Slicing Through Data Center Inefficiencies

Slicing Through Data Center Inefficiencies
HP Tech Dossier
Blade Servers:
Slicing Through Data
Center Inefficiencies
CIOs and IT managers are expected to understand and quickly respond to business needs while
providing needed technology and infrastructure more
cost-effectively than ever. Rising to the challenge,
savvy organizations are utilizing blade servers to
maximize their operational budgets and fulfill strategic
initiatives such as server consolidation, virtualization,
cloud computing and green IT.
Data continues to grow explosively, and rapid development of mobile applications and cloud computing is
expected to give an even greater impetus to future
growth—IDC recently forecast that between 2009 and
2020, digital data will grow by a factor of 44. Understandably, organizations are adding servers to deal with
this growth and accommodate business demands for
applications that create new revenue opportunities or
to extend and improve services to customers.
But simply installing a new server to fulfill each request
leads to server sprawl, with increased costs and
unrelenting complexity that further slows IT’s ability
to respond to business demands—IT has to deploy
and maintain more servers, stretching resources and
budgets. Virtualization promises some relief through
server consolidation, but that too can increase network sprawl at the server edge and result in memory
and I/O bottlenecks. If you’re relying on manual deployment, it can take weeks or even months to deliver
new services to the business. IT is also struggling
to control energy costs, and few organizations are
willing to commit to the additional power needs that
unbridled server growth requires.
Those factors make blade servers very attractive
to CIOs and IT managers trying to meet business
demands within budget constraints. “In many cases,
workload consolidation, combined with deployment
of new, power-efficient servers, will reduce operational costs related to IT personnel, downtime, power/
cooling costs and ongoing maintenance costs,” IDC
says in its enterprise server Top 10 predictions for
2011. HP—which, according to IDC’s third-quarter
2010 “Worldwide Quarterly Server Tracker” report,
leads the market for these systems, with a 54.1 percent revenue share—designed its HP BladeSystem
around a converged infrastructure that is poweraware and energy-optimized and takes advantage
of tightly integrated management tools.
// Blade Server Advantages
Blade servers perform the same function as rack servers while adding several compelling advantages: They
require less floor space, they use less power, they can
cost less to operate and they’re easier to deploy and
manage. By sharing resources such as power, cooling
and cabling through an integrated enclosure, blade
systems eliminate a great deal of the complexity and
overlap that can often plague the typical server stack.
A blade enclosure can accommodate up to 60 percent
more servers than a rack server enclosure of the
same size, with substantial savings in power and cooling costs as well as reduced requirements for cabling
and network switches. Blade servers are managed
through a browser-based graphical user interface,
which can result in savings of up to $25,000 for each
server rack simply due to elimination of individual keyboard, video and mouse (KVM) cables and switches.
// Leading the Way to a
Converged Infrastructure
Many organizations have traditionally responded to
business needs with a siloed approach, developing
infrastructure, applications and processes to address
a specific area of opportunity or pain. Technology suppliers have responded in kind, providing server silos,
network silos, storage silos—and even a management
silo to pull it all together.
HP Converged Infrastructure is intended to provide
2
// Blade Servers: Slicing Through Data Center Inefficiencies
CLICK HERE
to read how
Dallas
Cowboys
Generate
30% More
Revenue
with New
Stadium
and HP
Solutions
1
TTX Company customer success
story (June 2009).
IT with a blueprint for a forward-oriented data center
that eliminates silos and integrates technologies into
pools of interoperable resources that deliver operational flexibility as business needs change. These
pooled IT resources can be shared by many applications and can be managed as a service.
The HP BladeSystem fits that blueprint, with its
“change-ready architecture,” which provides one
common, highly standardized infrastructure designed
to accommodate changing business needs. This
solution enables you to maximize every hour, watt
and dollar, making the most of your investment. A key
element of that flexible architecture is HP’s wire-once
Virtual Connect technology, which makes server
changes transparent to storage and networks and
can result in as much as a 95 percent reduction in
switches, cables, network interface controllers (NICs)
and host bus adapters.
2
“Gaining Business Value and
ROI with HP Insight Control
Management Software”
(IDC, September 2010).
Server virtualization greatly speeds up server deployment and application growth, but storage and
Taking Full Advantage of the
Benefits of the Cloud
Nobody makes IT investments these days without some consideration of the transformational potential of cloud computing.
HP’s Converged Infrastructure strategy focuses on delivering operational flexibility that provides CIOs and IT managers with the ability
to move incrementally to a shared-services model or a private cloud.
