Why are so many still using guesswork to determine their needs for power?

It is 2010 & so many data center & IT managers are still relying on manual derated name plate calculations to manage the power required throughout their power chain even though many of these data centers are on the verge of running out of power & many have experienced outages due to tripped circuits. So many data center & IT managers come to us looking for real-time monitoring of power, many solutions are evaluated, but few ever get implemented. I'm trying to figure out why many are not investing in real-time power management.

If you read the Green Grid's white paper "Proper Sizing of IT Power and Cooling Load" it discusses the fluctuations in IT power draw due to inlet temperature changes, server component changes, virtualization, etc. http://www.thegreengrid.org/en/Global/Content/white-papers/Proper-Sizing-of-IT-Power-and-Cooling-Loads

I don't think we can underestimate the potential danger in using derated nameplate information to calculate power requirements. Unvirtualized servers typically use 15% of the processing power, virtualized we see #'s in the 60-95% range of processing utilization, this directly correlates to #'s closer to nameplate values as the Green Grid pointed out in the white paper. Most IT organizations are rapidly adapting virtualization technology to consolidate and operate more efficiently at the same time, which is a good thing, but it is putting rapid pressure on previously underutilized power infrastructures in data centers.

With so many variables to account for how can one depend on derated calculation tools? With so many real-time tools available to measure & trend power accurately including; branch circuit monitoring, outlet level monitored power strips, in-line power meters, IPMI and extensive software options why are so many still trying to use derated calculations to guesstimate the power they'll need for higher density virtualized deployments? This guesswork leads to potential circuit breaker trips & designed inefficiencies throughout the entire power chain. I am amazed with rising power costs, less power capacity available and so many looking to operate a more efficient "greener" data center footprint that so few are investing in real-time power monitoring tools that will allow them to plan & manage capacity effectively.

What is your definition of a "Green" Data Center solution?

Is your organization looking for "Green" Data Center Solutions or are you looking to incorporate "Green" into your Data Center Design in 2010 or in this decade? Below are some thoughts on this important issue in regards to building "Green" Data Centers. We're interested in hearing your opinions & ideas as well.

For the most part “Green” Solutions for the Data Center, is in my opinion a bit of an oxymoron, because most supposed “Green” solutions still have a carbon footprint & typically use power generated by fossil fuels in the Data Center industry. We also find that rarely are Data Center owners & operators willing to reduce availability to improve the efficiency of their Data Center. That being said, our design philosophy is to design “Greener” Data Center Infrastructure technologies where possible into any proposed new builds, renovations and upgrades for Data Center facilities.

In our opinion the 1st step towards “Greener” Data Centers is collecting accurate measurements & trending the environmentals in your Data Center facilities so we can model proposed changes & fine tune the efficiency. PTS has been running several monitoring & management tools in our own Data Center facility as well as in our clients Data Centers for several years. We use this base knowledge as well as industry best practices & PTS’ proven trade secrets during an engagement for design to propose “Greener” solutions where applicable & in line with the rest of the key design criteria for a project. In our experience many “Green” solutions such as solar & hydro power rarely can make a impact to a Data Center Design, however using water or air side economizers to take advantage of the free cooling days available in an applicable climate can provide a reasonable ROI while “Greening” the Data Center.

In addition by eliminating air mixing in Data Centers, we reduce the power consumed by the HVAC systems supporting a Data Center, and we prove these savings in cooling through CFD modeling before making investments. ASHRAE has widened the temperature range in the new TC9.9 recommendations for Data Center operations, but before we embrace this “Greener” standard and go maximizing the set points for supply & return air; we first must make sure that air mixing has been eliminated as much as possible because as we raise set points, “hot spot” issues & inefficiencies will be amplified, second raising set points reduces the availability of the Data Center so we have to make sure that any proposed increases in set point to make a Data Center “Greener” are in line with the availability requirements established for the Key Design Criteria of a project, third many servers fans will spin faster as the intake temperature rise so there is an inflection point where raising set points further will not continue to lower power consumption.

Focusing on effective Data Center capacity management is key to any "Greening" initiative:
• Better predictability of space, power, and cooling capacity and redundancy limits means more time to plan on ways to mitigate their affect
• Increased real-time availability of IT operations as a result of an enhanced understanding of the present state of the power and cooling infrastructure and environment
• Reduced operating cost from energy usage effectiveness and efficiency as well as operator effectiveness from the use of automated tool sets

In our experience most facility oriented "Greener" solutions provide only a fraction of the efficiency gains found in IT focused solutions such as: server consolidation, virtualization & data deduplication. That's not saying we shouldn't consider the facility oriented "Greener" solutions, especially if they fall in line with our design criteria & ROI needs, but it is saying we should focus on the IT side 1st because of the greater savings & our capacity requirements will be appropriately defined if we become IT efficient first.

The Devils in the Details - Enhanced SAN & Switching Solutions for Next Gen Data Centers

PTS is pleased to announce a new educational event, The Devils in the Details - Enhanced SAN & Switching Solutions for Next Generation Data Centers, in which we will introduce several new technology-based solutions, which will enhance data center optimization, consolidation, virtualization, and disaster recovery.

