The Cost Of Retaining Aging It Infrastructure

WHITE P APER
The Cost of Retaining Aging IT Infrastructure
Sponsored by: HP

Randy Perry Jean S. Bozman
Joseph C. Pucciarelli Jed Scaramella
February 2012

IDC OPINION
www.idc.com

Many organizations, when faced with budget challenges, put off capital expenditures
(capex) and seek alternatives to acquiring new hardware platforms, such as lengthening
server life cycles and extending software licenses. This pattern of stretching the useful
life cycle of servers has a number of near-term benefits for customers in terms of
F.508.935.4015

depreciating assets over a long period of time or prolonging an existing lease. But if a
transition to new technologies has been deferred too long, then the time comes when the
system has fallen far behind the performance and cost-efficiency levels being offered by
multiple vendors in the marketplace today. This has been especially true in recent years,
as the performance of processors has more than doubled each year, based on the
P.508.872.8200

emergence of multicore, multiprocessor system designs with improved system speeds.

This paper demonstrates that a buy-and-hold strategy can actually add costs to the
datacenter, for a number of reasons, as systems age in place:
Global Headquarters: 5 Speen Street Framingham, MA 01701 USA

 Hardware maintenance costs rise over time, and performance lags behind more
current server offerings.

 Energy efficiency is not as advanced in older server models — leading to rising
power/cooling costs in the latter years of the server's usable life cycle.

 Applications software and systems software fall behind the current versions
available in the marketplace, and security may require frequent updates. After
five years of use, the cost of replacement climbs.

To understand more about server replacement cycles and ongoing operational costs,
IDC studied many sites that remained on an existing platform long after its initial
introduction and then upgraded. When comparisons to the succeeding generations of
technology are made, customers have found that the increase in scalability and
performance of newer systems, combined with a reduction in server "footprint" size
and overall power/cooling requirements, resulted in significant reductions in ongoing
costs, or opex, per 100 end users supported.

This paper describes HP ProLiant Gen8 servers, the technology on which they are
based, and the way they address many of the causes of operational costs found at
customer sites. The hardware and software capabilities of the HP servers were designed
to be proactive, reducing the effort and knowledge required to run the server systems
and leveraging automation to reduce maintenance costs and IT staff costs.

SITUATION OVERVIEW

Saving Money by Leveraging Technology
Refresh: How Current Accounting Misses

Most organizations continue to purchase their servers and IT equipment and then,
following the initial investment, use a "standard" financially derived amortization
period — often five years. Typically, this has led to a useful server life cycle of three
to seven years, depending on the type of platform, operating system, and workloads
being used. While most IT shops replace their x86 systems every three to five years,
they have tended to hold onto their Unix servers supporting mission-critical workloads
for longer periods of time — generally five to seven years or more — given the
importance of the workloads being supported.

After acquiring and capitalizing equipment and then initiating the amortization period,
most IT managers avoid making further changes, resulting in a delay in updating the
systems or providing a technology refresh. Often, they do not replace the equipment
before its normal depreciation cycle runs its course, as long as the system is
performing adequately and meeting availability requirements. This approach to server
replacement/renewal cycles misses an important assessment of the actual conditions
and cost factors experienced. Instead, it relies on the calendar to determine when the
server should be replaced or refreshed with new technology.

During this time, system administrators may work to repeatedly upgrade and
reconfigure servers in support of workloads rather than to consider a fully burdened
cost assessment highlighting the cost reductions that could be gained by replacing
the servers sooner. In many cases, a cycle of repeated upgrades, security patches,
and rising maintenance and management costs can accelerate, over time, if the life
cycle of the server is extended to four years or more.

Current Capital Constraints Contribute to
Lengthened Server Life Cycles

IDC's supply-side data for the worldwide server market showed patterns of
lengthened server life cycles. The data documented the delay and deferral of many
midrange and high-end servers, starting in fall 2008 — at the onset of the economic
downturn — and continuing through 2010. At that point, IDC saw an uptick in
midrange and high-end server sales, including non-x86 server systems, that was fed
by a wave of technology upgrades across those server classes. At the same time, the
level of investments in x86 server technology has grown, now generating more than
95% of server unit shipments per year and more than 65% of server market revenue
per year.

