#Number
TR-PDS-1997-014

#Title
Fault-Tolerant Distributed Simulation

#Authors
Om P. Damani, Dept. of Computer Sciences, University of Texas at Austin
Vijay K. Garg, Dept. of Electrical and Computer Eng., University of
Texas at Austin, 
Austin, TX, 78712, USA

#Abstract
We present the first discussion of the issues involved
in fault-tolerant distributed simulation. We integrate an existing
optimistic fault-tolerance scheme with an existing optimistic
distributed simulation scheme. We make use of the novel insight that a
failure can be modeled as a straggler event with the receive time equal to
the virtual time of the last checkpoint saved on  stable
storage. This results in saving of implementation efforts, as well as
reduced overheads. We define stable global virtual time (SGVT), as the
virtual time such that no state with a lower timestamp  will
ever be rolled back. We make a simple change in existing GVT
algorithms to compute SGVT. Our use of transitive dependency tracking
eliminates antimessages. We club LPs into clusters to minimizee
stable storage access time.