Data Center

4 Processes that Require Care and Feeding for an Effective DCIM System

DCIM solutions can give data center operators a clear view of what is inherently a complex mix of disparate facility and IT systems and infrastructure, helping them make better, smarter decisions. But DCIM software can’t be effective without operators doing their part by following good processes when implementing, operating and maintaining the system.

The amount of operator effort and process required varies from one vendor’s DCIM offering to another and is a point of comparison to consider in the evaluation phase. The following are four processes that, if neglected, will undermine the functioning and benefits of the DCIM system.

1. Inventory/asset management

Some of the most valuable functions of today’s DCIM tools include modeling proposed changes or moves, conducting impact analysis of potential problems, and mapping IT device dependencies to power and cooling resources. These functions play a crucial role in ensuring adequate power, cooling and space is available, even in the event of component failures.

But such functions can only succeed if accurate inventory and asset management information is recorded and maintained over time, which requires on-going processes and action on the part of the operator.  As soon as this inventory becomes inaccurate, it could lead to faulty recommendations and even downtime. A DCIM recommendation on where to place a new server, for example, could obviously be erroneous if data on available power, cooling, rack space and floor weight capacity is not accurate.

Some DCIM tools will help in this regard by constantly comparing modeled data against actual measured values, and sending a warning when any new components are found – a valuable capability.

2. System configuration

Proper configuration is another crucial process that needs to be performed if the DCIM system is to live up to expectations. This includes setting up alarm thresholds, notification policies, user access rights, UPS and cooling unit operator parameters and lots more. All of this requires initial operator action as well as ongoing attention to keep up with new equipment and changing requirements.  It is also required to take full advantage of some advanced requirements of newer DCIM systems, such as the ability to automatically move virtual machines (VMs) away from servers that are experiencing power or cooling issues to more safe havens. That kind of capability requires configuration of the communication between the DCIM server and VM manager, population of physical infrastructure data and associated VMs within the DCIM server, and more.

3. Alarm integration

DCIM systems collect, analyze and report on lots of information. And when things go wrong, they are capable of sending alarms that appear either in the DCIM dashboard or in other management systems, such as a building management system (BMS) or IT management tool.

But that doesn’t guarantee that anyone ever sees or acknowledges the alarms. In some cases, DCIM alarms aren’t included in the data center issue resolution process, and nobody implemented a new process to accommodate the new DCIM alarms.

In other cases, the sheer volume of alarm data can overwhelm data center operators, especially if thresholds and notification policies are too broad.  As a result, the data gets ignored, including potentially important alarms.

4. Reporting for management or other stakeholders

Over time, DCIM systems generate lots of information that can be of great value – if anyone ever looks at it. That’s where reporting comes in. Most DCIM tools include a reporting function that allows for reports to be customized in terms of time period, content and format. Some allow for inclusion of data from other tools, such as a BMS.  All this allows data center operators to customize reports so their management teams and others can quickly home in on the particular data they care about most. Reports can convey useful information that can be used not only to judge the on- going health and effectiveness of the data center, but drive preventative actions to help prevent failures. And they’re typically easy to configure, save and generate automatically at whatever interval the user chooses, say weekly or monthly.

But again, reporting is a process that doesn’t happen by itself; it requires manual intervention up front and over time.

To learn more about what goes into selecting and operating an effective DCIM tool, check out Schneider Electric white paper number 170, “Avoiding Common Pitfalls of Evaluating and Implementing DCIM Solutions.

No Responses