When Data Center Layers Converge

(1)

[email protected]

Bernt Ostergaard Quocirca Ltd Tel: + 45 45 50 51 00 Email:

When Data Center Layers Converge

Pulling together the physical, logical and virtual

aspects of today’s IT platforms.

January 2014

The software defined data center (SDDC) is poised to redefine modern data

centers, from large to small. It helps facilitate the much-needed move

towards an optimized, balanced service level-to-cost ratio approach - away

from safe but expensive over-provisioning. However, SDDC tends to focus

on the logical layers, neglecting the physical, and so opening up the

platform to possible major issues. The emergence of cross-functional and

inclusive tools begs a more holistic approach in how the data center should

be measured, monitored and managed.

(2)

EXECUTIVE SUMMARY

When Data Center Layers Converge

Pulling together the physical, logical and virtual aspects of today’s IT platforms.

Private cloud

platforms show

promise – but also

bring issues

Private cloud promises to enable the better sharing of resources on a dynamic basis to improve overall utilization and availability rates for an IT platform. However, a lack of understanding of the dependencies between the virtual and physical worlds can lead to unexpected impacts – risks that need to be fully understood through full visibility of both sides of the issue.

SDDC is only part of

the answer

The software defined data center aims to manage a private cloud platform at the virtual level through abstraction of management activities to a software layer. However, current SDDC tools fail to provide effective management of the physical environment – and completely miss out on what any changes mean to the data center facility.

DCIM pulls SDDC,

private cloud,

physical hardware

and the data center

facility together

Data center infrastructure management provides the single view of the virtual and physical worlds to enable private cloud to deliver on its promise. Only through providing a full picture of the overall platform, through understanding what has happened in the past alongside what is happening now, can full and effective advice be provided as to what will be needed in the future – and how proposed changes to the physical equipment and workloads dependent upon it will impact the rest of the environment.

DCIM provides major

cost advantages to an

organization

With better visibility of what is happening across the complete IT platform, under-utilized hardware can be redeployed or decommissioned; systems and application availability improved; technology refreshes better-planned and implemented and cooling costs optimized.

DCIM provides the

insights a CIO needs

to better advise the

business

The insights DCIM provides enables a CIO to better advise the business on what will be needed to support the organization’s future needs. Through a full understanding of the costs and risks involved, the business can make a better-informed decision on the way forward. The CIO can therefore be involved at an earlier stage in business decisions, ensuring that decisions made at the business level are easily embraced and supported at the technology level.

An effective

technology platform

needs a combination

of tooling

Private cloud, built upon suitable virtualization, needs complete and full management. By bringing together SDDC and DCIM, the resulting platform will be what the business demands – flexible, fast to respond to needs, cost effective and dynamically optimized. The CIO will be better placed to help in making and supporting strategic business decisions through being able to provide more complete and useful advice to the business.

Conclusions

Private cloud will change the way that organizations utilize technology to support their computing needs. However, without the right tools in place, the risks that come with an unmanaged cloud cannot be overstated. While SDDC will go some way to helping, it currently misses out on understanding and managing the relationships between the virtual and physical worlds across the data center. DCIM is the only way that a complete picture of a technology platform can be maintained – and is therefore a necessary part of ensuring that an organization maintains a cost-effective, highly available and flexible cloud platform.

(3)

When Data Center Layers Converge

Why data center layers are colliding, and

why it matters

The ‘one app per server’ mentality is rapidly being killed off by the economics of the data center along with the increasing trend of virtualization and all things ‘software-defined.’ Engineering systems originally designed for peak loads rather than for resource sharing has led to rampant server over-provisioning, with the concomitant impact on energy usage, real estate usage for the data center and maintenance costs for hardware; not to mention operating system and application licensing and maintenance costs. Many servers were running at 5–10% utilization; storage arrays were running at around 30%.

Percentage of respondents (n=900)

Figure 1: Server utilization rates - source: Quocirca NGD Index 3, December 2012

As their businesses started to focus on costs versus service levels not optimized to cost, these became major issues for the CIO. The use of virtualization helped somewhat, and then technology vendors introduced converged platforms with closer engineering of servers, storage and network combining with virtualization to give a more flexible system.

As can be seen from Figure 1, by the end of 2012, overall reported utilization rates had risen – but only one quarter of respondents had managed to get utilization rates up above 50%.

Cloud computing aims to build upon virtualization and converged systems to raise utilization rates even further. With CIOs needing to move to a more visible provider of the right capability at the right time at just the right cost, the need to have a better understanding of the overall platform and the data center or data centers it resides in has become even more important.

