Cost-based transaction coordinator algorithm implemented at persistent distributed shared virtual memory

In order to support processing of highly concurrent transactions at low price on distributed database server systems, a network of workstations (NOW) is used as the hardware environment. In order to share resources that are distributed among different sites of NOW and support the database functionalities, persistent distributed shared virtual memory (PDSVM) is implemented on ShusseUo, an object database system developed by Kyushu University, Japan. In ShusseUo, all workstations cooperate to perform jobs submitted by database applications. Each job consists of several transactions. These transactions are executed on PDSVM and the cost of each transaction varies according to the workstation on which the transaction runs. We present the cost-based transaction coordinator (CTC) algorithm. In CTC, the load information of a transaction is collected automatically while the transaction is running, and it is fed back when the transaction is committed. In CTC, each transaction is coordinated to a certain workstation based on its cost as calculated using the fed back information and the distribution information of the database. The algorithm is evaluated in terms of the TPC-C benchmark. The benchmark result is presented and analyzed.

[1]  Gerhard Weikum,et al.  A Performance Evaluation of Multi-Level Transaction Management , 1991, VLDB.

[2]  David E. Culler,et al.  A case for NOW (networks of workstation) , 1995, PODC '95.

[3]  Hector Garcia-Molina,et al.  An Overview of Real-Time Database Systems , 1995, NATO ASI RTC.

[4]  Bill Nitzberg,et al.  Distributed shared memory: a survey of issues and algorithms , 1991, Computer.

[5]  Victor C. S. Lee,et al.  Priority and deadline assignment to triggered transactions in distributed real-time active databases , 2000, J. Syst. Softw..

[6]  Miguel Castro,et al.  A checkpoint protocol for an entry consistent shared memory system , 1994, PODC '94.

[7]  Miron Livny,et al.  Earliest deadline scheduling for real-time database systems , 1991, [1991] Proceedings Twelfth Real-Time Systems Symposium.

[8]  Gilbert Cabillic,et al.  The performance of consistent checkpointing in distributed shared memory systems , 1995, Proceedings. 14th Symposium on Reliable Distributed Systems.

[9]  Michael Stumm,et al.  Algorithms implementing distributed shared memory , 1990, Computer.

[10]  Alan L. Cox,et al.  TreadMarks: shared memory computing on networks of workstations , 1996 .

[11]  Ge Yu,et al.  Transaction management for a distributed object storage system WAKASHI-design, implementation and performance , 1996, Proceedings of the Twelfth International Conference on Data Engineering.

[12]  Brian N. Bershad,et al.  The Midway distributed shared memory system , 1993, Digest of Papers. Compcon Spring.

[13]  BeguelinAdam,et al.  Application Level Fault Tolerance in Heterogeneous Networks of Workstations , 1997 .

[14]  David Jordan,et al.  The Object Database Standard: ODMG 2.0 , 1997 .

[15]  Chung Laung Liu,et al.  Scheduling Algorithms for Multiprogramming in a Hard-Real-Time Environment , 1989, JACM.

[16]  Johannes Klein,et al.  Coordinating multi-transaction activities , 1990 .

[17]  Abraham Silberschatz,et al.  Database System Concepts , 1980 .

[18]  Miron Livny,et al.  Transition scheduling in (multiclass real-time database systems , 1992, [1992] Proceedings Real-Time Systems Symposium.

[19]  Alan L. Cox,et al.  Java/DSM: A Platform for Heterogeneous Computing , 1997, Concurr. Pract. Exp..

[20]  Willy Zwaenepoel,et al.  Implementation and performance of Munin , 1991, SOSP '91.

[21]  Paul Hudak,et al.  Memory coherence in shared virtual memory systems , 1989, TOCS.