Methods and apparatus for managing middleware service in a distributed system

Abstract

A distributed computing system includes a number of computers, workstations or other computing machines interconnected by a network. One or more service managers are introduced that provide a management interface to corresponding middleware services. The service manager monitors the corresponding middleware service, as well as the underlying distributed computer environment on which an application process that utilizes the middleware service is executing, and allows the middleware service to operate more efficiently, in response to run-time environmental conditions. A fault-tolerance service manager is provided as a management interface to a fault-tolerance service. The fault-tolerance service manager monitors the fault-tolerance service, as well as the underlying distributed computer environment, to make globally optimal decisions, based on run-time environmental data, and to provide the resulting information to the fault-tolerance service. The fault-tolerance service manager can notify the fault-tolerance service about hazardous network conditions (such as object hosts that may crash soon) and the fault-tolerance service may decide to migrate application objects or take other corrective action. The collected environmental data can be used to determine a health rating of components within the computing environment which can be utilized, for example, to select an optimal machine for migration, or to trigger migration or additional replication in the event the health rating indicates that a failure is expected.