Prior to an upcoming New Jersey Devils versus Philadelphia Flyers hockey game we will leverage our understanding of the synergies between Facility and IT Infrastructure and introduce two highly efficient and cost effective solutions. These solutions can dramatically reduce the costs and complexity of your IT environment while increasing your ability to adapt, manage, and grow your storage and computing infrastructure. Learn about flexible, scalable solutions that will meet your business and security challenges and better understand how IT requirements drive new needs for your data center support infrastructure.

February 10, 2010
NJ Devils vs. Philadelphia Flyers
Prudential Center, Newark
Presentation with dinner/drinks starting at 5:00 PM
Game time 7:00 PM

Join us for an informative discussion and learn about:

• PTS Data Center Solutions' strategic data center design approach combining both IT and support infrastructure expertise to design, manage and operate a superior data center.
• Dell EqualLogic PS Series SANs designed to cost-effectively integrate advanced data and disaster protection features directly with VMware virtual infrastructure to help provide seamless data protection and disaster recovery management.
• Enterasys S-Series® enterprise switching and routing solutions specifically designed for high speed core and SAN deployments.

Click here to learn more

Please RSVP by 1/5/2010. Tickets are limited and available on a first-come basis.

Data Center World, Spring 2010

PTS Data Center Solutions will be presenting and exhibiting at this spring’s Data Center World Event, held in Nashville from March 7-11. Data Center World is the largest global event of its kind and has been named one of the 50 fastest growing tradeshows in the U.S. It is the leading educational conference for data center professionals.

Our team will host roundtable discussion on Information Technology Infrastructure Library (ITIL) & ITSM Metrics Programs for the data center. This presentation will take a nuts and bolts approach to setting up an ITSM metrics program and will discuss how this process will allow IT to present data to senior management.

We’re also hosting a product information session, titled “Data Center Maintenance Management Software - Computerized Maintenance Management for the Data Center”, during which we’ll demonstrate how you can use best-in-class solutions to more effectively manage support infrastructure. The presentation will discuss Computerized Maintenance Management Systems (CMMS) and present our new Data Center Maintenance Management Software (DCMMS) Solution. This innovative software application from PTS Data Center Solutions allows the user to manage assets and parts, estimate and manage maintenance costs, track recurring problems to pinpoint those that may lead to more critical issues, and generate work orders with the details needed to properly perform preventative maintenance.

In addition, I’d like to invite you to visit us at booth #739 where you can get a first-hand look at our specially designed DCMMS solution. To learn more, please contact Amy Yencer at AYencer@PTSdcs.com (201-337-3833 x128).

To register for the event, please visit http://www.datacenterworld.com/. See you in Nashville!

PTS Announces a Strategic Distribution Relationship with Dell Corporation

I’m excited to announce that PTS has launched a strategic distribution relationship with Dell Corporation which includes the full breadth of Dell products targeted for the small to mid-size business segment.

As a leading data center design and turnkey solutions provider, we’ve been approached by many clients asking us to help them reduce overall data center operational costs through power efficiency analysis and improvements. The relationship with Dell allows us to provide consultative support by focusing upon key technology energy drains in the data center, namely routing, server processing, storage and security-based infrastructure products.

By partnering with Dell, we see ourselves as partnering with a best-of-breed solutions provider for our mid-market clients. Depending upon client applications, a host of solutions such as the Dell EqualLogic iSCSI storage family and PowerEdge blade and rack servers can improve power efficiencies, support growth within the data center and provide superior price / performance returns.

To learn more, please contact us today.

‘Lights Out’ Data Center Management

In a recent post at The Data Center Journal, titled “Save some money – work with outsiders,” Rakesh Dogra discusses the new trend to minimize power bills using Lights-Out data center and remote management. [As a side note, way back in 2006 we blogged about how “dim” data center designs are a realistic goal for most companies. You can read that post here.]

Dogra explains that the use of these tactics can lead to major cost savings. He suggests that, looking at your IT, security and facilities staff, it is unwise to cut back on security personnel but it may be prudent to use remote management to replace portions of the IT staff. Additional benefits may include:

• A lesser possibility of accidents and security breaches since fewer people will have physical access to a computer room.
• Response time is boosted with remote bios level access to a data center’s servers.
• Geographical independence can also be achieved through this system.

A potential downside of this system is that a “data center will need people within its premises too to fire fight something going wrong like outages. Also, a data center manager may not find someone with the required amount of experience and expertise to fend off crisis when it happens.”

It is surely a best practice to consider operating as ‘lights out’ a data center as possible, as the author suggests.

For PTS, the real secret to realizing operational costs savings from reduced energy consumption has less to do with facility based solutions than it does with IT. Our position is that there is far more operational cost savings potential coming from virtualizing servers and storage.

To prove the point, in 2010, PTS will perform a network re-design effort of our own operations and provide detailed documentation and analysis of the before and after conditions of our data center energy usage. So, stay tuned...

Data Center Education Series Expands to More Dates, Cities

I'm pleased to announce the expansion of our Data Center Education Series to include more dates and cities.

If you're not already familiar with the program, our Data Center Education Series provides students with comprehensive, vendor-neutral, module based training led by the data center design experts from PTS. The training series discusses the most pertinent topics in the data center industry, tying in case studies and real world situations to provide the knowledge IT professionals need to understand, operate, manage, and improve their data centers – ultimately reducing operating costs and improving service delivery to users.

