data center 2 efficiency

Power, Productivity and the Internet: Part 2 – All hands on deck

In part one, Power, Productivity and the Internet: Part 1 – The core of the problem, we looked at the issues inefficiencies of energy consumption in data centers here we look at what to do to address them.

A data center exists to support the data processing within it.  Data centers are rarely static and unchanging.  Data centers are seldom homogeneous in applications and data within them, or in the type and vintage of data processing equipment they contain.  As the business goes about its duty serving customers and earning money month after month, year after year, much changes in the server estate.  Servers are introduced to host new applications.  Servers are periodically swapped out with newer models.  Application configurations change, which also drive changes in server configurations.  Virtualization is applied to improve hardware utilization, but self-service provisioning and lack of good governance contributes to virtual sprawl.  As this transpires, it’s impossible to track what each of these servers are really doing, and especially to what extent these servers are delivering value to the business.

The result is that, at any point in time, we have a lot of investment in servers, some of which are very productive and returning value to the business, others somewhat productive, and some still that are not at all productive.  We’d like to know how we can best use the resources that are returning value to the business (those productively used), and especially to remove the resources that are costing energy and money but returning no value at all to the business.  As time goes on, a data center accumulates waste, and waste unnecessarily consumes energy.

Traditional methods of identifying server waste leave much on the table

Traditional methods of identifying server waste are based upon utilization measurements.  If the server’s CPU utilization is showing activity, then it’s probably doing something.  ‘Isn’t it?  Well, it may be doing something, but how do we know it is productive activity?

This is a problem recognized by data center managers across the industry.  In a recent survey commissioned by 1E, it was discovered that 83% of data center managers want a better view of server utilization though most still rely on simple CPU utilization as their primary metric.  Sixty five percent of those admit to migrating unused physical servers to virtual instances, thus simply propagating waste.

The simple fact is that utilization-based approaches simply do not lend the fidelity of information necessary to effectively minimize waste and to offer energy management at the server level.

Zeroing in on server waste

1E’s “Useful Work” technology is truly unique in its ability to provide clarity of data processing executing on the server.  With this Useful Work technology, each process is classified as either Useful or non-Useful.  This data is accumulated to provide a view of exactly where productive data processing is occurring over the server estate, when, and to what extent.  This provides an unparalleled opportunity to eliminate comatose servers or maximize consolidation, which directly translates into reduced data center energy consumption.

On another level, if the data processing is ultimately driving the power drawn by the server, and if we know that certain data processing is productive and useful to the Business while others is background activity (or non-useful to the Business), then what if we could reduce the power drawn by the server during non-useful activity, and restore it to normal for the productive and useful times?  This is an extension of the useful work technology and a feature that enables active power management of the server such that server power consumption is reduced when doing only non-useful work, and restored when doing useful data processing.  This is different than powering down a server overnight (after all, what business is not 24×7 these days?).  This is actively modulating power drawn based upon knowledge of the value of the data processing, with a view from inside the server itself.  This capability helped 1E win “Green IT Product of the Year” in 2011.

 

 


data center

Power, Productivity and the Internet: Part 1 – The core of the problem

A recent NYTimes article touches upon a number of topics in the ongoing conversation about data center energy efficiency. Some reading that article may react as if some secret revelation has been exposed, incriminating our beloved social media networks and data center as spendthrifts or environmentally ignorant.

The fact of the matter is that we live in an information driven world. Information systems are the foundation of our economies, governments, entertainment and many aspects of our daily lives. Maintaining this information and conducting the data processing around it is an industry. It is as much a part of our industrial fabric as steel and manufacturing were in the 20th century.

The data processing that serves our 21st century lives takes place in facilities called “data centers.”  Data centers are essentially industrial factories. From an energy profile perspective, they look exactly like any other factory in that they consume large amounts of resources (electricity and water in their case).

1E has a pedigree of addressing data center energy efficiency and we’ll share that with you presently but first we’d like to give you a little more background.

The core of the problem

There are some out there that will claim the heart of the problem is our dependency or desire for more and more data processing. That is, we are a data processing driven society, hurtling toward the planet’s demise. We’ll leave that to another discussion and instead assume that the increase of data processing demand in our society is a reflection of progress, commerce, and democracy. If you grant me that assertion, the core of our energy demand problem here is that silicon semiconductor-based data processing systems require energy to operate and produce a good bit of heat as a byproduct of their activity. This is compounded exponentially by a matter of scale. 