Following the 2008–2009 downturn, the recent rise in server market revenue reflected
that a technology replacement cycle was under way. There were also indications that
IT organizations needed to acquire new hardware platforms while taking advantage of
leveraging virtualization to consolidate workloads onto fewer server platforms for the
sake of operational efficiency and reduced IT costs.

2 #233175 ©2012 IDC

Focusing on Operational Costs

The drive to reduce capital expenditures is strong and understandably so given the
current economic climate. However, IT managers also know that the need to address
opex within the datacenter is equally important.

Although IT managers did a good job of capping IT spend on servers and storage
throughout the economic downturn, costs on the operational side of the IT
organization continued to grow. Starting in the late 2000s, and throughout the
economic downturn period, costs for maintenance and management, along with costs
for power/cooling, have soared. Power/cooling costs grew eight times as fast as
server acquisition costs — and costs for maintenance/management, viewed as a
category, grew four times as fast as server acquisition costs.

Maintenance/Management Costs and Power/Cooling Costs Rise over
Time
As Figure 1 shows, by 2010, maintenance/management costs generated twice as
much in total IT costs as server acquisition alone — and power/cooling costs grew
enough to nearly equal server acquisition costs worldwide; in some cities,
power/cooling costs already outstripped the server acquisition costs. Meanwhile, the
worldwide installed base now stands at more than 35 million units and is projected to
grow even more. Fortunately, the growth in logical servers (virtual servers or virtual
machines/VMs) is providing more usable capacity per physical server — and this is
improving server resource utilization for each server — over time.

©2012 IDC #233175 3

FIGURE 1

Worldwide Spending on Servers, Power and Cooling, and
Management/Administration

Source: IDC, 2012

Server Replacement Cycles

What does this pattern of maintenance, management, and operating costs mean to
server life cycles? How has this changed since 2010?

Figure 1 demonstrates that opex must be kept in check, or it will outpace the savings
from deferred server acquisitions. Certainly, midrange and high-end server revenue
and unit shipments have been held in check since the economic downturn began in
fall 2008 — but IDC supply-side research found that midrange and high-end servers
saw a return to revenue and unit growth in 4Q10 and 1H11. The changes in the
supply-side data indicate that a period of technology replacement has begun as
workloads are being consolidated onto fewer, more powerful platforms.

There are other signs of technology refresh: IDC's customer-based study of
Server Workloads found that technology refresh helped address opex. In 2010, the
IDC Server Workloads study of 1,000+ IT sites found that 39% of new server
acquisitions occurred as part of a routine, or planned, server refresh. New application

4 #233175 ©2012 IDC

projects drove another 33% of new server purchases, and 28% more were acquired
to support additional compute capacity.

As we see in this white paper, aging server infrastructures can play a substantial cost-
adding role in datacenter cost dynamics. The trend to leverage VMs running on the
hardware is key to improving resource utilization — and to providing highly granular
controllability of workloads. Further, workload isolation is enforced, which preserves
uptime by preventing workloads from interfering with one another — taking a "pooled
resources" approach to computing resources.

IDC'S STUDY OF SERVER TRAN SITION
EXPERIENCE
From 2008 to 2011, IDC studied more than 50 sites that had upgraded their server
infrastructure to determine the business value experienced by customers
consolidating on newer servers. The study highlighted the experiences at sites that
had consolidated disparate server workloads on newer servers. These companies
range in size from 1,500 to 175,000 employees and are located across geographies,
including the United States, Western Europe, and Central Europe.

Importantly, the organizations represent a wide variety of vertical markets, including
retail, financial services, manufacturing, and energy. Most of these organizations are
large companies with a server infrastructure that supports tens of thousands of intra-
enterprise end users — and an even larger number of extra-enterprise users,
including end customers who are accessing their enterprise systems.

This study provided substantial data about the organizations' deployments as part of
an IDC business value survey measuring the costs associated with deployment of
new systems and the operational results, such as reductions in IT operating costs,
reductions in costs related to system downtime, and employee productivity
improvements associated with those deployments.

