There's a huge opportunity for IT budget savings by reducing IT
labour requirements – primarily administration and support. In
fact, more than 70% of the total cost of ownership (TCO) for
typical datacentres is for labour or outsourced services.
The high cost of labour, particularly performing mundane
administrative and support tasks, is one of the key reasons why
little of the IT budget is left for innovative projects that can
help deliver competitive value.
That's where server consolidation enters the picture. It's one
of the most effective ways to lower TCO of a company's datacentre.
Typically performed using one of the four strategies highlighted
here, server consolidation methods can be applied independently or
simultaneously.
Physical consolidation
This means collecting servers distributed across multiple
remote/branch offices and business units into a central
datacentre.
Pros:
The team can improve configuration control by restricting server
access, and strengthening business resilience through the superior
datacentre infrastructure and security. It can also eliminate the
cost of moves, add-ons, and changes (MACs), as well as break-fix
maintenance and support by eliminating travel time and expenses.
Physical consolidation can help the team reduce complexity and
more easily standardize purchases, configurations and management
best practices. Costs to implement physical consolidation are low,
and consist of network enhancements to support the centralization,
datacentre build-out to support the consolidation, and physically
moving the servers. Ultimately, IT labour savings can reach
10%.
Cons:
The risks are performance degradations due to poor network planning
and business resilience risks by having all of the server assets in
"one basket," particularly if the datacentre does not have adequate
recovery plans.
Re-hosting
Porting from older legacy platforms and operating systems to newer
solutions often results in consolidation, as fewer new
high-performance systems are typically needed to support the
workload.
Pros:
Depending on the age of a legacy system, expensive support and
maintenance contracts can be eliminated. Since the number of
administrators and support labour is usually correlated to the
number of individual servers, having fewer servers generates
proportional administration and support labour savings.
Migrating the operating system to a newer version enhances
availability, security, management features and performance, and
provides better upgrade options.
Cons:
If the proposed system for re-hosting is not compatible with the
prior systems, the application may require porting to another
platform, custom code rewrites, procedures and data migration.
Porting costs are often underestimated.
Logical consolidation
Individual servers are often configured into individual server
"islands" with 40% or more headroom to allow for changes in
workload and growth. Using logical consolidation, hard partitions
can be established for the operating system, application,
processors and memory requirements so that these individual server
"islands" are pooled onto a single server or cluster. That way,
fewer servers are needed because headroom is reduced and the
applications are hosted on a single cluster. The team can change
the partitions to allocate more resources as needed for workload
changes, as opposed to managing moves, adds and changes physically
on multiple "islands" of individual servers.
Pros:
Logical consolidation on a shared server can save 40% or more of
overhead headroom, and a proportional decrease in server assets.
This can lead to a similar reduction in administration and support.
Cons:
Logical consolidation requires manually managing the hard
partitions, made difficult in a dynamic environment where workloads
change frequently. This process can be difficult and can introduce
management burden and complexity. Many business units will not
support logical consolidation where they must share servers, and
will need to be "sold" on the business merits of consolidation and
assured that service levels will hold steady or increase.
Workload optimization
The server operating system (such as with HP-UX11i's virtualization
features) or third-party utilities (such as EMC's VMWare) can be
configured to intelligently manage server resource allocation based
on workload demands. Partitions can be established based on demand
and schedule rules, and the system takes care of the rest,
allocating computing power to automatically meet needs.
Pros:
Fewer CPUs, and in turn, fewer servers are needed to support
multi-application workloads. For multi-application portfolios, this
approach maximizes asset utilization and consolidation, reducing
software licensing requirements, facilities costs and labour --
saving at leat 40 % based on the application profiles. Typically,
fewer, smaller applications that peak at different times drive the
highest consolidation. Because the system manages workloads and
partitions, administration and support are minimized.
Cons:
Establishing workload optimization configuration and rules will
take some time and can be complex, requiring professional services
assistance. As with logical consolidation, business unit
apprehensions and business resilience best practices apply.
Application Portfolio Scenarios |
Applications in the Portfolio | CPUs
Needed During Normal Operations | CPUs
Needed During Peak Operations |
Percentage of Applications that Peak at same Time of Day | CPUs
without Workload Optimization
(Islands Scenario) | CPUs
with Workload Optimization |
CPU's Saved | %
CPUs Saved |
Single application |
1 |
2 |
8 |
100% |
8 |
8 |
0 |
0% |
Few small applications |
5 |
0.5 |
2 |
50% |
10 |
7 |
3 |
30% |
Many medium applications |
10 |
2 |
8 |
50% |
80 |
50 |
30 |
38% |
Few applications where 2 workloads peak at
once |
3 |
1 |
5 |
66% |
15 |
11 |
4 |
27% |
Many small applications |
10 |
0.25 |
0.75 |
40% |
8 |
5 |
3 |
38% |
Few large applications |
2 |
5 |
25 |
50% |
50 |
30 |
20 |
40% |
Many applications, workloads peak at different
times |
10 |
2 |
6 |
25% |
60 |
30 |
30 |
50% |
Using workload analysis, standard and workload
optimized environments show where the maximum consolidation savings
could be achieved via workload optimization.
The ROI Analysis
The right consolidation decision takes careful
analysis of current TCO, proposed consolidation options and
architectures, required investments, and potential savings. Because
the analysis is complex, internal IT teams should consult with
independent analysts and performance benchmarking sites (such as
www.spec.org and put vendors to task (with requisite scrutiny), to
help propose and analyze current opportunities and various
consolidation options. Comparing the solutions' TCO and service
levels head-to-head with a TCO analysis tool can provide the team
with visibility into potential savings, and provide justification
needed to empower the business to make the right decision.
Tom Pisello is the founder and CEO of Orlando,
Fla.-based Alinean, an ROI consultancy and software provider. He
can be reached at tpisello@alinean.com. For
more information and exclusive access to server TCO analysis tools
and white papers, visit http://www.alinean.com.