Semiconductor devices have become increasingly dense (in terms of number of transistor gates per unit of area), with higher and higher clock speeds. As these increase, so does energy demand. As individual devices become increasingly dense, we correspondingly demand more and more of them. The result is computer rooms with massive quantities of data processing servers, each of which have massively dense semiconductor chips.

We mentioned a moment ago that a byproduct of the power going to the server is heat. These very dense silicon chips operate at temperatures so high that one could not possibly touch them bare handed. Interestingly, this large amount of heat produced by the semiconductor chips is also a threat to their very health.  Consequently, computer servers have lots of fans that pull cool air into the front of the server and blow hot exhaust air out of the back of the server. Yes, fans consume loads of energy too, but the bigger problem still is all this hot exhaust air from all the servers sharing the same space in the data center. For this reason, a large amount of mechanical equipment and resources are a part of data centers as well. These mechanical systems are in the form of air handlers, chillers, cooling towers, and plumbing that is in place simply to remove all this hot air from the data center for the purpose of maintaining a healthy ambient operating temperature for the servers.

In an average run-of-the-mill data center today, approximately half of the electricity supplied by the utility to the data center makes it to the power cord of the IT (server) equipment.  Why only half?  Well, the mechanical equipment that cools the data center requires a large amount of it, and there are other losses along the way due to common inefficiencies in power distribution and mechanical and electrical technology (one never gets 100% of what one puts in). To make matters worse still, of the electricity which actually makes it to the IT power cord, much less than that actually goes toward actual data processing due to fan energy consumption, conversion losses, and other subsystems within the server itself.

In summary, we need lots of data processing, and data processing technology consumes large amounts of energy.

All hands on deck

These issues have been thoroughly understood and very publically visible steps taken to address them for many years already. In the United States, the US Department of Energy (DoE) created the “Save Energy Now” program. This program partners the DoE with industry to drive energy efficiency improvements year over year in data centers, with specific goals of saving over 20 billion kWh annually (as compared to historic trends). In the EU, the “EU Code of Conduct” was created to establish a framework of best practices covering energy efficiency, power consumption, and carbon emissions.

Within the data center community, numerous industry groups, trade organizations, and ad hoc committees have been at work on these issues for years. The work of the Green Grid, in particular, has been instrumental in creating the common language used in the community addressing this problem, resulting in a number of energy efficiency management metrics and data center design conventions that we now consider de rigueur.

With governments and the industry itself working the problem, the equipment manufacturers have a role to play as well. Mechanical and Electrical plant (MEP) equipment manufacturers have responded with higher efficiency transformers and UPS, and innovations in pump, fan, and cooling technologies. When it comes to the IT equipment which is truly the engine of this factory we call a data center, the work of participating equipment manufacturers in the ASHRAE TC9.9 body of work is truly remarkable. This is remarkable in that major server manufacturers mutually revealed engineering details of their products to one another to the extent allowing specification of wider ranges of operating temperature and humidity envelopes. This is crucial to energy efficiency in that it is fundamental to allowing reduced energy consumption of MEP, and greatly expands the opportunities for use of free cooling.

Once can go on about this, but suffice to say the evidence is clear that energy consumption by data processing facilities is a widely recognized problem, and much is being done in a coordinated and public way, to provide relief. It’s improper to draw conclusions about a specific data center facility, based upon news of a high profile business with completely different data centers.  Some energy efficiency techniques are available to everyone everywhere, and many are not.  This is a complex subject with significant nuance, and generalizations can come with risk.

In the end, the Business has invested quite a lot of money in its data center, and to acquire the servers and software within it.  Over the years, the Business spends quite a lot of money maintaining and supporting these systems, and is also spending quite a lot of money on energy for power and cooling.

In part two, I’ll look at how to identify server waste and what you can do to eliminate it. 


1E Introduces “Useful Work”-based Data Center Governance, at Data Center Dynamics Converged, 2012 Washington DC

Data center performance metrics have struggled to accurately represent business value of IT assets invested in the enterprise data center.  Data center metrics are either constrained to raw power usage data, or make vague approximations about business-relevant performance through assumptive percentages or abstract proxies.

