The diagram shows what we agreed we mean by Infrastructure as a Service (IaaS), Platform as a Service (PaaS) and Software as a Service (right hand side) and the areas encompassed by the individual terms infrastructure / platform / software on the left. A better term than “software” might be “application” since the platform part is also really just software, but SaaS has already gained wide acceptance.

It is assumed that “as a service” means all services within the definition are fully integrated up to and including the respective level, thus incorporating any sub-levels. Therefore, SaaS providers could either sub-contract to a PaaS provider, or would incorporate the PaaS themselves and provide it as part of the SaaS “stack”. In turn the IaaS could be sub-contracted or incorporated. The customer would see an integrated service.

It is also worth explaining the overlap between ‘platform’ and ‘software’; that is because some advanced platforms are built on complex software solutions which go well beyond just operating systems and a bit of infrastructure software.

For example, one could consider bare operating system as the platform, with the bespoke software application incorporating its own software infrastructure elements (eg. a bespoke CRM solution). One might also consider a Linux-Apache-MySQL-PHP stack as the platform in its entirety, with only the PHP code itself being the software/application layer. The key differentiator between ‘platform’ and ‘software’ is that a platform is standardised and to an extent commoditised, with the software being the bespoke / custom element. A platform would also often, but not always, be highly scalable across multiple servers.

Standardised / commoditised software (hosted application) services, as opposed to bespoke / custom deployments, would most likely be considered to be SaaS.

Virtual differences

Until this point many experienced readers might be saying, “Yes, that that is just hardware, middleware and software renamed!”. To a large extent you would be right, with one small exception being subtle differences between modern platform/middleware, but there is an important difference between the old concept of “hardware” and ours of “infrastructure”: virtualisation.

It was agreed among the G-Cloud team that the virtualisation should now be considered as part of the hardware layer since it has become such an integral method of dividing and provisioning hardware resources. It is important to note that we drew the line precisely between the virtualisation layer (ie. the hypervisor) and operating system, viewing a bare-bones virtual machine without operating system or kernel as the unit(s) of hardware.

Of course, virtualisation is not ubiquitous. Indeed for many systems including highly scalable ones upon which PaaS and SaaS stacks are built do not use any virtualisation (Google App Engine does not, for example). In such cases one would simply view the stack without the virtualisation layer with the boundary between infrastructure and platform being between the physical hardware and operating system layers.

Network

Another critique of this model could be that the “interconnecting network” appears to link directly from the software layer through to the client device. In reality, of course, all network traffic has to sink back down through the layers from the software to via the networking & firewalling layer, then on to the client device. To keep the stack looking like a stack, however (which is correct from a logical perspective), it is better to stick the client device on top rather than off to one side. In the full postulated functional of the G-Cloud logical architecture the connections are more explicitly shown in a 2D rather than linear model. Hopefully that will be in the public domain soon!

Part of the solution, not part of the problem

The ICT sector is regularly harangued about the “2%” figure – the amount of global carbon emissions attributable to ICT according to a Gartner report. That figure is oft-quoted alongside real dirty polluters such as the airline industry (who dump CO2 straight into the upper-atmosphere, bypassing many of the natural ground-level sequestration mechanisms), but what is often forgotten is that in exchange for our emissions (2-3% of total in the UK) we are contributing roughly 10% of UK GDP and 15% of national trade.

Further, we (the ICT sector) have our own house well in order and have committed to reducing our own emissions as I will describe shortly. However, of much greater important is what the intelligent use of ICT can do to reduce emissions in other sectors, as highlighted by several groups including GeSI:

“ICT can reduce annual global emissions by 15 per cent by 2020 and deliver energy efficiency savings to global businesses of over EUR 500 billion”
– Global e‐Sustainability Initiative (GeSI), SMART 2020: Enabling the Low Carbon Economy in the Information Age, June 2008

Even the panda-people (the World Wildlife Fund) have got in on the act; their report with Gartner titled “Saving the 1st billion tonnes” puts the intelligent application of ICT in 10 key areas (eg. smart grid, intelligent buildings and transport avoidance) as being key to reducing our collective carbon emissions:

“‘Green IT’ is an oxymoron, until you consider use of IT to ‘green’ business and society.”
- Simon Mingay, Gartner10

Example: Transport avoidance

Perhaps the most obvious way that ICT can help is in transport avoidance. As David MacKay illustrates in his excellent (and free!) book Without Hot Air, personal transport in the form of driving cars and flying in jet aeroplanes are two of the worst things we do as a nation, together contributing to over 40% of our total energy consumption.

