In February 2010, the U.S. federal government unveiled the Federal Data Center Consolidation Initiative, an initiative aimed at addressing unfettered growth in the number of government data centers. The initiative, outlined by the government’s Office of Management and Budget (OMB), is an effort to assist government agencies identify existing data center assets and formulate consolidation plans that include a technical roadmap and specific targets.
Through the initiative, the government will assist its agencies leverage best practices from the public and private sectors. The government expects the consolidation efforts to promote green IT, reduce data center costs, increase efficiencies, and raise the overall IT security posture of the government. The OMB plans to release data center reduction targets by agency as part of the President’s fiscal year 2011 budget.
As the federal government prepares to implement this consolidation, agencies are taking a close look at their data center planning, processes, and operations. While public sector data centers have their own set of unique challenges, they can learn an important lesson from private sector data centers. That lesson: How to ensure potential efficiencies and savings are realized without compromising or disrupting data center availability and performance.
GOVERNMENT'S UNIQUE CHALLENGES
Although the Federal Data Center Consolidation Initiative is a step in the right direction to stop infrastructure sprawl, the public sector faces a number of challenges preventing the initiative from being the game-changing program it is intended to be. In many instances, these challenges will need to be addressed or discussed before consolidations can take place.
The decision-making process within the public sector, which can be complicated and lengthy, is one of the biggest of these challenges. In many agencies it is not unusual to have up to 15 to 20 people signing off on a decision.
In fact, it’s often difficult to identify participants in the decision-making process. A number of players are involved, including agencies and their parent, sister, and daughter organizations, as well as contractors and subcontractors. This complex structure hampers decision-making and invites infighting, as various parties jockey for position and refuse to give up control.
Data centers are complex environments, and consolidation is a significant undertaking. The decision-making process should not add to the already imposing challenges. The private sector streamlined its decision making process some time ago. Most corporate data centers operate under corporate mandates that promote centralized decision-making and benefits. Stakeholders, along with their roles and responsibilities, usually are clearly established and identified.
Any CIO or data center manager leading a data center consolidation can confirm it is no simple endeavor. Significant planning goes into the effort, from beginning to completion. This approach may present a challenge to government entities, which traditionally react to IT decisions, rather taking a proactive position. Policymakers dictate what is to be done and how. Focused on responding, IT professionals take a short-term view. Starting points, end goals, and planning may become afterthoughts.
While the Federal Data Center Consolidation Initiative makes strides in this area, there is still much to be learned from the private sector. Proper planning is also an issue faced by private sector data centers, which now well understand the value of proper planning to meet current and future capacity needs.
The increased use of data center infrastructure management (DCIM) solutions is a recent trend affecting private sector data centers. DCIM solutions manage the data center infrastructure layer (power, cooling, and the physical space), the IT infrastructure layer, (compute, storage, and communications equipment), and the gap between the two layers. Having management tools across the gap gives data center operators visibility into the true capacity of their IT and infrastructure systems.
In addition, many private sector data center managers conduct detailed audits of their data centers, acquiring precise information about the equipment they have and how it is used. They can use information from the audit to help develop benchmarks for success, as well as roadmaps to get from point A to point B-and even point C if the opportunity presents itself.
FUNDING
The public sector and private sector fund projects in very different ways, many of these differences are unavoidable and unchangeable. Even so, the public sector could benefit from aligning itself better with the private sector approach to financing a project.
Most public sector data centers collect, store, and manipulate data. Dollars go toward computing power and upgrades around the mission, program objectives, or information sharing-such as moving troops for military operations or sharing data and research with the public, making it difficult to determine a tangible return on investment (ROI).
In private sector data centers, investment is based on transaction speed and storage capabilities that drive revenue generation and translate to measurable ROI. For businesses, a data center outage can result not only in lost revenue from operational downtime but also reputation damage that may threaten existing and future business opportunities. As a result, these critical data centers are designed to be flexible so they can grow based on capacity and availability needs, customer demands, and ROI.
“Time to market” is yet another difference between the two sectors. The private sector typically works with a capital budget of one-year or less, while the public sector usually has a three-year cycle that includes budget proposal, review, and appropriation by Congress. In the data center world, three years is a long time, during which new technologies are introduced and old ones become obsolete. Work with an operating budget, rather than a capital budget, is one way around this delay. Recent moves toward cloud computing and private hosting environments are taking the government in this direction.
Real estate usage also complicates public sector data centers. There may be shared space within government data centers, but not shared dollars. Agencies may share data center storage space, without separately allocating the data center budget. Conversely, the private sector utilizes a variety of tools, including DCIM solutions, to implement sophisticated pricing models for allocation and charge-backs to different departments or divisions.
Once addressing these challenges, the public sector needs to drive the Federal Data Center Consolidation Initiative using the same dedication to efficiency the private sector has embraced during the last few years without compromising availability for the initiative to succeed.
EFFICIENCY AND AVAILABILITY
In 2008 and 2009, a number of businesses experienced well-publicized data center outages that caused service disruption, lost data, and the loss of hundreds of thousands of dollars. In the wake of these outages, the private sector gained a renewed respect for availability. By the end of the decade, the focus for private sector data centers became to reduce costs and increase efficiency while maintaining or improving availability.
To meet these sometimes-conflicting objectives, private-sector data center management began to enter a new stage of maturity. Data center infrastructures began to leverage four distinct opportunities for enhancing efficiency without compromising availability. These opportunities-high-density design, high availability, flexible support, and visibility-drive data center infrastructure design and management in the private sector and can do the same in the public sector.
The private sector understands if it can’t monitor and control infrastructure performance, it can’t improve it. DCIM systems that provide a combined IT and facility view of the entire data center are key to ensuring availability, improving efficiency, planning for the future, and managing change. Gaining control of the infrastructure environment leads to an optimized data center that improves availability and energy efficiency, extends equipment life, proactively manages the inventory and capacity of the IT operation, increases the effectiveness of staff and decreases the consumption of resources.
A comprehensive DCIM solution is key to achieving these goals. DCIM typically progresses through four successive phases.
-
Monitor and access, which provides the ability to quickly react to potential problems in the data center infrastructure and improve management. Data centers have visibility into equipment operating status and receive real-time alerts and alarms to notify them of potential equipment operating problems. Real-time performance data also can be used for planning.
-
Data capture and planning, in which data centers have the ability to automatically collect data about what assets are in the data center and where they are located, as well as how they are interconnected. These data can be used to address key planning issues including how equipment can be commissioned and decommissioned more efficiently.
-
Analyze and diagnose, which provides data centers with the ability to respond more quickly to changes in the infrastructure and manage more efficiently. Operating data available through monitoring and data capture initiatives can be used to extend the life of the data center, reduce mean-time-to-repair, and synchronize infrastructure with virtualization automation.
- Recommend and automate, which enables data center optimization by providing data centers with the visibility and control to optimize performance while maintaining or improving availability. Data center management becomes proactive as personnel anticipate potential failures and automatically shift compute and physical resources to eliminate downtime, while increasing resource utilization to optimize efficiency.
The Federal Data Center Consolidation Initiative provides significant opportunity for public sector data centers to improve efficiency and optimize performance. The fact that the effort is being spearheaded by a government CIO helps ensure that decisions being made are in the best interest of the agency and government as a whole. Data centers that succeed in this initiative will be the ones that take a page from the private sector and approach the consolidation effort with a strong focus on achieving efficiencies without compromising performance and availability.