At Data Center Dynamics in Washington, DC this week, 1E introduced an improved method of data center performance measurement and governance based on empirically derived measures of data processing “usefulness.”

Continue reading


2010 Energy Efficient IT Report from CDW – Key Facts

 

I do like a good report! I know it’s all too easy to throw around stats and numbers in this game, and the huge growth in Green IT and Energy Efficiency in IT has meant that Whitepapers and reports on these subjects are appearing with increased frequency.

Anyway, a new report from CDW, entitled – 2010 ENERGY EFFICIENT IT REPORT dropped into my inbox today and it’s definitely on the ‘must share’ list. Possibly because it’s only 25ish pages long which suits my ever decreasing attention span, but mostly because those 25 pages provide a great current snapshot of Energy Efficiency in IT. It’s always useful to get a feel for what your peers are thinking on a subject, and what they may be up to. This report makes for some interesting reading, and here are some key points..

First off is that 74% of companies have or are developing programs to manage and reduce IT energy use. I thought that this figure may be higher, but the good news is that it’s up 5% on 2008, at a time of restricted economic growth. I think that this shows quite strongly that companies are really taking IT efficiency quite seriously. Additionally, the percent of IT managers who know what portion of their IT budget is spent on energy increased from 50% in 2009 to 57% in 2010.

 

CDW E2IT Reducing Energy Use Graphic

When it comes to results, the report shows that 56% of IT departments that employ power management strategies have reduced costs by 1% or more. Now while this may seem a little disappointing, you have to bear in mind that 20% of organizations questioned have flattened or reduced IT energy use, but increasing prices of electricity continue to drive up IT energy costs.

 

There’s also an interesting section on some of the main barriers to implementing energy efficient IT. Here’s the top 6

We have too little budget left for new, more efficient systems after meeting internal client demands (32%)

Senior management gives higher priority to other investments (32%)

The people who pay our energy bills do not pay attention to IT’s energy use (31%)

We do not have a way to isolate and measure energy use (27%)

We do not know all of the things we could do to improve efficiency (26%)

If we cut IT energy costs, our IT budget is cut by a corresponding amount (16%)

Also covered in some detail is the growing picture of Data Center consolidation. It shows that many organizations are turning to data center consolidation for IT energy reductions, with of 79% of IT managers reporting that their organization currently has or is developing a data center consolidation strategy.

There are a few surprises here too, in the take up of EPA/Energy Star programs. Many had not heard of the Data Center rating program for instance, and although folks are aware of metrics such as Power Usage Effectiveness (PUE) and Data Center infrastructure Efficiency (DCiE), only a tiny proportion actually use them to track power usage (only 15% use PUE).

 

Overall, the report shows that although there is steady progress, both in awareness and implementation of Energy Efficient IT measures, there’s still a long way to go, and billions of dollars out there being wasted every year. I suggest that you take 10 minutes out to read this report, and see just where you are on the road to Energy Efficient IT, and how you might kick start some further efforts.

http://www.computeruser.com/CDW2010EnergyEfficientITReport.pdf


New Green Grid Whitepaper: Unused Servers Survey Results Analysis

 

Now try saying that title three times quickly!

 

In December 2009, The Green Grid conducted a brief survey to learn more about the number and nature of unused servers currently running in data centers. Results showed that only one-fifth of data center operators attempt to identify unused servers as part of their regular day-to-day operations. Wow..come on guys. If you walked into your data center and found a suitcase full of cash, what would you do, walk away? Thought not.. This is such an easy cost saver – no excuses!

Those respondents who do look have an average of 10 percent unused servers in their data centers. Knowing whether servers are being well-used for productive work, and turning off those that are not, will help data centers be more energy efficient, reduce redundant infrastructure, and avoid unnecessary spending and environmental impact.

 

This paper is interesting in that it’s not just a review of ‘look how much money/energy/time we’re wasting here, but it also examines the reasons why these servers become idle, and what you can do to prevent such a build up of waste.

Get the whitepaper here: http://www.thegreengrid.org/~/media/WhitePapers/Unused%20Server%20Study_WP_101910_v1.ashx?lang=en


Could the Carbon Reduction Commitment Close UK Data Centers?

