V. Lanin and D. Shasha. Concurrent set manipulation without locking. In Proceedings of the Seventh ACM Symposium on Principles of Database Systems, pages 211--220, March 1988.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....instructions that are stronger than simple reads and writes. Implementations of various types of queues have been presented by Lamport [53] by Herlihy and Wing [38] by Israeli and Rappoport [41] by Wing and Gong [81, 82] and byMichael and Scott [64] Anderson and Woll [15] and Lanin and Shasha [56] present implementations for various set operations. Valois presents lock free implementations for various data structures, including queues, lists, trees, and dictionaries [78, 79, 80] Finally, Massalin and Pu have implemented an entire operating system using lock free data structures such as ....

V. Lanin and D. Shasha. Concurrent set manipulation without locking. In Proceedings of the Seventh Annual ACM Symposium on Principles of Database Systems, pages 211--220. ACM, 1988.

....be effectively accessed in parallel. This requires both the elimination of locking, and the distribution of the representation to remove serialising influences that limit scalability[1] Parallel data structures and their operations have been presented for queues[9, 12, 13, 23] trees[8] and sets[18] amongst others. These developments have tended to focus on single structures, and has defined their semantics in an instance dependent manner. There is the potential to develop a new parallel programming model, based on the use of these data structures. Before this can be achieved, the problems ....

Vladmir Lanin and Dennis Shasha. Concurrent set manipulation without locking. In 7th ACM Symposium on the Principlies of Database Systems, pages 211--220, March 1988.

....universal operations. His result, however, does not concern the efficiency of the implementations. Later papers on the implementation of concurrent data structures address their efficiency, and can be partitioned into three groups. The first group are implementations of specific data structures [15, 18, 3, 12]; the second group are implementations of multi word (k ary) operations from single word operations [2, 10, 20, 13] while the third group introduces general methods for implementing concurrent data structures [2, 9, 1, 6] Next we describe the works, elaborating on works from the second and third ....

....from single word operations [2, 10, 20, 13] while the third group introduces general methods for implementing concurrent data structures [2, 9, 1, 6] Next we describe the works, elaborating on works from the second and third groups, which are most related to this thesis. Lanin and Shasha in [15] present a non blocking implementation of a concurrent set, with a linked list data structure. A set supports Read , Write, Insert , Delete and Member operations, and uses the fetch add and two other primitives which can be viewed as simple cases of C S . Prakash, Lee and Johnson ( 18] present a ....

V. Lanin and D. Shasha. "Concurrent Set Manipulation Without Locking", Proceedings of the Seventh ACM Symposium on Principles of Database Systems, pages 211--220, March 1988.

....that we have designed, implemented, tested and verified. We focus here on the proofs of correctness of the implementations of these objects; a companion paper [8] describes our simulator, used for testing our implementations. Proving linearizability of a data object is a nontrivial task. In [6], the proof of a simple concurrent set consists of five propositions, one lemma and one theorem. All our proofs are structured similarly by first giving a list of three to five lemmas and then a final theorem. Thus, in the spirit of reuse through program libraries, one of our goals is to supply ....

....history accepted by the Stuttering j Queue Queue, then H is linearizable. Proof: Similar to the proof for the unbounded FIFO queue using Lemmas 1.2 1.4 and 4.1 4.3. 6. Set 6.1. Specification Figure 12 contains the specification for a set. 6.2. Implementation The original design appeared in [6]. Our implementation is given in Figures 13 and 14. The set operations are implemented in terms of the following atomic instructions. The first two are operations on integer variables; the last three on arrays. int READ(int x) ensures Reads and returns the value of the integer pointed to by x. ....

[Article contains additional citation context not shown here]

V. Lanin and D. Shasha. Concurrent set manipulation without locking. In Proceedings of the Seventh ACM Symposium on Principles of Database Systems, pages 211--220, March 1988.

