Dealing with network partitions in structured overlay networks

Shafaat, Tallat M.; Ghodsi, Ali; Haridi, Seif

doi:10.1007/s12083-009-0037-7

Cited by 10 publications

(8 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We conjecture that when designed to support reversible phase transitions, a SON can survive in extremely hostile environments. We support this conjecture by analytical work [15], system design [23], and by analogy from physics [16]. We are currently setting up an experimental framework to explore this conjecture.…”

Section: Introductionmentioning

confidence: 59%

Overcoming Software Fragility with Interacting Feedback Loops and Reversible Phase Transitions

Roy

2008

Electronic Workshops in Computing

View full text Add to dashboard Cite

Programs are fragile for many reasons, including software errors, partial failures, and network problems. One way to make software more robust is to design it from the start as a set of interacting feedback loops. Studying and using feedback loops is an old idea that dates back at least to Norbert Wiener's work on Cybernetics. Up to now almost all work in this area has focused on how to optimize single feedback loops. We show that it is important to design software with multiple interacting feedback loops. We present examples taken from both biology and software to substantiate this. We are realizing these ideas in the SELFMAN project: extending structured overlay networks (a generalization of peer-to-peer networks) for large-scale distributed applications. Structured overlay networks are a good example of systems designed with interacting feedback loops. Using ideas from physics, we postulate that these systems can potentially handle extremely hostile environments. If the system is properly designed, it will perform a reversible phase transition when the node failure rate increases beyond a critical point. The structured overlay network will make a transition from a single connected ring to a set of disjoint rings and back again when the failure rate decreases. We are exploring how to expose this phase transition to the application so that it can continue to provide a service. For validation we are building three realistic applications taken from industrial case studies, using a distributed transaction layer built on top of the overlay. Finally, we propose a research agenda to create a practical design methodology for building systems based on the use of interacting feedback loops and reversible phase transitions.

show abstract

Section: Introductionmentioning

confidence: 59%

Overcoming Software Fragility with Interacting Feedback Loops and Reversible Phase Transitions

Roy

2008

Electronic Workshops in Computing

View full text Add to dashboard Cite

show abstract

“…Recently published work may prove a solution for the lookup inconsistency problem with faster writes based on a simple quorum algorithm though this approach has yet to be proven in practice [18]. Alternatives, such as Bigtable used by Google for web indexing, Google Earth and Google Finance, have also proven to be scalable to petabytes of data and thousands of machines whilst meeting the latency requirements [19].…”

Section: Resultsmentioning

confidence: 99%

Distributed Storage Healthcare — The Basis of a Planet-Wide Public Health Care Network

Kakouros

2013

TOMINFOJ

View full text Add to dashboard Cite

Background:As health providers move towards higher levels of information technology (IT) integration, they become increasingly dependent on the availability of the electronic health record (EHR). Current solutions of individually managed storage by each healthcare provider focus on efforts to ensure data security, availability and redundancy. Such models, however, scale poorly to a future of a planet-wide public health-care network (PWPHN). Our aim was to review the research literature on distributed storage systems and propose methods that may aid the implementation of a PWPHN.Methods:A systematic review was carried out of the research dealing with distributed storage systems and EHR. A literature search was conducted on five electronic databases: Pubmed/Medline, Cinalh, EMBASE, Web of Science (ISI) and Google Scholar and then expanded to include non-authoritative sources. Results:The English National Health Service Spine represents the most established country-wide PHN but is limited in deployment and remains underused. Other, literature identified and established distributed EHR attempts are more limited in scope. We discuss the currently available distributed file storage solutions and propose a schema of how one of these technologies can be used to deploy a distributed storage of EHR with benefits in terms of enhanced fault tolerance and global availability within the PWPHN. We conclude that a PWPHN distributed health care record storage system is technically feasible over current Internet infrastructure. Nonetheless, the socioeconomic viability of PWPHN implementations remains to be determined.

show abstract

“…The reactive correction of successor using MLookup with queue greatly reduces peers' maintenance overhead in the overlay network. It makes use of Passive lists [5] which are maintained by each node to detect underlying network partitions and mergers. ReCircle did not consider using a peer as bootstrap server instead of merging individual peer manually by administrator or passively by MLookup.…”

Section: Related Workmentioning

confidence: 99%

Investigate SPRON Convergence Time Using Aggressive Chord and Aggressive AP-Chord

Min

Ming

2015

2015 12th International Conference on Information Technology - New Generations

View full text Add to dashboard Cite

Private overlay network is a network that consists of groups of known peers that have been accepted as members. SPRON is the proposed private reappearing overlay network that will be used by schools in Malaysia to solve the distribution and sharing issues of teaching material among them. There are about nine thousand schools in Malaysia and these schools are grouped into morning only, evening only, and morning evening sessions. Peers bootstrap and reappear in a reappearing overlay network could cause maintenance overhead. One of the challenges of this research is that the P2P must be bootstrapped within a short period of time before school session starts. The convergence time for SPRON P2P must be able to converge within the time constraint to be usable and implementable in schools. The study of the network convergence time in aggressive Chord and aggressive Chord with Anchor Peers (AP-Chord) were carried out to ensure bootstrapping time for all the peers can converge into a fully connected overlay network within specific amount of time. Our study shows that the performance of aggressive Chord and aggressive AP-Chord are able to bootstrap 3000 peers that take about 1090s and 1050s seconds respectively using random join rate which clearly shown AP-Chord performs with lot of improvement. If peer joining rate is fixed at 1000 peers per second or higher, both Chords did not guarantee that all the peers are able to join the network entirely in the bootstrapping phase. The outcomes of this study are AP-Chord have the capability to bootstrap 3000 or possibly more with aggressive join in considerably shorter period of time fulfilling the time constraint.

show abstract

Dealing with network partitions in structured overlay networks

Cited by 10 publications

References 33 publications

Overcoming Software Fragility with Interacting Feedback Loops and Reversible Phase Transitions

Overcoming Software Fragility with Interacting Feedback Loops and Reversible Phase Transitions

Distributed Storage Healthcare — The Basis of a Planet-Wide Public Health Care Network

Investigate SPRON Convergence Time Using Aggressive Chord and Aggressive AP-Chord

Contact Info

Product

Resources

About