On the performance of concurrent tree algorithms

Ford, Ray; Jipping, Michael J.; Shultz, Roger K.; Wenhardt, Brion

doi:10.1016/0743-7315(90)90100-4

Cited by 3 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mukkamala and Shultz [21] measured the performance of the Blink-tree on two simulated architectures, one with shared output devices, and the other with one output device for each processor. Ford Srinivasan and Carey [26] is for the the same algorithms used in [8] and the B-tree algorithm due to [14]. Colbrook et al [3] implemented their message passing algorithms on a simulator.…”

Section: Introductionmentioning

confidence: 99%

B/sup mad/-tree: an efficient data structure for parallel processing

Das

Demuynck

Proceedings of SPDP '96: 8th IEEE Symposium on Parallel and Distributed Processing

View full text Add to dashboard Cite

B-trees are used for accessing large database files, stored in lexicographic order on the secondary storage devices. Algorithms for concurrent B-tree data structures achieve only limited speedup when implemented on a parallel computer. To improve the performance, we propose a variant of the Pink-tree, called the Bmadtree, which allows insertion without node splits, with multiple access in its leaf nodes, and dilation in both the index and the leaf nodes. Parallel algorithms for search, insert and restructuring are designed f o r partitioned, locked and distributed models. Only part of an insertion node is locked during the insert, and simultaneous insertions by multiple processors in the same node are allowed. A restructuring algorithm runs periodically in the background and requires at most one wait by any search or update operation. Our implementations demonstrate that the Fad -tree algorithms outperform the best known pink-trees, and compare favorably with linear hashing. W e achieve good speedup (e.g., 4.79 with 8 processors) for partitioned algorithms, and moderate speedup (2.49 with 8 processors) for locked algorithms, even including overhead costs. The insert times obtained for Bmad-trees are 50% to 60% less than that for the Blink -trees in partitioned implementations, and 70% to 80% less in locked implementations. The speedup results o n the distributed memory platform (a network of workstations) were not that encouraging due to high communication costs. 0-8186-7683-3/96 $05.00 0 1996 IEEE

show abstract

Section: Introductionmentioning

confidence: 99%

B/sup mad/-tree: an efficient data structure for parallel processing

Das

Demuynck

Proceedings of SPDP '96: 8th IEEE Symposium on Parallel and Distributed Processing

View full text Add to dashboard Cite

show abstract

Concurrent processing of linearly ordered data structures on hypercube multicomputers

Ghosh

Das

John

1994

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

This paper presents a simple and effective method for the concurrent manipulation of linearly ordered data structures on hypercube systems. The method is based on the existence of an augmented binomial search tree, called the pruned binomial tree, rooted at any arbitrary processor node of the hypercube such that 1) every edge of the tree corresponds to a direct link between a pair of hypercube nodes, and 2) the tree spans any arbitrary sequence of n consecutive nodes containing the root, using a fanout of at most [log, n1 and a depth of at most [log, i t 1 + 1. Search trees spanning nonoverlapping processor lists are formed using only local information, and can be used concurrently without contention problems. Thus, they can be used for performing operations such as broadcast and merge simultaneously on sets with nonuniform sizes. Extensions of the tree to !+ary 11 -cubes and faulty hypercubes are presented. Applications of this concurrent data structure to low-and intermediate-level image processing algorithms, and for dictionary operations involving multiple keys, are also outlined.

show abstract

A framework for the performance analysis of concurrent B-tree algorithms

Johnson

Shasha

1990

Proceedings of the Ninth ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems

View full text Add to dashboard Cite

Many concurrent B-tree algorithms have been proposed, but they have not yet been satisfactorily analyzed. When transaction processing systems require high levels of concurrency, a restrictive serialization technique on the B-tree index can cause a bottleneck. In this paper, we present a framework for constructing analytical performance models of concurrent Btree algorithms. The models can predict the response time and maximum throughput. We analyze three algorithms: Naive Lock-coupling, Optimistic Descent, and the Lehman-Yao algorithm.The analyses are validated by simulations of the algorithms on actual B-trees. Simple and instructive rules of thumb for predicting performance are also derived. We apply the analyses to determine the effect of database recovery on B-tree concurrency.

show abstract

On the performance of concurrent tree algorithms

Cited by 3 publications

References 15 publications

B/sup mad/-tree: an efficient data structure for parallel processing

B/sup mad/-tree: an efficient data structure for parallel processing

Concurrent processing of linearly ordered data structures on hypercube multicomputers

A framework for the performance analysis of concurrent B-tree algorithms

Contact Info

Product

Resources

About