Research Methodology

This study used research interviews to determine the sources of cost — both capex
and opex. By capturing these components of cost, IDC was able to calculate the
impact of moving from older servers to new servers in terms of hardware acquisition
costs, IT staff costs, downtime, and productivity — both for IT staff and for end users.

The interviews yielded information defining up-front investment costs in the
technology, as well as deployment and ongoing maintenance costs. The interviews
also elicited the companies' experiences with tangible and measurable IT and
end-user business benefits over varying periods. IDC's Business Value team
combined all of these factors in the synthesis of an overall cost of aging infrastructure
assessment.

©2012 IDC #233175 5

Key Findings

IDC's customer-based research found that failure rates began to climb as servers
aged into their fourth year — and beyond. It found that upgrading resulted in a return
on investment (ROI) of more than 150% over three years. Importantly, savings from
the technology transition covered the initial investment (payback period) after less
than a year (11.7 months).

The savings from reduced maintenance and support costs paid for the investment in
new technology. While servers have become much more powerful over time,
acquisition costs and energy requirements for power and cooling have dropped
dramatically. The IDC study found that, for every dollar invested in the new
technology, two and a half times as much was eventually saved, over a period of
three years, per 100 users using the new system.

Research consistently showed that upgrading from aged servers to newer server
platforms reduced cost and increased performance. Two recurring factors appeared
to directly affect these benefits of upgrading:

 Servers experience an optimal life span, and continued usage beyond that
optimal life span causes maintenance costs to spiral and downtime to increase.

 Newer platforms consistently provide the price performance increases inherent to
Moore's law at lower power consumption.

As Figure 2 indicates, as servers age beyond the 3- to 3.5-year optimal replacement
cycle, the cost of annual maintenance increases annually by 24% to 44%. Multiple
conditions contribute to this increase. Older systems break down more frequently as
average failure rates increase from 7% to 18%. Operating system software and
application software designed for three-year optimal life experience more issues.
Beyond that threshold, patching becomes a more frequent activity — and most
companies lose interest in keeping up with the more frequent upgrades. Migrating to
newer software while running on the same hardware platform creates compatibility
issues and business alignment issues of its own.

6 #233175 ©2012 IDC

FIGURE 2

Effects of Time on IT Infrastructure (Server) Costs

Notes:
 Support cost values equal annual cost in US$ per 10 users.
 Failure rate refers to the frequency of failure per year and per server based on the age of the
server.
 Downtime refers to hours of downtime per year.
Source: IDC's Business Value Research, 2012

To create an IDC Dynamic White Paper that estimates expected cost savings for your
organization, click here. This tool will create a customized version of this White Paper
with the results of your estimated cost savings inserted.

To understand the reasons these upgrade changes become so pronounced, one
needs to look at the technology changes between generations of servers, which we
describe in the following sections.

©2012 IDC #233175 7

HOW NEW TECHNOLOGY IMPROVES
BUSINESS

Innovations in HP ProLiant Systems

HP ProLiant systems have introduced new technologies with each new generation of
systems design. With its HP ProLiant Gen8 servers, HP increased the automated
management capabilities of the servers by embedding special firmware and logic
directly on the system motherboard. This built-in intelligence addresses the variation
in IT skill sets at customer sites so that successful deployments and maintenance
best practices take place in a consistent way. This approach enables ongoing
operations and avoids unplanned downtime.

HP ProLiant Gen8 servers are designed to reduce the time and costs associated with
installing, provisioning, and maintaining these systems, including the DL rack-
optimized servers, the BL blade servers, the ML tower servers — and the SL scale-
out servers for cloud computing and service providers.

Innovations in the HP ProLiant Gen8 design improve problem detection, monitor
system temperature, and launch responsive actions to keep the server within a series
of preset parameters. The features proactively seek any signs that hardware
components might fail and forward the related operational information to a unified
console — providing a comprehensive view about the "state" of the system. Equally
important, the system has the capacity to take many actions that will allow it to stay
online, without further intervention by IT staff. For small and medium-sized business
(SMB) sites — and for large organizations with remote business units — these
capabilities are designed to reduce the number of actions that must be taken,
throughout the server life cycle, to maintain smooth operations.

