Highlighting thought leadership in the data center
-
Colocation for the Changing Cloud
July 27th, 2010 : Industry PerspectivesKevin Dean, Senior Vice President of Marketing and Chief Marketing Officer, is responsible for Interxion’s pan-European marketing and business development strategy and implementation.
KEVIN DEAN
InterxionCloud computing is widely acknowledged as the major force driving IT into the future. International Data Corporation (IDC) has predicted that spending on cloud services is set to increase from $16.2 billion in 2008 to $42 billion by 2012. (1) But as the cloud revolution continues, companies need to consider how they’re going to update their IT infrastructures to prepare for this growth.
Several companies have already realized the benefits of colocating to a carrier-neutral data center to meet these needs. The environment found in such data centers is ideal for cloud services because it provides the opportunity to scale to match fluctuating demand, as well as the power, connectivity and secure processes needed to ensure reliable performance and continuous availability. It also provides significant economies of scale, which helps keep costs to a minimum at this critical stage in the development of cloud services. An additional benefit is the drastic cost savings in CapEx and OpEx, which can quickly and easily reach $25 million for the data center build alone.
With this in mind, there are several key factors for having an ideal environment within which cloud computing services can grow and prosper:
1. Limitless Scalability
Cloud computing demands higher levels of faster scalability than previous delivery models. Bandwidth and processing power need to be instantly available for surges in demand, with the added ability to reduce resources when peaks in traffic have passed. By outsourcing to a large data center, companies do not have to worry about over-provisioning for spikes in demand, therefore avoiding issues of under-utilization. Using a third-party data center also prevents the risk of running out of capacity for such heightened demands.
2. Physical and Virtual Security
Although there are many benefits of moving to the cloud, there are also some risks. The Ethernet-based cloud is not impenetrable or fail-safe and is certainly not immune to data loss. Organizations must identify operational and security risks associated with the cloud, namely data security, integrity and privacy, so as to better choose a solution that addresses these concerns.
Large data center environments are ideally suited to secure delivery of cloud applications, such as Storage-as-a-Service and Software-as-a-Service. This is due to the robust nature of the data center’s infrastructure and the inherent need for high-quality, efficient and up-to-the-minute technologies and hardware. Larger facilities excel in both physical and data security, with multiple security layers and fail-safes, as well as back-up and recovery systems that protect against data loss.
3. High-density Power
While most corporate servers average 15 percent utilization, virtualized servers can run at 60 to 80 percent. As a result, high-density power has become a near necessity. High-density power availability enables cloud service providers to deploy the very latest and most efficient equipment while minimizing the space required and, therefore, the cost to the business.
4. Broad Connectivity Choices
As virtualized infrastructures and the demand for “anywhere, anytime” access continue to increase, connectivity has become as important as processing power for users, meaning a company’s implementation of cloud computing will succeed or fail based on the quality of the end-user connection. Maximum bandwidths and multiple connectivity options will drive adoption of the pay-per-use model, and anything less will have the reverse effect. A carrier-neutral data center can provide the widest possible range of connectivity options, and with increased choice, comes more opportunities for lower costs.
5. Low Cloud Costs
Having economies of scale is the greatest benefit of scaling up the infrastructure supporting the cloud. Large data centers drive down the cost of hosting cloud computing infrastructures, multiplying the economies generated by the cloud delivery model and protecting profit margins for customers.
A recent University of California study showed that, when looking at storage, networking and processing costs, very large data centers reduce costs by five to seven times. (2) Additionally, the build-out cost per square-foot reduces data center capital costs by up to 60 percent, according to Tier 1 Research. (3)
Outsourcing cloud services also helps companies that cannot afford to build or continue to expand their own data center(s), thereby reducing their CapEx and OpEx. Facility costs are growing rapidly, and according to the Uptime Institute, the true costs of running a server are often four to five times the cost of the server alone over a five-to-10-year lifetime. (4) Using a third-party data center equates to great savings in both cost and administration for the business.
6. Dedicated Community
Moving the capabilities beyond simple colocation, some data center providers have built up specific “cloud communities” – or communities of interest – of organizations that benefit from colocating in close proximity to markets and within the same colocation services provider. For instance, a data center community built within the financial services sector, where speed of trading between businesses is crucial, will help companies gain the benefits of speed to market and proximity to financial markets.