Cars are the worst offender, consuming a whopping 40 kilo Watt-hours (kWh) per day per person (to put that in perspective, we use about 4 kWh/d each on lighting). Even with electric cars we still have to get the energy to run them from somewhere, and there are simply not going to be enough renewables to go around at current usage levels. The only way to significantly reduce the energy consumption attributable to cars & planes is to use them less, and that is where ICT comes in; for example by enabling home working (tele-working), even if just one day a week, and reducing travel to meetings with telepresence technologies.

Keeping our own house in order

Although we can help reduce carbon emissions elsewhere, we absolutely must do so in a sustainable manner, which is why we in the ICT industry are putting lots of effort into keeping our own house in order. Last year, Intellect UK (Britain’s high-tech trade association) release their High-Tech: Low-Carbon report , which articulates an action plan on how the UK technology sector is going to reduce its emissions.

Further, Digital Europe (formerly EICTA) has committed to reduce Europe’s ICT-related carbon emissions by 20% by 2020. Many of us think that target is achievable by 2015, but how can I be so sure of dramatic carbon savings when our collective use of ICT is increasing constantly?

A lot of the existing inefficiencies of the sector lie in the data centre, and that is also where I expect to see the largest efficiency gains. The UK, in particular the BCS Data Centre Specialist Group, has taken a global lead in advancing the field of energy efficiency within the data centre, and was instrumental in developing the European Union’s Code of Conduct for data centres, which stipulates a range of best practices for every layer of the IT service delivery stack (from mechanical & electrical to software selection).

Memset recently become the first British Web hosting provider become a participant to the Code of Conduct, and we encourage others to follow suit (which many already are). The Code is free, is not hard to do (I did ours in a day) and the best practices contained in it are designed to to improve efficiency which means saving money, so it is just good business sense.

Moore transistors please!

However, there is a much bigger effect that incremental improvements to data centre design, and that is the combination of Moore’s Law with virtualisation technology. The work done per Watt by servers has been increasingly roughly in line with Moore’s Law, ie. doubling every 18 months, and is expected to continue to do so. Now that virtualisation has reached the main stream it is being deployed en-masse, allowing legacy servers to be shut down and replaced with vastly more efficient virtual systems, usually consolidating physical machines by a factor of more than 10 to 1.

Take us as an example; this year we have deployed roughly 1,000 virtual servers. Each virtual machine (VM) would otherwise have been a physical server (or in many cases used to be before it was migrated to us), and in fact many people are still using cheap old tower PCs for cheap hosting, but thankfully that practice is dying out. A normal server or PC uses around 90-120 Watts continuously, whereas one of our Xen-based Miniserver VMs uses 5-10Watts, but does the same work. Taking into account cooling and other data centre inefficiencies lets just call it 100Watts saving in round numbers:

1,000 VMs x 100 Watts = 100,000 Watts
x 30.4 days x 24 hours = 73,000 kWh / month
x 430g / kWh = 31,400 kg CO2 / month

So just from what we have done in our little corner of the ICT sector, just with new customers and in just one year, we have helped avoid over 30 tonnes per month, or 360 tonnes per year, of carbon dioxide emissions. To put that in context, each British citizen is responsible for about 9 tonnes of CO2 emissions per year. Not bad for 18 people in Guildford!

Being green is just good business sense

When it comes to ICT services, especially in the data centre, the two things that cost you the most money also cause the most carbon emissions; manufacturing the hardware (the servers / computers) and electricity to run them. In short:

Green = Efficient = Lower costs

There really is no excuse for us as an industry not to improve our energy-and-carbon efficiency, and companies that don’t will end up with higher cost bases and ultimately will be driven out of business by their more efficient competitors.

Conclusion: Let ICT do its job

The Intellect Work Programme has estimated that the knowledge economy now employs 41% of the UK workforce, and that it will account for roughly 50% of GBP by 2010. Data centres are ever-more becoming the backbone of UK PLC, and a healthy ICT industry is vital for both cutting our carbon emissions (as described above) and for driving our economic growth in the next decade.

Further, the ICT sector already has its house well in-order, so it is important that any policy measures do not interfere with the industry’s growth. Unfortunately, well-intended but poorly-conceived legislation such as the Carbon Reduction Commitment, which in the next few months is being rushed through with little-to-no consultation with industry, threatens ICT’s ability to deliver on its promise of supporting a prosperous, more sustainable society. Hopefully the next government will just let us do our job.

• What does it take to be really green?
• What needs to be in IT policies?
• How can we tell myth from truth in an emotive area?