For instance, the Data Center Infrastructure Management course will show attendees:

• Power and cooling infrastructure in the data center and how hardware and configuration impact energy efficiency and availability
• Methods to improve data center energy efficiency
• Management tools available to help you optimize data center performance and availability
• Practical steps to implement ITIL
• How to measure the IT Service Management metrics that really matter
• How to monitor your data center to optimize performance and availability
• What impacts data center availability and how you can improve it

The course schedule for the first half of 2010 is as follows:

• Jan 17 - 19, 2010 in San Francisco, CA
• Jan 25 - 27, 2010 in Washington, DC
• Feb 8 - 10, 2010 in Chicago (Schaumburg), IL
• Feb 22 - 24, 2010 in Dallas, TX
• Mar 15 - 17, 2010 in Ottawa, ON
• Mar 22 - 24, 2010 in San Jose, CA
• Apr 19 - 21, 2010 in Washington, DC
• Apr 26 - 28, 2010 in New York, NY
• May 3 - 5, 2010 in Chicago (Schaumburg), IL
• May 10 - 12, 2010 in Atlanta, GA
• May 17 - 19, 2010 in Dallas, TX

To learn more about the Data Center Infrastructure Management course and to register, visit http://www.data-center-education.com/DataCenterInfrastructureManagement.asp.

Related courses, taught by experts in each field, are also available and include:

• How to Get Started with ITIL (Information Technology Infrastructure Library)
• ITIL Service Capability: Planning, Protection and Optimization
• ITIL Service Capability: Service Offerings and Agreements
• ITIL Service Catalog
• ITIL Service Lifecycle: Service Strategy
• ITIL v3 Foundation
• Understanding Networking Fundamentals
• TCP/IP Networking
• Telecommunications Fundamentals
• Voice over IP Foundations

For more information regarding each of the courses including costs and the dates and cities where they are available, visit our Data Center Education website.

PTS Data Center Solutions Showcase

PTS' growth of solutions to design, build and manage the data center has never been stronger.This post showcases two industry-leading solutions that you may want to consider for your own data center.

Energy Monitoring Systems

Would device-level power consumption monitoring help you manage costs for effectively?

Working in conjunction with Packet Power, PTS is pleased to announce a cost effective per-device energy monitoring system which is easy to deploy and highly accurate. The system provides device level monitoring & trending without having to change out power supplies or PDU's.

Features include:

• All billing-quality power monitoring hardware is built into standard equipment power supply cables.
• All standard cable connector con-figurations (C13/C14, C19/C20 etc.) as well as voltages and current loads are available. PP Monitoring Nodes
• Data collection network automatically supports thousands of devices in a single facility, is configuration-free, entirely wireless, secure and operates independently of any Wi-Fi or other networking infrastructure.
• All information gathered by our system and all advanced monitoring, billing and management functions are accessible via the web & e-mail.
• All available without any additional hardware or software.
• All information generated by the system can be integrated with your existing operations management and billing systems.

Learn More...

Air Curtains - A Green Alternative

Reduce data center cooling costs by directing cold air where it is needed most - through the computer racks! Air Curtains and strip doors separate cold air and warm air aisles, maximizing the dynamics of air flow to cool your data center. A system can pay for itself in months!

• Save energy on both air conditioning and fan systems - 15% and 67% respectively (according to a study by the Lawrence Berkeley National Laboratory)
• The Air Curtain product line includes transparent curtains, strip doors, panels and patented hardware; create a solution specific to your needs.
• Specially formulated vinyls are low-outgassing and anti-static while meeting ASTM and NFPA fire retardancy requirements.
• Hardware is also designed so curtains fall away in the case of fire, allowing fire sprinklers full operating range.

Learn More...

And remember, PTS typically designs these solutions and performs Computational Fluid Dynamics (CFD) modeling prior to deployment to guarantee the results, savings & performance. To learn more, please contact us today.

Introducing PTS' Information Technology Solutions Group

For years our team has provided exceptional service to analyze, survey, design, plan, commission and manage Data Centers for our clients. We are now pleased to leverage our expertise in All Things Data Center to launch an exciting new division, PTS Information Technology Solutions Group (ITSG).

ITSG provides information technology based consulting, design, implementation/integration, and ongoing support services as well as IT infrastructure solutions to companies nationwide. ITSG extends PTS' data center expertise beyond facility planning, design, engineering, construction, and maintenance to include service and solutions pertaining to:

• LAN/WAN Networking
• Information/Network Security
• Servers & Systems
• Virtualization Technologies
• Enterprise Storage
• Unified Communications
• Software
• Application Development

ITSG's services and solutions are tailored specifically to the needs of our client's project needs, including:

• Technology Roadmaps
• Data Center Relocation
• Consolidation
• Technology Refresh

ITSG follows our proven project delivery process:



PTS' goal is to provide our clients with 100% turnkey, people, process, and technology solutions from data center facility to IT operations.

ITSG will be led by Rich Horowitz, an industry veteran, who has been involved in all facets of the technology industry for more than 20 years. Rich is actively involved in business development, operations, Channel Partner development, Mergers & Acquisitions, and services delivery. Rich has been involved in approx $700 million in technology hardware sales, software sales and technical services engagements. Rich will be responsible for establishing and strengthening the PTS IT Solutions Group brand, and working with our clients to understand their needs and how we can provide value to them.

To learn more, please contact us today.

Intel's Active Management Technology {AMT} provides KVM access & console access eliminating the need for external KVMs or console servers?

