Data Replication for Reducing Computing Time in Distributed Systems with Stragglers
Preprint
Abstract
In distributed computing systems with stragglers, various forms of redundancy can improve the average delay performance. We study the optimal replication of data in systems where the job execution time is a stochastically decreasing and convex random variable. We show that in such systems, the optimum assignment policy is the balanced replication of disjoint batches of data. Furthermore, for Exponential and Shifted-Exponential service times, we derive the optimum redundancy levels for minimizing both expected value and the variance of the job completion time. Our analysis shows that, the optimum redundancy level may not be the same for the two metrics, thus there is a trade-off between reducing the expected value of the completion time and reducing its variance.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Straggler Mitigation at ScaleIEEE/ACM Transactions on Networking, 2019
- The tail at scaleCommunications of the ACM, 2013
- Distributed Optimization and Statistical Learning via the Alternating Direction Method of MultipliersFoundations and Trends in Machine Learning, 2011
- A new parallel matrix multiplication algorithm on distributed-memory concurrent computersConcurrency: Practice and Experience, 1998