Communications of the ACM
The effectiveness of multiple hardware contexts
ASPLOS VI Proceedings of the sixth international conference on Architectural support for programming languages and operating systems
A survey of rollback-recovery protocols in message-passing systems
ACM Computing Surveys (CSUR)
Fault tolerant high performance computing by a coding approach
Proceedings of the tenth ACM SIGPLAN symposium on Principles and practice of parallel programming
Performance evaluation of adaptive MPI
Proceedings of the eleventh ACM SIGPLAN symposium on Principles and practice of parallel programming
Algorithm-Based Fault Tolerance for Matrix Operations
IEEE Transactions on Computers
FTPA: Supporting Fault-Tolerant Parallel Computing through Parallel Recomputing
IEEE Transactions on Parallel and Distributed Systems
International Journal of High Performance Computing Applications
A higher order estimate of the optimum checkpoint interval for restart dumps
Future Generation Computer Systems
Correlated set coordination in fault tolerant message logging protocols
Euro-Par'11 Proceedings of the 17th international conference on Parallel processing - Volume Part II
Evaluating the viability of process replication reliability for exascale systems
Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis
HydEE: Failure Containment without Event Logging for Large Scale Send-Deterministic MPI Applications
IPDPS '12 Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium
Hi-index | 0.00 |
Failures are increasingly threatening the efficiency of HPC systems, and current projections of Exascale platforms indicate that rollback recovery, the most convenient method for providing fault tolerance to general-purpose applications, reaches its own limits at such scales. One of the reasons explaining this unnerving situation comes from the focus that has been given to per-application completion time, rather than to platform efficiency. In this paper, we discuss the case of uncoordinated rollback recovery where the idle time spent waiting recovering processors is used to progress a different, independent application from the system batch queue. We then propose an extended model of uncoordinated checkpointing that can discriminate between idle time and wasted computation. We instantiate this model in a simulator to demonstrate that, with this strategy, uncoordinated checkpointing per application completion time is unchanged, while it delivers near-perfect platform efficiency.