According to the Register, almost half of the UK’s data centre operators believe the UK’s Carbon Reduction Commitment (CRC) efficiency scheme could drive UK data centre investment offshore, with one-third saying it could send UK data centers overseas as well.

The findings are from a survey of Britain’s largest data centre operators by Datacenter Dynamics.

Now we wrote about the chaotic state of the Carbon Reduction Commitment (CRC) back in September – http://blogs.1e.com/index.php/2010/09/24/last-chance-saloon-for-uk-crc-registrations/ and a couple of months down the line, it seems that 83 per cent of the respondents in the survey stated that they are concerned about the rising cost of purchasing carbon allowances and 81 per cent were concerned about the rising uncertainties surrounding the CRC scheme.

The problem lies in the recent UK government spending review in October, which changed the ballgame somewhat..

The government has decided to discarded a plan to rebate carbon credit fees paid by companies which were the best performers in reducing energy use. Instead, they announced that they would retain these fees paid for carbon credits (which must be purchased from April 2011 by companies using 6,000MWH of power) which effectively turns the scheme into a not-so-stealthy-tax.

The irony in all this, is that the CRC, which is supposed to aid in the reduction of carbon emissions, could force operators to move to locations in countries where such restrictions don’t apply, potentially resulting in an increase in emissions. With energy prices rising too, this looks like it could become a real problem.

All thought out? Possibly, but here to stay, so if your company will be affected, here’s a good summary of the changes to the scheme. http://www.carbonfootprint.com/crcnews.html

And as ever, 1E is here to help with the great reporting capabilities of both NightWatchman and NightWatchman Sever Edition.


Facebook Pokes Green IT

..will Green IT ignore Friend Request? After the fierce lambasting over placing it’s data centre in the middle of ‘coal country’, Facebook seems to be going all out to embrace the greener side of life.

As ecoInsite reports, Facebook is now making a concerted effort to become synonymous with Green IT in it’s Data Center operations. They are implementing some ‘greener’ software that lowers CPU usage for example, and have already published some of their Data Centre cooling strategies on their website. Will this be enough to deflect the fact that the whole place seems to be running on so called ‘dirty energy’? Who knows.

It’s interesting that Facebook have gone as far as looking at things at the server level. Many companies focus so heavily on saving energy coming through the door of the facility (cooling etc), that they simply overlook the servers. As our own research has shown, on average 15% of servers in companies are quite simply doing nothing. 

The fact is that server energy savings really are there for the taking, and the more servers, the bigger the savings possible. Companies the size of Facebook run thousands upon thousands of servers. For example, Facebook users currently upload 220 million new photos a week, or about 25TB worth of data. Of those thousands of servers humming away and munching coal by the ton, how many are actually performing Useful Work 24 hours a day?

Our approach at 1E is to make every kilowatt count, and once installed, NightWatchman Server Edition gives you instant visibility of the power consumption of your servers, but more importantly it tells you exactly what that power is being used for.

I think some server managers are possibly phased by the thought of impacting the server availability when using NightWatchman, and prefer to keep their hardware running at full tilt all the time, but there’s nothing to fear. A server which is not performing useful work can be placed in what we term a ‘Drowsy State’, which means that it’s still available for work at a moment’s notice. Efficient IT is all about gaining those tiny savings all across the board, and Server Efficiency is a hugely untapped available saving for most companies.

As our own Andy Dominey said recently, ‘Want to avoid the wrath of the environmentalists? 1E can help…’.


Reduce Server Energy Usage. Three Tips from Forrester and One From 1E

The ups and downs of the economic climate are mirrored in IT hardware sales. As economies recover and grow, so server sales in particular take off as customer demand for good and/or applications booms. In a great article from Doug Washburn Forrester reports that 25 percent of organizations expect server spend to grow by 5 percent to 10 percent, and 6 percent expect it to grow by 10 percent or more.

As we have seen over the last few years, one of the fastest and cost effective ways to deploy new servers is using virtualization. Deploying virtual servers provides a fast time to market for new apps, and can reduce operating costs. But it seems there’s a new reason for companies to choose virtual over real servers. Energy.

