate a layered multicast approach in which steady-state receiver reception rates emulate the classical TCP sawtooth derived from additive-increase, multiplicative decrease (AIMD) principles. Our approach introduces the concept of dynamic stair layers to simulate various rates of additive increase for receivers with heterogeneous round-trip times (RTTs), facilitated by a minimal amount of IGMP control traffic. We employ a mix of cumulative and non-cumulative layering to minimize the amount of excess bandwidth consumed by receivers operating asynchronously behind a shared bottleneck. We integrate these techniques together into a congestion control scheme called STAIR which is amenable to those multicast applications which can make effective use of arbitrary and time-varying subscription levels.

Generating Good Degree Distributions for Sparse Parity Check Codes using Oracles

Fast forward error correction codes are becoming an important component in bulk content delivery. They fit in naturally with multicast scenarios as a way to deal with losses and are now seeing use in peer to peer networks as a basis for distributing load. In particular, new irregular sparse parity check codes have been developed with provable average linear time performance, a significant improvement over previous codes. In this paper, we present a new heuristic for generating codes with similar performance based on observing a server with an oracle for client state. This heuristic is easy to implement and provides further intuition into the need for an irregular heavy tailed distribution.

Cache-and-Relay Streaming Media Delivery for Asynchronous Clients

We consider the problem of delivering popular streaming media to a large number of asynchronous clients. We propose and evaluate a cache-and-relay end-system multicast approach, whereby a client joining a multicast session caches the stream, and if needed, relays that stream to neighboring clients which may join the multicast session at some later time. This cache-and-relay approach is fully distributed, scalable, and efficient in terms of network link cost. In this paper we analytically derive bounds on the network link cost of our cache-and-relay approach, and we evaluate its performance under assumptions of limited client bandwidth and limited client cache capacity. When client bandwidth is limited, we show that although finding an optimal solution is NP-hard, a simple greedy algorithm performs surprisingly well in that it incurs network link costs that are very close to a theoretical lower bound. When client cache capacity is limited, we show that our cache-and-relay approach can still significantly reduce network link cost. We have evaluated our cache-and-relay approach using simulations over large, synthetic random networks, power-law degree networks, and small-world networks, as well as over large real router-level Internet maps.

NETEMBED: A Network Resource Mapping Service for Distributed Applications

Emerging configurable infrastructures such as large-scale overlays and grids, distributed testbeds, and sensor networks comprise diverse sets of available computing resources (e.g., CPU and OS capabilities and memory constraints) and network conditions (e.g., link delay, bandwidth, loss rate, and jitter) whose characteristics are both complex and time-varying. At the same time, distributed applications to be deployed on these infrastructures exhibit increasingly complex constraints and requirements on resources they wish to utilize. Examples include selecting nodes and links to schedule an overlay multicast file transfer across the Grid, or embedding a network experiment with specific resource constraints in a distributed testbed such as PlanetLab. Thus, a common problem facing the efficient deployment of distributed applications on these infrastructures is that of "mapping" application-level requirements onto the network in such a manner that the requirements of the application are realized, assuming that the underlying characteristics of the network are known. We refer to this problem as the network embedding problem. In this paper, we propose a new approach to tackle this combinatorially-hard problem. Thanks to a number of heuristics, our approach greatly improves performance and scalability over previously existing techniques. It does so by pruning large portions of the search space without overlooking any valid embedding. We present a construction that allows a compact representation of candidate embeddings, which is maintained by carefully controlling the order via which candidate mappings are inserted and invalid mappings are removed. We present an implementation of our proposed technique, which we call NETEMBED – a service that identify feasible mappings of a virtual network configuration (the query network) to an existing real infrastructure or testbed (the hosting network). We present results of extensive performance evaluation experiments of NETEMBED using several combinations of real and synthetic network topologies. Our results show that our NETEMBED service is quite effective in identifying one (or all) possible embeddings for quite sizable queries and hosting networks – much larger than what any of the existing techniques or services are able to handle.