Raynal M. A simple taxonomy for distributed mutual exclusion algorithms. Operating System Review 1991; 25:47--50.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....in a way that preserves the happened before relationship. Of course, this one figure does not prove the correctness of the LLC algorithm, but multiple experiments of this type can be performed to provide more insights and confidence in understanding the behavior of the (1) 2) 3) 1) 1] [4] [5] 6] 7] 3] 4] 6] 7] 2] 3] Terminals ID s Virtual Time (Events) Figure 8. Time sequence graph displayed by Xplot for LLC: a) original plot; b) expanded part (1) protocol. Note that one advantage of the Xplot tool is its ability to let the user isolate segments of a plot and ....

....preserves the happened before relationship. Of course, this one figure does not prove the correctness of the LLC algorithm, but multiple experiments of this type can be performed to provide more insights and confidence in understanding the behavior of the (1) 2) 3) 1) 1] 4] 5] 6] 7] 3] [4] [6] 7] 2] 3] Terminals ID s Virtual Time (Events) Figure 8. Time sequence graph displayed by Xplot for LLC: a) original plot; b) expanded part (1) protocol. Note that one advantage of the Xplot tool is its ability to let the user isolate segments of a plot and create expanded views. ....

Raynal M. A simple taxonomy for distributed mutual exclusion algorithms. Operating System Review 1991; 25:47--50.

....K MUTUAL EXCLUSION PROBLEM 17 systems. To enter a critical section, a process must assure that there is no process which is being in a critical section in the distributed system. Many algorithms have been proposed to solve the distributed mutual exclusion problem. They are classified into two types[Ray91b]: Permission based principle A process P wising to enter a critical section requests some other processes to permit it to enter a critical section. If a permission is given from each process P is asking, P can enter the critical section. Token based principle There is an object ....

Michel Raynal. A simple taxonomy for distributed mutual exclusion algorithms. ACM Operating Systems Review, 25(2):47--51, 1991.

....the concept of k coterie and propose a distributed k mutual exclusion algorithm using this concept. Several distributed k mutual exclusion algorithms have been proposed[6] 10] There are two paradigms for distributed mutual exclusion algorithms: the permissionbased and the token based ones [7]. Raymond [6] proposed a permission based algorithm as an extension of Ricart and Agrawala s mutual exclusion algorithm[8] Since a process wishing to enter a critical section sends a request message to each of the other processes, its message complexity is # n) Srimani and Reddy[10] proposed a ....

M. Raynal. A simple taxonomy for distributed mutual exclusion algorithms. ACM Operating Systems Review, 25(2):47--51, 1991.

....a more precise one, which introduces a term of first order (i.e. the variance) in the bounding which highlights the load balancing feature. Let us present some distributed mutual exclusion algorithms to see the influence of the non equiprobability of processes requests. In token ring algorithms [11], the token circulates on the ring of computers. When a process requests the critical section, it waits for the arrival of the token. If a process requests frequently the critical section, that does not modify the circulation of the token. In Lamport s algorithm [4] a requiring process broadcasts ....

M. Raynal. A simple taxonomy for distributed mutual exclusion algorithms. ACM Operating Systems Review, SIGOPS, 25(2):47--50, April 1991.

....processes to a critical resource. Several solutions have been proposed to solve the mutual exclusion problem in distributed systems [Lam78, RA81, CR83, Mae85, SK85, vdS87, Sin88, HPR88, Ray89] These solutions can be broadly categorized into two types: permission based and token based solutions [San87, Ray91]. The advantage of permission based mutual exclusion algorithms is that they exhibit excellent fault tolerance and load balancing characteristics. The general approach underlying this type of algorithms is that a process (or equivalently a site in the network) wishing to enter the critical section ....

M. Raynal. A Simple Taxonomy for Distributed Mutual Exclusion Algorithms. ACM SIGOPS Operating Systems Review, 25(2):47--50, April 1991.

....on practical distributed architectures. 1 Introduction The problem of mutual exclusion (MX) was rst discussed by Dijkstra [8] A distributed mutual exclusion algorithm is designed to work in a system where processes do not share memory or clock. Such algorithms have been studied extensively [19, 21, 23]. The two main performance metrics the MX algorithms designers try to optimize are message complexity and synchronization delay [23] Message complexity is the number of messages needed for one critical section (CS) access. Synchronization delay is the number of causally related message exchanges ....

M. Raynal. A simple taxonomy for distributed mutual exclusion algorithms. ACM Operating Systems Review, 25(2):47-50, 1991.

.... mutual exclusion algorithms proposed in the last decade [3, 12, 16, 26, 37, 40, 41, 43, 45, 47, 49, 51, 57, 58, 59, 62, 63, 64, 67, 68, 69, 74, 78, 79] A nice summary can be found in a book by Raynal [61] These algorithms have been classified into two types: token based and permission based [60, 68]. In token based algorithms, a node may enter the critical section only after receiving the token. In permission based algorithms, a node may enter the critical section only after receiving permission from a quorum of nodes. Token based algorithms can be further subdivided into those that impose ....

M. Raynal. A simple taxonomy for distributed mutual exclusion algorithms. Technical Report 560, IRISA, Rennes, France, 1990.

