Archive for the ‘N+1 Data Center Redundancy’ Category
When I visited the data center for 1&1 Internet, a huge hosting and cloud services provider located in Lenexa, Kan., I was struck by the size of the emergency generating system. The Caterpillar diesels that power the generators are the size of locomotive engines.
The four generator sets power the 40,000 servers in an N+1 configuration, and they provide the power to operate the cooling and other building services necessary to keep the data center alive when the power goes out. N+1 refers to a widely used practice in IT to allow for at least one extra system or a set of systems that will serve as a backup in case of failure.
It’s all on a grand scale. The rows of server racks seem to go on forever, networking equipment rooms line each side of the building. The main hallway of the building seems to stretch into infinity. In short, 1&1′s data center is one big place.
More of the CIO Insight article
Why are companies moving primary data centers to wholesale colocation facilities like Lifeline Data Centers? More companies are using outsource data centers to meet data center certification and data center compliance requirements.
There are dozens of data center certifications. Popular data center certifications include SAS 70 Type II, TIA-942 compliant data centers, and Uptime Institute Tier IV data center ratings.
SAS 70 certified data centers define a set of controls and commit to adhere to those controls. Some call that the fox guarding the hen house. SAS 70 Type II data centers audit the adherence to these controls using a third party auditor. SAS 70 is being replaced by a new standard, SSAE 16.
TIA-942 was designed by the Telecom Industry Association. It is a granular look at the design and implementation of a data center or telecom facility. TIA 942 compliant data centers offer high levels of uptime. With data centers, redundancy is a good thing. N+N data center redundancy is sought by most companies, because it translates to a higher level of data center uptime. Redundancy refers to the existence backup system for every important system, including redundant utility feeds, redundant generators, redundant UPS systems, redundant data center cooling, and redundant telecommunications. Two of everything is expensive, but it’s the only way to guarantee high levels of uptime.
The Uptime Institute tiering system is probably the most talked about certification, though few data centers carry the actual certification. The tiering system rates data centers based how they are designed, focusing on the power architecture and other features inside the four walls of the data center. Tier IV data centers are designed to deliver 99.995% uptime. The benefit of these redundancy certifications is that they help companies evaluate providers’ relative levels of uptime with the theoretical goal of a zero downtime data center. Companies that are shopping for outsource data center may choose to combine certification requirements with a “see for yourself” approach to the outsource computer room’s N+N data center redundancy.
Data center compliance is about passing audits. Common audits in the data center include HIPAA, Sarbanes Oxley, FDA, FISMA, NIST, and PCI. Wholesale colocation providers should meet a company’s industry, government, vendor and client compliance requirements. A good provider will come to the table with the company when an audit is taking place. This doesn’t take the compliance burden away from a company; it allows the company to address the physical security and compliance problems by handing them off to the wholesale data center.
Why are companies moving primary data centers to wholesale colocation facilities? Outsource data centers offer a way to “buy” data center certifications and compliance. Companies can avoid the incremental FTE burden of data center compliance issues. And the right data center provider will act as a trusted agent of the company when the auditors come to call.
In Part 5 of this series, we’ll address how wholesale colocation can solve data center consolidation challenges.
Why are companies moving primary data centers to wholesale colocation facilities like Lifeline Data Centers? Better uptime, also known as higher computer reliability, is a driving reason.
Regardless of size, companies continue to bet their business on the reliability of their computer systems. The cost of downtime is lost revenue, lost credibility, and in the worst case, lost clients.
How do companies avoid downtime with in-house data centers? By building the same data center redundancies that outsource providers use. N+N data center redundancy means that a company employs two of everything for their critical data center support systems: two utility power feeds, two generators, two UPS systems and two HVAC systems.
But building data centers with N+N redundancy is expensive. And companies often times cut corners when the actual building occurs. I cannot tell you how many times we have seen in-house data centers change plans and end up with one generator, even though two were planned in the original design. Very few companies go to the expense of two utility feeds from the power company. For each corner cut, the risk of downtime increases significantly.
Why are companies moving primary data centers to wholesale colocation facilities? Higher uptime. Data center redundancy for in-house data centers is expensive. Companies often cut corners to keep costs down, increasing the risks of downtime. The outsource data centers that are built to Tier IV data center standards deliver 99.995% uptime or better. That’s less than 32 minutes of downtime per year or less. Outsource data centers with N+N power redundancy and redundant data center cooling can help companies improve to 99.995% uptime just by moving equipment to the data center.
In Part 4 of this series, we’ll address how the need for data center compliance or data center certifications has become a reason to move to a wholesale colocation facility.