The protagonists:

• Chair: BCS managing editor Brian Runciman.
• Tracey Rawling Church from Kyocera Mita
• Louise Richards, chief executive, Computer Aid International
• David Critchley, director of retail and professional services at Cisco
• Kate Craig Wood, managing director of Memset and a member of the BCS Data Centre SG

“The current design of the scheme will encourage transfers of carbon liability, rather than a net overall reduction in emissions across the UK.”

“The current design of the scheme will only encourage energy efficiency in a context of stunted growth. At the heart of this problem lies the proposed design of the league table, and the suggested metric to be used for ranking and recycling purposes.”

In this article I will look at how the CRC works in the context of data centres, why it will will not significantly reduce our carbon emissions, and how the it threatens to stifle growth and innovation in a sector vital for our economic and environmental health.

Data centres use in the region of 2.2-3.3% of Britain’s total grid power. While that is a considerable amount, ICT has been repeatedly identified as a key mechanism through which our society will reduce our carbon emissions. The World Wildlife Fund have identified ICT as the way to “save the first billing tons” of carbon, and the Global eSustainability Initiative SMART 2020 report has identified now the intelligent application of ICT can reduce our annual global emissions by 15% by 2020.

Data centres lie at the heart of ICT’s potential to reduce our collective carbon emissions. We, the ICT sector, are not the enemy; we are part of the solution to climate change.

Further, data centres are absolutely key to our national prosperity. Britain’s knowledge economy now employes 41% of the population, and will account for 50% of GDP by 2010. Data centres are the backbone of UK Plc, vital to the resilience of public services and the competitiveness of British business. The ICT sector, powered by data centres, promises to be one of the engines of economic growth which can lift us out of recession, and must be allowed to do so.

We are not idle about our The European IT industry, through Digital Europe (formerly EICTA) has already committed to reducing its carbon emissions by 20% by 2020. The UK has taken a leadership role in on data centre energy efficiency. The British Computer Society in particular has been a key player in the development of the EU Code of Conduct for Data Centres, and the globally-leading cost and energy data centre simulator (in partnership with the Carbon Trust). We, the UK data centre industry, have our house well in order.

The CRC scheme is part of the UK government activity seeking to cut carbon emissions by 80% of 1990 levels by 2050. The most effective way to achieve this goal is to encourage energy users responsible for emissions to reduce their energy consumption on the one hand, and adopt efficiency measures on the other.

However, the government’s scheme plans to allocate the entire carbon liability to the utility bill payer, irrespective of whether the bill payer is in fact using the energy, or a key player in the decision to use this energy.

The basic mechanism for the purpose of this discussion is that any organisation that consumes greater than 6,000 Mega-Watt Hours (mWh) electrical energy per year is automatically captured and all of the electrical (and some other) consumption of that organisation and all subsidiaries is totalled to represent the carbon of the organisation.

6,000 mWh per year is equivalent to a continuous load of 685 Kilo-Watts (kW), roughly 500 kW of IT equipment load in a moderately well-run data centre, which is around 5,000 efficient modern 1U servers (assuming 100W per server). For a poorly run monolithic ‘old school’ data centre with an excess of power and cooling infrastructure, using 3-4 year old servers it might be as few as 2,000 machines.

Operators will have their energy use base lined and then be required to report their energy consumption. The organisation then has to purchase allowances to cover the total carbon in a similar way to the power generators under the EU ETS6. This is intended to add direct financial incentives for the carbon associated with the electrical energy consumed by the data centre operator.

Data centre operators do have the ability to reduce the carbon footprint in newer more modern data centres, and by taking advantage of the relentless improvements in the energy-efficiency of IT equipment. They could contract out the carbon liability of the utility bill back to the customer. At Memset, we have that facility already; it is a trivial matter to put a customer’s approximate share of our total energy consumption onto invoices.

The customer would then would be incentivised to alter its behaviour and chose more energy-efficient criteria in the data centre. An example might be choosing to migrate older servers into a virtualised environment. Furthermore, the high price of energy is already an incentive for operators to encourage their customers to embrace more environmentally friendly solutions; electricity already accounts for roughly one third of our direct costs.

However, as the government’s CRC scheme places the onus to reduce emissions on the organisation which pays the electricity bill, not the end-user, responsibly organisations like us cannot pass the carbon down the supply chain and thus encourage our customers to reduce their usage.

As a result of this, it makes no sense to own your own data centre, and I expect to see a massive increase in data centre outsourcing. That will actually be a good thing for my business, but I so firmly believe that the CRC as it stands will be detrimental to our emissions overall that I am speaking out against it.

