0
Research Papers

Impact of Server Thermal Design on the Cooling Efficiency: Chassis Design

[+] Author and Article Information
Sadegh Khalili, Bahgat Sammakia

Department of Mechanical Engineering,
Binghamton University-SUNY,
Binghamton, NY 13902

Husam Alissa

Microsoft,
Redmond, WA 98052

Kourosh Nemati

Future Facilities, Inc.,
San Jose, CA 95110

Mark Seymour

Future Facilities, Ltd.,
London SE1 7HX, UK

Robert Curtis, David Moss

Dell,
Austin, TX 78682

1Corresponding author.

Contributed by the Electronic and Photonic Packaging Division of ASME for publication in the JOURNAL OF ELECTRONIC PACKAGING. Manuscript received September 21, 2018; final manuscript received January 29, 2019; published online April 10, 2019. Assoc. Editor: Wei Li.

J. Electron. Packag 141(3), 031004 (Apr 10, 2019) (11 pages) Paper No: EP-18-1075; doi: 10.1115/1.4042983 History: Received September 21, 2018; Revised January 29, 2019

There are various designs for segregating hot and cold air in data centers such as cold aisle containment (CAC), hot aisle containment (HAC), and chimney exhaust rack. These containment systems have different characteristics and impose various conditions on the information technology equipment (ITE). One common issue in HAC systems is a pressure build-up inside the HAC (known as backpressure). Backpressure also can be present in CAC systems in case of airflow imbalances. Hot air recirculation, limited cooling airflow rate in servers, and reversed flow through ITE with weaker fan systems (e.g., network switches) are some known consequences of backpressure. Currently, there is a lack of experimental data on the interdependency between overall performance of ITE and its internal design when backpressure is imposed on ITE. In this paper, three commercial 2-rack unit (RU) servers with different internal designs from various generations and performance levels are tested and analyzed under various environmental conditions. Smoke tests and thermal imaging are implemented to study the airflow patterns inside the tested equipment. In addition, the impact of hot air leakage into the servers through chassis perforations on the fan speed and the power consumption of the servers are studied. Furthermore, the cause of the discrepancy between measured inlet temperatures by the intelligent platform management interface (IPMI) and external sensors is investigated. It is found that arrangement of fans, segregation of space upstream and downstream of fans, leakage paths, the location of baseboard management controller (BMC) sensors, and the presence of backpressure can have a significant impact on ITE power and cooling efficiency.

Copyright © 2019 by ASME
Your Session has timed out. Please sign back in to continue.

References

Shehabi, A. , Smith, S. J. , Sartor, D. A. , Brown, R. E. , Herrlin, M. , Koomey, J. G. , Masanet, E. R. , Horner, N. , Azevedo, I. L. , and Lintner, W. , 2016, “ United States Data Center Energy Usage Report,” Lawrence Berkeley National Laboratory, Berkeley, CA, Report No. LBNL-1005775. https://eta.lbl.gov/publications/united-states-data-center-energy
Zhou, R. , Wang, Z. , Bash, C. E. , and McReynolds, A. , 2011, “ Modeling and Control for Cooling Management of Data Centers With Hot Aisle Containment,” ASME Paper No. IMECE2011-62506.
Ponemon Institute, 2016, “ 2016 Cost of Data Center Outages,” Ponemon Institute LLC, Traverse City, MI.
Tradat, M. , Khalili, S. , Sammakia, B. G. , Ibrahim, M. , Peddle, T. , Calder, A. R. , Dawson, B. , Seymour, M. , Nemati, K. , and Alissa, H. , 2017, “ Comparison and Evaluation of Different Monitoring Methods in a Data Center Environment,” ASME Paper No. IPACK2017-74105.
Sundaralingam, V. , Arghode, V. K. , Joshi, Y. , and Phelps, W. , 2014, “ Experimental Characterization of Various Cold Aisle Containment Configurations for Data Centers,” ASME J. Electron. Packag., 137(1), p. 11007. [CrossRef]
Makwana, Y. U. , Calder, A. R. , and Shrivastava, S. K. , 2014, “ Benefits of Properly Sealing a Cold Aisle Containment System,” 14th Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems (ITherm), Orlando, FL, May 27–30, pp. 793–797.
Khalili, S. , Tradat, M. , Nemati, K. , Seymour, M. , and Sammakia, B. , 2018, “ Impact of Tile Design on the Thermal Performance of Open and Enclosed Aisles,” ASME J. Electron. Packag., 140(1), p. 010907. [CrossRef]
Nemati, K. , Alissa, H. A. , Murray, B. T. , and Sammakia, B. , 2016, “ Steady-State and Transient Comparison of Cold and Hot Aisle Containment and Chimney,” 15th IEEE Intersociety Conference On Thermal and Thermomechanical Phenomena in Electronic Systems (ITherm), Las Vegas, NV, May 31–June 3, pp. 1435–1443.
Khalili, S. , Alissa, H. , Desu, A. , Sammakia, B. , and Ghose, K. , 2018, “ An Experimental Analysis of Hot Aisle Containment Systems,” 17th Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems (ITherm 2018), San Diego, CA, May 29–June 1, pp. 748–760.
Niemann, J. , Brown, K. , and Avelar, V. , 2011, “ Impact of Hot and Cold Aisle Containment on Data Center Temperature and Efficiency,” Schneider Electric's Data Center Science Center, White Paper No. 135. https://it-resource.schneider-electric.com/white-papers/wp-135-impact-of-hot-and-cold-aisle-containment-on-data-center-temperature-and-efficiency-5
Alissa, H. A. , Nemati, K. , Sammakia, B. G. , Seymour, M. J. , Tipton, R. , Mendo, D. , Demetriou, D. W. , Schneebeli, K. , Tipton, R. , Mendo, D. , Demetriou, D. W. , and Schneebeli, K. , 2016, “ Chip to Chiller Experimental Cooling Failure Analysis of Data Centers: The Interaction Between IT and Facility,” IEEE Trans. Compon., Packag. Manuf. Technol., 6(9), pp. 1361–1378. [CrossRef]
Tradat, M. I. , Alissa, H. A. , Nemati, K. , Khalili, S. , Sammakia, B. G. , Seymour, M. J. , and Tipton, R. , 2017, “ Impact of Elevated Temperature on Data Center Operation Based on Internal and External IT Instrumentation,” 33rd Thermal Measurement, Modeling & Management Symposium (SEMI-THERM), San Jose, CA, Mar. 13–17, pp. 108–114.
Texas Instruments, 2015, “ TMP75 Datasheet,” Texas Instruments, Dallas, TX, accessed Jan. 2018, http://www.ti.com/lit/ds/symlink/tmp75.pdf
Great Internet Mersenne Prime Search, 2015, “ MPrime (Prime95),” Mersenne Research, Inc., accessed Jan. 2018, https://www.mersenne.org/download/
Alissa, H. A. , Nemati, K. , Sammakia, B. , Seymour, M. , Schneebeli, K. , and Schmidt, R. , 2015, “ Experimental and Numerical Characterization of a Raised Floor Data Center Using Rapid Operational Flow Curves Model,” ASME Paper No. IPACK2015-48234.
Nemati, K. , Alissa, H. A. , Murray, B. T. , Sammakia, B. G. , and Seymour, M. , 2015, “ Experimentally Validated Numerical Model of a Fully-Enclosed Hybrid Cooled Server Cabinet,” ASME Paper No. IPACK2015-48244.

Figures

Grahic Jump Location
Fig. 1

Internal view of servers with the top cover removed: (a) server 1, (b) server 2, and (c) server 3

Grahic Jump Location
Fig. 2

Chimney exhaust cabinet, wind tunnel, and instrumentations: (a) chimney ductwork and wind tunnel, (b) location of pressure probes in HAC with the rear door open, (c) location of servers in the middle of the cabinet, and (d) location of discrete temperature sensors in the cold aisle

Grahic Jump Location
Fig. 3

Smoke tests demonstrate the impact of backpressure on the extent of internal recirculation: (a) free delivery point (no backpressure), (b) backpressure = 10 Pa (0.04 in wc), and (c) backpressure = 25 Pa (0.1 in wc)

Grahic Jump Location
Fig. 4

Variation of IPMI IAT, discrete IAT, CPU temperatures, and averaged fan speed with backpressure

Grahic Jump Location
Fig. 5

Internal recirculation can expand to the cold aisle

Grahic Jump Location
Fig. 6

Air enters the chassis through perforations on the top of server 2

Grahic Jump Location
Fig. 7

Schematic of the test bench

Grahic Jump Location
Fig. 8

Impact of Thz on the performance of server 2

Grahic Jump Location
Fig. 9

Flow field inside server 2

Grahic Jump Location
Fig. 10

Active flow curve and leakage ratio for server 2

Grahic Jump Location
Fig. 11

Internal recirculation in server 3

Grahic Jump Location
Fig. 12

Impact of Thz on the performance of server 3

Grahic Jump Location
Fig. 13

Results for server 3: (a) active flow curves and (b) improved airflow at the front intake

Grahic Jump Location
Fig. 14

Experimental results of scenario 1: (a) pressure inside hot and cold aisles and (b) variation of averaged fans speed

Grahic Jump Location
Fig. 15

(a) Inlet air temperature and (b) temperature of CPUs for the selected servers—scenario 1

Grahic Jump Location
Fig. 16

Thermography from the face of the cabinet at the end of scenario 1: (a) order of servers and (b) thermography

Grahic Jump Location
Fig. 17

Openings on the side of chassis—server 1

Grahic Jump Location
Fig. 18

Location and shape of gaskets for servers 2 and 3—scenario 2

Grahic Jump Location
Fig. 19

Experimental results for scenario 2: (a) pressure inside hot and cold aisles and (b) variation of averaged fans speed

Grahic Jump Location
Fig. 20

Inlet air temperature data for the selected servers—scenario 2

Tables

Errata

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In