by clicking on the page. A slider will appear, allowing you to adjust your zoom level. Return to the original size by clicking on the page again.
the page around when zoomed in by dragging it.
the zoom using the slider on the top right.
by clicking on the zoomed-in page.
by entering text in the search field and click on "In This Issue" or "All Issues" to search the current issue or the archive of back issues respectively.
by clicking on thumbnails to select pages, and then press the print button.
this publication and page.
displays a table of sections with thumbnails and descriptions.
displays thumbnails of every page in the issue. Click on a page to jump.
allows you to browse through every available issue.
GCN : November 2013
7 • Diagnostics, troubleshooting, event analysis and proactive management of resources • Interdependency analysis between operational functions and various IT resources • Cause and effect, high utilization versus poor availability or response time • Physical and virtual asset and facilities management In a government data center, for example, capacity planning practices could apply to gauging power consumption of outlets. Airlines use them to determine when to buy more aircraft. Electric companies use them to decide when to build power plants and transmission networks. By the same token, data centers should use capacity planning and capacity management to derive maximum value and use from servers, storage, networks and facilities (power, cooling and floor space), while meeting service-level objectives and other requirements. e "Capacity Forecast" graphic, on the previous page, provides an example of a simple capacity forecast, combined with usage tracking information. It depicts servers, storage and networking along with associated power, cooling, floor space and environmental (PCFE) requirements; thresholds for PCFE; and anticipated growth demands. On the right of the graph, improvements have been made to PCFE demands and server, storage and networking optimization. e result is some breathing room to support demand that requires more processing, network and storage resources while fitting into an existing environment. A data center accomplishes PCFE optimization by fine-tuning servers, storage, networking and virtualization to achieve a data footprint reduction and drive up the energy efficiency of devices. Newer HVAC and CRAC devices and PDUs also can help optimize PCFE capabilities in a holistic DCIM approach. Capacity planning can be applied as a one-time or recurring exercise to determine how much and what types of resources are needed to support an application or an array of services. A strategic approach would be to evolve from short-term tactical capacity planning to long-term focused planning so that the data center makes the most use of its resources now and in the future. Ultimately, poor metrics and insight will lead to poor decisions and management. It's essential to look at servers from more than a percent utilization perspective. It's equally important to consider response time and availability. ink about storage from the perspective of IOPS and bandwidth performance. Also factor in response time or latency, and available capacity. And for networking, take into account latency, cost per given bandwidths and percent utilization. In the end, the information DCIM provides, and the timely adjustments it allows an organization to make, can only lead to bluer skies. ere's very little that a strategic approach to DCIM can't help you do with greater certainty and savvy. FOLLOW US 3 ROADBLOCKS TO DCIM INTEGRATION An ideal DCIM system would immediately integrate with all other hardware and software in the data center. Unfortunately, there are still some obstacles that can delay this comprehensive unification of the data center. One of the most fundamental issues is vendor diversity. If all data center equipment is manufactured by the same company --- servers, storage, and networking; power distribution units (PDUs); uninterruptible power supplies (UPSs); and heating, ventilation and air-conditioning (HVAC) systems --- it will be a much simpler task to manage the environment uniformly. Most data centers procure components from many different vendors, however, so it becomes necessary to look for integration points using a range of techniques, including application programming interfaces, appliances and sensors. Integrating facilities and IT with DCIM is particularly challenging. Not all facilities' tools or IT management software expose standard interfaces that a DCIM system can use. Even when they do offer hooks, someone must configure and validate the integration. Beyond the basic challenges, there are a number of limitations with many of the DCIM products on the market today: • Cooling: Some DCIM software products are limited to controlling power and cannot monitor, manage or control cooling systems, which are often based on outdated protocols. is significantly limits the solution's value because there is still a need to monitor the air-conditioning and ventilation systems separately. • Cross-vendor visibility: ere is limited standardization in this area, which leads to a lack of compatibility. Some DCIM products can integrate with a wide variety of systems. However, others support a certain list of hardware vendors and are not flexible to configure or integrate with other vendors. • Platform support: e best DCIM software can see across a range of platforms --- from commodity x86 systems to hardware appliances and mainframe systems. Legacy equipment is a particular area of concern because older systems may lack the newer management and monitoring interfaces, which would allow easy integration with DCIM. In summary, DCIM is a fractured and evolving technology. erefore, it is vital to check which monitoring systems are in use and which interfaces they expose in order to make sure that any DCIM system chosen will be able to accommodate them. CDWG.com | 800.808.4239