Optimal replica placement in hierarchical Data Grids with locality assurance

Wu, Jan‐Jan; Lin, Yang-Kuei; Liu, Pangfeng

doi:10.1016/j.jpdc.2008.08.002

Cited by 38 publications

(32 citation statements)

References 27 publications

(35 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We revisit the well-known replica placement problem in tree networks [6,19,2], with two new objectives: reusing pre-existing replicas, and enforcing an efficient power management. In a nutshell, the replica placement problem is the following: we are given a tree-shaped network where clients are periodically issuing requests to be satisfied by servers.…”

Section: Introductionmentioning

confidence: 99%

“…Note that the distribution tree (clients and nodes) is fixed in the approach. This key assumption is quite natural for a broad spectrum of applications, such as electronic, ISP, or VOD service delivery (see [10,6,12] and additional references in [19]). The root server has the original copy of the database but cannot serve all clients directly, so a distribution tree is deployed to provide a hierarchical and distributed access to replicas of the original data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Power-Aware Replica Placement and Update Strategies in Tree Networks

Benoît

Renaud-Goud

Robert

2011

2011 IEEE International Parallel &Amp; Distributed Processing Symposium

View full text Add to dashboard Cite

This paper deals with optimal strategies to place replicas in tree networks, with the double objective to minimize the total cost of the servers, and/or to optimize power consumption. The client requests are known beforehand, and some servers are assumed to pre-exist in the tree. Without power consumption constraints, the total cost is an arbitrary function of the number of existing servers that are reused, and of the number of new servers. Whenever creating and operating a new server has higher cost than reusing an existing one (which is a very natural assumption), cost optimal strategies have to tradeoff between reusing resources and load-balancing requests on new servers. We provide an optimal dynamic programming algorithm that returns the optimal cost, thereby extending known results without pre-existing servers. With power consumption constraints, we assume that servers operate under a set of M different modes depending upon the number of requests that they have to process. In practice M is a small number, typically 2 or 3, depending upon the number of allowed voltages. Power consumption includes a static part, proportional to the total number of servers, and a dynamic part, proportional to a constant exponent of the server mode, which depends upon the model for power. The cost function becomes a more complicated function that takes into account reuse and creation as before, but also upgrading or downgrading an existing server from one mode to another. We show that with an arbitrary number of modes, the power minimization problem is NP-complete, even without cost constraint, and without static power. Still, we provide an optimal dynamic programming algorithm that returns the minimal power, given a threshold value on the total cost; it has exponential complexity in the number of modes M , and its practical usefulness is limited to small values of M . Still, experiments conducted with this algorithm show that it can process large trees in reasonable time, despite its worst-case complexity.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Power-Aware Replica Placement and Update Strategies in Tree Networks

Benoît

Renaud-Goud

Robert

2011

2011 IEEE International Parallel &Amp; Distributed Processing Symposium

View full text Add to dashboard Cite

show abstract

“…They studied this problem in graph and tree networks. Several works considered this constraint in data grid tree network where the objective function is either replication cost minimization or load balance on servers [6], [16]. Also, Shorfuzzaman et al [17] investigated the placement of k replicas with QoS constraint in data grid tree network such that the replication cost, which is a summation of write, read, and storage costs is minimized.…”

Section: Related Workmentioning

confidence: 99%

“…The number of nodes n ranges from 100 to 5000 and the number children of each node follows a uniform distribution in (1)(2)(3)(4)(5) for n ≤ 1000 and [1][2][3][4][5][6][7][8][9][10] for n > 1000. It is set q with a fraction of the tree height h. That is, q = 1/4h, q = 1/2h, q = 3/4h and q = h + 1.…”

Section: A Simulation Setupmentioning

confidence: 99%

“…Wu et al [6] investigated a problem in which the objective function is to minimize the number of replicas with QoS in terms of a range limit (i.e., hops number). Rehn-Sonigo [7] proposed a major extension [6], with the same objective function but with an additional constraint, i.e., link bandwidth. Our work is different with both of these previous works in terms of the objective function.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cost Optimization of Replicas in Tree Network of Data Grid with QoS and Bandwidth Constraints

Chamkoori¹,

Heidari²,

Parhizgar³

2017

ijacsa

View full text Add to dashboard Cite

Abstract-Data Grid provides resources for data-intensive scientific applications that need to access a huge amount of data around the world. Since data grid is built on a wide-area network, its latency prohibits efficient access to data. This latency can be decreased by data replication in the vicinity of users who request data. Data replication can also improve data availability and decreases network bandwidth usage. It can be influenced by two imperative constraints: Quality of Service (QoS) that is locally owned by a user and bandwidth constraint that globally affects on link that might be shared by multiple users. Guaranteeing both constraints and also minimizing replication cost consisting communication and storage costs is a challenging task. To address this problem, the authors propose to use a dynamic algorithm called Optimal Placement of Replicas to minimize replication cost and coupled with meeting both mentioned constraints. It is also designed as heuristic algorithms that are competitive with optimal algorithm in performance metrics such as replication cost, network bandwidth usage and data availability. Extensive simulations show that the Optimal algorithm saves 10% cost compared to heuristic algorithms and provides local responsiveness for half of the user requests.

show abstract

Strategies for replica consistency in data grid – a comprehensive survey

Vashisht¹,

Sharma

Kumar

2016

Concurrency and Computation

View full text Add to dashboard Cite

Summary Data grid provides an efficient solution for data‐oriented applications that need to manage and process large data sets located at geographically distributed storage resources. Data grid relies on data replicas to enhance the performance and to ensure the fault tolerant results to the users. Replicas are developed to increase the availability of data and to provide better data access. Replicas have their own advantages, but there are a number of issues that must be resolved. Among various existing issues, the critical concern is replica consistency. Various replica consistency strategies are available in the literature. These strategies rationalize and investigate various parameters like bandwidth consumption, access cost, scalability, execution time, storage consumption, staleness, and freshness of replicas. In this paper, several asynchronous replica consistencies are classified and analyzed based on various strategies such as topology, level of abstraction, update propagation, and locality. Some other strategies are also discussed and analyzed like adaptive consistency, quorum‐based consistency, load balancing, and agent‐based economically efficient, check‐pointing, fault tolerance, and conflict management. Parameters on which these strategies are analyzed are methodology, replication classification, consistency, grid topology, environment, evaluation parameters, and performance. Copyright © 2016 John Wiley & Sons, Ltd.

show abstract

Optimal replica placement in hierarchical Data Grids with locality assurance

Cited by 38 publications

References 27 publications

Power-Aware Replica Placement and Update Strategies in Tree Networks

Power-Aware Replica Placement and Update Strategies in Tree Networks

Cost Optimization of Replicas in Tree Network of Data Grid with QoS and Bandwidth Constraints

Strategies for replica consistency in data grid – a comprehensive survey

Contact Info

Product

Resources

About