Multiprocessor Database Systems Research Articles

Simulation of hierarchical multiprocessor database systems

The paper is dedicated to issues concerning simulation and analysis of hierarchical multiprocessor systems oriented to database applications. Requirements for a parallel database system model are given. A survey and comparative analysis of known parallel database system models are presented. A new multiprocessor database system model is introduced. This model allows us to simulate and evaluate arbitrary hierarchical multiprocessor configurations in the context of the OLTP class database applications. Examples of using the database multiprocessor model for simulation study of multiprocessor database systems are presented.

Towards modeling the query processing relevant shape complexity of 2D polygonal spatial objects

The shape complexity of two-dimensional (2D) polygonal spatial objects has implications for how the object can be best represented in a spatial database, and for the query-processing performance of that object. Nevertheless few useful definitions of query-processing relevant spatial complexity are available. A query-processing oriented shape complexity measure is likely to be different from a fractal measure of shape complexity that focused on compression/decompression or a shape complexity measure that would be used for pattern recognition, and should give better performance for the analysis of query processing. It could be used to classify spatial objects, cluster spatial objects in multiprocessor database systems. In a recent paper Brinkhoff et al. (T. Brinkhoff, H-P. Kriegel, R. Shneider, A. Braun, Measuring the complexity of spatial objects, Proceedings of the 3rd ACM International Workshop on Advances in Geographic Information Systems, Baltimore, MD, 1995, pp. 109–117) demonstrated the usefulness of a spatial complexity measure. They did not, however, offer much theoretical justification for their choice of parameters nor for the functional form that they used. In this paper we present a conceptual framework for discussing the query processing oriented shape complexity measures for spatial objects. It is hoped that this will lead to the development of improved measures of spatial complexity.

DECOPOL — Codes for decomposing a polygon into convex subpolygons

The shape complexity of two-dimensional (2D) polygonal spatial objects has implications for how the object can be best represented in a spatial database, and for the query-processing performance of that object. Nevertheless few useful definitions of query-processing relevant spatial complexity are available. A query-processing oriented shape complexity measure is likely to be different from a fractal measure of shape complexity that focused on compression/decompression or a shape complexity measure that would be used for pattern recognition, and should give better performance for the analysis of query processing. It could be used to classify spatial objects, cluster spatial objects in multiprocessor database systems. In a recent paper Brinkhoff et al. (T. Brinkhoff, H-P. Kriegel, R. Shneider, A. Braun, Measuring the complexity of spatial objects, Proceedings of the 3rd ACM International Workshop on Advances in Geographic Information Systems, Baltimore, MD, 1995, pp. 109–117) demonstrated the usefulness of a spatial complexity measure. They did not, however, offer much theoretical justification for their choice of parameters nor for the functional form that they used. In this paper we present a conceptual framework for discussing the query processing oriented shape complexity measures for spatial objects. It is hoped that this will lead to the development of improved measures of spatial complexity.

A hierarchical approach to parallel multiquery scheduling

There has been a good deal of progress made recently toward the efficient parallelization of individual phases of single queries in multiprocessor database systems. In this paper we devise and experimentally evaluate a number of scheduling algorithms designed to handle multiple parallel queries. (Scheduling in this context implies the determination of both processor allotments and temporal processor assignments to individual queries and query phases.) One of these algorithms performs the best in our experiments. This algorithm is hierarchical in nature: In the first phase, a good quality precedence based schedule is created for each individual query and each possible number of processors. This component employs dynamic programming. In the second phase, the results of the first phase are used to create an overall schedule of the full set of queries. This component is based on previously published work on nonprecedence-based malleable scheduling. Even though the problem we are considering is NP-hard in the strong sense, the multiple query schedules generated by our hierarchical algorithm are seen experimentally to achieve high quality results.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Scheduling multiple queries on a parallel machine

There has been a good deal of progress made recently towards the efficient parallelization of individual phases of single queries in multiprocessor database systems. In this paper we devise and evaluate a number of scheduling algorithms designed to handle multiple parallel queries. One of these algorithms emerges as a clear winner. This algorithm is hierarchical in nature: In the first phase, a good quality precedence-based schedule is created for each individual query and each possible number of processors. This component employs dynamic programming. In the second phase, the results of the first phase are used to create an overall schedule of the full set of queries. This component is based on previously published work on nonprecedence-based malleable scheduling. Even though the problem we are considering is NP-hard in the strong sense, the multiple query schedules generated by our hierarchical algorithm are seen experimentally to achieve results which are close to optimal.

