Energy Efficient Data Storage Systems
57
Energy Efficient Data Storage Systems Xiao Qin Department of Computer Science and Software Engineering Auburn University http://www.eng.auburn.edu/~xqin [email protected]
-
Upload
xiao-qin -
Category
Technology
-
view
1.165 -
download
5
description
With the rapid growth of the production and storage of large scale data sets it is important to investigate methods to drive the cost of storage systems down. We are currently in the midst of an information explosion and large scale storage centers are increasingly used to help store generated data. There are several methods to bring the cost of large scale storage centers down and we investigate a technique that focuses on transitioning storage disks into lower power states. This talk introduces a model of disk systems that leverages disk access patterns to produce energy saving opportunities for parallel disk systems. We also focus on the implementation of an energy-efficient storage cluster, where a couple of energy-saving techniques are incorporated. Our modeling and simulation results indicated that large data sizes and knowledge about the disk access pattern are valuable for storage system energy savings techniques. Storage servers that support applications that stream media is one key area that would benefit from our strategies.
Transcript of Energy Efficient Data Storage Systems
Energy Efficient Data Storage
Systems
Xiao Qin
Department of Computer Science and Software Engineering
Auburn Universityhttp://www.eng.auburn.edu/~xqin
2
Investigators
Ziliang Zong Adam Manzanares
Xiaojun Ruan Shu Yin
3
Data-Intensive Applications
Stream Multimedia Bioinformatic
3D Graphic Weather Forecast
4
Cluster Computing in Data Centers
Data Centers
Computing and Storage Nodes in a Cluster
Client Network switch
Computing Nodes
Storage Node (or Storage Area Network)Internet
Head Node
6
Clusters in Our Lab at Auburn
7
Energy Consumption was Growing
EPA Report to Congress on Server and Data Center Energy Efficiency, 2007
2020 Projections
Network:Increases by 300%
Clients:number – increases by 800%Power – increases by 300%
Data Center: increases by 200%
Data Centers consume 110 Billion kWh per Year
Storage37%
Server40%
Network 23%
Dell’s Texas Data Center
Energy Efficiency of Data Centers
Average cost: ¢9.46 per kWh
Storage 37%
Other; 63%
Storage system may cost 2.8 Billion Dollars!
Build Energy-Efficient Data Centers
Energy Conservation Techniques
Energy Efficient Devices
Multiple Design Goals
Performance Energy Efficiency
Reliability
Security
High-Performance Computing Platforms
DVS – Dynamic Voltage Scaling
14
Trade performance for energy efficiency
Energy-Aware Scheduling for Clusters
Z.-L. Zong, X.-J. Ruan, A. Manzanares, and X. Qin, “EAD and PEBD: Two Energy-Aware Duplication Scheduling Algorithms for Parallel Tasks on Homogeneous Clusters,” IEEE Transactions on Computers, vol. 60, no. 3, pp. 360- 374, March 2011.
Parallel Applications
1
2 3 4
5 6 7
8 9
10
3
3
4
2
1020
75
8
3 3
3
33
42
1 1010
20
57
1
Entry Task
Exit Task
Energy-Aware Scheduling: Motivational Example
Motivational Example (cont.)
The EAD and PEBD Algorithms
19
Generate the DAG of given task sets
Find all the critical paths in DAG
Generate scheduling queue based on the level (ascending)
select the task (has not been scheduled yet) with the lowest level as starting task
For each task which is in the same critical path with starting task, check
if it is already scheduled
allocate it to the same processor with the tasks in the
same critical pathYes
No
mee
t ent
ry ta
sk
Save time if duplicate this task?
Yes
Calculate energy increase
and time decrease
Ratio= energy increase/ time decrease
Ratio<=Threshold?No
Yes
Duplicate this task and select the next task in the same
critical path
Calculate energy increase
more_energy<=Threshold?
Duplicate this task and select the next task in the same
critical path
Yes
No
No
PEBD EAD
Energy Dissipation in Processors
20
http://www.xbitlabs.com
Parallel Scientific Applications
21
T1
T2 T3
T4 T5 T6 T7
T8 T9 T10 T11
T12 T13 T14 T15
T1
T2 T3 T4 T5 T6
T7
T8 T9 T10 T11
T12
T13 T14 T15
T16
T17 T18
Fast Fourier Transform Gaussian Elimination
Large-Scale Parallel Applications
04/08/2023 22
Robot Control Sparse Matrix Solver
http://www.kasahara.elec.waseda.ac.jp/schedule/
Impact of CPU Power Dissipation
23
EAD PEBD TDS MCP0
5000
10000
15000
20000
25000
30000
35000
40000
Total Energy Consumption
Athlon 4600+ 85W
Athlon 4600+ 65W
Athlon 3800+ 35W
Intel Core2 Duo E6300
Ener
gy (J
oul)
Energy consumption for different processors (Gaussian, CCR=0.4)
EAD PEBD TDS MCP0
5000
10000
15000
20000
25000
30000
35000
40000
Total Energy Consumption
Athlon 4600+ 85W
Athlon 4600+ 65W
Athlon 3800+ 35W
Intel Core2 Duo E6300
Ener
gy (J
oul)
Energy consumption for different processors (FFT, CCR=0.4)
19.4% 3.7%
CPU Type Power (busy) Power (idle) Gap
104w 15w 89w
75w 14w 61w
47w 11w 36w
44w 26w 18w
Observation: CPUs with large gap between CPU_busy and CPU_idle can obtain greater energy savings
Performance
24
Impact to Schedule Length:
0.1 0.5 1 5 100
20
40
60
80
100
120
140
160
Schedule Length
TDS EAD
PEBD MCPTim
e Un
it (S
)
0.1 0.5 1 5 100
20
40
60
80
100
120
140
160
180
200
Schedule Length
TDS
EAD
PEBD
MCP
Tim
e Un
it (S
)
Schedule length of Gaussian Elimination Schedule length of Sparse Matrix Solver
Application EAD Performance Degradation (: TDS)
PEBD Performance Degradation (: TDS)
Gaussian Elimination 5.7% 2.2%
Sparse Matrix Solver 2.92% 2.02%
Observation: it is worth trading a marginal degradation in schedule length for a significant energy savings for cluster systems.