Outsourcing a corporate data centre or entire ICT department would, under the current
allocation approach result in the carbon also being outsourced. While clear ‘carbon dumping’ could otherwise lead to reputational damage, data centre outsourcing is a common practice; there would be no way of determining whether the outsourcing that might take place post CRC implementation was driven by genuine business reasons, or a desire to shift the carbon liability.

Furthermore, as energy costs in the UK are currently less competitive than in continental Europe, the additional carbon costs could encourage businesses to offshore. Data centres are by nature geographically flexible. Off-shoring to the continent is a realistic possibility, and the cost of running a data centre in the UK may tip the scales in its favour. This in turn will have wider implications for jobs in the UK, and data and application security.

That said, if organisations do outsource the bulk of their energy-consuming activities to more efficient third parties, the overall net emissions for the UK will reduce, and the CRC will have proved fit for purpose. However, the current design of the performance league table inhibits this from being the case.

The league table is an apparently simple mechanism for the processing and comparison of the carbon reported by each CRC organisation, but will actually create utterly perverse incentives.

The current proposals suggest that rankings in the table will be determined by two metrics: absolute growth in emissions, and relative growth in emissions. After the initial phase of the scheme, the former metric is expected to be weighted at 75%, and the latter at 25% (though it is unclear how DECC reached these figures). As a result, any business growth, even if accompanied by increased overall energy efficiency, could result in an organisation dropping down the league table!

For a data centre, our energy consumption is directly related to our revenues, and as previously mentioned the sector’s continued growth is key to supporting UK PLC and delivering ICT’s promise of reduced carbon emissions across society. The CRC as it stands will reputationally damage data centres who dare grow.

Further still, for companies like Memset that are already leading the market in terms of energy efficiency, and for whom the opportunities for improvement are very few, the CRC is quite simply unfair. It will have been much better to start out as being really bad and then to artificially manage a slow improvement in energy efficiency in order to maximise the league table position. We will look significantly worse than our horribly energy-inefficient competitors, which will result in the customers being mis-directed to use more carbon-intensive providers.

In summary, the CRC as it stands will encourage “carbon laundering” with the outsourcing (or even off-shoring) of data centre operations to avoid brand value damage, will inhibit the growth of one of the UK’s most important business sectors, and will encourage end-users to use the least efficient providers.

The CRC is already changing business behaviours in negative ways. We (as a managed hosting provider) were planning to invest in a leading, semi-experimental, “super-green” data centre in Surrey, which would incorporate a number of the latest innovations in efficient data centre design, and push the boundaries of the technologies further.

However, because the CRC penalises companies that pay the electricity bill it no longer makes sense for us to own and operate a data centre, since instead we can just rent space and power from an existing data centre and let their brand get hit by the league tables, not ours. In this case, the CRC has been directly responsible for stopping an award-winning leader in the field of green IT from investing in the next stage of innovation.

Further, as it stands the CRC may make it more economical to offshore part of our data centre operations; as long as the servers are within a hundred miles of their users it does not matter for 99% of applications.

This is especially frustrating since we already have the capability to account to our customers for their carbon usage (we have been able to do that since becoming Carbon Neutral!), so we could easily pass the carbon levy / “credits” along to our customers. That in turn would further incentivise them to minimise their indirect energy usage through us.

As the CRC stands it will make managed hosting providers with UK-based data centre operations (like Memset) less competitive to those not under the jurisdiction of the CRC (like Amazon EC2), regardless of how well-managed and how efficient we are.

The CRC at present creates the incentive to launder, rather than reduce, carbon emissions and rewards organisations good at playing the ‘carbon game’, not those who are most energy-efficient.

The legislation is a threat to UK skills and employment. From the British Computer Society’s review of the proposed CRC legislation:

“The combined impact of the incentives created by the CRC driving outsourcing of ICT and data centre services both within and outside the UK is likely to reduce the number of skilled jobs in this sector as well as removing the most significant opportunity afforded by this political will, the development in the UK of world leading, exportable skills and technology in energy constrained ICT. “

Finally, contrary to its purpose, the CRC threatens to impede growth and innovation in the data centre industry, and thus inhibit ICT’s ability to deliver the massive carbon savings so clearly identified by numerous reputable sources.

I was at the preview of this tool on 30th April in Southampton Street, and it is an amazingly powerful tool. It allow you to rapidly put together a simulated version of your data centre (including characteristics of everything from power cables to server virtualisation systems to external temperature variation), and then ‘run’ it over a period of time to see the costs and power requirements.