This requires full vision of not only the software and hardware IT components of a technology platform, but also of how these are architected to operate together. It also requires an understanding of how these interdepend on aspects of the data center facility itself and how the business workloads themselves require dynamic management to ensure that the business is fully served.

0% 10% 20% 30% 40% 50% Don’t know <5% 5% - 10% 11% - 20% 21% - 50% > 51%

Se

rve

r uti

liz

at

ion r

at

es

(4)

However, CIOs wanting to be seen as an effective part of an organization’s strategic planning team should strive to be more than just a provider of an effective technology platform at the right price. CIOs have to become a strategic advisor to the business. They can no longer afford to react to decisions fed down in a command and control manner from the business level. In order to ensure that what they provide meets the business’ needs, they have to be able to participate at a peer level with other C-level staff to provide early-stage advice against business requirements anticipating current and future states.

To gain such insights, CIOs need to look for a system that can holistically monitor, measure and report on all aspects of a data center facility and the equipment housed within it, predicting its future state, as well as providing demonstrable corporate value in areas such as proactive asset lifecycle management. Such a system needs to be able to operate in a manner that provides deep, meaningful insights and advice into capacity planning, enabling just-in-time supply against predicted demand to be managed. Such a system also needs to optimize IT spend by enabling modular growth, rather than ongoing rip-and-replace updates, with completely new platforms being introduced at high cost and business impact.

This paper will be of interest to CIOs and other senior IT decision makers needing to better understand the linkage between the concept of the software defined data center (SDDC) and the dependencies on data center infrastructure management (DCIM) in ensuring that the virtual and physical platforms operate in a consistent, cost-effective manner.

The role of private cloud and SDDC

Private cloud platforms are becoming more common as an extension of the traditional IT infrastructure. In many cases, they are still only being implemented as partial clouds, alongside a heterogeneous mix of one-application-per-server and standard virtualized platforms. The idea is that private cloud builds on basic virtualization allowing all the resources of a set of IT equipment to be shared in real time across multiple workloads. A workload that requires more CPU is given what it needs; if this results in the need for more storage, then it is given that; network bandwidths are adjusted in real time to meet the needs of specific network traffic. Or so the theory goes.

Technology vendors across the server, storage and network markets are pushing the concept of an abstracted means of managing private clouds, where the hardware is managed from a management and control plane run as a software layer on top of the overall hardware platform. This has become necessary as virtualization and cloud have been adopted, whereas attempting to manage each server, storage subsystem and network switch and router in isolation will not provide the contextual knowledge of the total platform that is required.

Each area of computing has its own ‘software defined’ area – software defined networks (SDN), software defined compute (SDC) and software defined storage (SDS) are the three main constituents. These are increasingly being rolled up under the umbrella term of the software defined data center (SDDC). The idea is that high level decisions can be made on top of the platform, with the required actions or provisioning the platform being initiated and driven through the SDDC software.

The key to successful management of a private cloud is in enabling individual applications and services to be optimized, while ensuring that any changes made to better support one application does not have an adverse impact on the other workloads operating on the same platform. The SDDC sub-categories, on their own or even in aggregate, struggle to achieve this. Only by bringing together a coordinated view of the software-defined and hardware-defined environments can a holistic view be taken that ensures that the overall platform remains optimized as individual workloads are changed.

(5)

When Data Center Layers Converge

Private cloud and SDDCs are aimed at de-risking the data center environment, yet blindly adopting such an approach could lead to the exact opposite. Many more workloads will be sharing a single environment; the failure of a critical physical component could impact all of these workloads, rather than just one.

The idea that a private cloud solves everything by providing shared elastic resources across multiple workloads only goes so far – that elasticity can only extend as far as the physical limits of the underlying resources. A petabyte of storage can only store a petabyte of actual data: a CPU will fail to operate effectively as it approaches 100% physical utilization.

The overall platform still has dependencies on what underpins it and, as such, requires a system that can understand the operation of the overall platform as well as the interactions of the parts that make up the platform itself.

DCIM and SDDC

Data center infrastructure management (DCIM) is becoming necessary to ensure that SDDC works. Bringing together SDN, SDC and SDS in a coherent manner requires a full knowledge of the assets deployed within the data center, the interdependencies between them and the requirements that any change will place on the facility itself.

Tools aimed at managing everything as if they reside within the virtualized space of the cloud will miss any underlying issues within the individual hardware assets; tools that only look at the individual assets will not understand the requirements of workloads moving dynamically across from one logical space to another.

Only through pulling together an intelligent view of the physical and virtual will the data center give the flexibility that the business is demanding, and allow the CIO to provide proactive advice that helps the business operate and compete effectively in its markets.

