DocumentCode
1679274
Title
GreenCHT: A power-proportional replication scheme for consistent hashing based key value storage systems
Author
Nannan Zhao ; Jiguang Wan ; Jun Wang ; Changsheng Xie
Author_Institution
Wuhan Nat. Lab. for Optoelectron., Wuhan, China
fYear
2015
Firstpage
1
Lastpage
6
Abstract
Distributed key value storage systems are widely used by many popular networking corporations. Nevertheless, server power consumption has become a growing concern for key value storage system designers since the power consumption of servers contributes substantially to a data center´s power bills. In this paper, we propose GreenCHT, a power-proportional replication scheme for consistent hashing based key value storage systems. GreenCHT consists of a power-aware replication strategy - multi-tier replication strategy and a centralized power control service - predictive power-mode scheduler. The multitier replication provides power-proportionality and ensures data availability, reliability, consistency, as well as fault-tolerance of the whole system. The predictive power-mode scheduler component predicts workloads and exploits load fluctuation to schedule nodes to be powered-up and powered-down. GreenCHT is implemented based on Sheepdog, a distributed key value system that uses consistent hashing as an underlying distributed hash table. By replicating twelve real workload traces collected from Microsoft, the evaluation results show that GreenCHT can provide significant power savings while maintaining an acceptable performance. We observed that GreenCHT can reduce power consumption by up to 35%-61%.
Keywords
computer centres; cryptography; data integrity; fault tolerant computing; power aware computing; power consumption; scheduling; storage management; GreenCHT; Microsoft; Sheepdog; centralized power control service; consistent hashing based key value storage systems; data availability; data center; data consistency; data reliability; distributed hash table; distributed key value storage system; load fluctuation; multitier replication strategy; networking corporation; node scheduling; power savings; power-aware replication strategy; power-proportional replication scheme; predictive power-mode scheduler component; server power consumption; system fault-tolerance; workload prediction; workload traces; Measurement; Peer-to-peer computing; Power demand; Resource management; Schedules; Servers; Switches; CHT; Key Value Storage System; Power Management; Replication; Sheepdog;
fLanguage
English
Publisher
ieee
Conference_Titel
Mass Storage Systems and Technologies (MSST), 2015 31st Symposium on
Conference_Location
Santa Clara, CA
Type
conf
DOI
10.1109/MSST.2015.7208289
Filename
7208289
Link To Document