P. Yu and A. Dan. Performance Evaluation of Transaction Processing Coupling Architecutres for Handling System Dynamics. IEEE Transactions on Parallel and Distributed Systems, 5(2):139--153, June 1994. 12  Home/Search   Document Not in Database   Summary   Related Articles   Check

....8 Related Work Many studies have demonstrated the performance advantages of using SM implementation platforms for database systems. Based on a TP1 benchmark performed on a Sequent Symmetry shared memory multiprocessor, 27] conclude that an SM database system can deliver very high performance. In [28], an analytical and simulation study compares SN (shared nothing) SD, and SIM (shared intermediate memory 7 ) This comparison concludes that the data sharing architectures, especially SIM, are more resilient to transaction load surges. In [4, 5] simulation studies compare SN, SD, and SM ....

P. Yu and A. Dan. Performance Evaluation of Transaction Processing Coupling Architecutres for Handling System Dynamics. IEEE Transactions on Parallel and Distributed Systems, 5(2):139--153, June 1994. 12

....is impossible for them. Access to resources is permitted to this class, only when nobody else needs them. We now turn our attention to those features of a distributed OLTP system that influence the design and analysis of a transaction routing algorithm. 2.2. Data Affinity Yu and Dan, [YD94], define the affinity of a transaction class to a collection of database objects (relations and rows in a relational database system or just objects in an object oriented database system) as the fraction of the number of database objects referenced by this class of transactions that are in that ....

....of the overall throughput or the minimization of the overall response time. This, however, is not always the case. Transaction classes can represent unequal load to the system and allocation algorithms have been proposed to assign them whole or fractional to the disk sharing processors, see [YD94]. More discussion on such algorithms in section 3.1. 2.2.2. The Shared Nothing Case When nodes of a distributed OLTP system are not sharing storage devices, then a facility to support function shipping [CDY86] is usually provided: when a database call cannot be satisfied by the local node, a ....

P. S. Yu and A. Dan. "Performance Evaluation of Transaction Processing Coupling Architectures for Handling System Dynamics". IEEE Transactions on Parallel and Distributed Systems, 5(2), February 1994.

....of message traffic or by reducing the number of cache misses. 1 Introduction Coupling multiple computing nodes for transaction processing for the sake of capacity and availability has received considerable interests. Shared disks environment (SDE) is a representative architecture of the coupling [6, 7]. In SDE, all coupled nodes are connected via a high speed network and share a common database at the disk level. Since every node may access any portion of the database on the shared disks, SDE can support dynamic load balancing, extensibility, and reliability [6] Each node in SDE has its own ....

P. Yu and A. Dan, "Performance Evaluation of Transaction Processing Coupling Architectures for Handling System Dynamics," IEEE Trans. on Parallel and Distributed Systems 5(2) (Feb. 1994) 139-153. In: Proc. of Int'l Conf. on Systems Engineering

....better than CL. There has been considerable debate about whether a SM implementation platform is suitable for database systems. Based on a TP1 benchmark performed on a Sequent Symmetry shared memory multiprocessor, 21] concludes that a SM database system can deliver very high performance. In [22], an analytical and simulation study compares SN (shared nothing) SD, and SIM (shared intermediate memory 10 ) This comparison concludes that the data sharing architectures, especially SIM, are more resilient to transaction load surges. In [3, 4] simulation studies compare SN, SD, and SM ....

P. Yu and A. Dan. Performance Evaluation of Transaction Processing Coupling Architecutres for Handling System Dynamics. IEEE Transactions on Parallel and Distributed Systems, 5(2):139--153, June 1994.

....7 Related Work Many studies have demonstrated the performance advantages of using SM implementation platforms for database systems. Based on a TP1 benchmark performed on a Sequent Symmetry shared memory multiprocessor, 25] conclude that an SM database system can deliver very high performance. In [26], an analytical and simulation study compares SN (shared nothing) SD, and SIM (shared intermediate memory 7 ) This comparison concludes that the data sharing architectures, especially SIM, are more resilient to transaction load surges. In [3, 4] simulation studies compare SN, SD, and SM ....

P. Yu and A. Dan. Performance Evaluation of Transaction Processing Coupling Architecutres for Handling System Dynamics. IEEE Transactions on Parallel and Distributed Systems, 5(2):139--153, June 1994.

....the problem is so severe that it requires more dramatic steps. In addition, the stage 4 options are the only means that can counteract problems that arise with evolving workloads. The dynamics of the workload is a major cause of problems in guaranteeing good multi user performance [8] 75] 78] [96]. Therefore, as we are particularly concerned with multi user tuning issues, the COMFORT project has put most emphasis on stage 4. The COMFORT Automatic Tuning Project 385 2.2. Rationale of COMFORT Since we were specifically interested in the impact of workload dynamics, we followed a ....

P. S. Yu and A. Dan.Performance Evaluation of Transaction Processing Coupling Architectures for Handling System Dynamics, Technical Report RC 16606, IBM T.J. Watson Research Center, Yorktown Heights (1992). 432 Gerhard Weikum et al.

....and or disk groups is interesting in its own right. Short term load imbalance across servers and or disk groups implies that extra server capacity has to be provided to satisfy certain performance objectives, whereas improved load balancing reduces the amount of required excess server capacity [17]. Static replication of all files for high availability and also for load balancing in the file server context has been proposed in [10, 15] This is not desirable in multimedia systems due to the large size of multimedia objects. Replication of the relatively small and frequently accessed ....

....the static policy. Note that the DSR policy has a lower rejection rate even though the simulation is set up to favor the static policy by pre replicating the hottest movies. In many environments, a system is configured to handle dynamic load changes while satisfying certain performance objectives [17]. In the current environment, one such performance objective for configuring the server could be to contain the rejection rate below a certain threshold (say 1 ) The horizontal dotted line represents a 1 rejection rate. If the server capacity is considered to be the load at which the rejection ....

Yu, P. and A. Dan. "Performance Evaluation of Transaction Processing Coupling Architectures for handling System Dynamics", IEEE Trans. on Parallel and Distributed Systems,

.... cross invalidation phenomenon and improve the overall system performance [5] 12] The advantages that such coupled systems can offer include better price performance, improved capacity and responsiveness due to parallelism, scalability, enhanced fault tolerance and better dynamic load balancing [15] [16] A significant amount of research effort has investigated various issues for such data sharing environments, or related client server paradigms, including the impact of data skew [4] global buffer management [1] 5] 7] locking, and concurrency and coherency protocols [6] 11] 14] As ....

P. S. Yu and A. Dan. Performance Evaluation of Transaction Processing Computing Architectures for Handling System Dynamics. IEEE Transactions on Knowledge and Data Engineering, pages 139--153, February 1994.

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