Data Center Management – Solutions to mitigate most Common Risks

November 1, 2012 By

 

Organizations today heavily depend on IT to support all their activities. This is why data centers have become a go-to facility for maintaining network and system functions. Customers too expect nothing but the best. This is why it is crucial to maintain a high performance service. Managing this infrastructure effectively is the key to enhanced operation rates. That is why data center managers should be able to track and assess the performance of individual sections of the data center effectively. Providing them with industry specific products should help them measure performance efficiently and mitigate potential risks. Let us look at these performance measurement products/tools and find out what they can do for the data center.

Availability of IT Equipment:

Downtime is data center manager’s worst nightmare. Generally customers expect system availability almost 100% of the time. Hence, IT personals need to access the reliability of the equipments of the data center so that that can reduce downtime considerably. The data obtained from assessing the equipments should also help them identify and alleviate issues.

Solution:

Technology has provided monitoring solutions which are based on the changing environmental factors and offers real time feedback about systems responding to factors like temperature, amperage draw, humidity, dew point, and physical security. These readings help the experts set thresholds for different atmospheric conditions. Additionally, this system also provides past information which can alert the personnel about the changing trends so that they are equipped with practices for that event.

Assessing Critical Services

Critical services means determining, classifying and rating the highest priority sites and facilities.  Systems like the four tiered classification system which is based on factors like useable capacity, fault tolerance, maintainability and sustainability helps in the evaluation .After undergoing the process, the administrators should be able to employ suitable managements and control systems for these critical sites which will help them mitigate potential vulnerabilities.

Solution:

Management solutions like KVM or service processor aggregation appliances offer the IT administrators access to servers, devices and even to equipments which are available locally and remotely. These provide BIOS – level access and offer assistance to reduce downtime by allowing instant access to all failed resources and data center management. These solutions also provide analysis and audit logging which helps the personnel gain valuable insight to the daily occurrence of the various operations in the data center.

Measuring the Data Center’s Energy Consumption

The rising rate of energy consumption is a cause of concern for most organizations. This has been a prime concern since companies are employing high density server racks which consume significant amount of energy. Experts are always looking for methods and practices to reduce the energy usage and making the data centers much more efficient. Proposition of implementing PUE and the DCE metrics should enable the data center managers estimate the efficiency of that data center. As Per Gris Grid which is consortium of IT companies, Power Usage Effectiveness (PUE) = Total Facility Power/ IT Equipment Power; Datacenter Efficiency (DCE) = IT Equipment Power/ Total Facility Power.  The PUE results are compared to different data centers to find out if the data center needs improvements to increase its efficiency.

Solution:

By using the results of PUE and DCE, administrators can evaluate the efficiency of their data center. Other than these, one can also use application specific data for evaluation. Performance rating tools like EPA energy star and Portfolio manager offers rating to the data center after comparing the results with other data centers. Switching to higher voltage power is also a practice which allows the IT equipment to operate much more efficiently. Regular audits of the facility including the racks and equipment will provide valuable insights like if the under the floor plan should be improved  or if some servers should be discarded. Using blanking panels and cable management accessories in the rack can also assist in reducing the energy usage of the data center making them energy efficient.

Data Center Talk updates its resources everyday. Visit us to know of the latest technology and standards from the data center world.

Please leave your views and comments on DCT Forum

Share on TwitterSubmit to StumbleUpon
Filed Under: Articles, Data Center Management Tagged With: ,

Joyent Tools’ New Strategy to Cut Down Power Consumption in their Data Centers

September 21, 2012 By

Data centers have been for long used as a cost-effective and energy efficient method to store massive chunks of information; however, the power usage of these centers has been so enormous that new tools are being used in the battle of reducing power consumption and cooling costs. With companies designing new ways of reducing the power usage effectiveness rating (PUE) i.e. the amount of electricity drawn to get a unit of computing done, Google, Yahoo, Facebook, and Microsoft are vying to get to the least possible PUE. Most of the older companies reach a PUE of 1.9-2.0, with all the extra power used for cooling, lights and other ancillary units.

Average PUE rating at 2.0, Google manages 1.22 or 1.16 at its new data centers, Yahoo on the second line, operates on a 1.07 PUE. FACEBOOK leads with a least PUE of 1.06.

