We have remarked several times in this space about the tremendous changes in the data center in such a short period of time. Not only are device footprints shrinking and functionalities converging, but the way that hardware and software are managed has become more comprehensive and streamlined. Now the same thing that has happening to the IT stack is taking place in the facilities arena. In fact, what have traditionally been two distinct arenas — data management and facilities management — are melding into one discipline. It’s called data center infrastructure management (DCIM).
According to a technical article from Delta Power Solutions, “the first DCIM solutions started appearing on the market around a decade ago”. The starting point is not very precise (particularly since we don’t know the date the article was written), but it’s clear that DCIM is a fairly new concept in the IT world. But a 2015 article from DataCenter Knowledge says, “Despite continued skepticism in the industry, the data center infrastructure management software market is growing.”
You can get a sense of what DCIM must mean simply from the term itself. It is the management of infrastructure within a data center. Techopedia gives us a clearer definition:
“Data center infrastructure management (DCIM) refers to the processes, guidelines, tools and methodologies used for the provisioning, governance and overall management of data center assets and infrastructures.”
Another way to describe DCIM is to describe the combining factors that we discussed earlier. The definition from TechTarget highlights this unification of IT and facilities:
“Data center infrastructure management (DCIM) is the convergence of IT and building facilities functions within an organization. The goal of a DCIM initiative is to provide administrators with a holistic view of a data center’s performance so that energy, equipment and floor space are used as efficiently as possible.”
Others recognize the apparent ambiguity of the term DCIM. Robert McFarlane of Shen Milsom & Wilke LLC writes that the definition of DCIM can vary. Some think of it as a suite of software, while others may see it as a collection of tools. The number of DCIM software vendors has grown from just a handful a few years ago, so it looks like the term DCIM may soon become synonymous with the software packages that manage the various tools and systems of infrastructure management within a data center.
So what are the main areas that are dealt with by DCIM? There is no definitive list, of course, but there are some terms that are commonly used to describe the various aspects of data center infrastructure management. We will detail some of the more common ones here, plus a few others that don’t fit in those categories. We’ll use the main pillars described in a video by the solutions company Anixter.
One of the biggest challenges in developing a comprehensive approach to data center management is identifying and defining all its components. In fact, this may be one reason that many companies have been reluctant to adopt the DCIM approach. It takes a lot of work to create and maintain a complete inventory system. This may be particularly true when different components are managed by different entities. IT systems may monitor their own managed objects, but this doesn’t necessarily include all parts that are usually associated with facilities management. Facility managers, likewise, may maintain their own inventory database. And third-party vendors and customers keep their own lists. DCIM aims to integrate all data center assets into one system.
These days facility managers not only want to make sure that there is sufficient power available for data center systems. They also want to make sure that power is being used efficiently. One key term in this discipline is power usage effectiveness (PUE). Good PUE saves money and is good for the environment. Jon Trout of TrendPoint offers his company’s top five best practices for data center power monitoring:
Trout says that “data center power monitoring systems can be a powerful tool to help achieve the overall initiatives in the facility”.
We wrote about environmental monitoring in a recent blog post for Total Uptime. We pointed out that environmental monitoring seeks to control such areas as temperature, humidity, water, airflow, and security. Environmental monitoring systems include tools that can be integrated into a large DCIM approach. According to one website, the top five data center environmental monitoring systems are:
For lack of a good change management programs, many IT environments have suffered great harm. Without careful change control, anything could happen. You can decrease downtime with effective change management, as we wrote in a previous blog article. Today’s DCIM software packages include change management as a component of the larger system. The idea is to tie methods of procedure (MOP) with planned changes and managed assets.
DCIM solutions provider Geist writes about the benefits of capacity planning with DCIM. “Capacity planning allows both IT and facilities managers to plan for critical resource allocation within the data center,” they tell us. Technical author Bill Keyman tells us more in “The Science Behind Successful Data Center Capacity Planning”:
“Capacity planning brings together all the key resource and output factors that constitute a data center’s reason for commission and its means of fulfilling that. As critical resources become more expensive or scarce, being able to plan for future capacity requirements becomes more critical.”