There has been a lot of talk in the industry on how Intels new onboard AMT could replace service processors, such as; ILO, DRAC, RSA & ILOM.

http://sof​tware.inte​l.com/en-u​s/blogs/20​09/10/18/i​ntel-kvm-t​his-is-you​r-sol-on-s​teroids/

According to the Blog the local user has to allow the remote user in so I’m not sure this is a valid KVM or ILO replacement as much as a replacement for desktop tools like PCAnywhere & GoToMyPC?

If Intel does have a strategy to lead server remote access & control with AMT, I don't believe it will work. 1st of all, I'd like to point out AMT is an Intel product so it isn't an open standard for a management console. What about those who are buying AMD Opteron processors and/or Sun UltraSparc?

Secondly an open standard for server managment is already well underway from 1998 with IPMI & I think we need to look at what has transpired with IPMI to see what if any support will be given to AMT at the server level. IPMI was originally proposed in 1998 and driven by market leaders Intel, Dell, HP and NEC. Since then IPMI has been adopted by more than 150 other companies, including IBM, Sun, and every major server platform vendor. IPMI is now on its third major release. A significant percentage of rackoptimized servers and most blade computing platforms now include some form of built-in server processor technology that can work with IPMI. Obviously, IPMI data from across the enterprise can only be useful if management teams can view it from a common console. Otherwise, it would offer no advantages over a fragmented, vendor-specific management architecture. Thus, to take full advantage of IPMI, management teams need a solution that 1) delivers aggregated IPMI data to a single application, and 2) supports the IPMI implementations of different vendors.

This second point is critical. While most server vendors include the IPMI protocol in their platforms, they often hide it behind proprietary software/firmware extensions and/or bundled management solutions. An effective server management solution must be able to handle these variations in IPMI implementation in order to provide a unified view into the computing environment. My point is if AMT is to be successful like IPMI the Server OEM's are going to build their own management tools around it to differentiate themselves. Then there will also be 3rd party vendors that build central management tools to centralize access to the different Server OEM's tools that leverage AMT just as there was for IPMI. However, I'm not sure I see all of this happening for AMT because it is proprietary to Intel. IPMI is already included on most systems for these system mangement & diagnostic purposes. The Server OEM's have invested heavily in tools like ILO, DRAC, RSA & ILOM to take advantage of the IPMI chipset. Unlike AMT, IPMI is independent of the CPU and thus independent of a CPU chip failure and can be run on most systems out of band on a separate NIC. Although a few years old. Here is a good whitepaper that covers the development of IPMI and what has occured with its development.

http://www.avocent.de/web/de.nsf/AttachmentsByTitle/IPMI+WP_5+Reasons+to+Cap_0406.pdf/$FILE/IPMI+WP_5+Reasons+to+Cap_0406.pdf

The Devils in the Details - Data Center Management Event

Managing a data center is tough. With all its complexity, just keeping track of your assets can be a full time job, not to mention finding opportunities to run the data center more efficiently.

To help you do your job more efficiently, PTS Data Center Solutions and Raritan are teaming up to host a Data Center Education seminar on November 4th, starting at 5pm, at the Prudential Center in Newark. And, since all work and no play makes for a dull evening, after the seminar we’ll head to a private box at the rink for dinner, drinks, and an evening of fun watching the NJ Devils play the Washington Capitals.

I’ll kick off the night with a presentation on leading edge solutions that are available to improve data center availability and management. Khaled Nassoura, General Manager of the Green Data Center Initiative at Raritan, will also give a presentation on how to optimize data center operations with dcTrack™.

We’ll cover the latest trends in data center management, including new approaches to asset management, tracking and maintenance. Plan to learn about DC Infrastructure Management (DCIM) and DC Monitoring Systems (DCMS) which offer you broad and deep visibility into your operations in real time, as well as allow you to plan for growth and change by optimizing your current operations, assets and infrastructure.

Please RSVP by 10/23/2009. Tickets are limited and available on a first come basis. To learn more, please visit the Data Center Management event page or contact Amy Yencer at AYencer@PTSdcs.com (201-337-3833 x128). See you at the rink!

New York Jets Power Camp 2009

Thank you to everyone who joined PTS Data Center Solutions and the New York Jets last night at Power Camp 2009, hosted at the new Jets Training Facility in Florham Park, NJ.

We kicked off the training event with the Power Players Buffet … after all, if you want to be a pro you have to eat like a pro. There were about 80 people in attendance and it was great getting the opportunity to talk with everyone.



Together with the folks from APC, Avocent and Packet Power, we tackled a range of data center power issues during our Power Drills, including techniques for effective management, monitoring, availability and control.



Mike Petrino, vice president of PTS, gave the crowd a tour of the data center we designed for the NY Jets Training Facility:



All in all, the Power Camp training event was a huge success. Highlights for me included our field goal kicking contest, hanging out with NY Jets legend Bruce Harper and coaching my junior football team, the Franklin Lakes War Eagles, during a scrimmage on the Jets practice field under the lights.

Talking with Bruce Harper, the all-time kick returner in New York Jets history, at Power Camp:


Coaching the Franklin Lakes War Eagles on the Jets practice field:


Field goal kicking contest for attendees of PTS' Power Camp:


I hope everyone who attended enjoyed the event as much as I did. If you want to see more photos from this year’s Power Camp, please visit our Facebook Page at http://www.facebook.com/ptsdatacenter.