“Operating for efficiency and failing will get you yelled at. Operating for availability and failing will get you fired,” summed up Steve Hassell, president of the Avocent business unit of Emerson Network Power, which specializes in producing power management devices. When availability in the data center is of prime importance, surplus power usage needs to be reduced by analyzing the device’s real time needs. Jason Hoffman, CEO of a San Francisco-based company- ‘Joyent’, which provides infrastructure-as-a-service (IaaS) from a dozen data centers understands that if the power consumption is reduced, his infrastructure will be amongst the big names of the market and an added feature on the server racks that it ships to other cloud computing enterprises.

In an interview, Hoffmann described an appliance that can amass and perform analytics on the data received from data centers, just like the microcontrollers, and the service processors on the motherboard. The Avocent Universal Management Gateway accepts information spewed out by such components and sends it to the network gateway. Same work is carried on by the network interface cards, and switches on the servers, and other data centers.

After EMERSON acquired AVOCENT, Information from the gateway is delivered to Emerson’s Trellis data center management software, from where it accomplishes different goals including power consumption.

The four modules are-

Inventory Manager: It is a device mapping system that detects communication between devices and tracks their location to build an essential blue-print of the data center.

Site Manager: reports about the health of the data center, the temperature and voltage fluctuations if any, and the cooling status of the data center. It has the ability to collect information from every single device in order to report on the health of the data center.

Change Planner: enables capturing device additions, moves, or decommissions and keeps the inventory manager informed on every bit of fresh information.

Energy Insight: calculates total data center energy consumption and electricity costs, as well as individual device consumption. According to Hassel, energy insight can also be used to calculate the PUE of the data center.

Trellis software and the Universal Management Gateway provide “big data and big data analytics for the data center,” said Hoffman.

Joyent has gained enough experience after its acquisition of AVOCENT that it’s become a secondary business to its IaaS, offered as a feature on a server rack of Joyent infrastructure destined for installation on a customer’s premises

Emerson says in information on its website that the Gateway-Trellis combination can save 25% of a data center’s energy consumption. Hoffman claims that savings is borne out by Joyent’s own experience. “We think we can do better than that,” he added.

 

Data Center Talk updates its resources everyday. Visit us to know of the latest technology and standards from the data center world.

Please leave your views and comments on DCT Forum.

Share on TwitterSubmit to StumbleUpon
Filed Under: Data Center Management, Data Center Power, Data Center Solutions Tagged With: ,

Essentials for Data Center Competence

June 27, 2012 By

If you thought shopping for daily amenities was a tough task, then you cannot even comprehend the factors and parameters which are to be considered while choosing a data center. Usually different companies have their own distinctive approach. They take parameters like Energy efficiency, cooling systems and the all important power supply into consideration. With the economic meltdown underway, it has become important to implement solutions which will save energy and moolah. But often, the goal of operating an energy efficient data center can get a little overwhelming to deal with. The reason is, the big data centers can operate with high failure risks when dealing with energy efficient methods as they can shift their operations to another facility in case of a failure, but the small ones cannot afford to mainly due to lack of resources.

So the question is how can these data centers which lack the perks of the large data centers achieve the requirement of being energy efficient data center without compromising on the quality and that too at low costs? Well, the key to this a list of top 3 essential pointers which you should consider while designing a data center which offers efficient performance without loading you up with long bills.

Go Back to Basics:

Industry experts suggest that designing the data center by structuring the different components can help in more efficient energy flow in the data center. Keeping everything organized will largely help you in tasks like data duplication.

Another method of lowering the power use is to implement the tiered storage method .In this method, older data is stored by archiving them in a storage device from where information can be retrieved as and when needed.

Cool the Facility with the Right Tools:

Usually, data center facilities implement the hot aisle/clod aisle method as a cooling strategy. In this method hot and cold air are contained separately. The process to keep these airs separate creates a considerable temperature difference which is sensed by the A/C system. As a result, less energy is consumed to fulfill the cooling needs.

The question which arises here is how to keep this air from mixing. A simple alignment arrangement of the servers in the same direction solves the problem i.e. all the backs of the servers in one direction and all the fronts face one direction thereby creating a hot and cold aisle.