Additionally, organizations within such communities gain direct access to financial exchanges, brokers, market data suppliers, and a large range of managed services providers and ISVs, many of which connect and use a common infrastructure and/or applications. This type of community approach also applies to substantial areas of interest among digital media and service providers, carriers and Internet exchange and enterprise sectors.
The Maturing Cloud
Ultimately, what will be vital to the success of cloud computing, and to those wanting to take full advantage of its benefits, is a reliable infrastructure that can scale, while simultaneously providing the required connectivity and security.
Colocation data centers are growing because they satisfy the basic need to access useful information, quickly, at lowest cost and minimal risk. More and more companies are realizing the benefits of having a portion of their data processing, storage and networking needs in a third-party facility to help ensure their operations can continue free of disruption.
Cloud computing is still an evolving paradigm that will take many years to fully mature. However, with improvements in understanding and awareness of security, infrastructure and regulatory procedures, and with solid infrastructure foundations in place, the cloud looks set to continue its path of growth and adoption.
End Notes: Back to Top
1. Worldwide IT Cloud Services Spending 2008-12. IDC, Oct 2008.
2. Above the Clouds: A Berkeley View of Cloud Computing. EECS Department University of California at Berkeley, Feb 2009.
3. Data Center Selection, Tier 1, Spring 2009.
4. A Simple Model for Determining True Total Cost of Ownership for Data Centers, 2007, Uptime Institute.Industry Perspectives is a content channel at Data Center Knowledge highlighting thought leadership in the data center arena. See our guidelines and submission process for information on participating. View previously published Industry Perspectives in our Knowledge Library.
Read More » -
Cloud Computing a Catalyst for Virtualization
July 21st, 2010 : Industry PerspectivesEllen Rubin is the founder and Vice President of Products for CloudSwitch, which allows enterprises to run applications in the cloud without re-architecting the application or changing existing management tools.
ELLEN RUBIN
CloudSwitchAt first glance, cloud computing can appear to be “virtualization taken to its logical conclusion.” After all, if the main benefit of virtualization is to consolidate data center resources and increase the speed of provisioning, then cloud is the ultimate pay-off: don’t own the resources at all and cut provisioning down to a few minutes with instant self-service gratification.
But upon further thought, cloud seems to be giving virtualization a return to the spotlight. A recent Gartner study noted that cloud computing is the number two priority for CIOs – trumped only by virtualization. And many panel discussions and sessions at recent cloud-related trade shows have addressed the benefits of extending virtualization footprints within the data center and starting to turn these into internal clouds, or at least “cloud-like” environments.
Still More Virtualization To Be Done
So is virtualization what’s old but new again? Remember that most enterprises have adopted virtualization in some way, but are only about 20% virtualized so far. So there’s plenty of room left to penetrate, and there’s still lots of opportunity for optimization and better management. Virtualization has primarily been used for consolidation, not for optimizing workload management and self-service. And many companies have large investments in existing hardware and virtualization licenses that they’d like to use more efficiently. In many ways, cloud computing has emerged on the scene as a disruptive force while virtualization is still an evolution in progress.
Read More » -
-
Energy Star for Data Centers: Help or Hype?
July 6th, 2010 : Industry PerspectivesDavid Dunn is Senior Vice President of Marketing and Business Development for CoreSite, which operates more than two million square feet of wholesale data center and colocation space.
DAVID DUNN
CoreSiteApproximately half of the nation’s electricity consumption comes from office and industrial buildings. Given the rising costs associated with direct and indirect energy consumption, it’s imperative that the public and private sectors focus on overall energy consumption and efficiency benchmarking. Data centers and their associated electrical consumption continue to grow as communications, information processing and storage demand increase rapidly. In 2006, the Environmental Protection Agency (EPA) estimated that data centers represented approximately 1.5 percent of the United State’s total electrical demand (to the tune of $4.5 billion) and that the combined data center consumption could double by 2011.
Given the rising energy consumption of data centers, the EPA sought to establish an Energy Star rating for this relatively new real estate asset class. In 2007, the federal agency collected data from 120 participating data centers. The sample ranged in size, location, and whether or not the data centers were stand-alone or within multi-use facilities. Just this month, the EPA approved an annual Energy Star label for data centers using Power Usage Effectiveness (PUE) as its primary metric.
