SPBC: Leveraging the Characteristics of MPI HPC Applications for Scalable Checkpointing
|Title||SPBC: Leveraging the Characteristics of MPI HPC Applications for Scalable Checkpointing|
|Publication Type||Conference Paper|
|Year of Publication||2013|
|Authors||Cappello, F, Ropars, T, Martsinkevich, RV, Guermouche, A, Schiper, A|
|Conference Name||Super Computing (SC13)|
|Conference Location||Denver, CO|
The high failure rate expected for future extreme-scale supercomputers requires the design of new fault tolerant solutions. Most existing checkpointing protocols are designed to work with any message-passing application but suffer from scalability issues at extreme scale. In this paper, we take a different approach: We identify a property common to many HPC applications, namely channel-determinism, and introduce a new partial order relation, called always-happens-before relation, between events of such applications. Leveraging these two concepts, we design a protocol that combines an unprecedented set of features. Our protocol called SPBC combines in a hierarchical way coordinated checkpointing and message logging. It is the first protocol that provides failure containment without logging any information reliably apart from process checkpoints, and thus, without penalizing recovery performance. Experiments run with a representative set of HPC workloads demonstrate a good performance of our protocol during both, failure-free execution and recovery.