MSN 数学媒体与信息存储 1/27 Zhuo Liu, Fei Wu, Xiao Qin, Changsheng Xie, Jian Zhou, and Jianzong Wang TRACER: A Trace Replay Tool to Evaluate Energy-Efficiency of.

Slides:



Advertisements
Similar presentations
Sabyasachi Ghosh Mark Redekopp Murali Annavaram Ming-Hsieh Department of EE USC KnightShift: Enhancing Energy Efficiency by.
Advertisements

Solving Manufacturing Equipment Monitoring Through Efficient Complex Event Processing Tilmann Rabl, Kaiwen Zhang, Mohammad Sadoghi, Navneet Kumar Pandey,
Decentralized Reactive Clustering in Sensor Networks Yingyue Xu April 26, 2015.
1 Conserving Energy in RAID Systems with Conventional Disks Dong Li, Jun Wang Dept. of Computer Science & Engineering University of Nebraska-Lincoln Peter.
Evaluating Energy and Performance for Server- Class Hardware Configurations Chenguang Liu, Jianzhong Huang, Qiang Cao, Shenggang Wan, Changsheng Xie School.
ANALYZING STORAGE SYSTEM WORKLOADS Paul G. Sikalinda, Pieter S. Kritzinger {psikalin, DNA Research Group Computer Science Department.
RIMAC: Redundancy-based hierarchical I/O cache architecture for energy-efficient, high- performance storage systems Xiaoyu Yao and Jun Wang Computer Architecture.
Host Load Trace Replay Peter A. Dinda Thesis Seminar 11/23/98.
An Adaptable Benchmark for MPFS Performance Testing A Master Thesis Presentation Yubing Wang Advisor: Prof. Mark Claypool.
1 A Framework for Lazy Replication in P2P VoD Bin Cheng 1, Lex Stein 2, Hai Jin 1, Zheng Zhang 2 1 Huazhong University of Science & Technology (HUST) 2.
Accurate and Efficient Replaying of File System Traces Nikolai Joukov, TimothyWong, and Erez Zadok Stony Brook University (FAST 2005) USENIX Conference.
Energy Efficient Prefetching – from models to Implementation 6/19/ Adam Manzanares and Xiao Qin Department of Computer Science and Software Engineering.
Energy Efficient Prefetching with Buffer Disks for Cluster File Systems 6/19/ Adam Manzanares and Xiao Qin Department of Computer Science and Software.
Hardware-based Load Generation for Testing Servers Lorenzo Orecchia Madhur Tulsiani CS 252 Spring 2006 Final Project Presentation May 1, 2006.
I.1 ii.2 iii.3 iv.4 1+1=. i.1 ii.2 iii.3 iv.4 1+1=
Energy Efficient Web Server Cluster Andrew Krioukov, Sara Alspaugh, Laura Keys, David Culler, Randy Katz.
Differentiated Multimedia Web Services Using Quality Aware Transcoding S. Chandra, C.Schlatter Ellis and A.Vahdat InfoCom 2000, IEEE Journal on Selected.
I.1 ii.2 iii.3 iv.4 1+1=. i.1 ii.2 iii.3 iv.4 1+1=
An Energy-efficient Target Tracking Algorithm in Wireless Sensor Networks Wang Duoqiang, Lv Mingke, Qin Qi School of Computer Science and technology Huazhong.
Comparing Coordinated Garbage Collection Algorithms for Arrays of Solid-state Drives Junghee Lee, Youngjae Kim, Sarp Oral, Galen M. Shipman, David A. Dillow,
23 September 2004 Evaluating Adaptive Middleware Load Balancing Strategies for Middleware Systems Department of Electrical Engineering & Computer Science.
Usage Centric Green Metrics for Storage Doron Chen, Ealan Henis, Ronen Kat and Dmitry Sotnikov IBM Haifa Research Lab Most of the metrics defined today.
Analyzing the Energy Efficiency of a Database Server Hanskamal Patel SE 521.
Toolbox for Dimensioning Windows Storage Systems Jalil Boukhobza, Claude Timsit 12/09/2006 Versailles Saint Quentin University.
PARAID: The Gear-Shifting Power-Aware RAID Charles Weddle, Mathew Oldham, An-I Andy Wang – Florida State University Peter Reiher – University of California,
THIN CLIENT COMPUTING USING ANDROID CLIENT for XYZ School.
Microsoft Research Asia Ming Wu, Haoxiang Lin, Xuezheng Liu, Zhenyu Guo, Huayang Guo, Lidong Zhou, Zheng Zhang MIT Fan Long, Xi Wang, Zhilei Xu.
Bottlenecks: Automated Design Configuration Evaluation and Tune.
OPTIMAL SERVER PROVISIONING AND FREQUENCY ADJUSTMENT IN SERVER CLUSTERS Presented by: Xinying Zheng 09/13/ XINYING ZHENG, YU CAI MICHIGAN TECHNOLOGICAL.
Energy Profiling And Analysis Of The HPC Challenge Benchmarks Scalable Performance Laboratory Department of Computer Science Virginia Tech Shuaiwen Song,
Location-aware MapReduce in Virtual Cloud 2011 IEEE computer society International Conference on Parallel Processing Yifeng Geng1,2, Shimin Chen3, YongWei.