During the demonstration in April, Liam & Zahl (the technical and business brains behind the project) used the tool to great effect, neatly and intuitively demonstrating some of the following:

• The inadequacies of DCiE/PUE as useful a metric due to variation with light work loads; you need to measure facilities power and IT power separately.
• How virtualisation drops the total cost of a datacenter by 75% or more (or you can migrate to us and save >85% of course .
• How simply changing from nameplate (typically >400W on the label on the back of a£1,000 1U server) to peak power provisioning (most modern 1U servers never use more than 150W) reduces the 4-year lifetime server cost from £8,000 to just £5,000.
• That a modular build-out is good, but to be most energy- & cost-efficient you really need a dynamic modular approach so that you can switch M&E equipment on/off with diurnal load variations.
• How data centre costs vary with geo-location! Putting it in Iceland does not save you much after all, contrary to popular belief.

The simulator itself is a pure command-line driven tool that has been released under an open source software licence (OSL V3.0), but there is a Web-based interface that is now available to DCSG members, here, although you will need to read the user guide first unless you have a brain the size of a planet.. If you are a member of the BCS but not of the DCSG, you can find out information here: bcs.dcsg.org. If you are not a member of the BCS but are British and an IT professional, then shame on you!

The beta test is likely to last until Autumn, and feedback is welcomed so that the tool can be further improved and any bugs ironed out. Also, the Carbon Trust and BCS are looking for members willing to trial the tool on a case-study basis over the next few months. If you are interested, visit the Carbon Trust data centre sub-site.

In other words, utility computing is the provision of computing resources as a utility, in the same way that the familiar utilities (electricity, water, gas) are provided; on a pay-as-you-use basis. Sometimes utility computing it is called “on-demand computing” – the terms are synonymous. In a utility computing model the following resources would be available “on tap”:

• CPU time
  • Cores
  • Clock cycles per second
  • Floating point processing vs. integer processing (MIPS vs. FLOPS)
• Data storage (RAM, disk etc)
  • Data space (bytes)
  • Maximum I/O throughput (bytes per second)
  • Maximum transactions per second (I/O operations per second)
  • Error correction level
  • Redundancy (eg. RAID level)
• Bandwidth / connectivity
  • Throughput (bytes per second)
  • Latency to specific locations
  • Network redundancy

Grid -> Utility -> Cloud

So, how does utility computing relate to grid & cloud computing? Those terms are often used in the same breath as utility computing, or the three are confused with each other. While interconnected, though, they are different concepts:

• Grid computing is a technical approach spanning an application across multiple computers within one administrative domain (one provider, not necessarily one location).
• A compute grid is a collection of computers within one administrative domain capable of hosting a distributed application.
• Grid is about infrastructure.
• Utility computing is a sales approach, treating computing resources as a utility in the way we treat the familiar utilities (water,gas,electricity etc.). A utility computing provider would sell resources on their own grid(s).
• Utility is about business relationships.
• Cloud computing means an open market for computing resources; utility computing applied to multiple grids.
• A compute cloud is a grid spanning multiple administrative domains with applications able to move between domains in response to cost and SLA requirements.
• Cloud is about scale and the computing resource market.

Is Cloud Computing already here?

Amazon’s Elastic Compute Cloud is actually rather mis-named, and is really just a very large utility computing facility that spans multiple data centre locations, all of which are within one administrative domain (ie. Amazon’s massive grid).

Google’s App Engine is also not “cloud computing”, but instead a somewhat constrained sort of utility computing (you can only run applications specifically coded for the app engine). Some might call it “IT as a service”, but that term is rather too vague also.

Arguably there is only really one “cloud”, which is the mass-market for utility computing resource. To state “I am going to host this in the Cloud” would mean that you are going to run your app on one (or many) of the available utility computing providers.

Globe-trotting applications (aka. ‘Follow the moon’)

The ultimate vision of cloud computing is where you do not actually know where your application is being run at any one time. You would specify your SLA (eg. uptime, latency to a certain location) requirements and certain financial limits, and then give it with those specifications to some sort of broker. The application would then be able roam between administrative domains (eg. a data centre, a collection of PCs like Seti@Home, a super computer, your neighbours’ home appliances, etc), automatically seeking out the most cost effective resources that fit within the SLA requirements.

