Euro-Par'11 Proceedings of the 17th international conference on Parallel processing - Volume Part I
Evaluating the viability of process replication reliability for exascale systems
Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis
Robust distributed orthogonalization based on randomized aggregation
Proceedings of the second workshop on Scalable algorithms for large-scale systems
Impact of over-decomposition on coordinated checkpoint/rollback protocol
Euro-Par'11 Proceedings of the 2011 international conference on Parallel Processing - Volume 2
Evaluating operating system vulnerability to memory errors
Proceedings of the 2nd International Workshop on Runtime and Operating Systems for Supercomputers
Alleviating scalability issues of checkpointing protocols
SC '12 Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis
Containment domains: a scalable, efficient, and flexible resilience scheme for exascale systems
SC '12 Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis
The viability of using compression to decrease message log sizes
Euro-Par'12 Proceedings of the 18th international conference on Parallel processing workshops
Replication for send-deterministic MPI HPC applications
Proceedings of the 3rd Workshop on Fault-tolerance for HPC at extreme scale
Evaluating the feasibility of using memory content similarity to improve system resilience
Proceedings of the 3rd International Workshop on Runtime and Operating Systems for Supercomputers
BlobCR: Virtual disk based checkpoint-restart for HPC applications on IaaS clouds
Journal of Parallel and Distributed Computing
SPBC: leveraging the characteristics of MPI HPC applications for scalable checkpointing
SC '13 Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis
International Journal of High Performance Computing Applications
Containment domains: A scalable, efficient and flexible resilience scheme for exascale systems
Scientific Programming - Selected Papers from Super Computing 2012
| Hi-index | 0.00 |
As reported by many recent studies, the mean time between failures of future post-petascale supercomputers is likely to reduce, compared to the current situation. The most popular fault tolerance approach for MPI applications on HPC Platforms relies on coordinated check pointing which raises two major issues: a) global restart wastes energy since all processes are forced to rollback even in the case of a single failure, b) checkpoint coordination may slow down the application execution because of congestions on I/O resources. Alternative approaches based on uncoordinated check pointing and message logging require logging all messages, imposing a high memory/storage occupation and a significant overhead on communications. It has recently been observed that many MPI HPC applications are \emph{send-deterministic}, allowing to design new fault tolerance protocols. In this paper, we propose an uncoordinated check pointing protocol for send-deterministic MPI HPC applications that (i) logs only a subset of the application messages and (ii) does not require to restart systematically all processes when a failure occurs. We first describe our protocol and prove its correctness. Through experimental evaluations, we show that its implementation in MPICH2 has a negligible overhead on application performance. Then we perform a quantitative evaluation of the properties of our protocol using the NAS Benchmarks. Using a clustering approach, we demonstrate that this protocol actually succeeds to combine the two expected properties: a) it logs only a small fraction of the messages and b) it reduces by a factor approaching 2 the average number of processes to rollback compared to coordinated check pointing.