Impact of Checkpoint Latency on Overhead Ratio of a Checkpointing Scheme
IEEE Transactions on Computers
A first order approximation to the optimum checkpoint interval
Communications of the ACM
Experimental Assessment of Workstation Failures and Their Impact on Checkpointing Systems
FTCS '98 Proceedings of the The Twenty-Eighth Annual International Symposium on Fault-Tolerant Computing
Fault Tolerant Matrix Operations for Networks of Workstations Using Multiple Checkpointing
HPC-ASIA '97 Proceedings of the High-Performance Computing on the Information Superhighway, HPC-Asia '97
Performance Analysis of Two Time-Based Coordinated Checkpointing Protocols
PRFTS '97 Proceedings of the 1997 Pacific Rim International Symposium on Fault-Tolerant Systems
Failure Data Analysis of a Large-Scale Heterogeneous Server Environment
DSN '04 Proceedings of the 2004 International Conference on Dependable Systems and Networks
Checkpointing for Peta-Scale Systems: A Look into the Future of Practical Rollback-Recovery
IEEE Transactions on Dependable and Secure Computing
Filtering Failure Logs for a BlueGene/L Prototype
DSN '05 Proceedings of the 2005 International Conference on Dependable Systems and Networks
Modeling Coordinated Checkpointing for Large-Scale Supercomputers
DSN '05 Proceedings of the 2005 International Conference on Dependable Systems and Networks
Cooperative checkpointing: a robust approach to large-scale systems reliability
Proceedings of the 20th annual international conference on Supercomputing
Optimization of checkpointing-related I/O for high-performance parallel and distributed computing
The Journal of Supercomputing
A higher order estimate of the optimum checkpoint interval for restart dumps
Future Generation Computer Systems
Cooperative checkpointing theory
IPDPS'06 Proceedings of the 20th international conference on Parallel and distributed processing
| Hi-index | 0.00 |
The large scale of current and next-generation massively parallel processing (MPP) systems presents significant challenges related to fault tolerance. For applications that perform periodic checkpointing, the choice of the checkpoint interval, the period between checkpoints, can have a significant impact on the execution time of the application and the number of checkpoint I/O operations performed by the application. These two metrics determine the frequency of checkpoint I/O operations performed by the application and, thereby, the contribution of the checkpoint operations to the demand made by the application on the I/O bandwidth of the computing system. Finding the optimal checkpoint interval that minimizes the wall clock execution time has been a subject of research over the last decade. In this paper, we present a simple, elegant, and accurate analytical model of a complementary performance metric - the aggregate number of checkpoint I/O operations. We present an analytical model of the expected number of checkpoint I/O operations and simulation studies that validate the analytical model. Insights provided by a mathematical analysis of this model, combined with existing models for wall clock execution time, facilitate application programmers in making a well informed choice of checkpoint interval that represents an appropriate trade off between execution time and number of checkpoint I/O operations. We illustrate the existence of such propitious checkpoint intervals using parameters of four MPP systems, SNL's Red Storm, ORNL's Jaguar, LLNL's Blue Gene/L (BG/L), and a theoretical Petaflop system.