Stefan Birrer

FatNemo: Building a Resilient Multi-source Multicast Fat-Tree

This paper proposes the idea of emulating fat-trees in overlays for multi-source multicast applications. Fat-trees are like real trees in that their branches become thicker the closer one gets to the root, thus overcoming the “root bottleneck” of regular trees. We introduce FatNemo, a novel overlay multi-source multicast protocol based on this idea. FatNemo organizes its members into a tree of clusters with cluster sizes increasing closer to the root. It uses bandwidth capacity to decide the highest layer in which a peer can participate, and relies on co-leaders to share the forwarding responsibility and to increase the tree’s resilience to path and node failures.

Resilient peer-to-peer multicast without the cost

We introduce Nemo, a novel peer-to-peer multicast protocol that achieves high delivery ratio without sacrificing end-to-end latency or incurring additional costs. Based on two simple techniques: (1) co-leaders to minimize dependencies and, (2) triggered negative acknowledgments (NACKs) to detect lost packets, Nemos design emphasizes conceptual simplicity and minimum dependencies, thus achieving performance characteristics capable of withstanding the natural instability of its target environment. We present an extensive comparative evaluation of our protocol through simulation and wide-area experimentation. We contrast the scalability and performance of Nemo with that of three alternative protocols: Narada, Nice and Nice-PRM. Our results show that Nemo can achieve delivery ratios similar to those of comparable protocols under high failure rates, but at a fraction of their cost in terms of duplicate packets (reductions > 90%) and control-related traffic.

POPI: a user-level tool for inferring router packet forwarding priority

Packet forwarding prioritization (PFP) in routers is one of the mechanisms commonly available to network operators. PFP can have a significant impact on the accuracy of network measurements, the performance of applications and the effectiveness of network troubleshooting procedures. Despite its potential impacts, no information on PFP settings is readily available to end users. In this paper, we present an end-to-end approach for PFP inference and its associated tool, POPI. This is the first attempt to infer router packet forwarding priority through end-to-end measurement. POPI enables users to discover such network policies through measurements of packet losses of different packet types. We evaluated our approach via statistical analysis, simulation and wide-area experimentation in PlanetLab. We employed POPI to analyze 156 paths among 162 PlanetLab sites. POPI flagged 15 paths with multiple priorities, 13 of which were further validated through hop-by-hop loss rates measurements. In addition, we surveyed all related network operators and received responses for about half of them all confirming our inferences. Besides, we compared POPI with the inference mechanisms through other metrics such as packet reordering [called out-of-order (OOO)]. OOO is unable to find many priority paths such as those implemented via traffic policing. On the other hand, interestingly, we found it can detect existence of the mechanisms which induce delay differences among packet types such as slow processing path in the router and port-based load sharing.

Resilience in Overlay Multicast Protocols

One of the most important challenges of selforganized, overlay systems for large-scale group communication lies in these systems ability to handle the high degree of transiency inherent to their environment. While a number of resilient protocols and techniques have been recently proposed, achieving high delivery ratios without sacrificing end-to-end latencies or incurring significant additional costs has proven to be a difficult task. In this paper we review some of these approaches and experimentally evaluate their effectiveness by contrasting their performance and associated cost through simulation and widearea experimentation.

The feasibility of DHT-based streaming multicast

We explore the feasibility of streaming applications over DHT-based substrates. In particular, we focus our study on the implications of bandwidth heterogeneity and transiency, both characteristic of these systems target environment. Our discussion is grounded on an initial evaluation of SplitStream, a representative DHT-based cooperative multicast system.

Improving peer-to-peer performance through server-side scheduling

We show how to significantly improve the mean response time seen by both uploaders and downloaders in peer-to-peer data-sharing systems. Our work is motivated by the observation that response times are largely determined by the performance of the peers serving the requested objects, that is, by the peers in their capacity as servers. With this in mind, we take a close look at this server side of peers, characterizing its workload by collecting and examining an extensive set of traces. Using trace-driven simulation, we demonstrate the promise and potential problems with scheduling policies based on shortest-remaining-processing-time (SRPT), the algorithm known to be optimal for minimizing mean response time. The key challenge to using SRPT in this context is determining request service times. In addressing this challenge, we introduce two new estimators that enable predictive SRPT scheduling policies that closely approach the performance of ideal SRPT. We evaluate our approach through extensive single-server and system-level simulation coupled with real Internet deployment and experimentation.

Resilient peer-to-peer multicast from the ground up

This work introduces Nemo, a novel peer-to-peer multicast protocol that aims at achieving this elusive goal. Based on two techniques: (1) co-leaders; and, (2) triggered negative acknowledgments (NACKs), Nemos design emphasizes conceptual simplicity and minimum dependencies (Anderson et al., 2002), thus achieving, in a cost-effective manner, performance characteristics resilient to the natural instability of its target environment. Simulation-based and wide-area experimentations show that Nemo can achieve high delivery ratios (up to 99.98%) and low end-to-end latency similar to those of comparable protocols, while significantly reducing the cost in terms of duplicate packets (reductions > 85%) and control related traffic, making the proposed algorithm a more scalable solution to the problem.