HP ProLiant Gen8 Servers with HP ProActive
Insight Architecture

In designing its HP ProLiant server products, HP focused not only on improving
performance but also on how to resolve the escalating problems of managing a
server throughout its life cycle while avoiding downtime for planned and unplanned
outages. HP leveraged its service databases, reviewing patterns in system conditions
that have been made evident over a period of 20 years of incident responses. This
review formed the automation features that have been built into the HP ProLiant
Gen8 design. Design components have been built into the hardware at the system-
board level, instrumenting them to respond to a variety of operational conditions and
triggering remediation of many of the negative conditions, including firmware conflicts
and memory faults.

HP addressed the customer issues that were revealed in IDC's customer-based
research. As Figure 2 shows, while there is some advantage to lengthening server life
cycles, a "knee in the curve" develops in year 4, which makes continued operation of
the server progressively more expensive over time. It reaches a point of diminishing
returns by years 5, 6, and 7 — making it more expensive to operate older servers by
a factor of 2.5 (server administration and support costs in year 5 versus those costs in
year 1) as failure rates increase and support costs rise sharply.

8 #233175 ©2012 IDC

HP ProLiant Gen8 Design Addresses Operational Costs
To address these costs of operation, HP is providing HP ProActive Insight
architecture, a multifaceted set of capabilities for HP ProLiant Gen8 servers that
directly address many causes of planned and unplanned downtime. HP ProActive
Insight architecture delivers these new capabilities across four major categories of
server use as follows:

 HP Integrated Life-Cycle Automation. HP has focused many of the
enhancements in its HP ProLiant Gen8 on addressing IT organizations'
increasing challenge of administering the IT environment. Many of the features
are designed to simplify and automate as much as possible, with servers now
executing or easing many of the life-cycle tasks that add to system
administrators' management overhead. Each HP ProLiant Gen8 server now
incorporates scores of onboard functions for identifying the current state of the
server (e.g., firmware, provisioning location, operating system version,
hypervisor, warranty status) and operating variables (e.g., temperature, memory
usage, power utilization). The HP ProActive Insight architecture uses this data to
centrally manage and automate operations, where needed. This approach to
system administration and management gives clients a fuller view of the installed
environment — even as it automates and simplifies system provisioning, problem
troubleshooting, and the process of periodically installing software updates.

 HP Dynamic Workload Acceleration. To accelerate data-intensive application
performance, HP engineers tuned the system architecture for solid state
technology and to improve data caching size and speed, increasing the number
of storage drives that each server can support and extending cached data
retention to avoid data loss. HP has also expanded customers' options for
integrating storage and compute resource. This approach brings storage and
compute closer together and eliminates much of the cost and complexity. It
addresses the most common performance bottleneck — storage. The addition of
the data protection analytics and the intelligent performance features is aimed at
improving overall system performance at a time when customers are discovering
that the amount of data for each workload is rising rapidly.

 HP Automated Energy Optimization. As highlighted in Figure 1, many IT
executives are struggling with the space, power, and cooling required to host
additional systems in an already-crowded datacenter. To address this challenge,
HP has extended the HP ProActive Insight architecture to provide more
intelligent sense-and-respond technologies that reduce the electrical power and
airflow needed to operate HP ProLiant Gen8 servers. For example, the expanded
web of temperature sensors, which HP calls the HP 3D Sea of Sensors, detect
more precisely the part of the server that needs cooling, direct fans to this area,
and reduce unnecessary fan power by dozens of watts per server. This approach
allows workloads to be run in less space, with fewer power and cooling
requirements than in previous generations of HP servers. It also reduces the
amount of manual checking for power and rack configurations, which often leads
to inefficient onsite management, manual configuration errors, and downtime.

©2012 IDC #233175 9

 HP Proactive Service and Support. HP expects this combination of information
and automation to lead to an improved IT service experience, whether that
service is provided by HP or by its channel partners. As part of the HP ProLiant
Gen8 release, HP created a comprehensive IT management and support
solution to integrate and take advantage of the centrally consolidated repository
of service outcomes that HP has gathered over 20 years. HP ServiceONE
support teams can now leverage this information to help clients as they
proactively resolve issues and deliver real-time insight leading to quick
resolutions while continuously improving datacenter operations through quick
repairs and optimized "windows" for planned downtime. For example, HP support
can alert customers and act on conditions such as degrading performance,
memory errors, or other service conditions well before customers are aware that
such actions should be taken. This access has been strengthened through use of
a cloud-based "portal" that delivers customer service information. This will help
customers with limited IT staff reduce periods of planned downtime and avoid
unplanned downtime.