Kleyman lists several issues that come into play in the challenging arena of capacity planning:
Notice that the availability of technical resources is not the only consideration. Capacity planning also deals with matters related to finances, power, and the environment.
Other areas dealt with in DCIM include network cabling and patching, rack and floor diagrams, computer room air conditioning (CRAC), physical access, security, workflow management, reporting, analytics, and business intelligence. In fact, DCIM can include anything that might be considered part of the infrastructure of a data center.
Another way to look at the scope of DCIM issues is to consider the risks involved with managing data center infrastructure. The Uptime Institute has effectively described data center risks in their white paper called “Top 14 Considerations for Addressing Data Center Facilities Management Risks”. Rather than list them all here, we encourage you to download the white paper yourself to find out more. However, we’ll highlight a few of the more interesting issues.
You might not think of this as a DCIM issue, but people are important assets in any operation. The paper warns against trying to save money by keeping a lean staff. Piling all the work on a skeletal staff can lead to dangerous and expensive mistakes due to fatigue. Those of you in IT know how it is. Some organizations don’t mind employees working 12-hour shifts (or longer) and taking extra shifts if they are willing.
Keeping spare parts onsite, or at least close by, can save the day when the worst happens. Redundancy is a key concept in information technology. Have a look at our blog post “Redundancy: When Too Much is Just Right” to learn more. These spares may be kept onsite or held in a vendor warehouse, but critical spares must be readily available when needed.
Unless you’ve been on a tour of a data center, you might not know the scale of the backup power generators needed to keep everything going when the lights go out. You might want to check out this link and scroll down to the picture of diesel generators. The article from Data Center Huddle states: “Generators can provide power for hours or even days (however they will need to be refueled for ongoing operation) until the utility grid can provide power again.” One interesting fact is that diesel fuel can get stale over time, and that the quality of the fuel should be checked at least annually.
No one should take safety for granted. The Uptime Institute paper refers to NFPA 70E, which is the Standard for the Electrical Safety in the Workplace. Data center facilities must be compliant with other local, state, and federal regulations regarding safety. This includes protective equipment and written procedures.
We said that things change quickly in the management of data centers. At the risk of missing some of those changes, we refer to a 2015 article called “Who is Winning in the DCIM Software Market?”. At the time, the author of the article recognized three leaders in the DCIM software market: Schneider Electric, Emerson Network Power, and Nlyte Software. Using data from market intelligence provider IDC, the writer claimed, “Market leaders remain the same, but the fight for their market share is getting fiercer.”
Other players in the market include:
Data center management is a broad subject. We don’t claim to have covered all the issues in this article. There are so many things for managers of data centers to think about. How about “The Mystical World of Data Center Fire Suppression”? Then there are the biometrics involved in secure physical access, and the entrance portals that isolate the visitor when entering or leaving. The integration of IT management with facility management through DCIM is a major step in controlling every aspect of data traffic for IT providers and their customers.
A data center has many components, but none are more critical than the environmental monitoring system. The technology infrastructure may be state-of-the-art, but if such things as heat or moisture are left unchecked, then all that expensive equipment could fail and cost unnecessary expenses and downtime. Data center managers must have an all-of-the-above strategy that […]
Water and computers don’t mix, right? So why would anybody want to try to cool computer equipment with water? Lots of reasons. But the first thing you think, of course, is this: “Will it leak?” Well, probably not — but we’ll get into that. You should know that water and computers are definitely not mutually […]
Service providers do everything they know how to avoid downtime. Generally the best practice is not to touch a live network. If it ain’t broke, don’t fix it. But change is inevitable, and eventually every network or system will need improvements. The trick is to handle these changes with little to no disruption of running […]
IT systems go down for a lot of reasons. Some downtime causes are obvious, while others take some time to understand. And still others are just plain comical. In this article we’ll have a look at different approaches to assigning blame for outages, and we’ll offer a short list of our own. The concept of downtime applies […]