IT Energy usage is now firmly on the map of any cost conscious company, and Forrester have found that there are three main reasons for deploying virtual servers in the data center.

The first (and I would suspect main) reason is financial. Costs to power a real server are getting higher each year. Virtualization reduces the energy consumption per server.

Resiliency is another prime choice. Virtualization alleviates out-of-space, power and cooling constraints. Virtual Servers can be powered off and waiting in the wings for extra demand.

Third up is Green. As companies keep track of their carbon emissions and e-waste, either through mandatory regulatory requirements or of their own accord, virtualization provides a great chance to cut both.

In his article, Doug goes on to provide three great pointers which can give you up to 65% energy saving using virtualization.

I’m providing a cut-down version here, but I recommend that you read the full article if you’re interested in making the most of virtualization.

Increase the virtual to physical server footprint

This may seem obvious, but how do you measure this ratio? As Doug points out, you can use Forrester’s Green IT Maturity Assessment methodology which defines the following targets.

  • Needs improvement (1 percent to 25 percent virtualised);

  • Improving (26 percent to 50 percent virtualised);

  • Robust (51 percent to 75 percent virtualised); and

  • Best-in-class (76 percent to 100 percent virtualised).

  •  

    Maximize your virtual machine to physical host and utilization ratios

    Virtualizations alone is not enough. In addition to increasing the overall server virtualization footprint, drive additional energy savings by virtualizing more efficiently. Server virtualization ratios are not keeping pace with modern hardware and virtualization platform capabilities. It’s common to break even on the purchase of a new server with a 4-to-1 virtual machine (VM)-to-physical host ratio, but most servers can accommodate 15 VMs. Virtualizing more efficiently can help you avoid three new server purchases, not to mention the additional power, cooling, and space expenses from this new equipment.

    Source more energy-efficient servers and architectures

    Sourcing more energy-efficient servers and architectures may be your only remaining option to reduce energy consumption if you’ve maxed out virtualization ratios or realized that you’re going to need higher-end server infrastructure. Energy consumption will be higher on a per-server basis – but total server energy consumption will be lower due to the reduced number of overall servers.

    As the Forrester folks have found, Energy savings can be significant as recently stated by the VP of an online services company who said about his converged architecture: “We achieved 70 percent space savings, 25 percent operational expense savings, 30 percent to 40 percent heat dissipation improvements, and 40 percent power savings.”

    What Doug doesn’t mention in his piece however is the ongoing management of this virtualization.  Virtual Sprawl and Stall are well documented pitfalls of the Virtualization world. It’s no use racking up these energy savings if your operational costs sky rocket due to a proliferation of Virtual Servers that are ultimately not performing useful work. This is where I would implement tip number four..

    Ensure that your virtual (and real) servers are managed by NightWatchman Server Edition

    This will ensure that:

    Your servers (virtual and real) are always performing Useful Work.

    Your Energy and CO2 Savings can be captured and reported. NightWatchman can report on the energy usage of individual virtual servers.

    Any virtual servers that are no longer required can be decommissioned straight away, providing the most efficient licensing possible.

    As we say here, make every kilowatt count, and with these great pointers from Forrester, and 1E’s NightWatchman Server Edition, great savings are possible.


    New Metric from Green Grid Measures Energy Reuse

    Just as we’re all getting to grips with the base data center metric of Power Usage Effectiveness (PUE), along comes another one! As we are beginning to find, making every Kilowatt count is all about measurement. Our NightWatchman Server Edition software is already helping companies to increase data center efficiency by measuring the usefulness and energy usage of servers in racks. But what about energy from the data center that is re-used elsewhere? Data center designers are finding ever more innovative ways to save energy, and in recognition of this, the Green Grid have released a new whitepaper which will help leading edge energy efficient data center operators to put a figure on this important saving. Of course, in order to have this metric, we need another acronym! (sorry guys) ERE stands for Energy Reuse Effectiveness, and this whitepaper is worth a read if you are at all concerned with the finer points of data center energy usage. It is quite technical, having involvement from the guys at Lawrence Berkeley National Laboratory, and The National Renewable Energy Laboratory. These folks have been looking at energy usage in IT for many years now so it comes as no surprise that this paper is another great one from the Green Grid. It covers everything from the theory to the practice and includes mathematical workings along the way, although it does all of this in a very readable 15 pages.. Read the paper here – http://www.thegreengrid.org/en/Global/Content/white-papers/ERE

    Using NightWatchman Server Edition to control Virtual Sprawl

    What is virtual sprawl?