Reducing Administration Costs

As we have seen in this paper, operational costs for IT staff time, power/cooling, and
responses to unplanned downtime combine to drain IT budgets. However, to the
degree that any, or all, of these cost factors could be reduced, then the operational
costs and the ROI to acquire the computers would be reduced.

As servers age in place, the number of service incidents tends to increase over time.
That means that close oversight of all of the components — and the ability to address
any failing components prior to disruption of business services — is critical to
maintaining business continuity. HP has long provided such oversight through its HP
Integrated Lights-Out (iLO) technology and other system management software
capabilities, but it has greatly expanded them, in terms of granularity and coverage
and automation, in every HP ProLiant Gen8 server. As discussed, the HP ProActive
Insight architecture's embedded management features support the complete life cycle
of the server, from initial deployment, through ongoing management, to service
alerting and support. These features address some of the most time-intensive server
administration functions, which are illustrated in Figure 3. They reduce the time it
takes for IT administration tasks such as deploying, managing, and servicing the
virtualized and physical server infrastructure.

10 #233175 ©2012 IDC

FIGURE 3

Server Life-Cycle Administration Functions, Objectives, and
Steps

Source: IDC, 2012

Software and Hardware Capabilities

Firmware and software capabilities ensure that organizations install the appropriate
version and release number of the system-level software on the new servers.
HP Intelligent Provisioning provides a fully integrated tool for system configuration and
operating system installation. This allows system administrators to identify and correct
configuration errors before new servers are deployed. The built-in smart update
capability recognizes whether the system software is out of date and automatically
downloads the latest update, if needed. In addition, HP Active Health provides 24 x 7
automated monitoring, self-diagnosis, and alerting for the HP ProLiant systems.

Hardware-based mechanical improvements increase productivity and uptime as well.
For example, at initial physical provisioning and deployment, the HP Smart Socket
guide ensures proper processor placement and installation, preventing motherboard
damage and downtime that might otherwise result when processor pins are damaged.

©2012 IDC #233175 11

The HP Smart Drives prevent common causes of data loss, such as the untimely
removal of an active drive, and do so through a new, brightly lit LED display showing
that disk activity. In addition, upon installation, the new HP racks are able to
automatically register a server's location in a rack, recording its position for later asset
reporting. In support of server software configuration steps, the server records and
reports a series of server configuration details to the central console. These details
include the firmware state, the operating system version, the hypervisor version —
and the boot procedure that was used. In addition, HP ProActive Insight tracks and
reports on the warranty and service status of each device. The entire HP ProActive
Insight architecture supports not only the customer's IT staff but also HP's extensive
worldwide network of thousands of service professionals who monitor and alert from
their local vantage point. The entire solution reduces touches, reports on errors
before they occur, and, in general, reduces the downtime and associated labor of
system failures.

Measuring What You Manage: Data for
Automated Management

Many customers of x86 servers are facing rising costs for maintenance and
management of those servers over time. These challenges are compounded by the
economic uncertainties that are causing IT budgets to be limited, or reduced, for
2012. That is why efficient management and care of large numbers of x86 servers is
becoming vitally important to many customers in SMBs, midmarket companies, and
large enterprises.

Efforts to reduce manual processes traditionally used by IT staff will directly result in
operational cost reductions; therefore, technologies aimed at automating repetitive
tasks are well-suited to address these customer pain points.

Key to the automation process is the collection of server data and of parameters
indicating the health of the server system. The system proactively monitors the
servers via sensors, and this information informs the management console about
whether components need to be replaced or turned off prior to replacement.