How Energy Star Works and How It’s Measured
The annual Energy Star rating is based on a scale of 1 to 100 (with 100 being most efficient), benchmarked to similar buildings. Thus, a data center with a rating of 50 is in the 50th percentile for data centers or performs better than 50 percent of all similar buildings. To earn an Energy Star rating, a data center must earn a score of 75 or higher.The EPA selected the annual PUE metric as the method for determining efficiency. PUE is the most cited and best current single data point to use in benchmarking data center efficiency. As many people already know, PUE is broadly defined as “total facility energy divided by IT load” and generally runs between 1.4 and 3.0 (the lower the better, all else being equal).
Read More » -
The Advantages of Liquid Cooling
July 2nd, 2010 : Industry PerspectivesShlomo Novotny is the Chief Technology Officer of Coolcentric and Vice President and Chief Technology Officer of Vette Corporation.
SHLOMO NOVOTNY
CoolcentricData centers are an ever-growing part of our economy. The IT community is experiencing constantly increasing demands in areas such as Internet media and video, banking and finance, research, and government, just to name a few. Consequently, data centers continue to grow in both size and numbers. In addition, the performance of IT servers continues to follow Moore’s law. This improves the performance per dollar spent on IT equipment, but also increases the heat density inside the data center equipment. Driven by these factors, the cost of running a data center continues to grow, even as the cost of the IT performance continues to decline.
One of the most critical sustainability issues with many data centers today is cooling. Typically, air-cooled data center operators have managed heat density issues by spreading the load and under-populating racks. This is a result of the limitations of air cooling, which creates a very costly, complex, and inefficient infrastructure. Localized, passive, low-power dissipation liquid cooling devices at either rack level or rack proximity, when compared to traditional air-cooled methods, have the capability of reducing the power consumption of in-room cooling devices by as much as 90 percent. In addition, by allowing data centers to operate with higher-density racks, rack-level liquid cooling can reduce the data center IT footprint by as much as 80 percent.
Liquid-cooling technology also permits a “pay as you go” cooling implementation, saving significant capital expenditures (CAPEX) when constructing a new data center. Present air-cooled data center construction requires an implementation from “day 1″ of most of the cooling hardware for proper operation of the IT room. Localized liquid cooling is modular and would be implemented with IT expansion.
Water – an Efficient Cooling Alternative
The most energy-efficient and cost-effective way to remove the heat from the rack is by extracting the heat at the source (the rack), utilizing the airflow built in the rack through its servers and transporting the heat with liquid, which is significantly more efficient than air. Water is 3,400 times more efficient than air in removing heat. This heat extraction at the rack level could be done by a passive rear door heat exchanger (RDHx) or a side-car consisting of a liquid coil or by liquid-cooled cold plates mounted inside the servers for removal of heat from the power-dissipating components.
Alternatively, a hybrid of passive rear doors or side-cars and cold plates for high-power components inside the servers can be used. In any of these designs, one could eliminate or minimize the use of air cooling generated by the CRAC units. In addition, as much as 80 percent of the IT area could be reduced by densification utilizing liquid cooling. Furthermore, by fully populating the racks, one could obtain savings in CAPEX by eliminating excess racks and other ancillary equipment.
Free Cooling
A new trend is the introduction of air-side and water-side economizers to enable free cooling when external temperature permits. New data centers have increased their internal ambient temperature to the new American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE) permitted levels, thus maximizing the number of days per year external air could be used for cooling either through direct air-side economizers or through water-side economizers.
Although air-side economizers are very efficient for energy savings, they introduce the need for extensive filtration and use of internal blowers resulting in energy consumption and contamination reliability risks. Water cooling with water-side economizers take advantage of “free-cooling” while preserving the barrier between inside air and external air.
Thus, by extracting the heat at the source, new data centers could eliminate traditional air cooling by using only liquid-circulating pumps to transport the heat to a chiller or to a water-side economizer. A few traditional units may be needed for humidity control. Water cooling permits densification of the racks and the data centers while reducing the energy consumption significantly.