....the number of messages required for a critical section (CS) entry, and (2) synchronization delay, which is the number of rounds of message passing required for one node to leave the CS and another to enter the CS. Several taxonomic studies and generalizations of the algorithms have been published [10, 12, 14]. Generally, the algorithms are classified into two major categories: token based and permission based (also called non token based) algorithms. We use the term lock based to represent the latter category. In general, token based algorithms require less messages than lock based algorithms. ....

Raynal, M. A simple taxonomy for distributed mutual exclusion algorithms. ACM Operating Systems Review, 25(2):47--50, 1991.

....need the exchange of more information than in normal operation, in order to reconstruct the state of the system as it was before the failure. Hence, their performance will be evaluated under normal conditions. Distributed mutual exclusion algorithms are designed based on two basic principles [19, 24]: the existence of a token in the system, or the collection of permission from nodes in the system. These two approaches are described in the following section. 3. BASIC APPROACHES FOR THE DESIGN OF DISTRIBUTED MUTUAL EXCLUSION ALGORITHMS Distributed mutual exclusion algorithms can be classified ....

....of permission from nodes in the system. These two approaches are described in the following section. 3. BASIC APPROACHES FOR THE DESIGN OF DISTRIBUTED MUTUAL EXCLUSION ALGORITHMS Distributed mutual exclusion algorithms can be classified into two groups by a basic principle in their design [19, 24]. These two groups are token based algorithms and permission based algorithms. The basic principle for the design of a distributed mutual exclusion algorithm is the way in which the right to enter the critical section is formalized in the system. 3.1 The token based approach. In the token based ....

[Article contains additional citation context not shown here]

RAYNAL, M., "A simple taxonomy for distributed mutual exclusion algorithms," Operating Systems Review, vol. 25, no. 2, apr. 1991, pp. 47-49.

....achieves minimal heavy load synchronization delay and imposes very little storage overhead. 1 Introduction Many distributed mutual exclusion algorithms have been proposed [1, 2, 3, 5, 6, 7, 8, 9, 11, 12, 13, 14, 16, 17, 18, 19, 20, 21, 22, 23] These algorithms can be classified into two groups [15, 20]. The algorithms in the first group are permission based [1, 3, 6, 7, 14, 16, 18, 19] A node enters the critical section only after receiving permission from a set of nodes. The algorithms in the second group are token based [2, 5, 8, 9, 11, 12, 17, 20, 21, 22, 23] The possession of a ....

M. Raynal. A simple taxonomy for distributed mutual exclusion algorithms. Technical Report 560, INRIA, 78153 Le Chesnay Cedex, France, 1990.

....quorum agreement is used, the overall performance of the algorithm compares favorably with the performance of other mutual exclusion algorithms. 1 Introduction Many distributed mutual exclusion algorithms exist [5, 6, 8, 10, 11, 12, 13, 14, 15] These algorithms can be classified into two groups [9, 13]. The algorithms in the first group are token based [8, 11, 13, 14, 15] The possession of a system wide unique token gives a node the right to access a resource in mutual exclusion. The algorithms in the second group are permission based [5, 6, 10, 12] If a node receives permission from a ....

M. Raynal. A simple taxonomy for distributed mutual exclusion algorithms. Technical Report 560, INRIA, 78153 Le Chesnay Cedex, France, 1990, will appear in Operating Systems Review.

....the number of messages required for a critical section (CS) entry and (2) synchronization delay, which is the number of rounds of message passing required for one node to leave the CS and another to enter the CS. Several taxonomic studies and generalizations of the algorithms have been published [10, 12, 14]. Generally, the algorithms are classified into two major categories: token based and permission based (also called non token based) algorithms. We use the term lock based to repre sent the latter category. In general, token based algorithms require less messages than lock based algorithms. ....

Raynal, M. A simple taxonomy for distributed mutual exclusion algorithms. ACM Operating Systems Review, 25(2):47--50, 1991.

....lines. Simple mutual exclusion states that only one process at any time be in its critical section which is the part of the source code in which the process executes private operations with the shared resource. In recent years, many distributed mutual exclusion algorithms have been presented [23, 20] and generalizations to k mutual exclusion have been also considered [9, 16, 18] The k mutual exclusion allows at most k processes to enter the critical section at the same time. This problem corresponds to the case when there is a pool of k units of the shared resource and each process can ....

....allows at most k processes to enter the critical section at the same time. This problem corresponds to the case when there is a pool of k units of the shared resource and each process can requests at most one unit. All these mutual exclusion algorithms have been classified in two main categories [23, 20]: the quorum (or permission) based and the token based. In the latter a process allocates the shared resource as soon as it receives a token [8] In the former a process gets the resource as soon as it receives an explicit permission, by means of a message, from all processes constituting its ....

Raynal, M.: "A Simple Taxonomy for Distributed Mutual Exclusion," ACM Operating System Review, Vol. 25, No. 1, pp. 47--51 (1991). RR n2523 18 Roberto Baldoni, Yoshifumi Manabe, Michel Raynal, Shigemi Aoyagi

No context found.

M. Raynal. A simple taxonomy for distributed mutual exclusion algorithms. ACM Op. Systems Review, Vol. 25,2, (1991), pp. 47-50.

No context found.

M. Raynal. A simple taxonomy for distributed mutual exclusion algorithms. ACM Op. Systems Review, Vol. 25,2, (1991), pp. 47-50.

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