Results 1  10
of
13
The Performance of Concurrent Data Structure Algorithms
 Transactions on Database Systems
, 1994
"... This thesis develops a validated model of concurrent data structure algorithm performance, concentrating on concurrent Btrees. The thesis first develops two analytical tools, which are explained in the next two paragraphs, for the analysis. Yao showed that the space utilization of a Btree built fr ..."
Abstract

Cited by 14 (9 self)
 Add to MetaCart
This thesis develops a validated model of concurrent data structure algorithm performance, concentrating on concurrent Btrees. The thesis first develops two analytical tools, which are explained in the next two paragraphs, for the analysis. Yao showed that the space utilization of a Btree built from random inserts is 69%. Assuming that nodes merge only when empty, we show that the utilization is 39% when the number of insert and delete operations is the same. However, if there are just 5% more inserts than deletes, then the utilization is at least 62%. In addition to the utilization, we calculate the probabilities of splitting and merging, important parameters for calculating concurrent Btree algorithm performance. We compare mergeatempty Btrees with mergeathalf Btrees. We conclude that mergeatempty Btrees have a slightly lower space utilization but a much lower restructuring rate than mergeathalf Btrees, making mergeatempty Btrees preferable for concurrent Btree algo...
BTrees with Relaxed Balance
 In Proceedings of the 9th International Parallel Processing Symposium
, 1993
"... Btrees with relaxed balance have been defined to facilitate fast updating on sharedmemory asynchronous parallel architectures. To obtain this, rebalancing has been uncoupled from the updating such that extensive locking can be avoided in connection with updates. We analyze Btrees with relaxed bal ..."
Abstract

Cited by 13 (6 self)
 Add to MetaCart
Btrees with relaxed balance have been defined to facilitate fast updating on sharedmemory asynchronous parallel architectures. To obtain this, rebalancing has been uncoupled from the updating such that extensive locking can be avoided in connection with updates. We analyze Btrees with relaxed balance, and prove that each update gives rise to at most blog a (N=2)c + 1 rebalancing operations, where a is the degree of the Btree, and N is the bound on its maximal size since it was last in balance. Assuming that the size of nodes are at least twice the degree, we prove that rebalancing can be performed in amortized constant time. So, in the long run, rebalancing is constant time on average, even if any particular update could give rise to logarithmic time rebalancing. We also prove that the amount of rebalancing done at any particular level decreases exponentially going from the leaves towards the root. This is important since the higher up in the tree a lock due to a rebalancing operat...
Performance of B+ Tree Concurrency Control Algorithms
 VLDB JOURNAL
, 1993
"... A number of algorithms have been proposed to access B+trees concurrently, but they are not well understood. In this article, we study the performance of various B+tree concurrency control algorithms using a detailed simulation model of B +tree operations in a centralized DBMS. Our study covers a ..."
Abstract

Cited by 12 (0 self)
 Add to MetaCart
A number of algorithms have been proposed to access B+trees concurrently, but they are not well understood. In this article, we study the performance of various B+tree concurrency control algorithms using a detailed simulation model of B +tree operations in a centralized DBMS. Our study covers a wide range of data contention situations and resource conditions. In addition, based on the performance of the set of B +tree concurrency control algorithms, which includes one new algorithm, we make projections regarding the performance of other algorithms in the literature. Our results indicate that algorithms with updaters that lockcouple using exclusive locks perform poorly as compared to those that permit more optimistic index descents. In particular, the Blink algorithms are seen to provide the most concurrency and the best overall performance. Finally, we demonstrate the need for a highly concurrent longterm lock holding strategy to obtain the full benefits of a highly concurrent algorithm for index operations.
Index Concurrency Control in Firm RealTime DBMS
 In Proceedings of the 21st VLDB Conference
, 1995
"... Although realtime transaction concurrency control has been extensively studied, the design and evaluation of realtime index concurrency control algorithms has not yet been considered. In this paper, we develop realtime variants of several classical Btree concurrency control algorithms and ..."
Abstract

Cited by 12 (2 self)
 Add to MetaCart
Although realtime transaction concurrency control has been extensively studied, the design and evaluation of realtime index concurrency control algorithms has not yet been considered. In this paper, we develop realtime variants of several classical Btree concurrency control algorithms and compare their performance using a detailed simulation model of a firmdeadline realtime database system. The experimental results show that the performance characteristics of the realtime version of an index concurrency control algorithm could be significantly different from the performance of the same algorithm in a conventional (nonrealtime) database system. In particular, Blink algorithms, which are reputed to provide the best overall performance in conventional database systems, perform poorly under heavy realtime loads. We Permission to copy without fee all or part of this material is granted provided that the copies are not made or distributed for direct commercial a...
RealTime Index Concurrency Control
 SIGMOD Record
, 1996
"... Realtime database systems are expected to rely heavily on indexes to speed up data access and thereby help more transactions meet their deadlines. Accordingly, highperformance index concurrency control (ICC) protocols are required to prevent contention for the index from becoming a bottleneck. In t ..."
Abstract

