Submitted by scrawford on
|Title||Optimal Checkpointing Period with replicated execution on heterogeneous platforms|
|Publication Type||Conference Paper|
|Year of Publication||2017|
|Authors||Benoit, A., A. Cavelan, V. Le Fèvre, and Y. Robert|
|Conference Name||2017 Workshop on Fault-Tolerance for HPC at Extreme Scale|
|Publisher||IEEE Computer Society Press|
|Conference Location||Washington, DC|
In this paper, we design and analyze strategies to replicate the execution of an application on two different platforms subject to failures, using checkpointing on a shared stable storage. We derive the optimal pattern size~W for a periodic checkpointing strategy where both platforms concurrently try and execute W units of work before checkpointing. The first platform that completes its pattern takes a checkpoint, and the other platform interrupts its execution to synchronize from that checkpoint.
We compare this strategy to a simpler on-failure checkpointing strategy, where a checkpoint is taken by one platform only whenever the other platform encounters a failure. We use first or second-order approximations to compute overheads and optimal pattern sizes, and show through extensive simulations that these models are very accurate. The simulations show the usefulness of a secondary platform to reduce execution time, even when the platforms have relatively different speeds: in average, over a wide range of scenarios, the overhead is reduced by 30%. The simulations also demonstrate that the periodic checkpointing strategy is globally more efficient, unless platform speeds are quite close.