We are far from achieving true “cloud computing” at the moment, but we do have a number of utility computing providers coming online. As business slowly learns to let go of their attachment to tin and the concept that “this application run on that box” or even “this application runs in that data centre” then we shall see a massive commoditisation of the marketplace. This in turn will most likely result in the centralisation of compute resource into a small number of very large data centres in geographically strategic locations, and will enable much “greener” computing.

Cloud is not the most efficient form of computing purely because of optimal usage of IT resources, either. In the ultimate vision of cloud, one can envisage applications roaming the planet East-West, following the night time to take advantage of cheaper electricity prices (there is a surplus of power generation at night, and it is inefficient to transport electricity long distances at present), and lower temperatures (meaning less power for cooling).

Update: But isn’t Cloud also about IT services / SaaS?

Here I am merely trying to pin down one aspect of the poorly defined mess that is “Cloud”. In this article I am specifically talking about compute & storage resources (hence ‘Cloud Computing’) and am not attempting to define our contain the other areas to which many apply the same term.

I believe that when most people talk about “Cloud” they are referring to the phenomenon of increasing centralisation and commoditisation of ICT services – “everything over the wire”.

We need more terms; what I describe here is the mass-market for utility compute resources – the “power grid” of computing, if you will. What you are talking about could be called “Cloud Services” perhaps – services run on a compute utility and themselves delivered as a utility in a standardised manner. The problem I have with that is that while compute resources are interoperable, services are generally not (my compute and storage is directly comparable/interchangeable with Amazon’s, but Kashflow.co.uk is not so easily interchangeable with Xero.com).

Materials, manufacture and distribution of an average PC currently in use today is is between 750 kilo Watt hours (kWh) for the most modern “green” PCs, and 1,300 kWh for machines of a few years go. You then have to add on about 300kWh for a LED screen (500kWh for a CRT screen). Even if we take the best case scenario we are still looking at a minimum of 1,000kWh for a desktop system, and laptops will only be a little less (most of the energy in PC manufacture goes into making the small, complex components such as chips).

An average PC made within the last few years, with its screen, uses about 100W when powered up and 3W when in hibernate mode. If we assume that the PC is on for 8 hours per day, 5 days per week, and is hibernating overnight we get 200kWh/year “on” usage and 20kWh/year standby usage.

So, a 3-4 year old PC probably used 1,200kWh to make and uses 220kWh/year to run, whereas a modern super-green PC might use 1,000kWh to make and burn 150kWh/year. To look at it financially, you will save about £7/year by switching to a super-green PC. Therefore it makes neither financial nor environmental sense to swap out old PCs before about 6 years. If you need to update the software, then switch to some sort of virtual desktop infrastructure instead and use the PCs as thin clients.

The same sums applied to servers on 24/7 are quite different though. An average £1,000 1U rack-mount server bought 3-4 years ago probably “cost” about 1,000-1,500kWh to make and uses 120W at moderate load, which over a year is 1,050kWh, or at least 1,500kWh when data centre cooling is taken into account. The latest equivalent “green” servers use as little as 80W, so swapping to energy efficient servers will save 400kWh/year in electricity and get you 2-4 times more performance.

With good use of virtualisation to consolidate existing applications onto a smaller number of machines (thus taking advantage of the performance improvements) it makes clear environmental and economic sense to replace machines after 2-3 years. Alternatively, if IT is not your core business activity then you could always consider outsourcing your server infrastructure to a carbon neutral IT host such as Memset of course.

As for the old servers, why not give them away to Africa via Computer Aid International, where our “outdated” hardware is much needed and will be put to good & efficient use (ie. it will only be on when they need it).

Addendum June 2009: There are some very cool technologies like Very PC’s Greenhive (a hybrid between PCs and thin client) which are changing the argument around replacing desktop PCs.

Thin client is also reaching maturity now that you can get a decent amount of bandwidth from ADSL and that Windows Server 2008 includes most of the functionality of Citrix at no extra charge. Thin client is definitely the future I think.

First of all we need to be clear on what we mean by utility computing; very few organisations are offering true utility computing (ie. computing resources as a utility, in much the same way as gas, water or electricity is supplied) although there are some analogues. Our services, in some senses, can be regarded as utility computing, because we make computing facilities (specifically CPU resource, storage and bandwidth) available in convenient bite-sized chunks and allow customers to easily upgrade/downgrade.

A typical example is one of our Xen-based Miniserver Virtual Machines; a client might initially just want 256MB of RAM and 30GB of disk space, but in time their requirements might grow beyond one machine and onto a cluster of powerful dedicated servers. This approach (allowing the client to start small and grow the resource allocation as needed) gives very large cost savings to them (as well as no up-front capital expenditure) and is very green; we balance the load across our pool of Miniserver host machines to make efficient use of the available disk and CPU resource (bandwidth is secondary since if you don’t use it all, it is not really consuming power).