Energy Consumption of Disks
26
Active State: high energy consumption
Power States of Disks
Active StandbyState transition
penalty
Standby State: low energy consumption
27
A10000RPM Hard Drive may take 10.9 seconds to wake up!
A Hard Disk Drive
Parallel Disks
Performance Energy Efficiency
Put It All Together: Buffer Disk Architecture
RAM BufferRAM Buffer
m buffer disksm buffer disks n data disksn data disks
Buffer Disk ControllerBuffer Disk Controller
Data Partitioning Data Partitioning
Security Model Security Model
Load BalancingLoad Balancing
Power ManagementPower Management
PrefetchingPrefetching
Disk RequestsDisk Requests
Energy-Related Reliability Model Energy-Related Reliability Model
IBM Ultrastar 36Z15Transfer Rate 55 MB/s Spin Down Time: TD 1.5 s
Active Power: PA 13.5 W Spin Up Time: TU 10.9 s
Idle Power: PI 10.2 W Spin Down Energy: ED 13 J
Standby Power: PA 2.5 W Spin Up Energy: EU 135 J
Break-Even Time: TBE 15.2 S
Prefetching
Disk 1
Disk 2
Disk 3
Buffer Disk
Energy Saving Principles Energy Saving Principle One
◦Increase the length and number of idle periods larger than the disk break-even time TBE
Energy Saving Principle Two◦Reduce the number of power-state
transitions
A. Manzanares, X. Qin, X.-J. Ruan, and S. Yin, “PRE-BUD: Prefetching for Energy-Efficient Parallel I/O Systems with Buffer Disks,” ACM Transactions on Storage, vol. 7, no. 1, Article 3 June 2011.
Energy Savings Hit Rate 85%
04/08/2023
33
State Transitions
buffer disk
buffer disk
buffer disk
Requests Queue
Heat-Based Dynamic Data Caching
35
buffer disk
buffer disk
buffer disk
Requests Queue
36
Heat-Based Dynamic Data Caching
Energy Consumption Results
Large Reads: average 84.4% improvement (64MB)
Small Reads: average 78.77% improvement (64KB)
3704/08/2023
Energy consumption for large reads
Energy consumption for small reads
Load Balancing Comparison
3804/08/2023
Load balancing comparison for three mapping strategies
Energy Efficient Virtual File System
EEVFS Process Flow
Energy Savings
Improving Performance of EEVFSParallel Striping Groups
Disk 1
Disk 2
Group 1
Buffer
DiskStorage Node 1
Disk 3
Disk 4
Buffer
DiskStorage Node 2
Disk 5
Disk 6
Group 2
Buffer
DiskStorage Node 3
Disk 7
Disk 8
Buffer
DiskStorage Node 4
File 1
File 2
File 3
File 4
Striping Within a Group
Disk 1 Disk 2
Group 1
Buffer Disk
Storage Node 1
Disk 3 Disk 4Buffer Disk
Storage Node 2
1 3 5 7 9 4 6 8
4 6 81 3 5 7 9
10
10
1
2
1
2
File 1
File 22 2
Measured Results
04/08/2023
A Parallel Disk System with a Write Buffer Disk
Under High Workload Conditions
Data Disks can serve requests without buffer disks when workload is high
Wakeup Data Disks
Buffer Disk
Requests Queue
47
Energy SavingsLow Workload, UltraStar
49
Energy Conservation Techniques
Software-Directed Power ManagementDynamic Power ManagementRedundancy TechniqueMulti- speed Setting
49
How Reliable Are They?
50
Tradeoff between Energy Efficiency and Reliability
Example: Disk Spin Up and Down
MINT(MATHEMATICAL RELIABILITY MODELS FOR ENERGY-EFFICIENT PARALLEL DISK SYSTEMS)
Energy Conservation Techniques
Single Disk Reliability Model
System-Level Reliability Model
S. Yin et al. “Reliability Analysis for an Energy-Aware RAID System,” Proc. the 30th IEEE International Performance Computing and Communications Conference (IPCCC), Nov. 2011.
52
Frequency Utilization
Disk Age Temperature
Reliability of Single Disk
Single Disk Reliability Model
MINT(Single Disk)
MINT(MATHEMATICAL RELIABILITY MODELS FOR ENERGY-EFFICIENT PARALLEL DISK SYSTEMS)
Access Pattern
Reliability of A Parallel Disk System
Single Disk Reliability Model
Energy Conservation Techniques
System Level Reliability Model
54
Preliminary ResultComparison Between PDC and MAID
AFR Comparison of PDC and MAIDAccess Rate(*104) Impacts on AFR (T=35°C)
Summary• Energy-Aware Scheduling
• BUD - Buffer Disk Architecture
• Energy-Efficient File Systems
• Reliability Models for Energy-Efficient Storage Systems
Download the presentation slideshttp://www.slideshare.net/xqin74
Google: slideshare Xiao Qin
Questions
