The Community for Technology Leaders
Green Image
Issue No. 03 - May-June (2016 vol. 36)
ISSN: 0272-1732
pp: 94-104
Sheng Li , Intel Labs
Hyeontaek Lim , Carnegie Mellon University
Victor W. Lee , Intel Labs
Jung Ho Ahn , Seoul National University
Anuj Kalia , Carnegie Mellon University
Michael Kaminsky , Intel Labs
David G. Andersen , Carnegie Mellon University
Seongil O , Seoul National University
Sukhan Lee , Seoul National University
Pradeep Dubey , Intel Labs
Distributed in-memory key-value stores (KVSs) have become a critical data-serving layer in cloud computing and big data infrastructure. Unfortunately, KVSs have demonstrated a gap between achieved and available performance, QoS, and energy efficiency on commodity platforms. Two research thrusts have focused on improving key-value performance: hardware-centric research has started to explore specialized platforms for KVSs, and software-centric research revisited the KVS application to address fundamental software bottlenecks. Unlike prior research focusing on hardware or software in isolation, the authors aimed to full-stack (software through hardware) architect high-performance and efficient KVS platforms. Their full-system characterization identifies the critical hardware/software ingredients for high-performance KVS systems and suggests optimizations to achieve record-setting performance and energy efficiency: 120~167 million requests per second (RPS) on a single commodity server. They propose a future many-core platform and via detailed simulations demonstrate the capability of achieving a billion RPS with a single server platform.
Servers, Key value systems, Concurrency control, Memory management, Program processors, Performance evaluation, Field programmable analog arrays

S. Li et al., "Achieving One Billion Key-Value Requests per Second on a Single Server," in IEEE Micro, vol. 36, no. 3, pp. 94-104, 2016.
538 ms
(Ver 3.3 (11022016))