Tuesday, December 08, 2009

‘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...

Friday, November 20, 2009

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.

Friday, November 06, 2009

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.

Wednesday, November 04, 2009

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.

Monday, November 02, 2009

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

Monday, October 19, 2009

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!

Wednesday, September 30, 2009

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.

Sunday, September 27, 2009

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

Friday, September 18, 2009

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.

Wednesday, September 02, 2009

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.