Moving to More Efficient And Sustainable Operations
Data center operations have historically focused on addressing the accelerating demands of data center customers. Because of their primary focus on growth, data centers have become highly inefficient operations. Today, with other factors such as rising energy costs, limited space, and power and green initiatives, management’s focus is squarely on the cost and operational inefficiencies that have been building up in data centers.
With infrastructure costs now exceeding the costs of the IT equipment itself, management must focus on gaining significant efficiencies in the data centers, which are becoming the factories of the 21st century. With cooling being a major portion of data center infrastructure costs, sizable efficiencies can be found by rethinking how data centers are cooled.
Localized liquid cooling at rack level and rack proximity eliminates one of the most inefficient elements of data center infrastructure cooling, substantially reduces energy consumption, and allows for higher rack-level compute density. In addition, liquid cooling enables cooling modularity with a “pay as you grow” investment and ensures efficient infrastructure redundancy and availability. Localized liquid cooling is no longer simply a hot-spot solution, but is now a critical component in the basis of design for new, sustainable data centers.
References
1. American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE), 1 August 2008, 2008 ASHRAE Environmental Guidelines for Datacom Equipment, available at http://tc99.ashraetcs.org/documents/ASHRAE_Extended_Environmental_Envelope_Final_Aug_1_2008.pdf.2. American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE), 2005, Datacom Equipment Power Trends and Cooling Applications.
3. Koomey, J.G., Belady, C., Patterson, M., Santos, A., Lange, K-D., 17 August 2009, Assessing Trends over Time in Performance, Costs, and Energy Use for Servers.
4. Kurkjian, C., PE, 18 May 2009, Data Center Energy Savings – by the Numbers.
5. Schmidt, R., and lyengar, M., July 2009, IBM’s Rear Door Heat Exchanger and the New ASHRAE Recommended Environmental Guidelines, Proceedings of IPACK 2009 and ASME InterPACK 2009.
6. Sun Microsystems, 26 June 2008, Energy-Efficient Modular Cooling Systems, Case Study presented at the SVLG Data Center Summit.
7. United States Environmental Protection Agency, 2 August 2007, Report to Congress on Server and Data Center Efficiency, available at http://energystar.gov/ia/partners/prod_development/downloads/EPA_Datacenter_Report_Congress_Final1.pdf.
Industry Perspectives is a content channel at Data Center Knowledge highlighting thought leadership in the data center arena. See our guidelines and submission process for information on participating. View previously published Industry Perspectives in our Knowledge Library.
Read More » -
Air Economizers Can Work in Warm Climates
June 23rd, 2010 : Industry PerspectivesVali Sorell, P.E., is a lead technical resource for mechanical design in Syska Hennessy’s Critical Facilities Group. Syska Hennessy provides facility management consulting, engineering design, structured cabling/audiovisual/security design, commissioning and construction services.
VALI SORELL
Syska HennessyDesigners have long assumed that data center projects should not use outside air economizers (a.k.a. airside economizers) in warm climates. The reasons are usually obvious – when it’s 90°F or higher outdoors for much of the year, there couldn’t possibly be any benefit in bringing in that warm outside air. However, when specifically considering data center applications, there are several reasons why this logic is faulty.
Benefits from Using ‘Warm’ External Air
An important design consideration when sizing the cooling devices for data centers is that the higher the supply air temperature that goes into a cooled space, the more efficient is the cooling equipment. ASHRAE Technical Committee 9.9 publishes the recommended “Thermal Envelope” for IT equipment – a range defined as 64.4°F to 80.6°F at the INLET to the equipment.If air flow management strategies are well implemented in the computer space to assure that the supply air temperature and the IT equipment INLET temperatures are nearly the same, then substantial first cost and operating cost savings can be realized by selecting as high a supply air temperature as possible. A good supply air temperature to design for is 75°F. Although it’s not quite as aggressive as selecting for 80.6°F, it’s much more aggressive than the typical supply air temperatures from a few years ago, which often hovered in the 55°F to 60°F range.
Another aspect to consider is that most IT equipment takes in air through the front of the equipment, then adds the rejected heat from the internal components (such as processors, power supplies, disk drives, and memory), and finally rejects the heat at the back. Typically, the air exiting this equipment can be 30°F warmer than the air entering it. Assuming once again that the temperature of the air entering the IT equipment is at 75°F, the typical discharge temperature should hover at 105°F!