....any of the others. Moreover, critical regions are ill suited for asynchronous, fault tolerant systems: if a faulty process halts in a critical region, non faulty processes will also be unable to progress [9] Recently, other approaches for implementing concurrent objects have been proposed [10, 11, 1, 13, 14, 15, 16, 2, 5]. In the design and implementation of a concurrent object, we are faced with two problems: 1. What is our notion of correctness for a system composed of concurrent objects 2. Given some notion of correctness, how can we show a given implementation is correct Answering the first question is one ....

....With regard to the second question, we advocate using the complementary techniques of verification and testing. This paper in particular describes an environment for testing implementations of concurrent objects through simulation. Proving linearizability of a data object is a nontrivial task. In [15], the proof of a simple concurrent set consists of five propositions, one lemma and one theorem. The more definitive approach of verification is the subject of other papers [6, 15] including Herlihy and Wing s original POPL paper. Our simulation package provides a means of finding bugs in ....

[Article contains additional citation context not shown here]

V. Lanin and D. Shasha. Concurrent set manipulation without locking. In Proceedings of the Seventh ACM Symposium on Principles of Database Systems, pages 211--220, March 1988.

....the SB OCC on the VF transactions became significantly greater, surpassing the performance of the DB OCC. 5 An Application: Nonblocking Data Structures Many parallel data structures use locks to ensure simultaneous but non interfering access. Other parallel data structures avoid the use of locks [16, 20, 21, 15, 7, 8, 25, 27, 4, 28, 29, 30]. Nonblocking data structures avoid the use of locks, and also guarantee that no operation blocks the execution of any other operation for more than a finite number of steps [7] Nonblocking data structures are tolerant of SS SB V FF VF FF VF 5 3.456 4.157 4.019 5.000 10 5.146 7.174 6.455 10.000 ....

V. Lanin and D. Shasha. Concurrent set manipulation without locking. In Proceedings of the Seventh ACM Symposium on Principles of Database Systems, pages 211--220, 1988.

....that have efficient parallel implementations. Other work has focussed on concurrent objects which are analogous to sequential objects but capable of supporting multiple concurrent requests without using monitors or other exclusion techniques that introduce sequentialising influences into programs. [4, 14, 17, 8, 21, 22, . In our work, the focus is on studying the construction of parallel programs using Shared Abstract Data types (SADTs) In this paper, the term Shared Abstract Data type (SADT) is used to refer to a data abstraction (abstract data type) that is designed to support effective sharing between many ....

Vladmir Lanin and Dennis Shasha. Concurrent set manipulation without locking. In 7th ACM Symposium on the Principlies of Database Systems, pages 211--220, March 1988.

....and generally high overhead. In addition to the universal methods, algorithms have also been developed for lock free objects that are implemented directly. Most of this work has focused on the FIFO queue data type (cf. 27] for many references) but algorithms have also been developed for sets [18], union find [2] scheduling [16] and garbage collection [12] There has also been a large body of work on implementing more primitive types of objects, such as atomic registers and counters. We note that many of these papers present data structures that are based on the linked list; however, ....

V. Lanin and D. Shasha. Concurrent set manipulation without locking. In Proceedings of the Seventh Symposium on Principles of Database Systems, pages 211--220, March 1988.

....wait free concurrent implementations. There has been substantial work investigating efficient algorithms for specific data structures. Few examples below. Non blocking algorithms for implementing queues are presented in [Lam83, HW90, HW87] A non blocking set manipulation algorithm is given in [LS88]. A non blocking Union Find algorithm is designed in [AW91] A non blocking implementation of a priority queue is presented in [IR93] Practical and efficient implementations of nonblocking queues are described in [Val95, MS96] There are many constructions of concurrent B trees, mainly for use in ....

Lanin, V. and Shasha, D. Concurrent set manipulation without locking. Proceedings of the 7th ACM Symposium on Principles of Database Systems, pages 211--220, March 1988.

