Asynchronous Data Access and Transaction Decomposition in Distributed Databases

Abstract

A RDBMS is usually accessed using blocking drivers like JDBC/ODBC which require clients to block and wait for the result of each query they issue. An asynchronous database access mechanism would eliminate the need for such blocking and greatly improve client performance. Thread-Per-Connection and Thread Pooling are two methods currently being used to provide this asynchrony. These methods require the use of multiple threads in the database server, which provides the clients with access to the database. This is inefficient since a lot of memory and computing power is spent in creating, scheduling and switching multiple threads. In this paper, we show how asynchronous database access can be achieved with a single thread using the Fork-Join mechanism which employs Future objects in Java. We also show how Asynchronous Transaction Decomposition in distributed databases can help improve client performance.

Keywords: Asynchronous, Transaction Decomposition, Future objects, Fork-Join