Humidity is a Factor in Cooling
So, the big question is this: Which airstream requires less energy to cool to 75°F? Is it the outdoor air at 90°F or the air returning from the back of the equipment at 105°F? The simple answer would be the air at 90°F. However, reality is not quite that simple because the 105°F at the back of the servers is usually extremely dry; on the other hand, the 90°F outdoor air may be very humid. Yet, these humid conditions can be accounted for when considering hours of availability of airside economizers. Even after those humid hours are excluded from our count, there are still many hours of economizer availability in warm climates.Compare with Cooling Office Space
To put these hours of availability into perspective, consider that of the 8,760 hours in a year, the hours of airside economizer availability in areas such as Dallas, Raleigh, and Phoenix are somewhere in the range of 4,000 to 5,000 hours. Commercial office spaces with normal 8 a.m. to 5 p.m. operation run for approximately 2,500 hours per year. The airside economizer for data centers can enable a data center to run for more hours in a year than ALL the operating hours of a typical office building without ever turning on its cooling plant.In summary, one should not eliminate the use of an outside air economizer for a data center simply because of a perception that the climate may be too warm. The updated “Thermal Envelope” has allowed for many more hours of economizer use, and there is promise in the not too distant future that the envelope will be expanded even more. Only a complete Total Cost of Ownership analysis can determine whether there is enough availability of free cooling to justify the extra cost of the economizer.
Industry Perspectives is a content channel at Data Center Knowledge highlighting thought leadership in the data center arena. See our guidelines and submission process for information on participating. View previously published Industry Perspectives in our Knowledge Library.
Read More » -
Government Taps the Power of Cloud Computing
June 22nd, 2010 : Industry PerspectivesBruce Hart is the Chief Operating Officer of Terremark Federal Group which provides government agencies with a complete suite of managed infrastructure services for mission-critical federal applications, including cloud computing, colocation, network services, managed hosting and security services.
BRUCE HART
TerremarkSince taking office, the Obama administration has pushed the Federal government to improve efficiency in its IT systems and provide citizens with greater transparency through the use of innovative technology. Following this mandate, Federal CIO Vivek Kundra has recently promoted virtualizing and consolidating data centers and operations, and ultimately shifting government IT to a cloud-computing business model. This has led major governmental agencies to identify projects and IT operations that can benefit from moving to the cloud.
Until now, security concerns over physical access, information protection, privacy and control of the information impacted the way governmental agencies have built their infrastructure. However, increasingly high costs with few or no economies of scale and the inability of several agencies to share or aggregate information across departments in a timely manner are causing real problems. As a result, the government’s ability to respond to the needs of the public, while effectively protecting its infrastructure from 21st century threats, such as techno-terrorism and cyber-security attacks, are being affected.
The President’s Memorandum on Transparency and Open Government, issued on January 21, 2009, has been a step in the right direction, requiring agencies to develop public-facing web sites and post up-to-date information to support federal transparency, participation and collaboration goals. The memorandum has also set aggressive timelines for meeting these goals, instructing agencies to take prompt steps by making information available online in open formats that can be easily retrieved, downloaded, indexed, and searched by commonly used web search applications. However, creating public-facing web sites and converting stored data to user-friendly formats poses significant IT infrastructure and security challenges.
Can Cloud Computing Meet These New Infrastructure Demands?
With agencies having traditionally deployed and managed their own IT infrastructure, most intra-agency information was held captive by the constraints of security and compliance concerns. Cloud computing represents a fundamental change in managing and delivering information, because the information owners and users no longer need to work directly with the supporting physical infrastructure to benefit from the services and information it delivers.By enabling convenient, on-demand network access to a shared pool of configurable computing resources (e.g., networks, servers, storage, applications, and services) that can be rapidly provisioned and released with minimal management effort or service provider interaction, cloud computing offers a number of marked advantages to agencies seeking to meet these new open government requirements and make more effective, collaborative use of their data.
Is There a Model to Increase Scalability while Reducing Infrastructure Costs?
