A decentralized commit protocol is proposed for distributed database systems. This protocol is based on the hypercube network topology and is (log/sub 2/N)-2 resilient to site failures, where N is the number of sites ...
详细信息
A decentralized commit protocol is proposed for distributed database systems. This protocol is based on the hypercube network topology and is (log/sub 2/N)-2 resilient to site failures, where N is the number of sites in the system. In addition, the number of messages sent among N sites is O(N log/sub 2//sup 2/N) which is only a factor of log/sub 2/N over the message complexity lower bound O(NlnN).< >
The author introduces queueing network models for the optimization of the concurrent evaluation of complex database queries, which occur e.g. in deductive query processing. The basic principle for the optimization is ...
详细信息
The author introduces queueing network models for the optimization of the concurrent evaluation of complex database queries, which occur e.g. in deductive query processing. The basic principle for the optimization is the reduction of response time by a better load distribution. If data access leads to a bottleneck on any CPU, response time may possibly be reduced by a preceding dynamic replication of one or more tables, whose accesses make up the bottleneck, to a disc managed by a lighter loaded CPU. For the comparison of alternative concurrent execution plans only queueing network models give quantitative results, which consider the contention on resources like CPU or disc.< >
The authors study the response-time behavior of a symmetric distributed update-synchronization algorithm where nodes need to obtain permission from only O( square root N) (N being the number of database copies) other ...
详细信息
The authors study the response-time behavior of a symmetric distributed update-synchronization algorithm where nodes need to obtain permission from only O( square root N) (N being the number of database copies) other nodes before performing an update (as opposed to N/2+1 nodes in the well-known Thomas majority consensus algorithm). The algorithm used is an adaptation of M. Maekawa's O( square root N) distributed mutual exclusion algorithm (1985) to multiple-copy update-synchronization. This increase in the efficiency of the update-synchronization algorithm enhances performance in two ways. First, the reduction in transaction service time reduces the response time. second, the decrease in response time reduces the number of waiting transactions in the system. This reduces the probability of conflict between transactions. To capture the interaction between the probability of conflict and the transaction response time, the authors define a new measure called the conflict response-time product. They show that optimizing this measure yields a different and more appropriate choice of system parameters than simply minimizing the mean transaction response time.< >
Presents efficient hypercube algorithms for solving triangular systems of linear equations by using various matrix partitioning and mapping schemes. Recently, several parallel algorithms have been developed for this p...
详细信息
Presents efficient hypercube algorithms for solving triangular systems of linear equations by using various matrix partitioning and mapping schemes. Recently, several parallel algorithms have been developed for this problem. In these algorithms, the triangular solver is treated as the second stage of Gauss elimination. Thus, the triangular matrix is distributed by columns (or rows) in a wrap fashion since it is likely that the matrix is distributed this way after an LU decomposition has been done on the matrix. However, the efficiency of the algorithms is low. The motivation here is to develop various data partitioning and mapping schemes for hypercube algorithms by treating the triangular solver as an independent problem. Performance of the algorithms is analyzed theoretically and empirically by implementing them on a commercially available hypercube.< >
Summary form only given. The Datacycle database architecture is based on repetitive broadcast of database contents over high bandwidth channels and on-the-fly filtering of database contents to extract records of inter...
详细信息
Summary form only given. The Datacycle database architecture is based on repetitive broadcast of database contents over high bandwidth channels and on-the-fly filtering of database contents to extract records of interest. These two mechanisms-high speed broadcast and on-the-fly filtering-result in a system that achieves the goals of high performance transaction processing, a powerful and flexible query capability, and high levels of concurrent access to a single database by multiple applications. The prototype system comprises multiple pump boards, each of which stores up to 128 Mbytes of database contents, and multiple access manager boards, each of which contains three on-board VLSI data filter chips. Each VLSI filter executes queries against the contents of a 53 Mbyte/second broadcast channel; selected records and/or computed aggregate values are returned to the host application.< >
A prototype of an object-oriented system implemented in C_Prolog is described. Its main objective is to demonstrate system features that would support efficient management of objects and object-oriented databases in a...
详细信息
ISBN:
(纸本)0818620528
A prototype of an object-oriented system implemented in C_Prolog is described. Its main objective is to demonstrate system features that would support efficient management of objects and object-oriented databases in a persistent and distributed environment. Mechanisms at the low level of the system were considered to support object distribution, mobility control, and configuration management in a simple and uniform way. Objects exist in clusters, which are transparent to the applications. The prototype is a framework for a self-organizing object-oriented distributed system.
Integrity constraint handling is considered an important issue in relational database management systems. Many studies were already conducted in this area. Little attention has been paid however to the influence of re...
详细信息
ISBN:
(纸本)0818620528
Integrity constraint handling is considered an important issue in relational database management systems. Many studies were already conducted in this area. Little attention has been paid however to the influence of relation fragmentation and parallelism on constraint handling. This paper shows how relation fragmentation complicates matters on the one hand, but how parallelism can help to get better efficiency in enforcing constraints on the other hand. The ideas as presented in this paper are used in the context of the PRISMA database machine; they have a more general applicability though.
This paper considers text retrieval systems which store extremely huge amounts of text while providing a multi-user retrieval service for a large customer base. Due to the severe I/O demands of such a system, it is us...
详细信息
ISBN:
(纸本)0818620528
This paper considers text retrieval systems which store extremely huge amounts of text while providing a multi-user retrieval service for a large customer base. Due to the severe I/O demands of such a system, it is usually beneficial if not necessary to utilize a multi-processor system with multiple I/O facilities in an effort to increase the parallel I/O activity, the objective being to lower search response *** defining the problem, we model a solution and show that the application can be handled in a very effective fashion by a multi-processor system with a simple LAN-based topology. The final discussion describes a type of functional splitting which, if done in a careful manner, helps improve search response time.
The paper describes a preliminary evaluation of some multi-join strategies and their performances on parallel hardware. The hardware used was a Sequent (under UNIX) with 11 usable processors, each with shared and priv...
详细信息
ISBN:
(纸本)0818620528
The paper describes a preliminary evaluation of some multi-join strategies and their performances on parallel hardware. The hardware used was a Sequent (under UNIX) with 11 usable processors, each with shared and private primary memory. A multi-join was broken down into a series of single joins which were then allocated to clusters, each cluster being a collection of parallel processors. The results of single joins, which were studied by both binary search and hash-merge techniques, were then further processed as *** evaluation was conducted varying a number of parameters, such as cluster size, tuple size and cardinality. The comparative results were plotted. The study highlights the importance of a number of factors that influence the performance of a multi-join operation.
In this paper, we present a mixed MIMD / SIMD execution model for a reconfigurable computer. This model is adapted to the use of a specialized associative coprocessor, embedded in this host machine. A main characteris...
详细信息
ISBN:
(纸本)0818620528
In this paper, we present a mixed MIMD / SIMD execution model for a reconfigurable computer. This model is adapted to the use of a specialized associative coprocessor, embedded in this host machine. A main characteristic of the model is that it uses four types of processes (decoding, calculus, coprocessor communication and transaction manager), and that in principle one process of each type is allowed on each processor. Time intervals are allocated to operations into partitions of the set of processors. Transfers are usually limited to identifiers, logical addresses and locks. Simulations display a high level of processors occupation. Therefore the machine yield may be very high, and the operations should be very fast.
暂无评论