This is where DCIM comes in. Through gaining a full and accurate picture of all assets within a data center, as well as having an understanding of how these assets operate in real world situations, DCIM tools can build up a live view of what is happening. Providing an automated means of reconciling asset registers against equipment identified through existing asset discovery products, the addition of new and removal of old equipment, this view is maintained in real time. This real-time picture allows for faster, more accurate maintenance – engineers can be provided with work dockets that identify the item of equipment requiring attention immediately and without fear of the wrong equipment being taken off line.

It also allows ‘ghost servers’ to be identified – those running live in the data center but with no business workload being carried on them but using power, along with possibly using up licenses and human resources in managing them. Once identified, these servers can either be deployed elsewhere to better serve existing workloads, or can be deprovisioned, saving on energy, maintenance and licensing costs.

Maintaining a full picture of the underlying technology assets enables better planning of technology refreshes. Keeping a full log of when equipment will come up for planned maintenance and when maintenance contracts are coming up for review allows for replacement strategies to be more easily managed. Fully understanding what workloads are dependent on what physical resources enables planned movement of the virtual workload to allow for rapid and effective replacement and refresh of the physical equipment.

Through understanding the needs of the different workloads being applied to the platform, and of the interdependencies between the logical and physical worlds, DCIM can not only help in identifying the root cause to any issues, but it can also help avoid any problems through the provision of ongoing advice.

(6)

For example, a DCIM system can see where a system is going to run out of resources in the future, and can advise in plenty of time so that more resources can be purchased and applied to the system. It can identify where problems may be latent, such as hotspots, so that virtualized workloads don’t suddenly overburden that region of the data center. Such proactive reporting minimizes financial impacts to the business through unplanned downtime. Being warned prior to any failure enables maintenance to be carried out in a planned manner with little to no downtime to the business. Inventory can be kept to a minimum, with just-in-time replacement being possible due to early identification of possible problems.

DCIM systems can – and should – work alongside existing management systems. For example, systems such as VMware’s vCenter may still be used to plan and initiate virtual machine (VM) provisioning or movements using vMotion. With DCIM underpinning this, advice can be provided to ensure that the move is not going to overload the physical equipment underlying the virtual environment, and that the impact on the physical assets is not going to cause problems within the data center itself; for example with power distribution limits or cooling capabilities. Physical systems management tools, such as IBM’s Tivoli or BMC, can still be used to provision operating systems and other parts of software stacks on servers before they are fully virtualized. However, DCIM becomes the glue that binds all the other tools together – it is the only way to provide the overall view of what is happening, and to effectively and quickly remediate any problems that are building up across the physical and virtual environments. DCIM tools are the only way of tying in the aspects of the physical data center facility with the needs of the IT equipment. For example, increasing equipment densities are stressing the capabilities of many data centers in power distribution and effective equipment cooling. By virtue of collecting real-time monitoring information of the entire data center, DCIM can provide immediate information on whether the addition of new equipment to a specific rack will overstress power or cooling capabilities. DCIM can also predict whether certain configurations of racks and rows will create hotspots that existing cooling systems will be unable to deal with – and can also show how existing cooling systems are not optimized for existing configurations.

As cooling costs are one of the largest aspects of energy usage within a data center, this capability can provide major cost savings to an organization and provide higher levels of systems availability.

DCIM also provides the CIO with the right tools to be able to take information to the rest of the business. With a full knowledge of past and current operations and the capability to provide “what if?” reports against desired future states, the CIO can ensure that all the options and the associated risks are fully understood by the business before any decision is made.

Conclusions

Cloud computing, both public and private, is already impacting how many organizations implement aspects of their IT platform. The promise of higher utilization rates and dynamic resource sharing is driving cost-conscious businesses to review how well existing IT platforms are serving them.

However, implementing private cloud blindly without a full understanding of the interdependencies between the virtual and physical worlds will lead to high risks. This has to include the physical data center facility itself, as power distribution, cooling and other environmental monitoring aspects are key to ensuring the high availability of a shared platform.

Although much is being made of software abstraction of cloud management through to SDN, SDC and SDS under the overall SDDC banner, it does not go far enough. A system that ties everything together, ensuring that changes can be made with full knowledge of what impacts the change will have on other foundational systems, is needed. Only DCIM has the capability to provide the single vision of the whole technology environment so that the risks can be fully managed.

(7)

When Data Center Layers Converge

DCIM tools also provide the insights needed to provide solid ongoing value to the business through enhancing the lifecycle management of equipment, enabling better technical refreshes to be managed with little or no downtime to the business and to provide meaningful advice to the business as to what its options are when new workloads are needed to support the organization’s ongoing strategy. Bringing equipment into service quickly, keeping it up and running during its peak value period to the company, and ensuring it is retired and decommissioned when its value declines is something the CIO should indeed look to shepherd with DCIM.