Making agency data publicly accessible or available to other departments for collaborative action means that government CIOs will face a common challenge: how to support unpredictable usage peaks and patterns as interaction that is not easily modeled ebbs and flows. Traffic increases dramatically and performance degrades, when highly anticipated statistics are released, during times of natural disasters or other crises or at peak reporting times. As a growing volume of data is made public or otherwise shared, traditional infrastructure cannot scale to support surge requirements or the real-time responsiveness required. Building extra capacity into the infrastructure to accommodate usage peaks results in idle capacity and is not a cost-effective strategy.Cloud computing revolutionizes infrastructure cost and scalability decisions. First, IT decision-makers can leverage a massively scalable, shared virtualized infrastructure to avoid capital expenditures and reduce operating expenses. Agencies don’t have to gain approval for large capital expenditures, and can avoid the costs of hardware, software, salaries for specialized IT resources, training and ongoing support. Cloud computing also enables granular scalability, scaling up and down as needed to deliver guaranteed resources on demand.
If traffic volume spikes, additional capacity can be immediately enabled, either directly via a provisioning interface or programmatically via the use of application programming interfaces (APIs). And those resources can be retired just as easily after the event. With dynamic access to capacity on demand, agencies are not faced with building an infrastructure sized to accommodate usage peaks. And as an added benefit, agencies need only to pay for what they use, improving asset utilization and simplifying financial decision-making.
Ensuring Security and Compliance on The Cloud
Security and privacy concerns often present a strong barrier-to-entry and federal government CIOs need to find ways to secure their investments in the cloud. Key in this effort is the ability to balance mandated, broader access to their data with the need to secure the content of their information and to comply with various federal protocols for IT systems security. Commercial cloud infrastructure, like traditional IT infrastructure, can and must be audited and certified for a range of requirements under federal protocols.Multi-layer security services can be delivered through the cloud to defend websites, applications and data from malicious attacks, and cloud computing providers should employ these services while enabling agencies to acquire the appropriate level of risk protection. A service provider’s cloud computing infrastructure should also provide highly experienced, certified professionals, who are deeply familiar with government security requirements and can audit and certify an agency’s cloud infrastructure.
Advanced, managed security services should also be delivered through the cloud to fully protect mission-critical data and services. Service providers should be able to deliver services that will address federal best practices for a range of requirements, including logging, information security management, application firewalls, two-factor authentication, full packet analysis and vulnerability management. Providers must also be able to help agencies prepare and undergo required certifications and accreditations for cloud infrastructure, including conducting assessments and audits to ensure standards are met, as well as working with agency security and IT teams to enact policy for standards. Overall, the economies of cloud computing permit agencies to redirect resources toward even more stringent security provisions than they might have enjoyed before.
A Success Story: USA.gov and Data.gov in The Cloud
Today, the use of cloud computing services by agencies is poised for rapid gains, as seen in the case of USA.gov and Data.gov, which can now better benefit the public through the massive amounts of government-held information they offer. With an initial goal to cut down the cost of managing these sites by 50 percent, the General Services Administration (GSA) turned to Terremark’s Enterprise Cloud infrastructure to provide hosting, storage and disaster recovery services for the web portal that serves as the primary source of information about U.S. federal, state and local government services, such as grant instructions, consumer guides, health and nutrition updates, tax forms, voter registration, student financial aid and critical national disaster information. USA.gov had previously been deployed in-house and used a virtualized approach. It migrated to a service provider cloud infrastructure within 10 days.Now USA.gov can maintain a small persistent footprint and deploy on-demand scaling as traffic fluctuates. When traffic is at normal levels, the GSA pays only a contracted baseline fee, but it can seamlessly accommodate volume spikes when needed. Migration to the cloud has enabled GSA to avoid paying for idle server time without compromising its ability to deliver real-time performance for users.
As Federal CIO Vivek Kundra has repeatedly said publicly, the GSA reduced annual costs for this service from $2.5 million to $800,000 by moving it to cloud technology. This agile computing infrastructure allows GSA to deploy upgrades to USA.gov in 24 hours instead of the six months that would otherwise be required in a traditional infrastructure model.
In addition, the enterprise-class security that cloud providers are building into their cloud offerings allows for services to be audited and certified to meet government and agency-specific requirements.
Does Cloud Computing Work for All?
