- The Growing Significance of Green IT and Green Data Centers
- All Companies Can Take Basic Steps Toward Green IT
- What This Book Covers
All Companies Can Take Basic Steps Toward Green IT
According to Gartner research firm, the green wave has only begun to rise. The research company predicts that in 2009, more than one-third of all IT organizations will place environmental concerns among their top six buying criteria. By 2010, Gartner says, three-quarters of companies will use carbon-footprint considerations in calculating their hardware-buying strategy, and by 2011, large enterprises will develop policies requiring their suppliers to prove their green credentials through an auditing process.
Most companies are talking a good game but not actually going green where it counts. According to a survey of 124 IT operations by Forrester Research in May 2007, some 85 percent of respondents said environmental factors are important in planning IT operations. But only one-fourth of survey respondents have actually written green criteria into their company’s purchasing processes. Enterprises that have started the green journey, however, have found that reducing total energy requirements can be accomplished through some fairly straightforward improvements that don’t take years to implement or to bring return. The following six tasks are applicable to all green IT projects. Chapter 2, “The Basics of Green IT,” gives details on the five steps used by IBM to implement green data centers. Those five green data center steps include the virtualize, cooling, and measure tasks in the following list. Also, Chapter 9, “Green IT Case Studies for Energy Utilities,” and Chapter 10, “Green IT Case Studies for Universities and a Large Company,” give details on the five steps used for case studies.
1. Communicate Green IT Plans and Appoint an Energy Czar
Measuring the current state of affairs, energy wise, is one of the first steps to take. A baseline on which to start measuring the impact of an organization’s energy-saving initiatives in the green IT area is needed. Of course, you must also communicate your proposed energy-efficiency initiatives right away. Inform all employees about the plans and goals to save energy via green IT. Besides communicating with your employees, set up an organization to drive the effort. You may start by making one person responsible; give that person a title (like “Energy Czar”). Details on the importance of communication and collaboration for green IT is the subject of Chapter 3, “Collaboration Is Key for Green IT.”
2. Consolidate and Virtualize
Consolidating IT operations, and using virtualization to reduce server footprint and energy use, are the most well-recognized and most-often-implemented efficiency strategies of the past few years. Some of the largest technology organizations in the world—including Advanced Micro Devices®, Hewlett-Packard®, Intel®, IBM, and Sun Microsystems®—have recently (2008) completed major data center consolidation projects. The projects also included server consolidation and virtualization. Details on the significance of virtualization for your IT systems in going to green data centers is the subject of Chapter 6, “A Most-Significant Step—‘Virtualizing’ Your IT Systems.”
3. Install Energy-Efficient Cooling Units
In most cases, traditional data center design called for bulky computer room air conditioners (CRAC) units that are placed on the perimeter of the floor to move large amounts of air around the data center. However, in-row or supplemental cooling units have been shown to save energy. The in-row units typically enclose a row or two of servers, and the backs of all the servers are pointed into a single “hot” aisle. Heat in the aisle is contained by a roof and end-row doors, allowing cooling to be applied directly to the heat source, rather than trying to cool after the heat is dispersed into the general data center floor. Details on data center cooling strategies for green data centers are given in Chapter 8, “What About Chillers, Cooling Tower Fans, and All That Cooling Equipment Usually Ignored by IT?”
4. Measure and Optimize
In 2009, several groups (including the The Green Grid) are expected to release important deliverables in the form of metrics that businesses can use to measure the power-usage effectiveness of facilities infrastructure equipment. Most businesses can already readily identify areas where infrastructure optimization can achieve increased efficiency by simply monitoring and measuring their existing infrastructure equipment. The EPA is also working to create metrics. About 100 companies have indicated that they will provide raw power data and other information to the EPA for use in developing its new benchmark. The EPA indicated that the results of the benchmark should be available by 2010.
Until widely accepted metrics become available, businesses should make sure that the utility costs associated with their data center operations are broken out separately from those for other corporate facilities. In addition, metering specific equipment racks or types of equipment such as servers can provide valuable insight into which specific consolidation, virtualization, and optimization projects will yield the best ROI going forward. The status of energy-use metrics is the subject of Chapter 7, “The Need for Standard IT Energy-Use Metrics.”
5. Implement Efficient Applications and Deduplicate Data
Software and application efficiency can be significant for green IT. The author has had a recent experience where the procedure for creating a data warehouse report was reduced from eight hours to eight minutes merely by changing the Oracle data warehouse search procedure. (For example, don’t search the entire database each time when only a much smaller search is required.) During the eight hours required to create the report, the large server was running at near peak capacity. Sure, that type of significant application inefficiency has been created and fixed many times over the history of programming. But what about the cases where a few application efficiencies can make an application run 20 percent faster? That 20 percent more-efficient application can also result in 20 percent lower energy use. The steps required to improve application efficiency by a few percent are often not easy to determine; however, the added incentive of saving energy—while making the application run faster—is a significant plus.
Data-storage efficiency, such as the use of tiered storage, is also significant. Data deduplication (often called intelligent compression or single-instance storage) is a method of reducing storage needs by eliminating redundant data. Only one unique instance of the datum is actually retained on storage media, such as disk or tape. Redundant data are replaced with a pointer to the unique data copy. For example, a typical email system might contain 100 instances of the same one-megabyte (MB) file attachment. If the email platform is backed up or archived, all 100 instances are saved, requiring 100MB storage space. With data deduplication, only one instance of the attachment is actually stored; each subsequent instance is just referenced back to the single saved copy. In this example, a 100MB storage demand can be reduced to only one MB.
Data deduplication offers other benefits. Lower storage space requirements can save money on disk expenditures. The more efficient use of disk space also allows for longer disk-retention periods, which provides better recovery time objectives (RTO) for a longer time and reduces the need for tape backups. Data deduplication also reduces the data that must be sent across a WAN for remote backups, replication, and disaster recovery.
Data deduplication uses algorithms to dramatically compress the amount of storage space needed. Many organizations deal with increased scrutiny of electronically stored information because of various regulations; this need to preserve records is driving significant growth in demand for storing large sets of data. Depending on the type of information compressed, deduplication can enable a compression rate of between 3:1 and 10:1, allowing businesses to reduce their need for additional storage equipment and associated tapes and disks. Many businesses are already using the technology. Application efficiency as part of green IT strategy is discussed in Chapter 2.
6. Make Use of Rebates and Incentives
More utility providers offer rebates or other incentives that encourage businesses to update equipment and adopt efficient operational practices that can help reduce peak and total power demands. Companies doing this include Pacific Gas and Electric in San Francisco and Austin Energy in Austin, Texas.
New electric power-generation stations are very expensive, and power companies are more than willing to avoid building new capacity. Thus, the power companies encourage data center efficiency through rebates and other incentives. Also, the organization’s facilities team doesn’t have to build as much new data center space. The IT organization and engineering groups get new equipment that is smaller, cooler and faster than before—and everyone ends up happy. The roles of government and energy utility rebates and incentives are the subjects of Chapter 4, “The Government’s Role—Regulation and EPA Activity,” and Chapter 5, “The Magic of ‘Incentive’—The Role of Electric Utilities.”