Too many data center operators believe they don’t need physical infrastructure management tools to manage their data centers. Instead, they rely on “tribal knowledge” to get them through any rough patches. That can lead to costly errors – and downtime that doesn’t have to be.
The current generation of data center infrastructure management (DCIM) tools can identify and resolve issues with a minimum amount of human intervention and help you make smarter provisioning decisions.
If any of these situations sound a little too close to home to you, perhaps your company could benefit from some new management tools:
- In a large financial data center, provisioning and installing servers became so complex that only highly paid engineers were able to perform the task
- A veteran data center manager in New York was so concerned that his less-experienced staff in London wouldn’t know where to place a new server that he flew to London to place a sticky note on the rack position where he wanted the server placed.
- The owner of a mid-size data center in Florida intentionally oversized his cooling capacity for years in order to ensure that the data center would not run out of cooling.
- At a large health care industry data center, a low-density server was mistakenly installed in a rack intended for high-density servers. The error wasn’t discovered until the server was decommissioned. As a result, it cost the company about 20 times more than it should have to power the server throughout its life.
Modern DCIM tools can help companies address all of these issues and more by performing operations-related functions including:
- Illustrate the power path – from UPS to rack to individual device – within the rack, measured load, and rack capacity. This enables an operator immediately identify which servers will be affected if a particular rack or UPS happens fails, rather than relying on trial and error.
- Illustrate average and peak power usage by rack, to help determine where to locate new servers.
- Generate an audit trail for all changes and work orders during a specific time period, to help troubleshoot failures.
- Identify excess capacity and indicate which devices can either be decommissioned or used elsewhere, to help save energy costs.
- Generate a PUE value each day and track historical PUE values, to determine whether cost cutting and energy saving strategies are actually working.
In short, new DCIM, software planning and implementation tools can improve your data center power and cooling planning capabilities, provide rapid impact analysis during a failure, and leverage historical data to improve future performance.
To learn more about what these tools can do to help improve the operations of your data center, check out the APC by Schneider Electric white paper, “How Data Center Infrastructure Management Software Improves Planning and Cuts Operational Costs.”