Papers
 
Starfish: Fault-Tolerant Dynamic MPI Programs on Clusters of Workstations.
Adnan Agbaria and Roy Friedman.
In the 8th IEEE International Symposium on High Performance Distributed Computing, 1999.
Design, Implementation, and Performance of Checkpointing in NetSolve
Adnan Agbaria and James S. Plank
Technical Report UT-CS-99-433, University of Tennessee, 1999.
In the International Conference on Dependable Systems and Networks - DSN2000
Virtual Machine Based Heterogeneous Checkpointing
Adnan Agbaria and Roy Friedman

Technical Report CS-2000-11, Technion 2000
Quantifying Rollback Propagation in Distributed Checkpointing
Adnan Agbaria, Hagit Attiya, Roy Friedman and Roman Vitenberg
In the 20th Symposium on Reliable Distributed Systems, 2001,  New Orleans.
Evaluating Distributed Checkpointing Protocols
Adnan Agbaria, Ari Freund and Roy Friedman
Technical Report CS-2002-15, Technion 2002