Leveraging HP's Converged Infrastructure

Leveraging all of the assets listed earlier, along with leading offerings across the
storage, system, and network domains, HP has been providing converged IT
infrastructure in virtualized environments for many years. By design, HP's Converged
Infrastructure (CI) — combining server, storage, and networking components in the
same server-based solution — consists of preintegrated, tested, and supported
solutions. These CI solutions are optimized for cloud, virtualization, and next-
generation applications. HP intends for these systems to reduce time and cost
demands on IT staff resources and to reduce the amount of time required for
planning, procurement, and deployment, accelerating the time to value for acquiring
the server solution.

12 #233175 ©2012 IDC

HP provides customers with several options:

 HP VirtualSystem simplifies and extends converged infrastructure into optimized,
turnkey solutions for server and desktop virtualization. HP designed it to deliver a
high-performance virtualized environment with pretuned server, storage,
networking, management, and hypervisor resources. The HP VirtualSystem is
targeted for use cases including hosting one or multiple applications — including
mission-critical applications — and provides the foundation for the next level of
system, the HP CloudSystem.

 HP CloudSystem is an integrated system for building and managing services
across public, private, and hybrid clouds. It combines Converged Infrastructure
with HP Cloud Service Automation software, providing a cloud platform that aims
to increase the agility of enterprises and drive revenue growth for service
providers.

 HP AppSystems is a portfolio of integrated systems that have been optimized for
dedicated workloads such as data management, business reporting/analytics,
and collaboration. HP designed and tuned HP AppSystems for rapid deployment,
application performance, and support for service-level requirements.

IT Benefits

System administrators spend a lot of their working hours checking on mechanical
devices, such as electrical cables, power cords, system board connections, fans, and
the like. This work is time and labor intensive. Building in connections and
components directly on the system boards reduces the total number of connections
that must be checked, time and again, by system administrators. By detecting
hardware component issues in a more automated way, the HP ProLiant Gen8
technologies reduce the time associated with identifying and diagnosing server
hardware issues and speed the time to resolution of those problems. All of this
reduces IT staff time associated with deployment of physical servers and ongoing
maintenance.

Unplanned downtime has a big impact on operational costs and must be avoided
wherever possible. Preventive maintenance of hardware components — replacing the
components prior to an actual failure — reduces unplanned downtime appreciably.
"Phone home" capabilities provide an early warning system, allowing administrators
to proactively replace system components and avoid actual downtime.

Finally, upgrades and updates for any given server — multiplied by tens or hundreds
of servers — result in major costs within the enterprise datacenter. Automation of
care/maintenance avoids needless duplication of effort, reduces the number of
physical tasks, and helps avoid downtime.

©2012 IDC #233175 13

Business Benefits

Today's businesses rely on hundreds of servers operating efficiently — and doing so
on a 24 x 7 x 365 basis. Any prolonged disruptions in these operations, which
businesses sometimes call "computer glitches," are simply unacceptable because
they affect the availability of applications and databases being accessed by
employees and by end customers. Therefore, any interruptions are to be avoided. In
the event that processing is interrupted by an outage, it must be able to resume on
other systems as quickly as possible.

The ability to manage all servers from a single point of view, or console, has the
advantage of reducing time associated with identifying a problem in the first place. HP
has given all of these factors consideration in its HP ProLiant Gen8 servers, making it
easier to identify and to address hardware problems and to restart workloads on
alternate servers, if needed. There are at least two approaches to achieving those
operational goals: hosting more VMs per physical server — and allowing them to
migrate to alternate servers for future use — and clustering systems that support key
workloads; the clustered systems would allow applications to restart on other,
connected machines. Finally, HP is leveraging the use of cloud technology to gather
"server state" information and to make it universally available across all the "sites" at
a customer installation. This access to a cloud portal for first-line response supports
rapid response to any hardware operational issues and opens up the HP ProLiant
Gen8 deployment scenarios to remote locations and to a variety of SMB sites that
have few, if any, IT staff onsite to provision and manage new servers.

Technology Transition: Before and After

As servers age in place, various cost categories show that spending gets steeper as
time goes on. These categories include maintenance costs; costs for power and
cooling, managing, and monitoring servers; and staff costs. However, according to a
demand-side, customer-based study conducted by IDC, a server transition that takes
into account all these factors offers surprising findings that contradict and challenge
traditional IT depreciation cycles. Based on respondents' experiences with technology
refresh, the study shows that IT investments in new technology pay off in less than a
year — and that the cost savings benefits over three years are more than three times
as much as the initial amount invested.