DBJ — a Dynamic Balancing Hash Join algorithm in multiprocessor database systems

In this paper, a new hash join algorithm, the Dynamic Balancing Hash Join (DBJ), is proposed to handle the problem of skewed data in the join operation in multiprocessor database systems. The objective of this new algorithm is to avoid the high cost of preprocessing inherent in existing algorithms. The methods used include detecting the unbalanced output during the data partition process and overlapping the balancing process with the data partition process. The new algorithm only redistributes a small portion of the partitioned data and, thereby achieves a balanced output with little extra cost. Further, it balances the output dynamically and needs no knowledge of the input distribution. This is achieved without any need for a co-ordinating processor moreover. This algorithm has been fully implemented in a multiprocessor database system and a performance analysis is presented. The result shows that the new algorithm performs better than existing balancing hash join algorithms for a wide degree of skew.

The performance of disk arrays in shared-memory database machines

Disk arrays and shared-memory multiprocessors are new technologies that are rapidly becoming pervasive. They are complementary because disk arrays naturally balance the I/O workload by interleaving data across all disks while a shared-memory multiprocessor balances the processing workload across multiple processors. In this paper, we examine how disk arrays and shared memory multiprocessors lead to an effective method for constructing database machines for general-purpose complex query processing. We show that disk arrays can lead to cost-effective storage systems if they are configured from suitably small formfactor disk drives. We introduce the storage system metricdata temperature (IO/s/Gbyte) as a way to evaluate how well a disk configuration can sustain its workload, and we show that disk arrays can sustain the same data temperature as a more expensive mirrored-disk configuration. We use the metric to evaluate the performance of disk arrays in XPRS, an operational shared-memory multiprocessor database system being developed at the University of California, Berkeley.

Application of SLAM in the design and performance analysis of a multi-processor database system

The software-oriented, multi-processor database systems are characterized by a set of processing elements (PEs) which run identical software and operate on a partitioned database in parallel. Performance improvements and capacity growth can be achieved in this type of system by adding PEs to the configuration and replicating the existing software on the added PEs. Much work has been done applying graph theory, queuing theory, algorithmic approaches, and analytical techniques towards the design of multi-processor database systems. This paper describes a simulation approach and the application of a simulation language, SLAM, to the design and performance analysis of one such multi-processor database system. The system, relational replicated database system (RRDS), was developed using a five-phase design process. Simulation and analytical techniques were used throughout the development to determine critical elements, components, and design issues, and to evaluate proposed solutions. RRDS was modeled as an open queuing system with SLAM service times determined analytically. The model consisted of a workload scenario generator, a query processing module, and a statistics collection module. In phase one of the simulation study, different hardware organizations were evaluated. Results indicated that the RRDS approach performs approximately three times better than other approaches such as SIMD, MIMD, and functional specialization. In phase two, algorithms and mechanisms for data access were developed. Results favored the B +-tree approach over the clustering approach. A data placement strategy was determined in phase three. Results indicated that the value range partitioning (VRP) approach is more desirable than the round-robin (RR) approach. In phase four, a directory management strategy was selected. Results favored a partitioned and parallel-processed directory, as opposed to a rotating approach. Finally, phase five consisted reveal system strengths and weaknesses, and gain insight into optimal RRDS operating environments. This approach to database system design is both iterative and evolutionary, and can be applied regardless of the type of system being considered. Simulation can be a useful tool in all phases of database system design, from the actual physical hardware architecture to the resolution of software design questions. It plays an important role in predictive performance analysis to determine the extent to which original design goals are achieved.

The datacycle architecture for very high throughput database systems

The evolutionary trend toward a database-driven public communications network has motivated research into database architectures capable of executing thousands of transactions per second. In this paper we introduce the Datacycle architecture, an attempt to exploit the enormous transmission bandwidth of optical systems to permit the implementation of high throughput multiprocessor database systems. The architecture has the potential for unlimited query throughput, simplified data management, rapid execution of complex queries, and efficient concurrency control. We describe the logical operation of the architecture and discuss implementation issues in the context of a prototype system currently under construction.