Performance Implications of Periodic Checkpointing on Large-Scale Cluster Systems

Large-scale systems like BlueGene/L are susceptible to a number of software and hardware failures that can affect system performance. Periodic application checkpointing is a common technique for mitigating the amount of work lost due to job failures, but its effectiveness under realistic circumstances has not been studied. In this paper, we analyze the system-level performance of periodic application checkpointing using parameters similar to those projected for BlueGene/L systems. Our results reflect simulations on a toroidal interconnect architecture, using a real job log from a machine similar to BlueGene/L, and with a real failure distribution from a large-scale cluster. Our simulation studies investigate the impact of parameters such as checkpoint overhead and checkpoint interval on a number of performance metrics, including bounded slowdown, system utilization, and total work lost. The results suggest that periodic checkpointing may not be an effective way to improve the average...

• Type: Conference
• Year: 2005
• Where: IPPS
• Authors: Adam J. Oliner, Ramendra K. Sahoo, José E. Moreira, Meeta Sharma Gupta
• Keywords: Distributed And Parallel Computing, Hardware Failures, IPPS 2005, Job Failures, Periodic Application Checkpointing