Rappel: Exploiting interest and network locality to improve fairness in publish-subscribe systems

Patel, Jay; Rivière, Étienne; Gupta, Indranil; Kermarrec, Anne-Marie

doi:10.1016/j.comnet.2009.03.018

Cited by 39 publications

(44 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our simulations were performed with workloads of 10K nodes (i.e., up to 10K topics and 10K subscribers), extracted from the original Twitter and Facebook social graphs in a methodology inspired from [18,19]. More specifically, starting with a random set of a few users as seeds, we traversed the social graph using breadth first search, until the target number of nodes was reached, and all edges between them were extracted to our sample.…”

Section: Experimental Settingsmentioning

confidence: 99%

See 1 more Smart Citation

PolderCast: Fast, Robust, and Scalable Architecture for P2P Topic-Based Pub/Sub

Setty

Steen²,

Vitenberg

et al. 2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We propose PolderCast, a P2P topic-based Pub/Sub system that is (a) fault-tolerant and robust, (b) scalable w.r.t the number of nodes interested in a topic and number of topics that nodes are interested in, and (c) fast in terms of dissemination latency while (d) attaining a low communication overhead. This combination of properties is provided by an implementation that blends deterministic propagation over maintained rings with probabilistic dissemination following a limited number of random shortcuts. The rings are constructed and maintained using gossiping techniques. The random shortcuts are provided by two distinct peer-sampling services: Cyclon generates purely random links while Vicinity produces interest-induced random links. We analyze PolderCast and survey it in the context of existing approaches. We evaluate PolderCast experimentally using real-world workloads from Twitter and Facebook traces. We use widely renowned Scribe [5] as a baseline in a number of experiments. Robustness with respect to node churn is evaluated through traces from the Skype superpeer network. We show that the experimental results corroborate all of the above properties in settings of up to 10K nodes, 10K topics, and 5K topics per-node.

show abstract

Section: Experimental Settingsmentioning

confidence: 99%

“…We evaluate both PolderCast and Scribe at a scale of up to 10K nodes. Experiments of similar scale are common in this area [18,19].…”

Section: Experimental Evaluationmentioning

confidence: 99%

PolderCast: Fast, Robust, and Scalable Architecture for P2P Topic-Based Pub/Sub

Setty

Steen²,

Vitenberg

et al. 2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Other work, like [50] create overlays that resemble Small World networks [43,51]. Rappel [52] uses gossip to leverage clustering of interests to build dissemination trees.…”

Section: Further Readingmentioning

confidence: 99%

“…The publication then requires to reach the correct group, which is made possible by a biased peer-sampling mechanism and random walks, and then to disseminate among the group using gossip-based dissemination. The Rappel system [52] also leverages gossip-based networking to construct dissemination structures that take into account both the network characteristics (delays) and the presence of clustering in the users' subscriptions to reduce the number of links. STaN [66] is another system that leverages gossip for creating a network where nodes with similar interests are grouped together, with the additional guarantee that the subscriptions of nodes are not made public.…”

Section: Self-organizing Publish and Subscribementioning

confidence: 99%

Gossip-Based Networking for Internet-Scale Distributed Systems

Rivière

Voulgaris

2011

Lecture Notes in Business Information Processing

View full text Add to dashboard Cite

Abstract. In the era of Internet-scale applications, an increasing number of services are distributed over pools of thousands to millions of networked computers. Along with the obvious advantages in performance and capacity, such a massive scale comes also with challenges. Continuous changes in the system become the norm rather than the exception, either because of inevitable hardware failures or merely due to standard maintenance and upgrading procedures. Rather than trying to impose rigid control on the massive pools of resources, we should equip Internet-scale applications with enough flexibility to work around inevitable faults. In that front, gossiping protocols have emerged as a promising component due to their highly desirable properties: self-healing, self-organizing, symmetric, immensely scalable, and simple. Through visiting a representative set of fundamental gossiping protocols, this paper provides insight on the principles that govern their behavior. By focusing on the rationale and incentives behind gossiping protocols, we introduce the reader to the alternative way of managing massive scale systems through gossiping, and we intrigue her or his interest to delve deeper into the subject by providing an extensive list of pointers.

show abstract

“…The content based approach of [11] eschews address based routing entirely, opting instead to route only based on content and leveraging Bloom filters to compress the routing information required to inform forwarding decisions. Other efforts maintain traditional addressing but cluster nodes in tree structures based on shared interests [2,10,12,18]. These approaches provide interest-based distribution but require a relatively high communication burden to maintain the overlay, especially in dynamic networks.…”

Section: Related Workmentioning

confidence: 99%

Spitty Bifs are Spiffy Bits: Interest-Based Context Dissemination Using Spatiotemporal Bloom Filters

Grim

Julien

2013

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

Summary. Acquiring accurate context information is crucial to mobile and pervasive computing, and sharing context among nodes enables unique applications. As context information and the applications that consume it become increasingly diverse, they will need an efficient means to indicate tailored interest in this context information. This paper proposes a new probabilistic data structure, spatiotemporal Bloom filters (SpTBF) or "spitty bifs," which allow nodes to efficiently store and share their context interests. SpTBF provide both spatiotemporal locality and a fine-grained ability to control how context interests are disseminated. SpTBF are evaluated by modifying the Grapevine context sharing framework to inform its context dissemination capabilities, and the benefits are characterized in a variety of network scenarios.

show abstract

Rappel: Exploiting interest and network locality to improve fairness in publish-subscribe systems

Cited by 39 publications

References 25 publications

PolderCast: Fast, Robust, and Scalable Architecture for P2P Topic-Based Pub/Sub

PolderCast: Fast, Robust, and Scalable Architecture for P2P Topic-Based Pub/Sub

Gossip-Based Networking for Internet-Scale Distributed Systems

Spitty Bifs are Spiffy Bits: Interest-Based Context Dissemination Using Spatiotemporal Bloom Filters

Contact Info

Product

Resources

About