As SDDC and all the abstraction principles defined by SDDC materialize, it will be clear that DCIM becomes an essential critical path item for all the hardware underpinning of that SDDC. DCIM creates an effective platform for virtualization, private cloud and software defined data center tools, which can be all pulled together through coordinated physical-logical-virtual infrastructure management.

(8)

About Nlyte

Nlyte Software is the world’s leading software company focused on planning, managing and optimizing

data centers. Nlyte Software enables enterprises to extend IT management software to include the

physical layer with the logical and virtual layers of the data center, maximizing the financial benefits from

the optimized utilization of power, space and assets. Nlyte’s proven platform is used in the data centers

of some of the largest and most valued companies in the world.

The Nlyte product

The Nlyte Data Center Infrastructure Management (DCIM) Suite provides intelligent capacity planning

that delivers actionable information for optimizing the use of power, cooling and space through the

optimal placement of data center assets and business process automation and workflow that improves

availability and operational excellence.

Nlyte solutions

For CxOs, IT, Facilities or Data Center Management teams to manage the following challenges of:



Data Center Deferment – Finding and utilizing stranded resources plus capacity planning for

migrations and consolidations



Asset Lifecycle Management – Managing lifecycles of gear, project management and subsequent

financial impacts



Improve Operational Excellence – Streamlining operations, service tickets for remedial and

commissioning /decommissioning: improving accuracy



Create Energy Efficiency – Run a more efficient and green data center and save on energy

expenditures



Risk Management, Audit and Regulatory Compliance – Gain compliance, operational accuracy,

conduct impact analysis and establish documentation

Key benefits of using Nlyte Software



Reducing the cost, time and risk of migrations and consolidations by up to 50%



Decreasing the business risk and expense caused by unplanned downtime & catastrophic failure

by up to 50%



Deferring the capital expense for new data center build outs by 5 years or more



Cutting power expenses by 20% annually and reducing power usage effectiveness (PUE) to 2.0 or

less

(9)

About Quocirca

Quocirca is a primary research and analysis company specializing in the business impact of information technology and communications (ITC). With world-wide, native language reach, Quocirca provides in-depth insights into the views of buyers and influencers in large, mid-sized and small organizations. Its analyst team is made up of real-world practitioners with first-hand experience of ITC delivery who continuously research and track the industry and its real usage in the markets.

Through researching perceptions, Quocirca uncovers the real hurdles to technology adoption – the personal and political aspects of an organization’s environment and the pressures of the need for demonstrable business value in any implementation. This capability to uncover and report back on the end-user perceptions in the market enables Quocirca to provide advice on the realities of technology adoption, not the promises.

Quocirca research is always pragmatic, business orientated and conducted in the context of the bigger picture. ITC has the ability to transform businesses and the processes that drive them, but often fails to do so. Quocirca’s mission is to help organizations improve their success rate in process enablement through better levels of understanding and the adoption of the correct technologies at the correct time.

Quocirca has a pro-active primary research programme, regularly surveying users, purchasers and resellers of ITC products and services on emerging, evolving and maturing technologies. Over time, Quocirca has built a picture of long term investment trends, providing invaluable information for the whole of the ITC community.

Quocirca works with global and local providers of ITC products and services to help them deliver on the promise that ITC holds for business. Quocirca’s clients include Oracle, IBM, CA, O2, T-Mobile, HP, Xerox, Ricoh and Symantec, along with other large and medium sized vendors, service providers and more specialist firms.

Details of Quocirca’s work and the services it offers can be found at http://www.quocirca.com

Disclaimer:

This report has been written independently by Quocirca Ltd. During the preparation of this report, Quocirca may have used a number of sources for the information and views provided. Although Quocirca has attempted wherever possible to validate the information received from each vendor, Quocirca cannot be held responsible for any errors in information received in this manner.

Although Quocirca has taken what steps it can to ensure that the information provided in this report is true and reflects real market conditions, Quocirca cannot take any responsibility for the ultimate reliability of the details presented. Therefore, Quocirca expressly disclaims all warranties and claims as to the validity of the data presented here, including any and all consequential losses incurred by any organization or individual taking any action based on such data and advice.

All brand and product names are recognized and acknowledged as trademarks or service marks of their respective holders.

REPORT NOTE:

This report has been written independently by Quocirca Ltd to provide an overview of the issues facing organizations seeking to maximise the effectiveness of today’s dynamic workforce.

The report draws on Quocirca’s extensive knowledge of the technology and business arenas, and provides advice on the approach that organizations should take to create a more effective and efficient environment for future growth.