Fast reconciliations in fluid replication

Cox, Landon P.; Noble, Brian

doi:10.1109/icdsc.2001.918975

Cited by 19 publications

(12 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In step (6), all the mandatory replicas are added to R, because a mandatory replica has at least one replica that is not included in the range originators of any classified replicas.…”

Section: Calculation Of a Minimum Readmentioning

confidence: 99%

Scalable Load Distribution for View Divergence Control of Data Freshness in Replicated Database Systems

Yamashita

2006

ipsjdc

View full text Add to dashboard Cite

A scalable load distribution method for view divergence control of statistically defined data freshness in replicated database systems is proposed. This method enables a number of mobile and fixed client nodes to continue their processes even when they lose connectivity to a network or do not have sufficient bandwidth to meet application requirements, which is very likely to occur to mobile client nodes. This can be achieved by renewing copies of data in client nodes while they maintain connectivity to a network so that their copies of data are sufficiently fresh to meet application requirements while they lose network connectivity. The load distribution for view divergence control is achieved by determining multiple sets of replicas from which client nodes retrieve the values of data through read transactions. Client nodes calculate the value of data that reflect updates which have already reached one or more elements in the determined set of replicas. We show that our method reduces the load of processing read transactions to less than about 1/40 of that in the original method in order to improve data freshness to about 2/5 of the maximum update delay in a large-scale network.

show abstract

“…In step (6), all the mandatory replicas are added to R, because a mandatory replica has at least one replica that is not included in the range originators of any classified replicas.…”

Section: Calculation Of a Minimum Readmentioning

confidence: 99%

Scalable Load Distribution for View Divergence Control of Data Freshness in Replicated Database Systems

Yamashita

2006

ipsjdc

View full text Add to dashboard Cite

show abstract

“…In Fluid Replication [7], clients can create replicas dynamically, whenever and wherever they are necessary. When a client sees that performance is low, either because of increasing demand on the network, or because of client mobility, he can create replicas on a waystation, which is a node on which replicas can be created.…”

Section: Related Workmentioning

confidence: 99%

Generalization of the Fast Consistency Algorithm to a Grid with Multiple High Demand Zones

Acosta-Elias

Navarro

2003

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract.One of the main challenges of grid systems of large scale and data intensive is that of providing high availability and performance, in spite of the unreliability and delay occasioned by the size of Internet. Replication enables us to meet such a challenge with success. In the context of weak consistency, the fast consistency algorithm prioritizes replicas with high demand. Nevertheless, the fast consistency algorithm only works well in a single zone of high demand, whereas in multiple high demand zones its performance is poor. In this paper, we propose an algorithm chosen according to demand, whereby the replicas in each zone of high demand select leader replicas that subsequently construct a logical topology, linking all the replicas together. In this way, changes are able to reach all the high demand replicas without the low demand zones forming a barrier to prevent this from happening.

show abstract

“…Update Ordering Constraints: When updates are issued independently at multiple replicas (e.g., by 'WR' mode sessions), our model allows them to be applied (1) with no particular constraint on their ordering at various replicas (called 'none'), (2) in some arbitrary but common order everywhere (called 'total'), or (3) sequentially via serialization (called 'serial'). The ordering options can be specified on a per-session basis.…”

Section: Composable Consistency Modelmentioning

confidence: 99%

“…Several P2P systems were developed to share read-only data such as multimedia files (PAST [13], KaZaa) or access to rarely write-shared personal files [14], but not frequent write-sharing. Numerous consistency schemes have been developed individually to handle the data coherence needs of specific services such as file systems, directory services [9], databases and persistent object systems [8] [2] provides multiple selectable consistency policies for static hierarchical caching. In contrast, our approach offers primitive options that can be combined to yield a variety of policies, offering more customizability for peer-to-peer replication.…”

Section: Related Workmentioning

confidence: 99%