Use Offline Power:

Though it is a controversial process, it is a method which has been repeatedly encouraged by industry experts to try out. The logic is sound. Data centers have UPS for offline power supply in case of a failure. Experts suggest that using the same emergency supply kit to operate the data center can reduce the power consumption considerably. This is because the system is dormant unless there is a power failure. So the power lag between the power outage and the UPS taking control is negligible and that is why the IT equipments don’t even pick up the power drop.

Now, this method completely depends upon the person implementing it. So whether the person is operating it at high or low efficiency, there is a risk factor which includes the safety and the performance of the data center.

Some Other Methods:

Also, minimizing the number of transformers will lower the number of UPS which will elevate the risk factor. But experts state that transformer provides isolation between input and output, which can be achieved with circuit breakers and other tools.

Switching to higher voltage equipment is also believed to offer decent energy savings as these equipments have smaller physical conductors. Though higher voltage is a little dangerous, once implemented, it can do wonders in the field of energy savings.

Data Center Talk updates its resources everyday. Visit us to know of the latest technology and standards from the data center world.

Please leave your views and comments on DCT Forum

Share on TwitterSubmit to StumbleUpon
Filed Under: Data Center Equipments, Data Center Power, Data Center Solutions Tagged With: ,

eBay builds the Largest Clean Energy Project till Date

June 26, 2012 By

eBay recently announced its intentions of commiting to clean energy and hence have taken this initiative to a whole new level. According to industry reports, eBay will implement clean energy for its Utah data center. The company plans to use the local power grids for emergency backup power source. eBay has partnered up with Bloom Energy and has installed a 6 megawatt fuel cell installation in the data center campus. This data center is expected to be the largest non –utility fuel cell installation in the country.

It is reported that 30 Bloom Energy servers will be installed in the Utah data center. Each of these servers is capable of producing 1.75 million KWH of electricity annually. The fuel cells are going to be powered by biogas.

“By being a trail blazer and deploying a brand new, revolutionary architecture to build its new data center, eBay is raising the standard for the entire industry. It is 21st century infrastructure for the industry needs of the 21st century,” said KR Sridhar, principal co-founder and CEO of Bloom Energy. “Bloom Energy is thrilled to be supporting eBay on this innovative and inspiring large scale project.”

Bloom Energy operates a 650 kilowatt solar farm along with a 500- kilowatt fuel cell installation at its San Jose headquarters site. Once the eBay project is completed, it will become eBay’s largest renewable project.

Data Center Talk updates its resources everyday. Visit us to know of the latest technology and standards from the data center world.

Please leave your views and comments on DCT Forum

Share on TwitterSubmit to StumbleUpon
Filed Under: Data Center Power, Data Center Solutions, Featured News, Green IT, News Tagged With: , ,

Colt partners up with Verne Global-Sets up Services in the Campus

June 22, 2012 By

One of UK’s most innovative power-conscious data center campuses, Verne Global recently announced that Colt, which is the information delivery system for various European business has agreed for data center capacity, which is going to be powered by 100% renewable sources. With this move, Colt hopes to create a presence within Verne Global’s data center. Colt is also looking forward to enhance its productivity and its portfolio with 100% carbon-free data center services.

“Colt works very closely with our customers and partners to continually improve sustainability across all of our data center assets and modular data center builds,” said Bernard Geoghegan, Executive Vice President at Colt. “As the market continues to evolve, finding innovative methods to reduce the cost and environmental impact of the data centre industry is of tremendous importance and we believe that Verne Global offers a compelling value proposition to Colt and our customers.”

“Colt is a recognized player in delivering data center services to the marketplace and we are thrilled to have them locate at the Verne Global campus,” said Jeff Monroe, CEO of Verne Global. “It is clear that the industry is responding to Verne Global’s value proposition and we appreciate the trust and partnership of companies like Colt as we continue to expand our customer portfolio.”

As an information delivery platform, Colt enables its clients to deliver, process and store information efficiently. They offer services to major organizations, midsized business and also to wholesale customers. Colt has an impressive network which ranges across 21 countries and include major metropolitan area networks in Europe. In 2010, the Colt Data Centre Services business was launched to deliver innovative high quality modular data centers which are rapid to deploy and power efficient.

