Abdelkader Hameurlain

Data Management in Grid and Peer-to-Peer Systems

This book constitutes the refereed proceedings of theFirst International Conference on Data Management in Grid and Peer-to-Peer Systems, Globe 2008, held in Turin, Italy, September2008. P2P and grid computing are important for scale distributed systems and applications that require effective management of voluminous, distributed, and heterogeneous data. The 10 revised full papers presented were carefully reviewed and selected from 23 submissions. The papers are organized in topical sections on P2P storage systems and caching, P2P data integration systems, querying in grid and P2P systems.

Resource discovery in grid systems: a survey

Resource Discovery (RD) is one of the key issues in successful Grid systems. Yet, new methodologies for RD are constantly researched owing to the dynamicity, heterogeneity and large-scale characteristics of Grids. Recently, synergy and convergence between Grid, Agent and Peer-to-Peer (P2P) systems were pointed out clearly. This paper provides a survey and a qualitative comparison of the most promising approaches (P2P techniques and agent systems) for RD. Viability of Grid systems relies mainly on efficient integration of P2P techniques and mobile agent (MA) systems to bring scaling and decentralised control properties to Grids.

Large Scale Data Management in Grid Systems: a Survey

Today the grid computing, intended initially for the intensive computing, open towards the management of voluminous, heterogeneous, and distributed data on a large-scale environment. The grid data management raises new problems and presents real challenges: resource discovery, efficiency of access, autonomic management, security, and benchmarking. This importance comes out of characteristics offered by grid systems: autonomy, heterogeneity and dynamicity of nodes. Firstly, we recall the fundamental problems of the large scale data management in grid systems and characteristics of these systems. Then, we describe in a highlight way proposed approaches (Web services, P2P techniques, Agent-based approach) for resource discovery. The remainder of the paper is devoted to point out the contributions of mobile agents for some problems of large scale data management, in particularly: dynamic query optimization, task placement, and embedded cost model. We show how mobile agents can help for decentralized control, and scaling.

Mobile Agents Based Self-Adaptive Join for Wide-Area Distributed Query Processing

In this article, optimization of decision support queries is considered in the context of wide-area distributed databases. An original approach based on the “mobile agent†paradigm is proposed and evaluated. Agents’ autonomy and reactivity allow operators of the execution plan to adapt dynamically to estimation errors on relations and to evolutions in the state of the execution system, avoiding time overheads commonly associated with centralized monitoring. We present decentralized self-adaptive algorithms for dynamic optimization of join operators, and their implementations in Java using mobile agents. Then, we evaluate performance depending on error rate on statistical information on database, and on communication bandwidth and CPU frequency. The results show that the agent-based approach can lead to a significant reduction of response time and provide decision criteria for developing an effective migration policy.

CPU and incremental memory allocation in dynamic parallelization of SQL Queries

In order to re-adjust the parallel execution of SQL queries in case of metric estimation or discretization errors, we propose an incremental parallelization method which carries out simultaneously both scheduling and mapping in co-operation with two incremental memory allocation heuristics (ParAd: parallelism degree adjustment, and MaCRelax: mapping clues relaxation) in a dynamic multi-user context. The two incremental memory allocation heuristics are integrated in the mapping method which attempt to avoid time-consuming multibucket join execution generating numerous additional I/O. A performance evaluation of the ParAd heuristic shows: (i) a significant join response time savings (from 16.11% to 35.62%), and (ii) with many complex queries, a more significant gain in response time (from 29% to 54%).

Evolution of Query Optimization Methods

Query optimization is the most critical phase in query processing. In this paper, we try to describe synthetically the evolution of query optimization methods from uniprocessor relational database systems to data Grid systems through parallel, distributed and data integration systems. We point out a set of parameters to characterize and compare query optimization methods, mainly: (i) size of the search space, (ii) type of method (static or dynamic), (iii) modification types of execution plans (re-optimization or re-scheduling), (iv) level of modification (intra-operator and/or inter-operator), (v) type of event (estimation errors, delay, user preferences), and (vi) nature of decision-making (centralized or decentralized control). The major contributions of this paper are: (i) understanding the mechanisms of query optimization methods with respect to the considered environments and their constraints (e.g. parallelism, distribution, heterogeneity, large scale, dynamicity of nodes) (ii) pointing out their main characteristics which allow comparing them, and (iii) the reasons for which proposed methods become very sophisticated.

Mobile agent cooperation methods for large scale distributed dynamic query optimization

In this paper, we study the contribution of the execution model based on mobile agents to the distributed dynamic query optimization. We propose three cooperation methods allowing to the agents, reacting to the estimation errors, to move during the runtime. The performance evaluation shows the superiority of one of these methods. It is more powerful than a standard execution starting from 30% of estimation error and has a relatively small overhead compared to a standard execution when the estimation error is small.

Location-dependent query processing under soft real-time constraints

In recent years, mobile devices and applications achieved an increasing development. In database field, this development required methods to consider new query types like location-dependent queries (i.e. the query results depend on the query issuer location). Although several researches addressed problems related to location-dependent query processing, a few works considered timing requirements that may be associated with queries (i.e., the query results must be delivered to mobile clients on time). The main objective of this paper is to propose a solution for location-dependent query processing under soft real-time constraints. Hence, we propose methods to take into account client location-dependency and to maximize the percentage of queries respecting their deadlines. We validate our proposal by implementing a prototype based on Oracle DBMS. Performance evaluation results show that the proposed solution optimizes the percentage of queries meeting their deadlines and the communication cost.

Data replication strategies with performance objective in data grid systems: a survey

Replicating for performance constitutes an important issue in large-scale data management systems. In this context, a significant number of replication strategies have been proposed for data grid systems. Some works classified these strategies into static vs. dynamic or centralised vs. decentralised or client vs. server initiated strategies. Very few works deal with a replication strategy classification based on the role of these strategies when building a replica management system. In this paper, we propose a new replication strategy classification based on objective functions of these strategies. Also, each replication strategy is designed according to the data grid topology for which it was proposed. We point out the impact of the topology on replication performance although most of these strategies have been proposed for a hierarchical grid topology. We also study the impact of some factors on performance of these strategies, e.g. access pattern, bandwidth consumption and storage capacity.

Scheduling and mapping for parallel execution of extended SQL queries

In this paper, we present an extension of PSA strategy (Parallel Scheduling Algorithm ), to determine an appropriate mapping of operations onto physical processors, taking into account the interconnection network topology of a sharednothing architecture. Performance evaluation, which relies on two benchmarks shows the efficiency of PSA strategy by comparing to Static Right-Deep strategy and to Bushy Tree Scheduling strategy. The major contributions of this work are (i) the incorporation of the mapping process into PSA strategy and (ii) the PSA strategy which provides a good trade-off between response time minimization and throughput maximization.