Data center compliance and data center certifications at Lifeline Data Centers
Companies that are considering Lifeline Data Centers for their outsource data center needs often ask about our expertise with data center compliance. We are also asked about data our center certifications.
Rich Banta, co-owner of Lifeline Data Centers, holds the following certifications, which are from ISACA, the Information Systems Audit and Control Association.
CISA – Certified Information Systems Auditor. The CISA certification is known worldwide as the recognized achievement for those who control, monitor and assess an organization’s information technology and business systems.
CRISC – Certified in Risk and Information Systems Control. CRISC (pronounced “see-risk”) is designed for IT professionals who have hands-on experience with risk identification, assessment and evaluation; risk response; risk monitoring; IS control design and implementation; and IS control monitoring and maintenance.
Lifeline builds to the TIA 942 compliant data center standard. In our opinion, TIA 942 offers a more granular level of detail that the Uptime Institute Tier IV data center standard. Lifeline uses an N+N data center redundancy model which allows us to deliver 99.995% uptime or better. Lifeline has provided a zero downtime data center over the last five years.
Lifeline Data Centers is also a SAS 70 data center. Lifeline has a SAS 70 Type II certification.
Lifeline routinely passes HIPAA, FDA, FISMA, NIST, SOX, and PCI audits.
Need more info? Call Lifeline Data Centers at 317.423.2591.
Are you wasting time and resources on your data center?
If your company relies on your computer systems to generate revenue, deliver services, or manufacture your product, your computer room facilities can be a source or worry. You spend lots of money on power, cooling, equipment and labor to keep your most important computer systems up, running and reliable.
But are you wasting time and resources on your data center when you could be spending less money for more reliability?
If you care about uptime, you probably have a generator for your computer room. You may have one or more power conditioning systems with battery backup to protect from a power outage. If you are in the Midwest, you probably have a hardened data center that can withstand an F5 tornado. Your company has likely spent significant capital dollars on your computer room, all to improve the reliability (data center uptime) of your key computer systems.
But is it enough? The answer is another question. How many minutes, hours or days can your systems be down? 99.995% uptime is 28 minutes of downtime per year or less. But it takes two of everything (N+N data center redundancy) to deliver 99.995% uptime. That means TWO electrical feeds from the power company, TWO generators, TWO power conditioning systems, and two air conditioners, to start.
Companies uptime requirements have changed. Even small companies “bet their business” on their computer systems. Will your company spend the money to build a 99.995% level of reliability?
If your company needs 99.995% uptime, or anything close to that level, consider affordable colocation providers: carrier neutral, outsource data center facilities with shared space, private cages, and no cross connect fees. The cost per month may be less than your spending now. The reliability and data center uptime will likely be higher than what you can build. Lifeline Data Centers is at 317.423.2591. Email us if you’d like more information on improving your data center uptime.
The stuff you can’t (or won’t) build into your data center could be the cause of a future outage.
What stuff am I talking about?
- Data center power redundancy – dual utility power feeds, dual generators, and dual UPS systems for every cabinet of equipment in the data center.
- Data center cooling redundancy – dual cooling systems
- Hardened data center facilities – F5 tornado resistant buildings, engineered to withstand regional disasters
- Multiple telecommunications carriers – two or more choices for telecom circuits so you can pick the best carrier for your bandwidth and transport needs
You might be surprised at how rare it is, both in internal and outsource data centers, to have true N+N data center power redundancy. True power and cooling redundancy in the data center provides for 99.995% uptime (27 minutes of downtime per year or less). That is the same level of uptime as a tier IV data center. That’s because N+N data center redundancy (also known as 2N redundancy) allows for failures of equipment and for concurrent maintainability with no data center down time.
Why can’t you build these features into your data center? Or why won’t you? Data center capital costs are the number one reason. Generators cost hundreds of thousands of dollars. A second utility power feed into a facility can easily cost a quarter of a million dollars. Will the CFO sign off on such large capital expenditures when he knows your company can rent better facilities for less money?
Lifeline Data Centers provides affordable colocation facilities to keep uptime high and costs under control. And Lifeline is a carrier neutral data center with no cross connect fees. Need data center? Call Lifeline at 317.423.2591.
CIOs are reducing risks by employing outsource data centers to solve their compliance problems. CIO strategy now includes leveraging outsource data centers and the certifications and compliance they maintain to help the enterprise meet government regulations.
CIOs have used outsource data centers for years to drive higher uptime and reap the benefits of lower data center capital costs. Now, many companies are using outsource data center facilities to keep compliance costs under control.
