Paper Info
Title
TRACER: A Trace Replay Tool to Evaluate Energy-Efficiency of Mass Storage Systems
Abstract
Improving energy efficiency of mass storage systems has become an important and pressing research issue in large HPC centers and data centers. New energy conservation techniques in storage systems constantly spring up; however, there is a lack of systematic and uniform way of accurately evaluating energy-efficient storage systems and objectively comparing a wide range of energy-saving techniques. This research presents a new integrated scheme, called TRACER, for evaluating energy-efficiency of mass storage systems and judging energy-saving techniques. The TRACER scheme consists of a toolkit used to measure energy efficiency of storage systems as well as performance and energy metrics. In addition, TRACER contains a novel and accurate workload-control module to acquire power varying with workload modes and I/O load intensity. The workload generator in TRACER facilitates a block-level trace replay mechanism. The main goal of the workload-control module is to select a certain percentage (e.g., anywhere from 10% to 100%) of trace entries from a real-world I/O trace file uniformly and to replay filtered trace entries to reach any level of I/O load intensity. TRACER is experimentally validated on a general RAID5 enterprise disk array. Our experiments demonstrate that energy-efficient mass storage systems can be accurately evaluated on full scales by TRACER. We applied TRACER to investigate impacts of workload modes and load intensity on energy-efficiency of storage devices. This work shows that TRACER can enable storage system developers to evaluate energy efficiency designs for storage systems.
Year
DOI
Venue
2010
10.1109/CLUSTER.2010.40
CLUSTER
Keywords
Field
DocType
raid5 enterprise disk array,energy-efficiency,storage system developer,workload-control module,hpc centers,mass storage system,evaluation,computer centres,storage device,raid,energy-efficient storage system,trace replay tool,tracer,storage management,i/o load intensity,load intensity,energy conservation,o load intensity,mass storage systems,energy-efficient mass storage system,energy-saving techniques,tracer scheme,evaluate energy-efficiency,integrated scheme,data centers,workload mode,program diagnostics,real-world i/o trace file,energy-saving technique,storage system,block-level trace replay mechanism,energy efficiency,energy storage,benchmark testing,data center,energy efficient,generators,disk array
Energy storage,Disk array,Energy conservation,TRACER,Computer science,Efficient energy use,Computer data storage,Parallel computing,Real-time computing,RAID,Mass storage
Conference
ISBN
Citations 
PageRank 
978-0-7695-4220-1
5
0.50
References 
Authors
11
6
Name
Order
Citations
PageRank
Zhuo Liu111816.03
Fei Wu210435.76
Xiao Qin31836125.69
Changsheng Xie436666.54
Jian Zhou5121.83
Jianzong Wang66134.65