Cited by 7 (1 self)
 Add to MetaCart
Realtime database systems are expected to rely heavily on indexes to speed up data access and thereby help more transactions meet their deadlines. Accordingly, highperformance index concurrency control (ICC) protocols are required to prevent contention for the index from becoming a bottleneck. In this paper, we develop realtime variants of a representative set of classical Btree ICC protocols and, using a detailed simulation model, compare their performance for realtime transactions with firm deadlines. We also present and evaluate a new realtime ICC protocol called GUARDlink that augments the classical Blink protocol with a feedbackbased admission control mechanism. Both point and range queries, as well as the undos of the index actions of aborted transactions are included in the scope of our study. The performance metrics used in evaluating the ICC protocols are the percentage of transactions that miss their deadlines and the fairness with respect to transaction type and size...
Amortization Results for Chromatic Search Trees, with an Application to Priority Queues
, 1997
"... this paper, we prove that only an amortized constant amount of rebalancing is necessary after an update in a chromatic search tree. We also prove that the amount of rebalancing done at any particular level decreases exponentially, going from the leaves toward the root. These results imply that, in p ..."
Abstract

Cited by 7 (0 self)
 Add to MetaCart
this paper, we prove that only an amortized constant amount of rebalancing is necessary after an update in a chromatic search tree. We also prove that the amount of rebalancing done at any particular level decreases exponentially, going from the leaves toward the root. These results imply that, in principle, a linear number of processes can access the tree simultaneously. We have included one interesting application of chromatic trees. Based on these trees, a priority queue with possibilities for a greater degree of parallelism than previous proposals can be implemented. ] 1997 Academic Press 1.
A Unified Approach to Concurrent and Parallel Algorithms on Balanced Data Structures
 IN IEEE, EDITOR, PROC. OF XVII INT. CONF. CHILEAN COMPUTER SOCIETY
, 1997
"... Concurrent and parallel algorithms are different. However, in the case of dictionaries, both kinds of algorithms share many common points. We present a unified approach emphasizing these points. It is based on a careful analysis of the sequential algorithm, extracting from it the more basic facts, e ..."
Abstract

Cited by 6 (3 self)
 Add to MetaCart
Concurrent and parallel algorithms are different. However, in the case of dictionaries, both kinds of algorithms share many common points. We present a unified approach emphasizing these points. It is based on a careful analysis of the sequential algorithm, extracting from it the more basic facts, encapsulated later on as local rules. We apply the method to the insertion algorithms in AVL trees. All the concurrent and parallel insertion algorithms have two main phases. A percolation phase, moving the keys to be inserted down, and a rebalancing phase. Finally, some other algorithms and balanced structures are discussed.
A Distributed, Replicated, DataBalanced Search Structure
 International Journal of High Speed Computing
, 1994
"... Many concurrent dictionary data structures have been proposed, but usually in the context of shared memory multiprocessors. In this paper, we present an algorithm for a concurrent distributed Btree that can be implemented on message passing computer systems. Our distributed Btree (the dBtree) ..."
Abstract

Cited by 5 (1 self)
 Add to MetaCart
Many concurrent dictionary data structures have been proposed, but usually in the context of shared memory multiprocessors. In this paper, we present an algorithm for a concurrent distributed Btree that can be implemented on message passing computer systems. Our distributed Btree (the dBtree) replicates the interior nodes in order to improve parallelism and reduce message passing. The dBtree stores some redundant information in its nodes to permit the use of lazy updates to maintain replica coherency. We show how the dBtree algorithm can be used to build an efficient implementation of a highly parallel, databalanced distributed dictionary, the dEtree. Keywords: Concurrent dictionary data structures, Message passing multiprocessor systems, Balanced search trees, Blink trees, Replica coherency. 1. Introduction. We introduce a new balanced search tree algorithm for distributed memory architectures. The search tree uses the Blink tree [27] as a base, and distributes ow...
Transaction Synchronisation In Object Bases
, 1988
"... We propose a formal model of concurrency control in object bases. An object base is like a database except that information is represented in terms of "objects" that encapsulate both data and the procedures through which the data can be manipulated. The model generalises the classical model of datab ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
We propose a formal model of concurrency control in object bases. An object base is like a database except that information is represented in terms of "objects" that encapsulate both data and the procedures through which the data can be manipulated. The model generalises the classical model of database concurrency control: it allows for nested transactions (as opposed to flat transactions) which may issue arbitrary operations (as opposed to just read and write operations). We establish an analogue to the classical serialisability theorem and use it to derive simple proofs of correctness of two concurrency control algorithms for object bases, namely Nested TwoPhase Locking (Moss' algorithm) and Nested Timestamp Ordering (Reed's algorithm). Concurrency control in object bases can be viewed as a combination of intraobject and interobject synchronisation. The former ensures that each object's own methods are executed in serialisable fashion; the latter ensures the compatibility of trans...
OnLine Processing In LargeScale Transaction Systems
, 1992
"... In this thesis, we provide techniques to adapt current database technology to account for the following trends that can be observed in database management system (DBMS) usage: 1. DBMSs are being increasingly used in applications, like computerized stock trading, that have very high transaction rates ..."
Abstract

Cited by 4 (2 self)
 Add to MetaCart
In this thesis, we provide techniques to adapt current database technology to account for the following trends that can be observed in database management system (DBMS) usage: 1. DBMSs are being increasingly used in applications, like computerized stock trading, that have very high transaction rates. 2. Database sizes are growing rapidly, and future databases are expected to be several orders of magnitude larger than the largest databases in operation today. 3. Next generation DBMSs are expected to gravitate more and more towards what is referred to as 24(hour) \Theta 7(day) operation. In order to handle high transaction rates, future DBMSs have to use highly concurrent algorithms for managing oftenused auxiliary data structures like indices. To better understand the performance of concurrency control algorithms for index access, we first compare the performance of Btree concurrency control algorithms using a simulation model of a centralized DBMS. In our performance study, we look a...