Power Efficiency Comparison of the
Dell™ PowerEdge™ M915 and
HP ProLiant BL680c G7 Blade Solutions
A Dell Technical White Paper
Brian Bassett and Chris Christian
Solutions Performance Analysis
Dell | Enterprise Solutions Group
Power Efficiency Comparison of the Dell PowerEdge M915 and HP ProLiant BL680c G7 Blade Solutions
THIS WHITE PAPER IS FOR INFORMATIONAL PURPOSES ONLY, AND MAY CONTAIN TYPOGRAPHICAL ERRORS AND
TECHNICAL INACCURACIES. THE CONTENT IS PROVIDED AS IS, WITHOUT EXPRESS OR IMPLIED WARRANTIES OF
ANY KIND.
Dell, the DELL logo, and the DELL badge, and PowerEdge are trademarks of Dell Inc. Microsoft, Windows, and
Windows Server are either trademarks or registered trademarks of Microsoft Corporation in the United States
and/or other countries. Intel and Xeon are registered trademarks of Intel Corporation in the U.S. and/or other
countries. SPEC and the benchmark names SPECpower_ssj and SPECjbb are trademarks of the Standard
Performance Evaluation Corporation.
Other trademarks and trade names may be used in this document to refer to either the entities claiming the
marks and names or their products. Dell Inc. disclaims any proprietary interest in trademarks and trade names
other than its own.
August 2011
Revision 1.0
2
Power Efficiency Comparison of the Dell PowerEdge M915 and HP ProLiant BL680c G7 Blade Solutions
3
Power Efficiency Comparison of the Dell PowerEdge M915 and HP ProLiant BL680c G7 Blade Solutions
Figure 9: HP Blade Solution Benchmark Results ............................................................... 25
5
Power Efficiency Comparison of the Dell PowerEdge M915 and HP ProLiant BL680c G7 Blade Solutions
1
2
3
Executive Summary
Introduction
Dell commissioned its Solutions Performance Analysis team to compare the power efficiency of full-chassis
blade solutions using 4-socket blades from Dell and Hewlett-Packard (HP).
In July 2011, the Dell PowerEdge M915 blade server achieved the highest SPECpower_ssj2008 score of any 4socket server on the market1, so eight of these blades and a PowerEdge M1000e enclosure were used as the
PowerEdge solution.
For the ProLiant solution, HP’s similar BL685c G7 could have been chosen for this study. However, the BL680c
G7 is HP’s top-selling 4-socket blade2, so it was chosen to allow examination of HP’s claims of that server’s
unique 4P blade performance and improved power efficiency3. Due to its full-height, double-wide form factor,
only four of these blades can fit in a 10U BladeSystem c7000 blade enclosure.
Using the industry-standard SPECpower_ssj2008 benchmark, the performance, power draw, and
performance/watt of full-chassis configurations of both blade solutions were tested. The blade servers were
compared configured as similarly as possible given their architectural differences, with identical memory and
hard drive selections, and best known CPU choices for highest performance/watt ratio. To ensure the lowest
power draw, both blade chassis were equipped with six of their Platinum-rated power supplies for all tests.
The results showed the Dell solution using 8 PowerEdge M915 costs less than the HP solution consisting of just
4 BL680c G7 blades (the maximum that can fit in the BladeSystem c7000 enclosure). The Dell solution also
consumed less power at idle, provided higher raw performance, and achieved a better performance / watt
ratio. The Dell solution also fits twice as many servers in a 10U blade enclosure.
Key Findings
Performance/Watt
The Dell solution with 8 PowerEdge M915 blades achieved a 92% higher performance / watt ratio
across all load levels than the HP solution using 4 ProLiant BL680c G7 blades.
Performance
The chassis full of 8 PowerEdge M915 blades achieved 87% higher raw performance at 100% utilization
than the chassis full of 4 HP ProLiant BL680c G7 blades.
Power
Despite having 87% greater performance, the Dell solution with 8 PowerEdge M915 blades consumes
only 14% more power at 100% utilization compared to the HP solution with just 4 ProLiant BL680c G7
blades.
Despite having twice as many servers, the Dell blade solution consumes 35% less power at idle than
the HP blade solution.
In the published result, the 8-node M915 achieved 14,793,524 ssj_ops@100% target load and a SPECpower_ssj2008 result of 2,716 overall ssj_ops/Watt.
Benchmark results based on results published at www.spec.org as of July 2011. For the latest SPECpower_ssj2008 benchmark results, visit
http://www.spec.org/power_ssj2008/results/power_ssj2008.html.
According to IDC Q1 2011 Server Tracker, May 22, 2011
Power Efficiency Comparison of the Dell PowerEdge M915 and HP ProLiant BL680c G7 Blade Solutions
Price
Priced as configured, the Dell PowerEdge solution, including 8 M915 blades and the M1000e Blade
Chassis, costs 21% less overall than the HP ProLiant solution which includes 4 BL680c G7 blades and
the BladeSystem C7000 enclosure.
The Dell solution’s lower cost and greater power efficiency lead to a 59% better price / performance /
watt ratio.
Rack Density
The Dell solution provides 8 servers per 10U chassis, compared to the HP solution which provides
only 4 servers per 10U chassis.
Test methodology and detailed results are documented in this paper.
The comparison presented here is based on the respective enterprise-class servers configured as similarly as
possible and currently shipping by Dell and HP. Results based on SPECpower_ssj2008 performance testing by
Dell Labs in June 2011. For the latest SPECpower_ssj2008 benchmark results, visit
http://www.spec.org/power_ssj2008/results/power_ssj2008.html. For latest SPECjbb2005 benchmark results,
visit http://www.spec.org/osg/jbb2005.
7
Power Efficiency Comparison of the Dell PowerEdge M915 and HP ProLiant BL680c G7 Blade Solutions
Methodology
SPECpower_ssj2008 is an industry standard benchmark created by the Standard Performance Evaluation
Corporation (SPEC) to measure a server’s power and performance across multiple utilization levels. Appendix A
details the test methodology used by Dell, Appendices B and C provide detailed configurations for the tests,
and Appendix D provides detailed report data that supports the results in this paper. Full disclosure reports
from the valid SPECpower_ssj2008 runs used in this comparison are attached to this whitepaper for reference.
Configurations
The blade servers in both solutions were configured for their best known SPECpower_ssj2008 configurations,
and were matched as closely as possible given the differences between the architectures. Both solutions used
the maximum number of DIMMs and CPUs the blades could accommodate.
The configuration used is summarized in Table 1.
8
Loading...
+ 17 hidden pages
You need points to download manuals.
1 point = 1 manual.
You can buy points or you can get point for every manual you upload.