Checkpointing Workflows for Fail-Stop Errors

• Published in: IEEE transactions on computers Vol. 67; no. 8; pp. 1105 - 1120
• Main Authors: Han, Li, Canon, Louis-Claude, Casanova, Henri, Robert, Yves, Vivien, Frederic
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.08.2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE); Institute of Electrical and Electronics Engineers
• Subjects: Algorithms; checkpoint; Checkpointing; Computer Science; Data Structures and Algorithms; Distributed, Parallel, and Cluster Computing; Dynamic programming; fail-stop error; Failure; Graph theory; Graphs; Heuristic algorithms; Microprocessors; Probabilistic logic; Processors; Program processors; resilience; Schedules; Task analysis; Task scheduling; Workflow; Workflow software; checkpoint; workflow; resilience; fail-stop error
• ISSN: 0018-9340; 1557-9956; 2326-3814; 1557-9956
• DOI: 10.1109/TC.2018.2801300

We consider the problem of orchestrating the execution of workflow applications structured as Directed Acyclic Graphs (DAGs) on parallel computing platforms that are subject to fail-stop failures. The objective is to minimize expected overall execution time, or makespan. A solution to this problem consists of a schedule of the workflow tasks on the available processors and of a decision of which application data to checkpoint to stable storage, so as to mitigate the impact of processor failures. To address this challenge, we consider a restricted class of graphs, Minimal Series-Parallel Graphs ( M-SPGs ), which is relevant to many real-world workflow applications. For this class of graphs, we propose a recursive list-scheduling algorithm that exploits the M-SPG structure to assign sub-graphs to individual processors, and uses dynamic programming to decide how to checkpoint these sub-graphs. We assess the performance of our algorithm for production workflow configurations, comparing it to an approach in which all application data is checkpointed and an approach in which no application data is checkpointed. Results demonstrate that our algorithm outperforms both the former approach, because of lower checkpointing overhead, and the latter approach, because of better resilience to failures.