Year: 2021
Type: article
Abstract: Distributed computing enablesparallelexecution of smaller tasks that make up a large computing job. Its purpose is to reduce the job completion time. However, random fluctuations in task service times lead to straggling tasks with long execution times. Redundancy providesdiversitythat allows job completion when only a subset of redundant tasks is executed, thus removing the dependency on the straggling tasks. Under constrained resources (here, a fixed number of parallel servers), increasing redundancy reduces the available resources for parallelism. In this paper, we characterize thediversity vs. parallelismtrade-off and identify the optimal strategy among replication, coding, and splitting, which minimizes the expected job completion time. We consider three common service time distributions and establish three models that describe the scaling of these distributions with the task size. We find that different distributions with different scaling models operate optimally at different redundancy levels, thus requiring very different code rates.
Authors: Pei Peng, Emina Soljanin, Philip Whiting
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: National Science Foundation
OpenAlex ID: W3213046182