Optimal Object State Transfer - Recovery Policies for Fault Tolerant Distributed Systems

Recent developments in the field of object-based fault tolerance and the advent of the first OMG FTCORBA compliant middleware raise new requirements for the design process of distributed fault-tolerant systems. In this work, we introduce a simulation-based design approach based on the optimum effectiveness of the compared fault tolerance schemes. Each scheme is defined as a set of fault tolerance properties for the objects that compose the system. Its optimum effectiveness is determined by the tightest effective checkpoint intervals, for the passively replicated objects. Our approach allows mixing miscellaneous fault tolerance policies, as opposed to the published analytic models, which are best suited in the evaluation of single-server process replication schemes. Special emphasis has been given to the accuracy of the generated estimates using an appropriate simulation output analysis procedure. We provide showcase results and compare two characteristic warm passive replication schem...

• Type: Conference
• Year: 2004
• Where: DSN
• Authors: Panagiotis Katsaros, Constantine Lazos
• Keywords: Computer Networks, DSN 2004, Fault Tolerance, Fault Tolerance Schemes, Object-based Fault Tolerance