    Virtualization must be one of the most touted ‘silver bullet’ solutions of the last ten years. I can’t think of any company who hasn’t either implemented or considered virtualization. With Server hardware advancing leaps and bounds, and disk space becoming ever cheaper and more plentiful, the ability to partition that space into multiple virtual server environments or ‘Virtual Machines’ (VMs) has provided many benefits. For data center managers, it makes provisioning new servers a simple task. Extra server capacity can be brought online as and when required, with no additional hardware involved, and a low admin requirement. Once your virtual server image is created, you can have your new army of virtual playgrounds ready and waiting. If a customer needs a server fast – just start one up.

    In IT test or development departments it means that developers or tester teams can have access to a new server build at the click of a mouse, which they can then play with, before ditching it and starting up a new one.

    So it all sounds amazing, but as we know from past experience, nothing is for nothing. Enter Virtual Sprawl.

    Virtual sprawl can be described as the unmanaged spread of VMs without adequate management or control. Or, it’s a bit like my workshop at home, which suffers from the unmanaged spread of tools and other items without any management or control whatsoever.

    It usually comes about because of a lack of the correct management processes that are required to track and maintain a VM. Because we can’t actually see a VM in a rack it’s easy to forget about it, unlike a physical server which can be more easily accounted for. Companies jumped on the VM bandwagon without really thinking of the long term implications because virtualization was the answer to so many problems. If Virtual Sprawl is left unchecked it can also lead to what is becoming known as ‘Virtual Stall’ too, where the project is so unmanaged that management is forced to put a stop to the rollout. What does it all cost?

    I think that initially there was a general perception that because VMs are so easy to create and keep on standby they are somehow invisible to cost. If only.

    Some time ago I read that the costs associated with virtual servers can be broadly split into four categories. These are infrastructure, management systems, server software, and administration. So you need a physical box on which to host the virtual system, the server software (be that Windows or Unix etc), some admin time and some kind of management – virtual servers need patching too!

    However, I would add a fifth category to the above. Each VM that is out there and running is using up energy in the form of the electricity used to power the host server and disks. Just like a real server, a VM needs a slice of the processor time, memory and other hardware services.

    It shouldn’t all be cost however. If a company decides to implement a virtualization project, the savings can be immediate and quite significant. Depending on the level of virtualization, hundreds or indeed thousands of physical servers can be decomissioned. Once this has been achieved however, it’s easy for the rot to set in. Once customers (either internal or external) get to know how easy it is for a VM to be deployed, it creates demand for more and more servers. The number of VMs creeps up and up until you reach a situation where the very cost savings of virtualization have been wiped out and you have a rapidly growing problem on your hands.

    Visibility is the Key

    In our experiences so far, we have found that NightWatchman Server Edition (NWSE) is a great tool for preparing for virtualization. Using our Useful Work analysis on your physical server population will allow you to identify which servers can be virtualized and/or decommissioned. Armed with this information you can plan your consolidation and virtualization project with precision.

    However, it is also the perfect tool for monitoring your VMs once deployed.You can setup regular monitoring and reporting so that you can easily identify any VM which is running but no longer performing it’s original task, or is simply under utilised. Consolidation should not be a one-off task, and VMs can and should be included in an ongoing ‘server waste-management’ plan.

    If you suspect that you already have a bad case of virtual sprawl out there, and may have VMs out in the wild that are no longer required, you can also use NWSE to track them down and bring them under control. NWSE can easily highlight VMs which were commissioned in haste (perhaps for a one-off project) and are no longer in use. Or perhaps a whole group of VMs were ordered for a project that is now complete. Once these so called orphaned VMs are identified you can reclaim valuable disk space as well as reducing your energy usage.

    Virtualization is a great tool. It’s all about doing more with less, and with the right tools to control your VM sprawl you can achieve exactly that. http://staging.1e.com/softwareproducts/nightwatchmanserver/virtualmachinesprawl.aspx