Inflection point: Build for Higher Density or Plan for Efficient IT?

Over the last decade, the focus of the Data Center Industry has been to plan & renovate feverishly to support higher densities. Not too much of a surprise because there was actually an uptick in the scale of Morse's Law over the last decade as processing power, processing density & power consumption per rack unit all had risen faster than the industry had ever experienced.

Over the last few years the server manufacturers started to pay attention to power consumption as many of their clients couldn't deploy the new technology or had to wait until renovations or new facilities became available to upgrade to the newer servers that consumed more power in a smaller footprint. You are starting to see some products on the market that reverse the decade long trend & use less power. From innovations in operating systems that fine tune power usage as shown in this recent article by IBM:
http://www.ibm.com/developerworks/linux/library/l-cpufreq-1/

To Intel with its new Xeon 5500 series processors that is delivering up to 2.25x better performance and up to 3.5x improved system bandwidth are delivered in the same power envelope compared to Intel®Xeon®processor 5400. This processor also uses up to 50% lower idle power consumption during low utilization periods.
http://ipip.intel.com/go/wp-content/uploads/2009/05/intel_server_roadmap_050609.pdf

What is this forward thinking leading to? I believe we are going to cross the inflection point in the next couple of years where the high density environments we have or are constructing will outpace the power consumption demand of the new processors & servers we will need to deploy. It is difficult to say exactly when the big power saving breakthrough will happen at the chip level, but I think we all know it will happen. You don't want to be the last guy who built a MW facility @ 300 watts per square foot that now only needs 500KW & 150 watts per square floor. We often consider modular solutions that can scale up our density & capacity, but keep in mind that someday soon we may need to consume less power & cooling so we should make sure that our design is efficient at 50% or 30% of our design as well. Not just due to the inflection point where server power consumption will drop below data center power demand that Julius Neudorfer describes in the below article, but because our business requirements can also change where we won't need as much processing power to run our business.
http://www.itbusinessedge.com/cm/community/features/guestopinions/blog/inflection-point-the-future-of-the-data-center/?cs=36115

PTS & The New York Jets Invite You to Power Camp '09

PTS, in collaboration with the New York Jets, is excited to invite you to Power Camp ’09. Tackle power issues before they result in a defensive meltdown and make sure that your Data Center is powered up for many more winning seasons!

The three hour Power Camp includes a buffet dinner and 3 intense drills that teach the latest techniques and solutions for effective power monitoring and control, followed by a tour of the state-of-the-art data center PTS engineered and built for the New York Jets. Be sure to stay for the field goal kicking contest and to meet famous NY Jet, Bruce Harper!

For more information and to view the agenda, please visit our website at http://www.ptsdcs.com/eventNYJETS.asp.

If you’d like to attend Power Camp ’09, please RSVP by 9/23/2009 to Amy Yencer, AYencer@PTSdcs.com, 201-337-3833 x128.

Role of the CIO in Business Continuity, Disaster Recovery

Ralph DeFrangesco at ITBusinessEdge posted the following discussion question in their forums recently.

Corporations often confuse business continuity and disaster recovery. They also tend to put the CIO in charge of both. Should the CIO be the point person for both BC and DR? If so, why? If not why and who should it be?

It resulted in an interesting debate on the role of the CIO, so I reposted it on LinkedIn for so the members of our Computer Room Design Group could weigh in. Here are some of the insights they had to share...

Ken Cameron, IT Infrastructure & Outsourcing Executive:

The CIO should own Disaster Recovery. The business side (someone in Risk Management, Corporate Security, etc.) should own Business Continuity. The IT group should be represented on the Business Continuity council. IT plays a major role in Business Continuity, but does NOT own it.

IF the CIO gets Business Continuity, it needs to be made clear that his BCP responsibility is NOT part of his IT responsibility.

Christopher Furey, Managing Partner at Imaginamics:

This is one of those issues where it's a bit like asking the fox to watch the hen house. Only very small or inexperienced management teams put IT in charge of BC. The scope of the risk analysis is usually way beyond the skills of an IT Director or CIO, and even when it's not, business risk oversight is critical.

Ken is spot on. The CIO must be in charge of DR and IT Systems Continuity but not BC. Any CIO who wants to keep their job will work in tandem with Risk Management and key stakeholders on the business side to ensure critical business functions and the systems that support them are well considered.

BC is in the realm of Ops and is best handled with strong leadership (or at least advocacy) from the CFO, COO or GM - or the partners and owners in smaller firms. Management inadequately funds and supports BC unless it understands the risk and process in total beyond simply recovering IT systems or data.

Though it's often mentioned in the same breath with DR, BC is not an IT role, but ensuring the operational assurance of the key IT systems is.

K.M. Sreekumar, Consultant & Project engineer at Schnabel DC Consultants India Pvt Ltd:

IT is only an enabler to the business and business continuity though very critical it is not the business. Business overall is and should be the responsibility of the CEO, so we are back to square one CIO and CTO will only aid the BC plan and fully responsible for the IT and technology part. For example, CIO should not be responsible for even analysing the business impact of an IT black out. Secondly, threats to the business are varying in nature like pandemic, supplier lock outs, financial instability and very few have IT nature.

Another perspective would be to treat IT as a business and CIO be responsible for Business continuity of IT. Similar to what Christopher Furey wrote.