The HP BladeSystem Matrix enables organizations to more easily
make that leap, integrating compute, storage, network and facilities resources with advanced management to deliver a virtualized,
highly automated environment with pools of shared resources that
can be leveraged on demand. It helps IT accelerate complex projects,
simplify daily tasks and lower costs. It’s designed to save on capital
expenditures and operational expenditures and enables setup of
complex infrastructures and applications in minutes instead of
weeks or months.
Go to www.hp.com/go/matrix to learn more about the
HP BladeSystem Matrix and how it is being used today.
Find out what
customers are
saying about
HP Matrix
networking infrastructures can’t keep pace with the
resulting growth in data and network traffic. HP Virtual
Connect creates “pools of LAN and SAN addresses
that can be assigned dynamically to server bays in
software, instead of being hardwired into the servers’
NICs,” according to an IDC analysis. HP Virtual Connect
FlexFabric modules and FlexFabric adapters support
four times as many data and storage connections per
server, with a decrease of as much as 95 percent in
the network equipment at the server edge.
Another factor that differentiates the HP BladeSystem
is the HP Insight Management server management
software, built on a Systems Insight Manager (SIM)
foundation. HP Insight Control provides essential
server management that leverages the management
functionality built into the HP BladeSystem and also
provides seamless integration with industry-leading
management tools such as Microsoft System Center,
VMware vCenter and HP software. With Insight Control,
IT can deploy servers in as little as 20 minutes, a 12-fold
improvement1, and reduce unplanned downtime by
83 percent2 while also reducing system administration
expenses with complete remote operation.
// Realizing the Ultimate
Converged Infrastructure
By reducing costs through integration and consolidation of all physical components and by adding more
benefits through superior management, virtualization
and automation, the HP BladeSystem enables the
more simplified, agile infrastructure that business
leaders are demanding. HP offers a full spectrum of
Converged Infrastructure services that help IT make
the transition, including consolidation, service management and business service automation services,
as well as data center transformation services.
Ultimately, the decision usually comes down to return
on investment (ROI). When you consider that most
organizations sink 70 percent of their IT budgets into
operations and maintenance, freeing up any portion of
those funds provides a greater opportunity to invest in
business innovation.
Blade servers provide compute resources that
are more cost-effective and efficient, and the HP
BladeSystem takes advantage of the Converged
Infrastructure approach to maximize savings in power
and cooling, utilize networking and storage components more efficiently and transform IT infrastructure
into a service-centric next-generation data center
model. For more information on migrating to the
HP BladeSystem, go to www.hp.com/go/
bladesystem. n
3
// Blade Servers: Slicing Through Data Center Inefficiencies
Suggested Reading
These additional resources include business white papers
and previously published articles from IDG Enterprise.
////////////
Department of Human Services
finalises hosting consolidation
By Tim Lohman
Computerworld Australia
SYDNEY (01/07/2011) - The Department of Human
Services (DHS) has virtualised its internet hosting
environment as a means of reducing hosting costs
as well as improving business continuity and disaster
recovery capabilities.
The project, run with partner Macquarie Telecom, involved the consolidation of most of the DHS’ networking and security infrastructure as well as 36 physical
servers and 42 virtual servers to eight HP blade
servers.
In addition to cutting costs and increasing reliability,
the project is expected to provide power savings of
up to 83 per cent.
Further, the time for the DHS to set up new services
and websites has been reduced from three to four
weeks to three to four days.
Read the full article
////////////
Shrink your IT infrastructure costs
By Kathleen Lau
Computerworld Canada
TORONTO (07/28/2010) - It’s no wonder IT leaders are
focusing concern on IT infrastructure and operations costs when it accounts for 60 per cent of total
IT spend. Since things are still uncertain despite the
economy showing signs of improvement, this area of
IT “strikes a resonant cord,” said Jay Pultz, vice-president and distinguished analyst with Gartner Inc.
“It has such a high interest among CIOs because
they’re not going to meet their budget goals if (infrastructure and operations) doesn’t meet its (budget),”
said Pultz during a recent Webinar discussing ways
enterprises can cut costs in their IT infrastructure and
operations (I&O). Gartner defines I&O as everything in
IT except business applications.
There are 10 ways to cut costs in I&O that, if done
completely, will reduce spend by 10 per cent within 12
months and 25 per cent in three years, said Pultz.
1. Defer those I&O initiatives that don’t meet
business needs. “Look at your key initiatives and
focus on those that help you meet the business
needs, help you reduce costs and help you keep to
uptime requirements for crucial systems,” said Pultz.
