PeerSim: A scalable P2P simulator

Abstract-Decentralized topology construction protocols organize nodes along a predefined topology (e.g. a torus, ring, or hypercube). Such topologies have been used in many contexts ranging from routing and storage systems, to publish-subscribe and event dissemination. Since most topologies assume no correlation between the physical location of nodes and their positions in the topology, they do not handle catastrophic failures well, in which a whole region of the topology disappears. When this occurs, the overall shape of the system typically gets lost. This is highly problematic in applications in which overlay nodes are used to map a virtual data space, be it for routing, indexing or storage. In this paper, we propose a novel decentralized approach that maintains the initial shape of the topology even if a large (consecutive) portion of the topology fails. Our approach relies on the dynamic decoupling between physical nodes and virtual ones enabling a fast reshaping. For instance, our results show that a 51,200-node torus converges back to a full torus in only 10 rounds after 50% of the nodes have crashed. Our protocol is both simple and flexible and provides a novel form of collective survivability that goes beyond the current state of the art.

show abstract

“…All results were computed with PeerSim [26]. The code of our simulation is freely available on-line 4 .…”

Section: B Resultsmentioning

confidence: 99%

Polystyrene: the Decentralized Data Shape That Never Dies

Bouget

Kervadec

Kermarrec

et al. 2014

2014 IEEE 34th International Conference on Distributed Computing Systems

View full text Add to dashboard Cite

show abstract

“…The repairing protocol has been evaluated through an extensive number of simulations based on event-based model of PEERSIM [12]. Due to limited space, we present here a brief evaluation of the behavior of the system, leaving an extended description to future work.…”

Section: Discussionmentioning

confidence: 99%

P2P and Cloud: A Marriage of Convenience for Replica Management

Kavalionak

Montresor

2012

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. P2P and cloud computing are two of the latest trend in the Internet arena. They could both be labeled as "large-scale distributed systems", yet their approach is completely different: based on completely decentralized protocols exploiting edge resources the former, focusing on huge data centers the latter. Several Internet startups have quickly reached stardom by exploiting cloud resources, unlike P2P applications which often lack a business model. Recently, companies like Spotify and Wuala have started to explore how the two worlds could be merged, exploiting (free) user resources whenever possible, aiming at reducing the bill to be payed to cloud providers. This mixed model could be applied to several different applications, including backup, storage, streaming, content distribution, online gaming, etc. A generic problem in all these areas is how to guarantee the autonomic regulation of the usage of P2P vs. cloud resources: how to guarantee a minimum level of service when peer resources are not sufficient, and how to exploit as much P2P resources as possible when they are abundant.

show abstract

“…DS-means has been tested on PeerSim [7], a P2P simulator. In this section, first the experimental framework used to evaluate DS-means is presented, then the results are shown.…”

Section: Discussionmentioning

confidence: 99%

DS-Means: Distributed Data Stream Clustering

Guerrieri

Montresor

2012

Euro-Par 2012 Parallel Processing

Self Cite

View full text Add to dashboard Cite

Abstract. This paper proposes DS-means, a novel algorithm for clustering distributed data streams. Given a network of computing nodes, each of them receiving its share of a distributed data stream, our goal is to obtain a common clustering under the following restrictions (i) the number of clusters is not known in advance and (ii) nodes are not allowed to share single points of their datasets, but only aggregate information. A motivating example for DS-means is the decentralized detection of botnets, where a collection of independent ISPs may want to detect common threats, but are unwilling to share their precious users' data. In DS-means, nodes execute a distributed version of K-means on each chunk of data they receive to provide a compact representation of the data of the entire network. Later, X-means is executed on this representation to obtain an estimate of the number of clusters. A number of experiments on both synthetic and real-life datasets show that our algorithm is precise, efficient and robust.

show abstract

PeerSim: A scalable P2P simulator

Cited by 469 publications

References 6 publications

Polystyrene: the Decentralized Data Shape That Never Dies

Polystyrene: the Decentralized Data Shape That Never Dies

P2P and Cloud: A Marriage of Convenience for Replica Management

DS-Means: Distributed Data Stream Clustering

Contact Info

Product

Resources

About