Distributed Join-the-Idle-Queue for Low Latency Cloud Services
Abstract
Low latency is highly desirable for cloud services. To achieve low response time, stringent timing requirements are needed for task scheduling in a large-scale server farm spanning thousands of servers. In this paper, we conduct an in-depth analysis for distributed Join-the-Idle-Queue (JIQ), a promising new approximation of an idealized task-scheduling algorithm. In particular, we derive semi-closed form expressions for the delay performance of distributed JIQ, and we propose a new variant of distributed JIQ that offers clear advantages over alternative algorithms for large systems.
Keywords
Cite
@article{arxiv.1709.10119,
title = {Distributed Join-the-Idle-Queue for Low Latency Cloud Services},
author = {Chunpu Wang and Chen Feng and Julian Cheng},
journal= {arXiv preprint arXiv:1709.10119},
year = {2017}
}
Comments
10 pages, 10 figures. This work is inspired by Michael Mitzenmacher's recent work on distributed Join-Idle-Queue (arXiv:1606.01833) as well as Alexander Stolyar's recent work on centralized Join-Idle-Queue (arXiv:1512.07873 and arXiv:1407.6343)