To Repair or Not to Repair: Assessing Fault Resilience in MPI Stencil Applications
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910645335621632 |
|---|---|
| author | Rocco, Roberto Boella, Elisabetta Gregori, Daniele Palermo, Gianluca |
| author_facet | Rocco, Roberto Boella, Elisabetta Gregori, Daniele Palermo, Gianluca |
| contents | With the increasing size of HPC computations, faults are becoming more and more relevant in the HPC field. The MPI standard does not define the application behaviour after a fault, leaving the burden of fault management to the user, who usually resorts to checkpoint and restart mechanisms. This trend is especially true in stencil applications, as their regular pattern simplifies the selection of checkpoint locations. However, checkpoint and restart mechanisms introduce non-negligible overhead, disk load, and scalability concerns. In this paper, we show an alternative through fault resilience, enabled by the features provided by the User Level Fault Mitigation extension and shipped within the Legio fault resilience framework. Through fault resilience, we continue executing only the non-failed processes, thus sacrificing result accuracy for faster fault recovery. Our experiments on a specimen stencil application show that, despite the fault impact visible in the result, we produced meaningful values usable for scientific research, proving the possibilities of a fault resilience approach in a stencil scenario. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_08647 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | To Repair or Not to Repair: Assessing Fault Resilience in MPI Stencil Applications Rocco, Roberto Boella, Elisabetta Gregori, Daniele Palermo, Gianluca Distributed, Parallel, and Cluster Computing With the increasing size of HPC computations, faults are becoming more and more relevant in the HPC field. The MPI standard does not define the application behaviour after a fault, leaving the burden of fault management to the user, who usually resorts to checkpoint and restart mechanisms. This trend is especially true in stencil applications, as their regular pattern simplifies the selection of checkpoint locations. However, checkpoint and restart mechanisms introduce non-negligible overhead, disk load, and scalability concerns. In this paper, we show an alternative through fault resilience, enabled by the features provided by the User Level Fault Mitigation extension and shipped within the Legio fault resilience framework. Through fault resilience, we continue executing only the non-failed processes, thus sacrificing result accuracy for faster fault recovery. Our experiments on a specimen stencil application show that, despite the fault impact visible in the result, we produced meaningful values usable for scientific research, proving the possibilities of a fault resilience approach in a stencil scenario. |
| title | To Repair or Not to Repair: Assessing Fault Resilience in MPI Stencil Applications |
| topic | Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2410.08647 |