Abstract

With the rapid growth in demand for distributed computing, data centers are a critical physical component of the “cloud.” Recent studies show that the energy consumption of data centers for both cooling and computing keeps increasing, and the growth in server power densities makes it ever more challenging to keep the servers below their maximum operating temperature. This paper presents a new dynamic load-balancing approach based on individual server central processing unit (CPU) temperatures. In this approach, a load balancer assigns a task in real time to a server based on the objective to keep the CPU temperatures below a maximum value. Experimental studies are conducted in a single rack based on production workload traces of Google clusters. This study also compares the performance of this method with two other load balancing approaches, Round Robin, and a CPU utilization-based method in terms of temperature distributions, local fan rotation speeds, system loads, and server processing times. Furthermore, we investigate how the effect of the proposed load balancing changes with different assumed applications run on servers. The results indicate that this new method can more effectively reduce both server CPU temperatures and local fan rotation speed in a rack especially for the most of web applications.

References

References
1.
Cisco,
2016
, “
Cisco Global Cloud Index: Forecast and Methodology, 2015-2020
,” p. 5.
2.
Data Center Knowledge, 2018, “
Achieving Data Center Energy Efficiency
,” Data Center Knowledge, accessed Oct. 30, 2018, https://www.datacenterknowledge.com/industry-perspectives/achieving-data-center-energy-efficiency
3.
Balaras
,
C. A.
,
Lelekis
,
J.
,
Dascalaki
,
E. G.
, and
Atsidaftis
,
D.
,
2017
, “
High Performance Data Centers and Energy Efficiency Potential in Greece
,”
Procedia Environ. Sci.
,
38
, pp.
107
114
.10.1016/j.proenv.2017.03.091
4.
Alpha and Omega Semi-conductor,
2010
, Power Semiconductor Reliability Handbook,
Alpha and Omega Semiconductor
,
Sunnyvale, CA
, pp.
1
23
.
5.
Wang
,
X.
,
Wang
,
X.
,
Xing
,
G.
,
Chen
,
J.
,
Lin
,
C.
,
Chen
,
Y.
, and
Member
,
S.
,
2013
, “
Intelligent Sensor Placement for Hot Server Detection in Data Centers
,”
IEEE Trans. Parallel Distrib. Syst.
,
24
(
8
), pp.
1577
1588
.10.1109/TPDS.2012.254
6.
Gao
,
J.
, and
Jamidar
,
R.
,
2014
, “
Machine Learning Applications for Data Center Optimization
,”
Google White Paper
, pp.
1
13
.
7.
Sarood
,
O.
,
Miller
,
P.
,
Totoni
,
E.
, and
Kal
,
L. V.
,
2012
, “
Cool' Load Balancing for High Performance Computing Data Centers
,”
IEEE Trans. Comput.
,
61
(
12
), pp.
1752
1764
.10.1109/TC.2012.143
8.
Athavale
,
J. D.
,
Joshi
,
Y.
, and
Yoda
,
M.
,
2017
, “
Experimentally Validated Computational Fluid Dynamics Model for Data Center With Active Tiles
,”
ASME J. Electron. Packag.
,
140
, pp.
1
13
.10.1115/1.4039025
9.
Sundaralingam
,
V.
,
Joshi
,
Y.
, and
Arghode
,
V.
,
2012
, “
Controller to Regulate Maximum Server Cpu Temperatures in a Rack by Varying CRAC Supply Air Temperatures
,”
ASME
Paper No. IMECE2012-87600.10.1115/IMECE2012-87600
10.
Ghosh
,
R.
,
Sundaralingam
,
V.
, and
Joshi
,
Y.
, “
Effect of Rack Server Population on Temperatures in Data Centers
,”
13th InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems
,
San Diego, CA
,
May 30–June 1
, pp. 30–37.
11.
Wang
,
L.
,
Khan
,
S. U.
, and
Dayal
,
J.
,
2012
, “
Thermal Aware Workload Placement With Task-Temperature Profiles in a Data Center
,”
J. Supercomput.
,
61
(
3
), pp.
780
803
.10.1007/s11227-011-0635-z
12.
Tang
,
Q.
,
Gupta
,
S. K. S.
, and
Varsamopoulos
,
G.
,
2007
, “
Thermal-Aware Task Scheduling for Data Centers Through Minimizing Heat Recirculation
,”
IEEE International Conference on Cluster Computing
,
Austin, TX
,
Sept. 17–20
, pp.
129
138
.
13.
Zhao
,
X.
,
Peng
,
T.
,
Qin
,
X.
,
Hu
,
Q.
,
Ding
,
L.
, and
Fang
,
Z.
,
2016
, “
Feedback Control Scheduling in Energy-Efficient and Thermal-Aware Data Centers
,”
IEEE Trans. Syst., Man, Cybern.: Syst.
,
46
(
1
), pp.
48
60