Data Center Talk updates its resources everyday. Visit us to know of the latest technology and standards from the data center world.

Please leave your views and comments on DCT Forum

Share on TwitterSubmit to StumbleUpon
Filed Under: Data Center Power, Data Center Solutions, Featured News, News Tagged With: ,

Apple’s Green Data Center Project Causes Distress among Locals

June 19, 2012 By

According to reports, Apple decision to invest in solar farm and fuel cell installation to provide power to their massive data center which is being constructed in Maiden, N.C was positively received by the industry. Though it is an impressive project, this project is causing a lot of distress to the locals. Zelda Vosburgh’s back yard runs right up to the solar farm. According to her, she has endured a lot during the construction of the eco friendly project and can’t wait for it to be finished.
“When we get a storm or the wind blows bad this whole place turns into nothing but dust in the air. You can see it flying everywhere,” Vosburgh said.
Trevor Wilson said it’s not the dust but the noise he’s noticed the most near his parent’s home in Maiden. On Monday, crews were working to install the rows of supports needed for the solar panels. ”It is like beating of drums, but metal. Like banging pots together over and over, “Wilson said.
On the bright side, this project has proved fruitful for Randy Rush’s appliance business.
“I’ve got a couple people who stop a week and ask what they’re doing and most of the time of they stop they buy something, so it’s been good, ” Rush said.

Pastor William Painter’s church sits right next to the data center and commends Apple for trying to help the environment. ”It’s great that they’re using the solar power. We need more of that around. Cleaner power sources,” Painter said.

Data Center Talk updates its resources everyday. Visit us to know of the latest technology and standards from the data center world.

Please leave your views and comments on DCT Forum

Share on TwitterSubmit to StumbleUpon
Filed Under: Data Center Design Services, Data Center Equipments, Electrical Contractors, Featured News, News Tagged With: , ,

Power Usage Effectiveness (PUE) to Make Data Centers Efficient

June 13, 2012 By

A data center needs constant uninterrupted power supply to run smoothly. Power is required to keep the servers operational, provide cooling for the servers and also for lighting the facility. The efficiency of a data center is determined by the overhead energy consumption (cooling, power loss, lighting etc). Lower the overhead energy required to run the data center, the higher the efficiency. Looking at logistics, a conventional data center runs at an average of 100% overhead which is highly uneconomical.

To reduce unnecessary power consumption by data centers, Green Grid, a non profit organisation working towards improving the efficiency of data centers developed the Power Usage Effectiveness metric or PUE to measure the effectiveness of the data center.

What is Power usage Effectiveness (PUE)?

By definition, Power usage effectiveness (PUE) is a measure of how effectively a data center uses its power; specifically, how much of it is used by the computing equipments in contrast with overheads. In other words, PUE tells you how much extra energy is needed for each usable KWh for the IT equipment due to the power going into overheads like cooling, lighting, power distribution loss etc.

Why is it required?

It is important to know that running a data center alone is not enough; in today’s green obsessed world, one needs to find ways to run and maintain an energy-efficient data center. Equipments in the data center have to be constantly monitored to ensure they don’t draw unnecessary amount of power to sustain. If the data center is not fine-tuned every now and then to keep them running efficiently, you will have to shell out exorbitant amounts of money just to keep up with the power demands of the data center.PUE was created  keeping only one thing in mind- to run the data centers efficiently .

How is it measured?

In theory, it’s a very simple formula,

PUE = Total Facility Power/IT Equipment Power

The above formulae measures how much overhead energy is required to house and cool the computers inside a building relative to the amount the computers consume themselves

PUE is hence, expressed as a ratio where you will find out if your data center is energy efficient. You can find that out when/if the quotient decreases towards 1. Just remember, the lower your PUE, the more efficient is your data center infrastructure.

How to collect data to determine PUE?

  • Take down the readings of the energy use of the data center from the center’s utility meter.
  • Measure the various IT equipment load after power conversion, switching and conditioning is over. This measurement should represent the total power delivered to the server racks in the data center.