The IDC study found that transitioning server infrastructure on pace with newer
technology (e.g., every two years) can reduce multiyear server costs. This occurred
not only because today's servers can handle comparable workloads at less than 40%
of the aggregate power requirements that older servers require but also because of
HP's advanced technologies, which in turn reduce maintenance overhead and IT
labor costs.

Other cost savings benefits can be added to this list. They include administrative
labor associated with physical equipment management and cabling, as well as
upgrades to firmware and the associated regression testing prior to production
deployment.

14 #233175 ©2012 IDC

Because of the high cost and potentially disruptive nature of upgrades, IT
organizations strive to avoid this activity. Nevertheless, as the length of the
deployment increases, the cost of maintenance per server increases. Because newer
servers require less of this type of maintenance and management, labor cost savings
ensue. Operational expense factors can be materially reduced with newer servers.

CHALLENGES AND OPPORTUNITIES
The worldwide server market is a competitive one, with four top systems vendors
worldwide and dozens of others competing more closely at the regional and country
levels. Server platforms continue to compete in terms of price, performance, and
price/performance as well as in their capacity to support and manage virtualized
workloads and their ability to provide reliability, availability, and serviceability to IT
staff and end users.

For all vendors, product differentiation and a timely response to changing business
conditions are key to meeting customer expectations regarding technology refresh for
each product life cycle.

In the server market, there are four top vendors in terms of revenue — and HP is
currently ranked a leader by revenue in worldwide annual sales. This large market
share can be attributed to HP's deep investments, which led to the continued
development of HP ProLiant and the associated virtualization and systems
management software.

HP recognizes that its ability to integrate functionality into the platform (e.g., hardware
and software), while supporting open computing standards for software and key
hardware components (e.g., I/O, software APIs), is the basis for much of its
differentiation and business value as it goes to market with its server solutions. That
is why HP is emphasizing its role as a provider of cost-effective workload server
platforms that will support business continuity and business value based on customer
usage patterns and ongoing service requirements.

CONCLUSION
As we have seen, the continual increase in computing power, which is more than
doubling every two years, counters the conclusion that avoiding new equipment and
capital expense is the best way to reduce capex acquisition costs.

As organizations consider server transition in their datacenters, they also should
consider incorporating a full accounting of all of the relevant factors — including not
only capital costs but also labor, power/cooling, and electricity costs. This type of
analysis, including avoidance of opex costs, may provide surprising conclusions,
showing long-term cost projections over the server life cycle that challenge traditional
IT depreciation cycles.

One example of this approach is replacing older server technologies that have been
supporting specific workloads over many years. In-depth IDC interviews show that sites
that have updated server technology have reduced many types of operational costs,

©2012 IDC #233175 15

including costs of IT staff time for maintenance and management, per-workload energy
costs, and facilities costs. Respondents reported that through the process of workload
consolidation, they can run more workloads in less datacenter space with newer
systems than they could with previous-generation systems.

Refreshing server infrastructure on pace with newer technology — including server
acquisition costs, IT staff costs, and power/cooling costs — can reduce opex by as
much as 33%, as we have seen in this paper. Rather than put off capital expenditures
and extend server life cycles (buy-and-hold strategy), organizations that are faced
with sharp budget challenges should consider selectively upgrading their servers to
the latest available technology, targeting the workloads that would benefit most from
workload consolidation, including demanding workloads that require high levels of
availability and high levels of security.

Copyright Notice

External Publication of IDC Information and Data — Any IDC information that is to be
used in advertising, press releases, or promotional materials requires prior written
approval from the appropriate IDC Vice President or Country Manager. A draft of the
proposed document should accompany any such request. IDC reserves the right to
deny approval of external usage for any reason.

Copyright 2012 IDC. Reproduction without written permission is completely forbidden.

16 #233175 ©2012 IDC

The Cost Of Retaining Aging It Infrastructure

More Related Content

What's hot (18)

Similar to The Cost Of Retaining Aging It Infrastructure (20)

More from Josh Castellano (6)

The Cost Of Retaining Aging It Infrastructure