What are your thoughts on the role of the CIO and IT in relation to business continuity? Please share your experience by posting a comment here, or by continuing the discussion in the Computer Room Design Group on LinkedIn.

A Closer Look at PTS’ Data Center Education Series

Thanks to everyone who’s expressed interest in participating in our upcoming Data Center Education Series! The response has been very positive and we’re looking forward to the first session which will be held at our headquarters in Franklin Lakes, NJ from September 15 to 17, 2009.

A few of you have emailed me to ask for more information on what will be covered during the training sessions, so I’m posting the course descriptions here for your convenience:

Data Center Planning: Establishing a Floor Plan (Time: 2-3 hours) - A floor plan strongly affects the power density capability and electrical efficiency of a data center, yet many floor plans are established through incremental deployment without a central plan. Once a poor floor plan has been deployed, it is often difficult or impossible to recover the resulting loss of performance. This course provides structured floor plan guidelines for defining room layouts and for establishing IT equipment layouts within existing rooms.

Fire Protection Methods in the Data Center (Time: 1 hour) - Fire in any area of a business can result in millions of dollars of losses and even business failure, but fire in the data center represents one of the greatest risks to any company or institution. This is a foundational course which will introduce the basic theory, prevention, detection and suppression of fire specific to data centers. At the completion of this course you will have a better understanding of the safeguarding methods that are used to protect a data centers hottest commodity, information.

Fundamentals of Cooling (Time: 3-4 hours) - In every data center excess heat has the potential to create downtime. In addition, the performance and lifespan of IT equipment is directly related to the efficiency of cooling equipment. If you’re involved with the operation of computing equipment it's critical that you understand the importance of cooling in the data center environment. This foundational course explains the fundamentals of air conditioning systems, covering such topics as the refrigeration cycle, ideal gas law, condensation, convection and radiation, heat generation and transfer, and precision vs. comfort cooling.

Fundamentals of Power (Time: 3-4 hours) - Before you can understand the power needs of the Data Center, you must first understand the basic concepts and terms related to power measurement, electric power forms, and its generation. This elementary level course explains these power elements and some of today's power problems

Fundamentals of Physical Security (Time: 1 hour) - Today's Data Centers must consider not only network security, but also physical security. This course defines what physical security means for mission critical facilities and identifies what assets it needs to protect. Also discussed are the different means to control facility access, common physical security methods, security devices, and budget considerations related to physical security.

Cabling Strategies for the Data Center (Time: 2 hours) - From a cost perspective, building and operating a data center represents a significant piece of any Information Technology (IT) budget. The key to the success of any data center is the proper design and implementation of core critical infrastructure components. Cabling infrastructure, in particular, is an important area to consider when designing and managing any data center. The cabling infrastructure encompasses all data cables that are part of the data center, as well as all of the power cables necessary to ensure power to all of the loads. It is important to note that cable trays and cable management devices are critical to the support of IT infrastructure as they help to reduce the likelihood of downtime due to human error and overheating. This course will address the basics of cabling infrastructure and will discuss cabling installation practices, cable management strategies and cable maintenance practices. We will take an in-depth look at both data cabling and power cabling.

Data Center Management (Time: 2 hours) - There are a number of management tools currently available to help manage the data center from a number of perspectives - network, availability, asset management, infrastructure monitoring and control. Which of these tools are applicable to your data center? Which tools will best meet your needs?

Data Center Maintenance (Time: 2 hours) - Whether you own, rent or co-locate, whether your data center is 1,000 square feet or 100,000 square feet, whether you are dealing with legacy equipment or the latest high density configurations, you face the same issues with managing the maintenance of your equipment. Data center maintenance is essential to properly maintain and extend the life of your valuable data center infrastructure and prevent unplanned downtime, yet it is often relegated to spreadsheets and paper-based systems. All too often, critical maintenance is overlooked because someone didn’t remember to schedule it or have the right spare parts, tools or personnel available to properly perform the tasks required. This course will discuss the growing use computerized maintenance management systems (CMMS), including those designed specifically for the data center, and how the use of these systems can improve maintenance management in your data center.

Data Center Energy Efficiency (Time: 2 hours) - Is the concept of "greening" the data center hype or reality? This course will discuss practical and effective methods to make your data center more efficient to yield immediate cost savings.

Our instructors will tie in case studies and real world situations to provide concrete examples of how to apply the information learned in the course. Time each day will be spent on open discussion, allowing sharing of industry experience with your peers.

If you haven’t signed up already, please visit http://www.ptsdcs.com/educationseries_webform.asp to reserve your seat. Priced at only $999 per student, the vendor-neutral, module based training includes all course materials in addition to a continental breakfast and lunch each day. SPECIAL OFFER: If you attend with other colleagues from work, you'll all receive a 10% discount.

Our goal is to create a training series that presents the topics of most interest and value to the student. That being said, we welcome suggestions for how we can continue to improve the series. Is a three (3) day training program a good fit for your schedule? Is there a course you'd like to see added? What type of lunch should we serve? Feel free to post a comment to tell us what you think.

Data Center Education Series Sept. Training - IMPORTANT UPDATES

The Data Center Education Series training event on September 15-17 has been moved from NYC to the PTS Headquarters in Franklin Lakes, New Jersey.

The event cost has also been changed and is now just $999 per attendee.

For more details and the full agenda, visit our Data Center Education Series page. Hope to see you there!