Today, there is no better model to help organizations improve IT efficiencies, reduce operating costs, and ensure data security at a minimum risk. Agencies considering a cloud computing solution can benefit from adopting a service with the same characteristics as the USA.gov and Data.gov cloud computing solutions. To be successful though, it is critical for both the cloud computing service providers and government users to understand the drivers and challenges in federal, state and local government market, identify the areas that cloud computing can bring the most IT efficiencies, and raise the levels of awareness and trust in the model.Industry Perspectives is a content channel at Data Center Knowledge highlighting thought leadership in the data center arena. See our guidelines and submission process for information on participating. View previously published Industry Perspectives in our Knowledge Library.
Read More » -
Bridging the Gap Between IT and Facilities
June 8th, 2010 : Industry PerspectivesMark Harris is Vice President of Product Management at Modius, which develops intelligent measurement systems for mission-critical facilities.
MARK HARRIS
ModiusOver the past 25 years, Information Technology infrastructure has emerged as one of the enterprise’s most valuable and highly visible assets. IT touches nearly all aspects of a business, including the way products are developed, manufactured and delivered. Improved communication also enables innovation while strengthening corporate culture.
As such, it should be no surprise that IT infrastructure – commonly considered one of the top competitive corporate advantages – now consumes 2 to 5 percent of a typical company’s gross revenues. Despite this, the vast majority of companies worldwide today build IT infrastructure upon an assumption that essential supporting services (energy, space and cooling) will properly be there. This common yet dangerous assumption dramatically increases the risk of future service disruption and unnecessary maintenance costs.
So how did one of the most valuable corporate assets come to be built upon such a precarious foundation? The world of IT and the world of Facilities are very different, and arose from two very different sets of business needs. IT structures were developed to manage information flow, while facilities were part of a real-estate function.
This lineage created separate organizations with incompatible best-practices, and often inadequate cooperation. The gap between Facilities and IT today is very real and is usually recognized only when problems arise. In a minor example, a data center could lack the capacity for the hardware necessary to support a newly approved and funded business application. In a worst-case scenario, improper IT-Facilities coordination could result in catastrophic failure within the data center.
IT-Facilities Gap Equals Low Visibility
Read More »
The IT organization spends a great deal of resources ensuring that the logical flow of information is continuously optimized and guaranteed within the constraints of the IT hardware itself. However, the IT-Facilities gap creates a situation in which the IT-operations teams have little – if any – visibility into the normal performance characteristics of the facilities on a day-to-day basis. When facilities fail to support the IT hardware, the gap manifests itself as an outage of production systems. -
The Data Center Temperature Debate
June 7th, 2010 : Industry PerspectivesJason Friedler is Head of Hosting, Telstra International and works within Telstra’s Product Management area.
JASON FRIEDLER
Telstra InternationalIn 2010, the energy consumption of the data center industry has continued to climb the political and financial agendas. Tightened budgets mean that companies around the world are looking to reduce energy costs, while the regulatory environment is evolving to a state whereby heavy emitters could be penalized financially.
This has already happened in the UK, where the mandatory CRC Energy Efficiency Scheme was formally established in April of this year, and there is a genuine concern that the industry could be put under pressure from enforced government legislation in other parts of the world.
There has been complex and overlapping advice from all sides on how these pressures can be alleviated, which has meant one of the simplest methods to reduce power consumption has been all but completely drowned out: reducing data center cooling.
The majority of data centres around the world are cooled to approximately 72 degrees Fahrenheit (22 degrees Celsius) yet both data center providers and manufacturers (such as HP, IBM and Sun Microsystems) all state that server equipment will function perfectly at 80 degrees, if not higher. An estimated four percent reduction in energy costs can be gained for every degree of upward change in temperature – a significant saving both in costs and carbon emissions.
However, with reliability and availability still the key concerns for IT managers, many hosting customers are still looking to err on the side of caution and maintain the status quo in terms of the temperature of their racks.
Customer concern
Continued financial pressures on CIOs and CFOs mean our customers are unsurprisingly keen to discuss methods through which we can help them reduce energy costs. But on the subject of data center temperature, a variety of concerns linger.Many customers of managed hosting providers, for example, are reluctant to alter agreed SLAs, often a necessity if the cooling is to be reduced. But, the biggest and most common concern is often the notion that increases in temperature will affect overall reliability. This varies from the effect on server recovery time, to how potential increases in humidity would lead to greater condensation levels. There are also concerns of whether costs from equipment downtime caused by this will offset the cost savings from reduced cooling.