....presented in [ML82, SG88] Our requirement of completely non blocking readers, and techniques to interrupt long operations (e.g. scans) to allow efficient garbage collection distinguish our work. An investigation of latch free algorithms on a specific data structure (an array) is presented in [LS88] While interesting, these techniques do not fit in with transactional semantics or extend to other structures. The idea of using atomic actions to avoid latching is very generally related to the study of wait free data structures in operating systems, see e.g. Her89] These techniques attempt ....

V. Lanin and D. Shasha. Concurrent set manipulation without locking. In ACM SIGACTSIGMOD Symp. on Principles of Database Systems ., 1988.

....operations . His result, however, does not concern the efficiency of the implementations. Further works on the implementation of concurrent data structures address their efficiency. Those works can be partitioned into three groups. The first group are implementations of specific data structures [14, 17, 2, 11]. The second group are implementations of multi word (k ary) operations from single word operations [9, 19, 12] while the third group introduces general methods for implementing concurrent data structures [8, 1, 5] Clearly, our work belongs to the second group, however, the results may be used ....

V. Lanin and D. Shasha. "Concurrent Set Manipulation Without Locking." Proceedings of the Seventh ACM Symposium on Principles of Database Systems, pages 211--220, March 1988.

....queue implementation that permits one enqueuing process to execute concurrently with one dequeuing process. Herlihy and Wing [21] give a non blocking queue implementation, employing fetch add and swap, that permits an arbitrary number of enqueuing and dequeuing processes. Lanin and Shasha [32] give a non blocking set implementation that uses operations similar to compare swap. There exists an extensive literature on locking algorithms for concurrent B trees [4, 33, 42] and for related search structures [5, 15, 17, 20, 26] Anderson and Woll [1] give efficient wait free solutions to the ....

V. Lanin and D. Shasha. Concurrent set manipulation without locking. In Proceedings of the Seventh ACM Symposium on Principles of Database Systems, pages 211--220, March 1988.

.... include various improvements to Lamport s work on atomic registers, culminating in the important extension of the single writer case to the more general case of multiple writers [6, 11, 46, 47, 49, 54, 55] and work on atomic implementations of some basic data structures such as queues and sets [26, 31, 35]. The idea of a wait free implementation of a shared object was first formalized by Herlihy [24] The problem of getting processes to agree on a common value has played a pivotal role in the history of distributed computing. This ranges from work on the problem of having processes agree in the ....

V. Lanin and D. Shasha. Concurrent set manipulation without locking. In Proceedings of the 7th ACM Symposium on Principles of Database Systems, pages 211--220, 1988.

....approach. Examples include atomic registers from non atomic safe registers [19] complex atomic registers from simpler atomic registers [4, 5, 16, 23, 25, 26, 29, 31] read modify write operations from combining networks [11, 15] and typed objects such as queues or sets from simpler objects [14, 18, 20]. It is less clear how to show that such an implementation does not exist. In the first part of this paper, we propose a simple new technique for proving statements of the form there is no wait free implementation of X by Y . We derive a hierarchy of objects such that no object at one level can ....

V. Lanin and D. Shasha. Concurrent set manipulation without locking. In Proceedings of the Seventh ACM Symposium on Principles of Database Systems, pages 211--220, March 1988.

No context found.

V. Lanin and D. Shasha. Concurrent set manipulation without locking. In Proceedings of the Seventh ACM Symposium on Principles of Database Systems, pages 211--220, March 1988.

No context found.

V. Lanin and D. Shasha. Concurrent set manipulation without locking. In Proceedings of the Seventh ACM Symposium on Principles of Database Systems, pages 211--220, March 1988.

No context found.

Vladimir Lanin and Dennis Shasha. Concurrent set manipulation without locking. In the 7th ACM Symposium on Principles of Database Systems, pages 211--220, March 1988.

No context found.

V. Lanin and D. Shasha, "Concurrent Set Manipulation without Locking", Proceedings of the 7th Annual ACM Symposium on Principles of Database Systems , 1988, pp. 211220.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC