Eye on Blades Blog: Trends in Infrastructure
Get HP BladeSystem news, upcoming event information, technology trends, and product information to stay up to date with what is happening in the world of blades.

Aaron Delp Busts Blade Power Myths

We recently learned that Aaron Delp closed down his BladeVault blog and is focusing on creating more useful infomation to share with the greater community by contributing to Scott Lowe's blog.  For those of you that don't know Aaron, he's a senior engineer who is literally on the front lines of the blade and virtualization revolution. No, he doesn't work for HP or IBM.  But he does know just about everything there is to know about us both.  The good, the bad and the ugly.

power_meters

We not only like Aaron because he's a smart guy who shoots it straight, but also because he likes to share what he knows with the community.  Like I said, he knows a lot.


Well, here's what he's up to now.  In a series titled "Blades and Virtualization Aren't Mutually Exclusive", Aaron is sharing a ton of personal research and experience with blades.  In his first two articles in the series, he takes an insider look at the power advantages of blade versus rack servers - looking at both HP and IBM.  I know we told you blades use a lot less power before, but you still think we're full of crap.  Fine.  Take it from Aaron.


 



In his next article, Aaron promised to focus on the expansion abilities of both the IBM and HP blade servers. We'll be reading and linking his thoughts here.

Less Power to You

Following up from my previous post on how to measure server power accurately, I'd like to talk about ways you can figure out for yourself what the real power consumption is for your server blades and applications.


Power Calculators


Each vendor has a power calculator to help with power budgeting.  These can be useful for getting pretty good estimates of power consumption.  But because vendors have different methodologies for these estimates, you cannot fairly compare the outputs of one vendor's power calculator to another's.


Measuring Power


As it turns out, measuring power can be rather tricky.  It is critical to set up the measurement equipment just right, and we have frequently seen this done wrong.  Also be sure to measure all of the power being used.  We have seen some people only put power measurement devices on some of the power cords and assumed (wrongly) that others would be the same.  Fortunately with BladeSystems, getting accurate power measurements is really quite easy: the Onboard Administrator provides real-time and historical power consumption built-in.  We have compared power reported from the Onboard Administrator with externally measured power and found the two to be within 3% of one another.  I'll let other vendors comment on whether you can rely on the reported power to be accurate.


Workloads


Power consumption is strongly dependent on the workload that is run on the server.  Different applications require different amounts of power, and even the same application can vary power widely over time.  Most vendor-reported power measurements use a highly-controlled synthetic benchmark.  This may not be reflective of actual power consumption.  The only way to verify power consumption is to run the applications you plan on using in your production environment.  Some servers may perform better at lighter loads, while others perform better at high load.  Keep in mind also that the same application may vary in load as a function of time, so it is best to measure power over an extended period of time.


Which servers to compare?


When comparing two different vendors for power efficiency, it is best to compare the servers that best fit the performance, manageability, and availability features required for your application and environment.  For instance, if you are running a grid or HPC application, the BL2x220c (2 servers in 1 blade) might be the best fit.  If you are running terminal services, then the BL460c or BL465c with battery backed write cache option would likely be your best fit.  Once you select the best server for your application from each vendor, then you can run the power test.  This might not produce an apples-to-apples comparison, but if you want an orange anyway, then why settle on an apple?


Putting the power in your hands


Hopefully these tips can help.  We know from our own experience that measuring power can be maddeningly difficult.  However, if you follow these tips, then hopefully you can get some meaningful results.  And don't forget, you can read the power consumption straight from the Onboard Administrator, it is accurate and easy. 


Of course measuring power is only half the story - ultimately you want to reduce it.  This is where we provide Thermal Logic technologies and tools to reduce power and help forecast future potential power reductions. 

Games vendors play . . . with power efficiency claims

These days, server power efficiency is top of mind for everyone.  Five years ago, most customers had no idea how much power a server used.  Now, everyone knows - it's a lot.  In some cases, customers are making power consumption the primary criteria for vendor selection. 


So why is it so dang hard to get a straight story on exactly what options are the most power efficient?

secrets

In our experiences with power measurements, we found lots of ways to the results get skewed; whether intentionally or accidentally. We honestly try to avoid them, but here are some of the dirty little secrets a lot of vendors don't want you to know about their power testing results.  Consider these red flags next time someone spends lots of money in the Wall Street Journal to post a big claim with lots of fine print on power savings.


Lab Queens


One easy way for vendors to skew power results is to cherry-pick low power components.  Processors (even those in the same power grade) and memory DIMMs tend to consume significant power and can have wide variances in power consumed from one part to another. 


We call units built by cherry-picking components "Lab Queens".


Generally, these do not represent what a customer might actually be able to purchase.  Here's an example where we tried to avoid this scenario; the systems compared on this competitive power report on our website uses the exact same processors and DIMMs on all units tested, thereby eliminating differences due to component variances.  It would have been easy to create a Lab Queen and bump the results higher, artificially.


Configuration Errors


Peak power efficiency for a given system always requires the "best" configuration.  Memory power is mostly a function of DIMM count, and not capacity.  Therefore, to achieve minimum power, the minimum number of DIMMs should be used to realize the desired memory capacity. 


If you see a comparison where the DIMM count is different or not mentioned, you might notice the strong odor of dead fish. 


On the infrastructure side of the equation, a blade system can be configured with varying numbers of fans and power supplies.  Obviously some configurations will produce better power efficiency than others.  For instance, 4 power supplies run more efficiently than 6, assuming that 2+2 power redundancy delivers adequate power for a given configuration.  The most power efficient configurations though won't always be generated by a competitor when publishing a comparison.  Honestly, there are such big differences here that an apple to apple comparison is tough.  Only an HP BladeSystem dynamically throttles fan speeds based on demand across the different cooling zones in an enclosure.


Environmental Differences


The voltage level and room temperature can cause variances in the power supply efficiencies and the speed the system fans must run.  Consequently it is important that when comparing servers to verify that these parameters are held constant.  I once heard a story of an engineer setting up a box fan to blow air on his servers to try to reduce the fan power of the blades. 


Obviously he wasn't planning on counting the power from the box fan! 


Remarkably, there are published benchmarks that allow for external cooling to be deployed and not counted as a part of the system power.


Gaming the Benchmark


Any benchmark a vendor publishes is necessarily narrow in what it measures.  When looking at a published benchmark, you should consider how close the benchmark mimics your applications.  If the benchmark is similar to your applications, the results might be relevant to you.  If not, then you might do best just to ignore them.  Also, some benchmarks are very loose on configuration requirements, making it very easy to "game them" and making the results all but totally useless.  One benchmark that is broadly published in the industry falls into this category.


Where to go from here?


At this point, you are probably thinking "Wow! This is much more complicated than I really thought!"  And you are right.  Benchmarking fairly is very tricky business, even if you are trying to be fair.   The best results you can get are the ones you measure yourself.  In my next blog post, I'll comment on some of the techniques and challenges with measuring power yourself. 

Search
Showing results for 
Search instead for 
Do you mean 
Follow Us


About the Author(s)
  • More than 25 years in the IT industry developing and managing marketing programs. Focused in emerging technologies like Virtualization, cloud and big data.
  • I work within EMEA HP Servers Central Team as a launch manager for new products and general communications manager for EMEA HP Server specific information. I also tweet @ServerSavvyElla
  • Hello! I am a social media manager for servers, so my posts will be geared towards HP server-related news & info.
  • HP Servers, Converged Infrastructure, Converged Systems and ExpertOne
  • WW responsibility for development of ROI and TCO tools for the entire ISS portfolio. Technical expertise with a financial spin to help IT show the business value of their projects.
  • I am a member of the HP BladeSystem Portfolio Marketing team, so my posts will focus on all things blades and blade infrastructure. Enjoy!
  • Luke Oda is a member of the HP's BCS Marketing team. With a primary focus on marketing programs that support HP's BCS portfolio. His interests include all things mission-critical and the continuing innovation that HP demonstrates across the globe.
  • Global Marketing Manager with 15 years experience in the high-tech industry.
  • Network industry experience for more than 20 years - Data Center, Voice over IP, security, remote access, routing, switching and wireless, with companies such as HP, Cisco, Juniper Networks and Novell.
  • 20 years of marketing experience in semiconductors, networking and servers. Focused on HP BladeSystem networking supporting Virtual Connect, interconnects and network adapters.
  • Greetings! I am on the HP Enterprise Group marketing team. Topics I am interested in include Converged Infrastructure, Converged Systems and Management, and HP BladeSystem.
Labels
The opinions expressed above are the personal opinions of the authors, not of HP. By using this site, you accept the Terms of Use and Rules of Participation