Expert Data Center Education & Training In NYC

Just a quick reminder for all our readers: PTS' Data Center Education Series is coming to midtown NYC from September 15-17.

UPDATE 08/20/2009: The PTS Data Center Education Series for September 15-17 has been relocated to our headquarters in Franklin Lakes, NJ.

The three (3) day class provides students with comprehensive, vendor-neutral, module based training that covers the most pertinent topics in the data center industry, tying in case studies and real world situations to provide the knowledge you need to understand, operate, manage, and improve your data center. The training includes all course materials in addition to a continental breakfast and lunch each day. (Best of all, if you attend with other colleagues from work, you all receive a 10% discount.)

To view the agenda and reserve your seat, please visit our website at http://www.ptsdcs.com/datacentereducation.asp.

While I’m at it, I’d also like to take a moment to thank everyone who’s joined our Computer Room Design Group on LinkedIn. Your support and participation has helped the group get off to a great start, with over 300 data center and IT pros joining in the first month alone!

Here’s a quick snapshot of some of the recent discussions that have been posted:

• Will the cloud kill the data center?
• Hot & Cold Aisle Containment. How do you implement it when you have different cabs, heights and gaps?
• Who really cares most about Enterprise Data Center Efficiency? CIO? CFO? IT?
• TIA standard TIA-942: Tier - 2 takes 3- 6 months to implement, Tier - 3 takes 15 - 20 months to implement. Is this because of record keeping to demonstrate uptime?

Everyone is welcome to join! It’s a great opportunity to share news, ask questions, offer advice, and connect with your peers. Check it out at http://www.linkedin.com/groups?gid=2099901.

Google Cools Data Center Without Chillers; Data Center Pros Weigh-in

Google’s chiller-less data center in Belgium has received a lot of buzz. The facility relies upon free air cooling to keep its servers cool and will shift the computing load to other data centers when the weather gets too hot.

It's an approach that stands to greatly improve energy efficiency. However, as e-shelter explained to Techworld, there are some risks. For instance, it's possible that airborne particulates could cause havoc with hard disk drives and dampness from heavy humidity could cause electrical problems. To see what other data center professionals think of this cooling strategy, I posed the following question to the Computer Room Design Group on LinkedIn:

Is Google's Chiller-less Data Center the wave of the future, or is this approach too risky for most businesses to accept?

Here’s what some of our group members had to say…

Mark Schwedel, Senior Project Manager at Commonwealth of Massachusetts:

Please note that Google is doing many thing that are not available in current data centers they do not have UPS - They are doing battery backup on each server with 12 volt battery - SO will this be the future? Only when the rest of world can delivery the same aspect as Google.

Sean Conner, Datacenter Professional Services Consultant:

Google's design is well suited for an expansion of their cloud environment. However, it's clear that the facility in question does not run as the same level of criticality as most dedicated or hardened sites. This works well in an environment that can tolerate minor equipment loss and failure.

However, most dedicated sites host applications and data that would suffer, should similar equipment loss occur. So, the two approaches cannot be truly compared. It's like trying to compare the heart to the left hand. Both are useful. But if the left hand fails, you probably don't die.

Perhaps a larger question to ask is: What applications, data, or entire enterprises could migrate to a cloud environment? Those that can stand to gain huge savings from Google's approach.

Dennis Cronin, Principal at Gilbane Mission Critical:

This entire dialog is moot because the way of the future is back to DIRECT WATER COOLED PROCESSORs. All these sites chasing the elusive "FREE" cooling will soon find out that they cannot support the next generation of technology.I suspect that there will be a lot of finger pointing when that occurs with even more adhoc solutions.We need to stick to quality solutions that will support today's AND tomorrow's technology requirements.

David Ibarra, Project Director at DPR Construction:

There is a tremendous pressure on large enterprise customers ( social, search,etc) to use the same fleet of servers for all of their applications. The IT architects behind the scene are now been asked to stop been "geeks" and changing hardware every 3 years and try to make use of what we have or improve with systems that are lower cost. The recession is also amplifying this trend. A lot of water cooled servers and demonstrations held last year have gone silent due to cost and also standardization on hardware for the next 5 years. A lot of large DC customers understand the water cooling technology and are early adopters; however realities have driven the effort elsewhere within their organizations. Customer are pushing high densities ( +300W/sqft) using best of class techniques: containments, free cooling,etc. Plus large scale operators are understanding that the building needs to suit the server needs so there is a shift on how a building is configured. Chiller less data centers have existed since 2006 in countries such as Canada, Ireland, Germany, Norway. Data centers will be coming online at the end of this year in the US that are chiller less and cooling tower less and with a extraordinary reduction of air moving equipment.

Nitin Bhatt, Sr. Engineer at (n)Code Solutions:

Every single Data Center is unique in its own set-up. To adopt some technology which is suiting to one geographical location could not be a wise decision. It is wise to be "Orthodox" rather than lossing the business. If someone can afford the outage / shifting of the work load to DR site or to some other sites as a result of the thermal events, yes they can look into FREE COOLING w/o Chillers. We can save the energy used by chillers having VFDs and room temperature based response to chillers. It is good to have chillers as backup to the Free Cooling.

So what do you think? Please share your experience by posting a comment here, or by continuing the discussion in the Computer Room Design Group on LinkedIn.

