|
by James I. Nelson and Edward van Leent
Can you answer these questions?
- What are the tier levels to describe the availability
capability of a data center?
- How much air-conditioning capacity will you need
to build a data center with 150kW UPS power?
- True or False: Because of the rise in power consumption,
EMF is on the rise, potentially causing downtime
and health risks?
This is just a fraction of the knowledge
business continuity professionals
should understand in order to provide
an integrated approach for business
resiliency. Business continuity professionals
need to have practical experience
and insights in what works and what
doesn’t work when it comes to setting
up, maintaining, and running mission
critical sites such as the data center.
BC professionals will also benefit from
understanding the essential elements
of a high-available, fully available, and
efficient data center.
Traditionally, the focus of BC professionals
has been on ensuring the
continuity of business processes. The IT
department has taken the lead in disaster
recovery for the technical infrastructure,
operations, and data protection. The
facilities department takes the lead for
the physical plant, utilities and physical
security. A natural place for them to
come together is in the data center. As
we have become more dependent on the
IT infrastructure to support everything
we do, the resilience of the organization
has become very dependent upon
the data center. The BC team works to
coordinate with the business leaders and
also with IT and Facilities. So the time
has come for the people responsible for the resiliency of the organization to be
trained to speak the language of the
data center and to have a better understanding
of how IT and Facilities relate
to each other.
Main Causes of Data Center
Downtime
The main causes of data center
downtime are human error and hardware/
system failure. While the errors
usually made are not intentional, even
small mistakes can lead to big disasters.
Most of the time these hardware failures
occur due to the data center being
wrongly designed, maintained or managed.
Downtime is also often caused by
uneven cooling or power quality issues.
Training Can Improve
the Resiliency of Data Centers
Many of our current data center professionals
were in on the ground floor of
data center development, but many of
those professionals are moving towards
retirement. It is forecasted that there will
be a shortage of personnel with adequate
education and training to replace them,
so now is the time to begin training and
certifying personnel who work in and
around the data center.
Those best positioned to respond to this
need and take advantage of the opportunity
to grow professionally are current
data center managers, supervisors, auditors,
IT professionals, business continuity
professionals, and facility managers.
At a minimum, all personnel who
work in and around the data center or
with responsibilities that include the
data center need to have a good understanding
of the following elements and
should be able to:
- Choose an optimum site for the
data center based on current and future
needs
- Describe all components important
for hi-availability in a data center and
how to effectively set up the data center
and manage it
- Name and apply the various industry
standards
- Describe the various technologies for
UPS, fire suppression, cooling, monitoring
systems, cabling standards etc. and
how to choose and apply them effectively
to enhance the hi-availability of the data
center at minimum cost
- Create a robust electrical distribution
system to avoid costly downtime
- Enhance cooling capabilities and
efficiency in the data center by using
techniques and new methodologies for
future high-power cooling requirements
- Design a highly reliable and scalable
network architecture and learn how to
ensure installers use proper testing techniques
- Negotiate effective maintenance contracts
with equipment suppliers ensuring
the best “bang for the buck”
- Set up effective data center monitoring
to insure the right people get the
right message
- Insure proper security measures,
both process and technical, are in place
to safeguard your company’s precious
information in the data center
- Describe the various IT service management
standards, best practices and
processes and how to effectively use
them for increased efficiency of operations
while minimizing risk of downtime
caused by change.
About the Authors
James I. Nelson is the President of Business
Continuity Services, Inc. (www.BusinessContinuitySvcs.com) a consulting firm with a focus
on business continuity, crisis management, and
disaster recovery. He also serves as President
of the Board of Directors for the ICOR.
Edward van Leent is a certified lead
auditor and lead consultant for BS15000/
ISO-IEC20000, a world-wide standard for ITService
Management. He can be contacted at
Edward@epi-ap.com. |
