@inproceedings{602aa217cbb54983881e04b2f2708350,
title = "Low latency via redundancy",
abstract = "Low latency is critical for interactive networked applications. But while we know how to scale systems to increase capacity, reducing latency - especially the tail of the latency distribution - can be much more difficult. In this paper, we argue that the use of redundancy is an effective way to convert extra capacity into reduced latency. By initiating redundant operations across diverse resources and using the first result which completes, redundancy improves a system's latency even under exceptional conditions. We study the tradeoff with added system utilization, characterizing the situations in which replicating all tasks reduces mean latency. We then demonstrate empirically that replicating all operations can result in significant mean and tail latency reduction in real-world systems including DNS queries, database servers, and packet forwarding within networks.",
keywords = "Latency, Performance, Reliability",
author = "Ashish Vulimiri and Godfrey, {Philip B} and Radhika Mittal and Justine Sherry and Sylvia Ratnasamy and Scott Shenker",
note = "Copyright: Copyright 2019 Elsevier B.V., All rights reserved.; 2013 9th ACM International Conference on Emerging Networking Experiments and Technologies, CoNEXT 2013 ; Conference date: 09-12-2013 Through 12-12-2013",
year = "2013",
doi = "10.1145/2535372.2535392",
language = "English (US)",
isbn = "9781450321013",
series = "CoNEXT 2013 - Proceedings of the 2013 ACM International Conference on Emerging Networking Experiments and Technologies",
publisher = "Association for Computing Machinery",
pages = "283--294",
booktitle = "CoNEXT 2013 - Proceedings of the 2013 ACM International Conference on Emerging Networking Experiments and Technologies",
address = "United States",
}