Ideally, the PUE reading of an average data center reads 2.5. This ratio can be further decreased to just 1.6PUE by using efficient equipment and adopting green practices.

How can you bring the PUE down?

There are simple steps which can bring down your power consumption levels by 65%!

  • Space optimization– Other than the IT equipments, the main power consuming system is the cooling structure. Stacking the servers in racks and providing overhead cabling to prevent clutter under the raised floors optimises cooling .This, in turn, promotes an ideal environment and reduces power wastage.
  • Incorporating alternate energy– Depending upon the location, the data center can use energy sources like solar, wind, hydro, etc to run their data centers on a partial basis at least.
  • Upgrading the IT equipments– Upgrading old equipments not only improves the power consumption rate but also ensures the smooth running of the data center.

Data Center Talk updates its resources everyday. Visit us to know of the latest technology and standards from the data center world.

Please leave your views and comments on DCT Forum.

Share on TwitterSubmit to StumbleUpon
Filed Under: Data Center Design, Data Center Management, Data Center Power Tagged With: , , , ,

Apple’s data Center to Take Clean Energy to New Heights

May 30, 2012 By

According to industry reports, Apple’s 500,000 Sq. ft data center in Maiden, N.C has committed towards using clean energy for the facility. They have confirmed that the data center will completely run on renewable energy by the end of 2012.

Apple is planning on producing a staggering 60% of the clean energy onsite. The site will be installed with 100-acre of solar array. Each solar array is capable of producing 42 million kilowatt hours (kWh) of electricity on an annual basis.

The 84 million kWh combined solar power will be added to the 40 million kWh of electricity that will be produced by an onsite bio-gas powered 5-megawatt fuel cell installation for a total of 124 million kWh of clean onsite power. The amount of power which will be generated through this medium is enough to provide electricity to 11,000 homes.

Though Apple is generating a major part of power onsite, they will be purchasing the remaining 40% form local vendors. It is reported that they are considering Catawba County Landfill for this purpose. NC Greenpower is going to start work on the landfill to convert methane gas generated there into usable electricity which will in turn provide power solutions to the data center.

Data Center Talk updates its resources every day. Visit us to know of the latest technology and standards from the data center world.Please leave your views and comments on DCT Forum

Share on TwitterSubmit to StumbleUpon
Filed Under: Data Center Power, Data Center Solutions, Featured News, Green IT, News Tagged With: , ,

Apple Decides to Go ‘Green’

May 21, 2012 By

Apple Inc has decided to power its main U.S. data center entirely with renewable energy by the end of this year, an initiative to address longstanding environmental concerns about the rapid expansion of high-consuming computer server farms. The iPhone and iPad maker said on Thursday that it was buying equipment from SunPower Corp and new company Bloom Energy to build two solar array installations in and around Maiden, North Carolina, near its core data center. Once up, the solar farm will supply 84 million kWh of energy per year. The sites will employ high-efficiency solar cells and an advanced solar tracking system.

“The two solar farms will cover 250 acres, among the largest in the industry, Apple CFO Peter Oppenheimer told Reuters”. “Apple plans on using coal-free electricity in all three of its data centers, with the Maiden facility coal-free by the end of 2012”. ‘I’m not aware of any other company producing energy onsite at this scale,’ Oppenheimer said in a telephone interview. ‘The plan we are releasing today includes two solar farms and together they will be twice as big as we previously announced, thanks to the purchase of some land very near to the data center in Maiden, which will help us meet this goal.’

Concerns about the ever-expanding power consumption of computer data centers have mounted in recent years, as technology giants build enormous facilities housing servers to cater to an explosion in Internet traffic, multimedia use and enterprise services hosting, via cloud computing. ‘Our next facility will be in Prineville, Oregon. This is still in the planning stages and we have already identified plenty of renewable sources nearby,’ Oppenheimer said. ‘We haven’t finalized our plans for on-site generation, but any power we need to run our center in Prineville that we get from the grid will be 100 percent renewable and locally generated sources,’ the Apple CFO said.

Quite a few members of Greenpeace staged a protest this week at Apples Cupertino campus using a giant ‘iPod.’ Greenpeace, which has also targeted Amazon.com and Microsoft with clean energy campaigns, praised Apples decision.