LinkedIn Discussion on Power Usage Effectiveness (PUE)

Last week I posted the following discussion question in our Computer Room Design networking group at LinkedIn.com. I’m really impressed with the response from group members, so I’d like to share their thoughts with you here:

How can the industry address problems with the reporting of Power Usage Effectiveness (PUE) without undermining the usefulness of the metric?

In a recent post in Data Center Knowledge, Rich Miller points out that the value of Power Usage Effectiveness (PUE) as the leading 'green data center' metric "has become fuzzy due to a disconnect between companies’ desire to market their energy efficiency and the industry’s historic caution about disclosure." [Source: http://www.datacenterknowledge.com/archives/2009/07/13/pue-and-marketing-mischief/]

What are your thoughts on redefining PUE? Are additional refinements the answer? Or does increasing the complexity of PUE undermine the usefulness of the metric?

ANSWERS:

• Gordon Lane, Facilities Coordinator at Petro Canada, explained:

I don't see a real value in PUE.

If you leave unused servers powered on you can keep your PUE low.

Assume you have a PUE of 2
2MW total power consumption gives you 1 MW for servers.
If you can reduce your server consumption to 0.75MW by turning off comatose servers total consumption reduces to 1.75MW and gives you a PUE of 2.33

I know there would be some reduction in a/c power usage due to less heat output from the turned off servers but if you are using legacy a/c units with no VFD style control then you will not get a corresponding electrical consumption reduction.

• Scot Heath, Data Center Specialist, weighed in with:

PUE is difficult to measure in mixed facilities, is muddied by configurations such as the Google every-server-has-a-battery and varies widely with Tier level. A universal measurement that combines both IT capability (total Specmarks for example) and availability with respect to energy consumption would be most useful. PUE does have the advantage of being quite easily understood and for controlled comparisons (like tier level, etc.) is very useful.

• Dave Cole, Manager of Data Center Maintenance Management and Education Services at PTS, responded:

Gordon and Scot bring up very good points. I have mixed feelings about PUE. The concept is easily understood - we want to maximize the power that is actually used for IT work. The interpretation of the value is easy to understand - lower is better (or higher is better in the case of DCiE). The problem I see is that it's almost been made too simplistic. You still have to know your data center and the impact of the decisions you make in regards to design and operation. You can actually raise your PUE by virtualizing or by turning off ghost servers as Gordon pointed out. What needs to be understood is that when you lower the demand side, you should also be making corresponding changes to the supply side. At the end of the day, PUE can be valuable as long as you are also looking at what impacts the value. You need to be able to answer the question of WHY your PUE is changing.

What are your thoughts on the value of Power Usage Effectiveness (PUE) as a metric? Please share your experience by posting a comment here, or by continuing the discussion in the Computer Room Design Group on LinkedIn.

LinkedIn Discussion on Eliminating the Battery String

Thanks to everyone who’s participated in our Computer Room Design networking group at LinkedIn.com so far! We’re off to a great start, with over 200+ members joining in the first two weeks. I’d like to share highlights from one of our recent discussions…

Kevin Woods, Director of Business Development and Sales at i2i, asked:

Eliminating the Battery String? Does anyone have experience/opinion on the viability of the UPS/CPS systems? They incorporate a flywheel in between the generator and engine and in cases of power interruption, the flywheel uses kinetic energy to power the generator for up to 30 seconds while the engine is engaged.

ANSWERS:

• Mark Schwedel, business partner at EMC and advisor for Green Rack Systems, recommended taking a look at the patent for an improved UPS/CPS system, which employs a high-efficiency uninterrupted power supply function integrated with an engine-generator set that combines both short term protection against momentary power interruptions with longer term power generation.

• Gordon Lane, Facilities Coordinator at Petro Canada, shared his experience:

Not a direct comparison to gen/engine set up but I have a flywheel UPS system that has been in service for 23 years. Very reliable, change the bearings every 50000 hours - about 6 years - and we have just about completed a program of taking the MGs out for cleaning and re-insulation.

Obviously coming to end of life, 20 yrs was estimated life, but the serviceability has been phenomenal.

Certainly looking to replace with a similar system and I believe Caterpillar has a flywheel UPS solution that they integrate into their diesel offerings.

• Jason Schafer, Senior Analyst at Tier1 Research, explained in part:

My personal issue with flywheel solutions, aside from the reliability that both sides will argue, is that 30 seconds simply isn't enough time when you are talking about the criticality most datacenters need. The most common argument relates to allowing time to manually start a generator; and flywheel advocates will say "if a generator doesn't start in 30 seconds it's not very likely that it's going to start in 20 minutes" - I disagree with this. I've seen, on more than one occasion, where generator maintenance was being performed and through human error the EPO switch on the generator was mistakenly left pushed in. There's no way anyone is going to identify the problem and fix it in 30 seconds - I'd be surprised if anyone even got to the generator house in 30 seconds after a power outage. Minutes, however, are a different story.

I'm not saying that flywheels and CPSs don't have their place - I think they do, or rather will in large scale in datacenters, but we're not quite there yet. When virtualization plays a part in the redundancy and fault tolerance of a datacenter, where ride-through in the event of a power outage is more of a convenience than a necessity (a-la Google's datacenters - they can lose an entire facility and continue on for the most part), you'll see flywheels gain more traction.

What are your thoughts on the viability of the UPS/CPS systems? Please share your experience by posting a comment here, or by continuing the discussion in the Computer Room Design Group on LinkedIn.