We, however, are progressively moving towards true utility computing. The next step is our deployment of on-demand clusters where the client has 10 (say) servers dedicated to his/her application, but at normal loads only 3 are required, so only 3 are powered up most of the time. As demand increases our in-house management software spots the trend and (ahead of requirement) brings the other nodes in the cluster online. We plan to incentivise our clients to use this system by billing them separately for electricity, so if they let us turn off the machines that are there just to cope with load spikes and normally not being used, it costs them less.

Our longer-term vision is to combine the two so that we can fully virtualise customers’ server clusters and dynamically allocate them to machines in our server pool that are not necessarily dedicated to them. That is when you truly get the big cost and energy savings; imagine us hosting a big online game in the same data centre as a back office function of a large corporate. During the daytime the back office function might need 50 servers to run, and the game only 10, but during the night the game might need 50 and the back office 10. With traditional provisioning you would have at least 100 machines on and running all the time, but with our system you 60 or less. In reality it is even worse since no sane CIO would run his application without some overhead room to cope with load spikes, but again you get that for free with utility computing since the load spikes just become a ripple on top of all the baseline operations, saving you even more cost and carbon. I estimate that if all our UK data centre operations were running in a true utility computing environment we would be able to reduce our power and hardware requirements by a factor of ten.

There is a catch though; to get the really big savings (in terms of money, energy and hardware) you need to consolidate large numbers of diverse applications (with different load characteristics and different usage patterns) into a small number of big data centers, or at least a small number of big utility computing pools. The problem is that most CIOs are still unsure about the security of virtualisation (for no good reason I might add), let alone allowing their applications to “roam” freely across pools of servers, being allocated CPU & disk resources that might have moments ago been used for one of their competitors.

As with most green initiatives, to get the real benefits of utility computing we need to change the way we think and operate at a organisational level – rolling out some shiny new technologies by itself is not enough. In this case we need to lose our outdated attachment to tin and the idea that “this application runs on those boxes there”. Instead we should view CPU time and storage space as facilities to be rented as and when needed, in much the same way as we do with bandwidth. After all, the routers feeding your ‘net connection might have been being used for something quite other moments before, but we don’t care – why should we with servers?

The recent flurry of interest in getting the power consumption down in data centres in the UK has in large part been driven by a swathe of city firms suddenly realising that not only are they running out of power in their current central-London data suites, but they can’t get any more space and capacity either – power is already being reserved for the 2012 Olympics, for example. Also, there are a number of city data centres being run at dangerous capacities, and I’ll be watching with interest when the first of those super high density suites goes into thermal runaway after a brief power outage; the chillers are not run off the UPS, and therefore are shut down for a few mins while the backup generators start. At high power density in confined spaces that is potentially long enough to result in a non-reversible catastrophic failure process (similar to one we have seen in action). I suspect we may see a major bank with melted blade servers in the near future…

But I’m rambling; I’m not interested in those power-and-space constrained city firms (they should just move their non-trading- / non-latency-sensitive back-office applications out of town), my point here is that all CIOs should be taking note of their IT infrastructure’s energy usage. Why? Well on the one hand it is good for PR – in a recent survey that my company, Memset undertook 48% of the new customers we gained since going Carbon Neutral in August ’06 said that energy efficiency was “important” when choosing a supplier. Interestingly, only 39% said offsetting / carbon neutrality was important, which suggests to me that buyers are realising that treating the cause is better than treating the symptoms.

On top of the good PR, as an industry we need to be prepared to combat negative press on the issue. Recent calculations based on server sales in the UK estimate that 1.9% of the UK’s grid power goes to powering data centres, which is a massive amount. Some papers used a similar figure from Gartner (that the UK industry worldwide contributes 2% of total greenhouse emissions) to compare us with the airline industry (who also contribute 2% apparently, which is further worsened by the greenhouse effect of contrails), but that at least is easily dismissed; the IT sector contributes something like 10% to UK’s GDP, so we are putting our 2% power usage to very good use at least! Regardless, I would not be surprised to see data centres becoming targets of environmental protests in years to come if we are not careful.

Even if we put all that wholesome planet saving stuff aside for a moment though there is a still a solid reason to be taking energy efficiency in the data centre seriously: a few simple steps can much more than halve the electricity bill.