Data Center Talk updates its resources every day. Visit us to know of the latest technology and standards from the data center world.
Please leave your views and comments on DCT Forum

Share on TwitterSubmit to StumbleUpon
Filed Under: Data Center Institute, Data Center Power, Interviews, News Tagged With: , ,

Load balancing in Data Center

May 18, 2012 By

Balancing the data center power load means to understand additional power capacity in the facility. Load balancing is a computer networking line of tactic to distribute workload across multiple computers or a computer cluster, network links, central processing units, disk drives, or other resources. This can achieve the best possible resource utilization, exploit throughput, diminish response time, and avoid overload. Using multiple components with load balancing, instead of a single component, may increase reliability through redundancy. The load balancing service is typically provided by committed software or hardware, like, a multilayer switch or a Domain Name System server. Pete Sacco, president of PTS Data Center Solutions stated, “If I have loads of 186, 52 and 31 amps on my phases, I know that I can take loads off of A and spread them to B and C,” he said. “I’ve actually done nothing to deliver more power. I’ve just load-balanced it’’. Pete Sacco further opined that what often happens is a contractor would rather put in more capacity than balance the loads. The problem is when there’s no more capacity to add.  Making use of server load balancing, organizations can decrease the strain put on individual servers and increase the performance of data and application retrieval within its network. Dispensing the work that an individual server is required to perform can enhance application retrieval times and overall network performance. Server load balancing is a procedure where the wide-ranging workload of a network is consistently distributed across selected servers within a data center.

The promising cloud computing paradigm has motivated the creation of data centers that includes thousands of servers and that are accomplished of supporting a large number of divergent services. As the cost of installing and maintaining a data center is exceedingly soaring, achieving high deployment is fundamental. Therefore, emphasising on agility, to facilitate the ability to allocate any service to any server, is significant for a promising deployment of any data center.

Whether a business plainly uses a centralized business network for local application distribution, or it is employing a wide area network for global distribution, balancing user traffic is a significant factor for best transaction performance. Hence load balancing within data center is a favourable practice.

Various networking concerns in data center networks ought to be scrutinized in order to support agility. The network should have layer-2 semantics to permit any server to be allocated to any service. Along with this, the network should supply consistent high capacity between any pair of servers and hold up high bandwidth server-to-server traffics. A number of proposals that can accomplish these design goals have been reported in the recent times. All of these applications campaign use scale-out topologies, such as fat-tree networks. They present high bandwidth among servers. Even though fat-tree topologies have soaring bisection bandwidth and can tentatively support high bandwidth between any pair of servers, load balancing is necessary for a fat-tree topology to pull off great performance. Balancing network traffic in a fat-tree based data center network comes with considerable challenges as data center traffic matrices are highly contradictory and erratic. The existing solution addresses this trouble through randomization using Valiant Load Balancing (VLB).That achieves target autonomous random traffic dispersal across transitional switches.

VLB can accomplish near most favourable performance under two conditions:

  1. When  the traffics are spread homogeneously at the packet level
  2.  When the accessible traffic patterns do not disobey edge constraints.

Keeping the above conditions in mind, the packet-level VLB practice is perfect for balancing network traffics and has been proven to have many great load balancing properties. Nevertheless, even though the fat-tree topology is best suited for VLB, there is limitation in the adoption of VLB in data center networks. To be exact, for avoiding the inoperative packet issue in a data center network with TCP/IP communications, VLB can only be practical at the flow. It is uncertain whether flow-level VLB can attain comparable performance as packet-level VLB, or whether VLB flow-level is further successful in dealing with traffic instability with those load balancing practices that exploit the network state information.  Experiments show that flow-level VLB can considerably be worse than packet-level VLB for non-uniform traffics in data center networks.  There are importantly two alternating load balancing systems that make use of the instantaneous network state information to achieve load balancing. Recent experimental results point out that these techniques can improve network performance over flow-level VLB in many situations.

Data Center Talk updates its resources every day. Visit us to know of the latest technology and standards from the data center world.
Please leave your views and comments on DCT Forum

Share on TwitterSubmit to StumbleUpon
Filed Under: Articles, Data Center Power, Data Center Solutions Tagged With: , ,
« Older Posts