.10.1109/TSMC.2015.2434797
14.
Primas
,
B.
,
Garraghan
,
P.
,
McKee
,
D. W.
,
Summers
,
J.
, and
Xu
,
J.
, “
A Framework and Task Allocation Analysis for Infrastructure Independent Energy-Efficient Scheduling in Cloud Data Centers
,”
IEEE Ninth International Conference on Cloud Computing Technology and Science
,
Hong Kong, China
,
Dec. 11–14
, pp.
178
185
.
15.
Song
,
M.
,
Zhu
,
H.
,
Fang
,
Q.
, and
Wang
,
J.
,
2016
, “
Thermal-Aware Load Balancing in a Server Rack
,”
IEEE Conference on Control Applications
,
Buenos Aires, Argentina
,
Sept. 19–22
, pp.
462
467
.
16.
Moore
,
J.
,
Chase
,
J.
,
Ranganathan
,
P.
, and
Sharma
,
R.
,
2005
, “
Making Scheduling ‘Cool’: Temperature-Aware Workload Placement in Data Centers
,”
Annual Conference on USENIX Annual Technical Conference
,
Anahim, CA
,
Apr. 10–15
, pp.
61
74
.
17.
Nakajo
,
Y.
,
Athavale
,
J.
,
Yoda
,
M.
,
Joshi
,
Y.
, and
Nishi
,
H.
,
2018
, “
Improving Energy Efficiency in Data Centers by Controlling Task
,”
ASME
Paper No. IPACK2018-8305.10.1115/IPACK2018-8305
18.
Nakajo
,
Y.
, and
Nishi
,
H.
,
2017
, “
Temperature-Based Request Distribution for Effective CRAC and Equipment Life-Cycle Extension
,”
ASME
Paper No. IPACK2017-74341.10.1115/IPACK2017-74341
19.
Hewlett Packard Enterprise Support Center,
2018
, “
HPE ProLiant SL390 s G7 Server—Overview
,” Hewlett Packard Enterprise Support Center, accessed Feb. 18, 2018, https://support.hpe.com/hpsc/doc/public/display?docId=emr_na-c03287404
20.
Intel® Xeon®,
2018
, “
Intel® Xeon® Processors
,” accessed Feb. 18, 2018, https://www.intel.com/content/www/us/en/products/processors/xeon.html
21.
Linux,
2018
, “
Ipmitool(1)—Linux Man Page
,” accessed Oct. 31, 2018, https://linux.die.net/man/1/ipmitool
22.
Kameda
,
H.
,
Fathy
,
EI-Z. S.
,
Ryu
,
I.
, and
Li
,
J.
,
2002
, “
A Performance Comparison of Dynamic vs. Static Load Balancing Policies in a Mainframe—Personal Computer Network Model
,” IEEE Conference on Decision and Control, Sydney, Australia, Dec. 12–15, pp.
1415
1420
.
23.
NGINX, 2019, “
What Is NGINX? - NGINX
,” accessed Jan. 25, 2019, https://www.nginx.com/resources/glossary/nginx/
24.
Dave
,
S.
, and
Maheta
,
P.
,
2014
, “
Utilizing Round Robin Concept for Load Balancing Algorithm at Virtual Machine Level in Cloud Environment
,”
Int. J. Comput. Appl.
,
94
(
4
), pp.
23
29
.10.5120/16332-5612
25.
Resonate
,
2013
, “
Resonate Central Dispatch
,” White Paper, p. 15.
26.
Aggarwal
,
M.
, and
Aggarwal
,
S.
,
2010
, “
Dynamic Load Balancing Based on CPU Utilization and Data Locality in Distributed Database Using Priority Policy Monika
,”
Second International Conference on Software Technology and Engineering (ICSTE)
,
San Juan, PR
,
Oct. 3–5
, pp.
1134
1141
.
27.
Brown
,
R.
,
Masanet
,
E.
,
Nordman
,
B.
,
Shehabi
,
A.
,
Stanley
,
J.
,
Sartor
,
D.
, and
Chan
,
P.
,
2007
, “
Report to Congress on Server and Data Center Energy Efficiency: Public Law 109–431
,” Ernest Orlando Lawrence Berkeley National Laboratory,
Berkeley, CA
.
28.
Hellerstein
,
J. L.
,
2010
, “
Research Blog: Google Cluster Data
,” Google Research Blog, accessed Jan. 17, 2018, https://research.googleblog.com/2010/01/google-cluster-data.html
29.
Chen
,
Y.
, and
Katz
,
R. H.
,
2010
, “
Analysis and Lessons From a Publicly Available Google Cluster Trace
,” University of California at Berkeley, Berkeley, CA, Report No. UCB/EECS-2010-95.
30.
Olshefski
,
D.
, and
Nieh
,
J.
,
2006
, “
Understanding the Management of Client Perceived Response Time
,”
Joint International Conference on Measurement and Modeling of Computer Systems
,
Saint Malo, France
June 26–30
, pp.
240
251
.
31.
Psutil Documentation,
2018
, “
Psutil Documentation—Psutil 5.4.8 Documentation
,” accessed Nov. 2, 2018, https://psutil.readthedocs.io/en/latest/
32.
Linux,
2018
, “
Uptime(1)—Linux Man Page
,” accessed Nov. 2, 2018, https://linux.die.net/man/1/uptime
33.
Linux,
2018
, “
Linux Uptime Command Help and Examples
,” accessed Nov. 2, 2018, https://www.computerhope.com/unix/uptime.htm
You do not currently have access to this content.