Preferred initiatives include data centre modernization
and consolidation, virtualization, improving processes
with ITIL, upgrading PCs, unified communications, and
a mobile enterprise strategy.
2. Re-examine networking costs. “These tend to
be the largest contracts that you have if you’re not
doing a significant amount of outsourcing,” said Pultz.
By reviewing current telco contracts, enterprises can
renegotiate a lower rate, identify billing errors and
things they should no longer be paying for. Pultz also
suggests revisiting the network architecture and refining uptime requirements.
3. Consolidate I&O. “You must ask yourself if you
have consolidated all that you can,” said Pultz. Most
data centre managers understand the benefit of
replacing distributed and standalone servers with
new form factors in the data centre such as rack and
blade. Yet less than 10 per cent have consolidated
their servers, said Pultz.
4. Virtualize I&O. “Virtualization is an incredibly
powerful technology to reduce hardware costs,
reduce power costs, improve utilization and so forth,”
said Pultz. For instance, reducing server count by 75
per cent will reduce power consumption by a similar
amount. Pultz suggests: “Don’t go slow, accelerate
as much as possible your plans to virtualize servers”
because of the advantages that can be reaped from
high levels of virtualization.
Read the full list
4
// Blade Servers: Slicing Through Data Center Inefficiencies
Suggested Reading
////////////
Forrester: Ways to Cut Data
Center Energy Costs
By Doug Washburn
CIO.com
FRAMINGHAM (10/20/2010) - As the global economy
is recovers, pent-up business demand for new apps
and market initiatives is driving server investments.
Forrester finds that 25 percent of organizations expect
server spend to grow by 5 percent to 10 percent, and
6 percent expect it to grow by 10 percent or more. And
to reduce operating and capital costs, improve disaster
recovery, and accelerate time-to-market for new apps,
organizations are turning to server virtualization.
But a new motivator to expand and improve the use
of server virtualization is bubbling to the surface:
reducing energy consumption. Why? Forrester finds
that there are three primary motivators.
Financial. The costs to power and cool a server
over its life may actually exceed its purchase price.
Virtualization reduces the overall energy consumption
of your server footprint, thereby allowing the same
workload to run on fewer physical, energy-consuming
servers.
Resiliency. To ensure that uptime and service-level
agreements are maintained, virtualization alleviates
out-of-space, power, and cooling constraints.
Green. Virtualization reduces the overall server footprint and cuts energy-related carbon dioxide emissions as well as the electronic waste from purchasing
and then disposing server equipment in the future.
To cut server energy costs by up to 65 percent and exploit your energy savings potential from virtualization,
Forrester recommends three process improvements:
1. Increase your overall virtual-to-physical
server footprint.
There are significant opportunities for organizations
to increase their overall virtualization footprint across
all server environments and platforms. We found that,
while approximately 90 percent of firms are virtualizing or planning to virtualize their servers, only 37
percent of their x86 operating system instances are
virtual servers. In two years time, this is expected to
increase to 65 percent.
Additionally, the extent of virtualization varies significantly based on the server environment, and the
platform. The first step to maximizing energy savings is to increase the overall virtualization footprint
across all environments and platforms. To ensure
you’re actually saving energy, be sure to turn off or
decommission servers that are no longer running any
workloads. Forrester’s Green IT maturity assessment
methodology prescribes the following virtualization
targets to achieve one of four levels of green IT maturity: 1) Needs improvement (1 percent to 25 percent
virtualized); 2) Improving (26 percent to 50 percent
virtualized); 3) Robust (51 percent to 75 percent virtualized); and 4) Best-in-class (76 percent to 100 percent
virtualized).
2. Maximize your virtual machine to physical
host and utilization ratios.
Virtualization alone is not enough. In addition to
increasing the overall server virtualization footprint,
drive additional energy savings by virtualizing more
efficiently. Server virtualization ratios are not keeping pace with modern hardware and virtualization
platform capabilities. It’s common to break even on
the purchase of a new server with a 4-to-1 virtual
machine (VM)-to-physical host ratio, but most servers
can accommodate 15 VMs. Virtualizing more efficiently
can help you avoid three new server purchases, not
to mention the additional power, cooling, and space
expenses from this new equipment. n
Read the full article
4AA3-3848ENW
Was this manual useful for you? yes no
Thank you for your participation!

* Your assessment is very important for improving the work of artificial intelligence, which forms the content of this project

Download PDF

advertising