November , 2009SERVICE COMPUTATION 2009 Analysis of Energy Efficiency in Clouds H. AbdelSalamK. Maly R. MukkamalaM. Zubair Department.
The Center for Autonomic Computing is supported by the National Science Foundation under Grant No NSF CAC Seminannual Meeting, October 5 & 6,
Yaoshen Yuan Tufts University Virtual Machine Usage in Cloud Computing in Google EE-126.
1 Rapid Estimation of Power Consumption for Hybrid FPGAs Chun Hok Ho 1, Philip Leong 2, Wayne Luk 1, Steve Wilton 3 1 Department of Computing, Imperial.
Critical Power Slope Understanding the Runtime Effects of Frequency Scaling Akihiko Miyoshi, Charles Lefurgy, Eric Van Hensbergen Ram Rajamony Raj Rajkumar.
Tag line, tag line Power Management in Storage Systems Kaladhar Voruganti Technical Director CTO Office, Sunnyvale June 12, 2009.
© 2006 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice Profiling and Modeling Resource Usage.
An I/O Simulator for Windows Systems Jalil Boukhobza, Claude Timsit 27/10/2004 Versailles Saint Quentin University laboratory.
1 Distributed Energy-Efficient Scheduling for Data-Intensive Applications with Deadline Constraints on Data Grids Cong Liu and Xiao Qin Auburn University.
Eneryg Efficiency for MapReduce Workloads: An Indepth Study Boliang Feng Renmin University of China Dec 19.
1 PARAID: A Gear-Shifting Power-Aware RAID Charles Weddle, Mathew Oldham, Jin Qian, An-I Andy Wang – Florida St. University Peter Reiher – University of.
PARAID: A Gear-Shifting Power-Aware RAID Charles Weddle, Mathew Oldham, Jin Qian, An-I Andy Wang – Florida St. University Peter Reiher – University of.
Energy Management in Virtualized Environments Gaurav Dhiman, Giacomo Marchetti, Raid Ayoub, Tajana Simunic Rosing (CSE-UCSD) Inside Xen Hypervisor Online.
NAS 2011 Liang Kai,Xiaofang Zhang, Xiao Zhang Northwestern Polytechnical University Research on Energy Consumption of General Network Storage.
An Energy-efficient Task Scheduler for Multi-core Platforms with per-core DVFS Based on Task Characteristics Ching-Chi Lin Institute of Information Science,
Improving Disk Throughput in Data-Intensive Servers Enrique V. Carrera and Ricardo Bianchini Department of Computer Science Rutgers University.
1 PARAID: A Gear-Shifting Power-Aware RAID Charles Weddle, Mathew Oldham, Jin Qian, An-I Andy Wang – Florida St. University Peter Reiher – University of.
Performance and Energy Efficiency Evaluation of Big Data Systems Presented by Yingjie Shi Institute of Computing Technology, CAS
Overview and Comparison of Software Tools for Power Management in Data Centers Msc. Enida Sheme Acad. Neki Frasheri Polytechnic University of Tirana Albania.
PRESENTATION TITLE GOES HERE Emerald NAS Extensions Chuck Paridon Performance Architect H-P Enterprise Data Contributed by Nick Principe – EMC, Demartek.
Department of Computer Sciences, University of Wisconsin Madison DADA – Dynamic Allocation of Disk Area Jayaram Bobba Vivek Shrivastava.
University of Padova Department of Information Engineering On the Optimal Topology of Bluetooth Piconets: Roles Swapping Algorithms Daniele Miorandi &
Multi-Task Assignment for CrowdSensing in Mobile Social Network Mingjun Xiao ∗, Jie Wu†, Liusheng Huang ∗, Yunsheng Wang‡, and Cong Liu§
1 / 21 Providing Differentiated Services from an Internet Server Xiangping Chen and Prasant Mohapatra Dept. of Computer Science and Engineering Michigan.
LIOProf: Exposing Lustre File System Behavior for I/O Middleware
Outline System diagram Goal Schedule System Diagram RamDisk Flash Memory HardDisk Interface (Virtualization) Input (Configurations, Trace ) Input.
1 PARAID: A Gear-Shifting Power-Aware RAID Charles Weddle, Mathew Oldham, Jin Qian, An-I Andy Wang – Florida St. University Peter Reiher – University of.
PARAID: A Gear-Shifting Power-Aware RAID
Green Software Engineering Prof
DADA – Dynamic Allocation of Disk Area
Experiment Evaluation
PARAID: A Gear-Shifting Power-Aware RAID
Unistore: Project Updates
Background Energy efficiency is a critical issue for mobile device.
reFresh SSDs: Enabling High Endurance, Low Cost Flash in Datacenters
Qingbo Zhu, Asim Shankar and Yuanyuan Zhou
1.In your own words, explain the term Green IT.
Energy-Efficient Storage Systems
Monitoring Physical Activities Using Smartphones
Presentation transcript:

MSN 数学媒体与信息存储 1/27 Zhuo Liu, Fei Wu, Xiao Qin, Changsheng Xie, Jian Zhou, and Jianzong Wang TRACER: A Trace Replay Tool to Evaluate Energy-Efficiency of Mass Storage Systems WNLO, Huazhong University of Science and Technology; Computer Science Department, Auburn University

MSN 数学媒体与信息存储 2/27 Outline  I. Motivation  Why do we need TRACER?  II. Architecture  What does TRACER consist of?  How does TRACER work and look like?  III. Trace-replay control scheme  How does TRACER control load intensity?  IV. Measurement  How well does TRACER work?  V. Conclusion and future work

MSN 数学媒体与信息存储 3/27 I Motivation  New energy conservation techniques in storage systems constantly spring up:  such as MAID, DRPM, PDC…  Lack of systematic and uniform way to evaluate them:  present benchmarks and standards are most for CPU-intensive applications

MSN 数学媒体与信息存储 4/27 Current power-aware techniques

MSN 数学媒体与信息存储 5/27 Energy-efficiency Standards  SPEC (CPU-intensive)  Metric: Java_ops/Watt  SUN swap (CPU-intensive)  Metric: Performance/(Space*Watt)  Joule Sort (CPU-intensive)  Metric: Sort_ops/Joule  Energy Star  SNIA green  Classification of storage devices  Standards mainly for idle-mode tests

MSN 数学媒体与信息存储 6/27 Power increases with load intensity SNIA-Green

MSN 数学媒体与信息存储 7/27 What should TRACER do? Test the power consumptions Produce different modes of IO load Regulate IO load intensity: 10%-100% Metrics: to evaluate energy-efficiency TRACER

MSN 数学媒体与信息存储 8/27 II. Architecture of TRACER  TRACER consists of four parts: Evaluation host Workload generator Power analyzer Storage systems under test

MSN 数学媒体与信息存储 9/27 What does TRACER consist of?

MSN 数学媒体与信息存储 10/27 How is TRACER implemented?

MSN 数学媒体与信息存储 11/27 GUI of TRACER

MSN 数学媒体与信息存储 12/27 III. Trace-replay control scheme The structure of a blocktrace file

MSN 数学媒体与信息存储 13/27 Load-control algorithm for trace replay

MSN 数学媒体与信息存储 14/27 IV. Measurement: environment

MSN 数学媒体与信息存储 15/27 Measurement: hardware connects

MSN 数学媒体与信息存储 16/27 Measurement : traces  Three types of traces:  125 traces we connected using IOmeter Request size: 512B, 4KB, 16KB, 64KB, 1MB Random/sequential%: 0%,25%, 50%, 75%,100% Read/write%: 0%, 25%,50%,75%, 100%  HP lab: cello 96 and cello 99  The web server trace (FAST’09-BORG)

MSN 数学媒体与信息存储 17/27 Measurement : evaluation metrics  IO Throughput/Power Consumption  IOPS/Watt  MBPS/Kilowatt

MSN 数学媒体与信息存储 18/27 V. Measurement: results  1. Accuracy of load control for 125 traces  Accuracy % =Measured intensity% / configured%  2. How Energy-efficiency is influenced  By load intensity  By random%  By read%  3. Accuracy for Real traces  HP lab cello99 cello96, web server traces

MSN 数学媒体与信息存储 19/27 Accuracy of load control

MSN 数学媒体与信息存储 20/27 E-E influenced by load%

MSN 数学媒体与信息存储 21/27 E-E influenced by random%

MSN 数学媒体与信息存储 22/27 E-E influenced by read%

MSN 数学媒体与信息存储 23/27 Load control for real trace

MSN 数学媒体与信息存储 24/27 Accuracy of load control for real trace

MSN 数学媒体与信息存储 25/27 Conclusion and Future Work  1 TRACER is accurate, efficient and useful.  2 Storage system is more energy-efficient under higher load intensity, under lower random rate.  3 As temperature influences system’s performance and power, it’s necessary to add temperature as part of evaluation metrics.

MSN 数学媒体与信息存储 26/27 Add Temperature metrics Temp sensor

MSN 数学媒体与信息存储 27/27 Any question?