Of course, the biggest mitigating factor in this is the hardware the customer is using, and it is hardware vendors’ warranties that are the biggest means to allay these customer fears. Generally speaking, modern data center equipment comes with guarantees of continuous functionality at temperatures ranging from 78 degrees Fahrenheit to as high as 95 degrees.
It will only be through a unified educational program – from data center operators, hardware vendors and industry bodies alike – that the fears of end-user companies can be allayed. The industry has a responsibility to minimize its energy consumption, and self-governance in this manner will reduce the ever-present risk of enforced legislation.
Unified argument
Although never articulated by an industry body, the “the cooler is better” data center paradigm seems hard to shake for the majority of customers.The problem up until now is that messaging in this area has not been consistent. Understandably, vendors’ communication in this area has been focused on their own specific products – there has never been a sustained industry effort to promote the benefits, both in terms of carbon emissions as well as cost savings.
A greater debate needs to take place. The industry as a whole needs to work together in order to reduce our energy consumption, and a centralized campaign on data center temperature could be one of the most effective means to achieve this.
There are however, encouraging signs of more unified efforts to reduce the industry’s energy consumption. For example, the recent landmark agreement between the Green Grid, EU Code of Conduct, and governmental organisations in the US and Japan on the guiding principles of data centre energy efficiency metrics, shows the potential for international cooperation, with an ultimate goal of creating a set of globally accepted metrics. It is through independent organizations such as these that the message will best reach end-user companies.
Through greater collaboration and a more sustained educational push, the industry can reduce both the internal and external pressures to reduce energy consumption; raising data center temperature norms around the globe would be a great place to start.
Industry Perspectives is a content channel at Data Center Knowledge highlighting thought leadership in the data center arena. See our guidelines and submission process for information on participating. View previously published Industry Perspectives in our Knowledge Library.
Read More » -
The Competitive Threat of Public Clouds
June 4th, 2010 : Industry PerspectivesRodrigo Flores is the founder and chief technology officer of newScale, Inc. He co-authored the book “Defining IT Success through the Service Catalog” and has led the development of a formal ITIL certification for catalog practitioners.
RODRIGO FLORES
newScaleThe arrival of new data center service providers “in the cloud” such as Google, Amazon and Microsoft is changing the face of IT services, and for good reason: it’s increasing choice, while lowering the costs of infrastructure services. It’s also creating a time bomb for IT operations.
IT operations groups are going to be increasingly evaluated against the service and customer satisfaction levels provided by public clouds. One day soon, the CFO may walk into the data center and ask, “What is the cost per hour for internal infrastructure, how do IT operations costs compare to public clouds, and which service levels do IT operations provide?” That day will happen this year.
Many IT operations groups are responding by planning internal clouds so they can have more control and visibility, while taking advantage of their investment in IT resources. While that’s a good direction, it may come too late, at too high a cost, and not deliver the value the customer, or employee, expects. It’s hard to compete on price with groups (i.e., Amazon) who buy truckloads of servers per week.
For IT operations to stack up to public clouds, it must understand that cloud computing is an operating model underpinned by virtualization technology. And just as the virtualization layer abstracts the underlying hardware, there’s a front-office service definition layer which abstracts the infrastructure and operations from the customer.
The control point will be a front office that clearly explains what IT offers, how to contract it, the costs, policies, service levels and provides visibility into delivery from multiple sources. IT teams need to make IT self-service for their own resources as easy and robust as it is for public clouds.
The next three recommendations will help IT operations buy time and deliver assets and learning critical to the success of a private cloud.
First, give up the fight: Enable the safe, controlled use of public clouds. There’s plenty of anecdotal and survey data indicating the use of public clouds by developers is large. A newScale informal poll in April found that about 40% of enterprises are using clouds – rogue, uncontrolled, under the covers, maybe. But they are using public clouds.
The new role for IT is to become the trusted broker that actually enables enterprise agility. It’s not the big that eat the small, it’s the fast that eat the slow.
Read More »
