| |
Applying Data Center
Performance Measurement to Mitigate Challenges
by 42U
Abstract:
Measuring data center performance is vital to
maintaining the network and system availability that
internal customers expect. Data center managers need
to be able to track and assess equipment
availability, assess and manage critical facilities,
and measure data center energy consumption.
Monitoring solutions, remote management products,
and industry-specific metrics can help datacenter
managers measure performance, proactively identify
and mitigate potential issues, and improve the
overall organizational bottom line.
Download the
full-text article in PDF format.
Organizations increasingly depend on their IT
infrastructure to support mission-critical
activities. IT personnel are held accountable for
managing this infrastructure and data center
performance measurement is a vital tool in
maintaining high performance and delivery. From
assessing and ensuring the availability of critical
facilities, monitoring geographically dispersed
environments, and improving the overall
organizational bottom line, IT personnel require
tools that allow them to measure performance and
proactively identify and mitigate potential issues.
Several industry-related publications and groups
have noted the importance of data center metrics,
and have named the need to measure data center
performance as a key issue for 2006 and 2007.
(1)
Recommended Data Center Performance
Measurements and Solutions
Issue #1: Ability to Track and Assess Equipment
Availability
For most organizations, the cost of server or
network downtime is significant and internal
customers expect network and system availability of
"Five Nines" or 99.999%
(2). On a daily basis, IT managers need
to be able to assess availability/reliability of
equipment and all external components that support
operations, so that they can reduce downtime,
identify and mitigate issues, and provide a secure
environment for an organization's mission-critical
equipment. IT professionals also need an effective
way to review historical trends to identify
equipment or systems that need to be redesigned or
replaced.
Meeting the Challenge:
Environmental monitoring solutions provide
real-time feedback about critical systems with
continuous, proactive monitoring of all pertinent
factors including temperature, amperage draw,
humidity, dew point, and physical security. These
solutions allow administrators to set thresholds for
environmental conditions and send alerts securely
via e-mail, text message, or SNMP if said thresholds
are exceeded. In addition, environmental monitoring
systems provide valuable historical reports, alert
information, and logs that allow administrators to
identify trends and adapt practices accordingly.
This data can help with statistical analysis,
modeling, and forecasting.
Centralized Environmental Monitoring Solution
Issue #2: Ability to Assess
Availability/Reliability of Critical Facilities
When assigning critical resources, IT professionals
need to determine the highest-priority sites and
facilities. Several organizations have proposed
systems to help administrators classify and rate
their facilities. For example, the Uptime Institute
applies a four-tier classification system based on
factors such as fault tolerance, useable capacity,
sustainability, and concurrent maintainability
(3). As another approach, the Syska
Hennessy Group provides a seven-level criticality
classification system that aims to help data center
managers evaluate facilities that are vital to the
mission of their organizations and provides a
framework to help assess potential data center
vulnerabilities (4). After determining
critical sites, administrators need to be able to
implement appropriate management and control
systems.
Meeting the Challenge: Enterprise management
solutions, such as
KVM
over IP or
service processor aggregation appliances,
provide administrators with 24/7 access to servers,
serial devices,
remote power, and other equipment both locally
and remotely. These solutions provide BIOS-level
access to mission-critical equipment, reducing
system and network downtime by enabling immediate
access to failed resources and centralizing data
center management. These solutions also provide
visibility to daily operations and occurrences
through comprehensive audit logging and reporting
tools. Enterprise-level management tools provide
redundant architecture, including primary failover
access at both the hardware and software levels.
Issue #3: Ability to Measure Energy Consumption
in the Data Center
Across almost every industry, rising
data center power consumption and heat are major
issues, particularly as organizations are
incorporating blade servers and high-density
server
racks into their IT infrastructures. Many
organizations are studying how power consumption can
be reduced in the data center. For example, the EPA
is studying ways to make computer servers and data
centers more energy efficient, and is considering a
possible ENERGY STAR designation for servers and
other data center equipment.
(5) The Green Grid, a newly formed
non-profit consortium of information technology
companies, is proposing the use of Power Usage
Effectiveness (PUE) and Datacenter Efficiency (DCiE)
metrics, which would enable IT personnel to estimate
the energy efficiency of data centers, compare
results against other data centers, and determine if
energy efficiency improvements need to be made. As
defined by the Green Grid, Power Usage Effectiveness
(PUE)= Total Facility Power/ IT Equipment Power;
Datacenter Efficiency (DCE)= IT Equipment Power/
Total Facility Power. (6)
Meeting the Challenge: Utilizing PUE and DCE
information, IT personnel can begin to evaluate
their own energy efficiency. Using these metrics, as
well as application-specific data, data center
managers should start to consider ways of reducing
data center power consumption. Standalone data
centers can also use the EPA Energy Star building
performance rating tool, Portfolio Manager, to rate
a facility's energy performance in comparison to
similar facilities (at the whole-building level).
Some answers include transitioning to 208V or
three-phase power provisioning. Higher voltage power
reduces amperage requirements, allows equipment to
operate more efficiently, and can reduce the amount
of hardware required. IT personnel should conduct a
thorough audit of equipment, determine if any
servers can be consolidated or discarded, and clean
up any clutter under the data center floor, such as
cabling, that might be impeding air flow. The use of
blanking panels and
cable management accessories in the rack can
also assist in these efforts.
How Can The Latest Technologies Help You Improve
Data Center Performance?
The team at 42U
specializes in needs assessment, solution design,
and implementation support to ensure that IT
professionals maximize their use of current
technologies to improve overall business
performance. 42U provides complete remote management
solutions, including KVM over IP, intelligent power,
environmental monitoring,
rack cooling, and
rackmount solutions. A 42U sales engineer can
help you improve your data center performance by
helping you select solutions that are most
appropriate for your organization's particular needs
and environment.
References:
- Stansberry, Matt, "Top Ten Data Center
Stories of 2006"
- MacKinnon, Chris, "How Is Your Data Center
Performing? A Metric To The Madness. and
"Optimizing Datacenter Performance and Building
ROI: The TeamQuest Approach", IDC/TeamQuest,
- Brill, Kenneth; Pitt, Turner; and Seader,
John. "Tier Classifications Define Site
Infrastructure Performance," Uptime Institute
- Burkhardt, Jerry and Dennis, Richard.
"Assessing criticality levels in the data
center", Data Center Management Advisory
Newsletter
- "Enterprise Server and Data Center Energy
Efficiency Initiatives"
- "Green Grid Metrics: Describing Datacenter
Power Efficiency",
About 42U
42U focuses on providing Facilities and Data Center Managers with objective
and trusted independent information on
Data Center Power and
Data Center Cooling best practices along with
KVM over IP and Remote Power
lights out management to help them reduce their organization's power
consumption. Our Data Center Management
website has helped millions of IT professionals globally who search for best
practices and technologies to help them make their computer environment more
efficient.
This work is licensed under a
Creative Commons Attribution-No Derivative Works 3.0 Unported License.
|
|