Physical security is one of the main data center compliance benefits that outsource data centers provide. Outsource data center facilities employ multiple levels of physical security to meet state and federal regulations. It’s usually less costly to “rent” the physical security than to build physical security and managing the ongoing physical security costs in-house.
Some data center compliance centers around service levels, or uptime. High reliability for enterprise computer systems can only be achieved in “mission critical facilities” that employ N+1 data center power redundancy and other tier IV data center characteristics. Service levels of 99.995% uptime (27 minutes of downtime per year or less) can be be found in affordable colocation facilities. The cost of building an enterprise data center with similar levels of data center uptime usually reaches into the millions, even for a small facility.
Data center compliance pressures are coming from vendors and clients as well. Many companies now require that vendors and clients operate SAS 70 data centers, TIA 942 compliant data centers, tier III or tier IV data centers. The cost of maintaining these certifications alone can pay for outsource colocation facilities.
Would it make more sense for your organization to use compliance-centered outsource data center facilities rather than building and maintaining your own? Call the data center compliance experts to learn more.
Chris Smith: Power issues need to remain high on business continuity managers’ to-do lists
2010
Late last year a high-street financial institution experienced a power failure at an IT centre in Yorkshire, shutting down cash machines for a few hours, as well as undermining retail transactions and online banking. This incident was only the latest in a telling series of power failures affecting UK organizations including ISPs, hospitals and financial trading firms, highlighting the growing need for effective assessment of risks and disaster scenarios. This encompasses effective IT infrastructure planning, provision of power supplies and environmental concerns influencing organizations’ daily operations.
The scope for knock-on effects such as system failure and critical data loss has been intensified in recent years by the expansion, complexity and power constraints on ICT infrastructures as ‘UK plc’ migrates an increasing proportion of business processes and systems online. In 2008 Gartner made a global prediction that half of data centres will start to run out of effective power supplies. However, local conditions often present more immediate difficulties.
New year, new data center strategy: The coming of the new year offers a time for both reflection and for planning. Data center strategy is changing for many organizations. What changes do you envision for your data center in the coming years?
Your customers, staff and vendors expect your information technology applications to be available immediately and always. Expectations aside, if your company depends on your computer systems for your business processes, you need to assess your cost of downtime. In 2008, Amazon’s cost of downtime was $122,260 per hour. Downtime calculators are out there; every business is different. Assign a dollar figure to your cost of downtime so you can determine how much to spend on high availability, also known as data center uptime.
Your cost of downtime helps you determine what your uptime levels need to be. Data center industry people talk in terms like 99.995% uptime (also known as 4-1/2 9′s), which translates to 36 minutes of downtime per year or less. Is 99.995% uptime what your company needs?
Large and small companies are using outsource data center facilities (colocation) as a higher uptime alternative to the computer room at their headquarters. If the cost of downtime means lost revenue, lost credibility, and lost clients, using outsource data center facilities offers an easy way to improve uptime. Data center outsourcing takes care of mission critical facilities details like N+1 data center redundancy, security, HVAC and fire suppression, so you can concentrate on your mission critical applications and executing your business processes.
Companies who are required to maintain regulatory compliance can greatly benefit rom outsource computer room facilities. SAS 70 data center facilities can offer many tiers data center compliance. Data center compliance experts can help determine how your regulatory requirements affect your data center.
Affordable colocation has also been an incentive for many companies to move their main computers out of their headquarters. Prices are very competitive for midwest colocation. Outsource data center pricing models can offer both incremental grown and a drastic reduction in data center capital costs.
Check with outsource data center facilities experts to learn more about data center strategy.
Can you build enough data center redundancy? Most businesses today have little or no tolerance for downtime. The cost of downtime is lost revenues, lost credibility and lost clients. And the first step to avoid data center downtime is to house your critical systems in a computer room with multiple power feeds, generators, UPS systems and cooling. These so-called mission critical facilities are engineered to provide power and connectivity to your critical computer systems with no interruption in power or cooling.
How does this work? N+1 data center redundancy is when a data center has at least 2 of everything, including power feeds, generators, UPS systems and cooling units. Using this model, a data center can have a failure in a piece of equipment without downtime. This model also supports periodic maintenance of the power and cooling systems without any data center downtime.
But the question is, can you afford to build this sort of data center redundancy? The capital
costs of generators, UPS systems, and computer room cooling systems are very high. Many companies will spend the money for a single generator, but not for two. What’s the solution for reducing or eliminating data center downtime? It may be using an outsource data center to house your critical systems. These outsource computer rooms offer a range of data center redundancy to suit your requirements.
If downtime costs you big, consider outsource data center facilities to reduce your risks.