First lets consider the changes in server power usage. I did an article in May ’06 (getting value for wattage) highlighting the improvements in server energy usage, and since then things have improved even further with the advent of Intel’s multi core chips. Take a standard £1,000 ($2,000) Dell 1U “workhorse” server. Eighteen months ago that got you a dual Xeon machine that used about 200W when working at moderate load. Today, we are buying dual core machines that, thanks to Dell & Intel’s good work on efficiency, are more powerful yet use only 100Watts under moderate load (in other words the same as a bright light bulb).

Next lets factor in the changes in data centre infrastructure technologies and design in the last few years. At our new Reading site 70%+ of the power entering the building actually gets to power the servers. This gives a Power Usage Effectiveness (PUE) figure of roughly 1.5, erring on the side of pessimism. PUE, by the way, is the Green Grid’s proposed metric on measuring data centre efficiency. In my third article in this series (“Measuring IT”), I will explain why it is not a useful metric in practical terms and why the one going into the EU Data Centre Code of Conduct (being developed with the British Computer Society’s Data Centre Specialist Group and Intellect UK) makes more sense. For simplicity though it serves its purpose here; in many older data centres, the PUE is as high as 3 or 4 (ie. Only 25-33% of the power entering the building actually reaches IT kit). I’ll talk about how data centres can be made more efficient in the next article (“How”), but for now lets apply those figures to our workhorse example servers’ power usage.

For meaningful comparison I’m going to look at the costs in any one month. For the hardware, three years is a realistic lifetime so £1,000 over 36 months gives an amortised cost of £28/month ($56/m).

The 18-month old dual Xeon, when housed in a fairly average two year old data centre (I’ll be generous and give them a PUE rating of 2), would double its power usage (cooling, UPS inefficiencies etc), which gives us a figure of 400Watts which, at 10p/KWh, gives us a electricity bill of £29/month ($58/m). Yes – that is more than the cost of the hardware!

Our new, low-power dual core machine, installed in our nice energy-efficient modern data centre (PUE 1.5) gives us a total energy bill (at 10p/KWh again) of £11/month ($22/m). In other words, by installing modern, basic servers (not expensive, over-complex blade centres) in a modern data centre (most of whose efficiency gains are achived without massive cost of complexity), you can save £600-700 ($1,200-1,400) over the lifetime of a £1,000 server!

A final thought; those figures don’t include an allowance for carbon taxation or offsetting, and one should also bear in mind that commercial electricity prices have doubled in recent years, and look set to continue to rise, at least until they are at a level where nuclear power is commercial viable again. In short, taking note of your IT infrastructure’s energy efficiency can have a very significant effect on your bottom line.

In the next installment I’ll talk about some of the simple, practical steps that can be taken to improve a data centre’s power efficiency, as well as some methods of reducing the number of machines you need in the first place.

Normally our data centres have plenty of over-capacity in their air-conditioning systems. Cooling a data centre is one of their big design challenges – each of our 1 metre square racks uses around 4KWatts, all of which gets turned into heat which is roughly the same as four electric fire bars; standing behind one is positively toasty! Believe it or not we are fairly conservative as to how we stack the servers as well – a rack full of blade-servers might easily double that figure.

The record temperatures this month have caused problems though. When the outside air temperature increases it becomes harder for the air-con units to dump heat – after all, for the external units to be able to radiate heat away they need to be hotter than the ambient temperature, and that is compounded by the fact that the area they are trying to cool is being additionally heated as well. When temperatures spiked to over well over 30 degrees Celsius earlier this week one overworked air-conditioning unit at our Fareham site failed. The data centre team was swift to respond and it was back up and running within an hour, however what under normal circumstances would have been a reduction in capacity well short of the safety-margin over-capacity actually meant there was not quite enough cooling for that brief period, thanks to reduced efficiency of the air-con units and the generally increased ambient temperature.

The result was a small rise in the building’s internal temperature, which was then compounded. As the temperature increased slightly, the hotter-running servers had to increase their fan-rates to keep cooler, and hence use more energy. On top of that CPUs tend to become less efficient as they heat up, again using more power. More power usage means more heat generation, and suddenly you have a positive-feedback loop, although thankfully quite a slow acting one.

Thanks to a swift response no serious harm was done; however one of our busier machines did manage to pull a whopping 400Watts and contributed to a power-trip being blown which, frustratingly, caused an unscheduled reboot for the handful servers on that power bar.

Along with increasing energy costs and a moral responsibility to battle climate change, this sort of technical consideration in the face of ever hotter Summers is yet another reason why IT hardware & infrastructure providers need to have energy firmly on the agenda. We certainly do.