For the past few years, the buzz in data center trade shows around data center infrastructure management (DCIM) software has been substantial — much of it hype, not reality. But this market sector has been growing and maturing, and the technology around it has gone from being a “bleeding edge” utopian promise to a practical reality for many larger data centers.
DCIM is a category of software, not a single piece of software
Just as “office” software encompasses word processing, presentations, spreadsheets, email, and other applications, DCIM encompasses a range of applications that can help improve data center operations. Analysts peg the size of the DCIM market at around $600 million, and growing around 25% per year, meaning it’s on track to exceed a billion dollars in three years.
The two core building blocks of DCIM: DCIM monitoring and IT asset management (ITAM)
DCIM monitoring is about collecting information about the real-time, current, state of your data center — with power consumption and temperatures being two of the most important areas to monitor. Monitoring includes alerting (or alarming) of failures or potential issues, and tracking data historically, over time. It is by far the largest piece of the DCIM market comprising over half of DCIM spending in this category.
ITAM is the next-largest piece; this software focuses on the details of all the equipment in a data center.
Other applications riding atop DCIM monitoring and ITAM
Once the basics are in place, you know what you have in a data center (ITAM), and how it’s performing (DCIM monitoring). Now it’s time to take the next step, with capacity planning and management (space, power, cooling, cabling), or controlling the facilities side with dynamic/adaptive cooling, or controlling the power state of IT equipment, power capping, load shedding, or modeling the thermal environment using computational fluid dynamics (CFD) and more. Some of these applications have more “sex appeal” than the two foundations, but if you add up the market size for every one of these, put together, you get a number significantly smaller than the ITAM market alone, much less the DCIM Monitoring market.
You can buy integrated suites, or you can assemble “best of breed” modules
As with many other enterprise software solutions, you can select software from one vendor that has been pre-integrated (like a Swiss Army knife) or you can select individual modules and integrate them into a solution. The tradeoff here is ease of use and pre-integration vs. selecting the “best” module that fits your solution. While the knife blade in a Swiss Army Knife may be ideal for some uses, you may prefer a sashimi knife if you’re cutting raw fish, or a bread knife. Picking and choosing each module provides you the best tools for your requirements – but integrating multiple vendor modules may be more challenging and costly. The good news is that some vendors offer easy integration with others via various APIs. For now, there is no “industry standard” API, however.
Even a single DCIM module can offer a quick return on your investment
There are many benefits of DCIM, and these vary from module to module. Research by Enterprise Management Associates (available here) quantified these benefits. Here are six general areas where customers find benefits; in many cases, they need to focus on just one of these in order to benefit. Broader deployment can provide even more value, but you might want to consider a step-by-step approach rather than trying to “boil the ocean”:\
- Power chain efficiency. A DCIM tool should identify various areas of inefficiency, which you can address via reloading, rebalancing, consolidating, replacing, decommissioning, controlling or otherwise making changes in your Facilities and/or your IT environment. It is not unusual to find opportunities to reduce PUEs (and therefore power bills) by 15-30%.
- Cooling efficiency. Further power reductions can be achieved by effectively raising temperatures inside a data center; implementing monitoring to ensure raising temperatures doesn’t get you into trouble, and identifying areas of over-cooling and under-cooling, over time. By adjusting the cooling infrastructure, or moving around heat-producing IT devices and workload, one can safely raise temperatures, and every 1 degree Celsius increase can result in a 4% reduction in power costs.
- Operational efficiency. DCIM can help your IT and Facilities teams coordinate effectively in managing the data center, for example, collaborating on the optimal placement of new servers relative to existing equipment – but ensuring that there is sufficient power, space, connectivity and cooling to handle the new equipment. This results in faster, better-planned deployments, with less labor. Imagine a deployment process, which previously took 2 weeks, now taking an hour!
- Automation. Monitoring power, temperature and other aspects directly and continuously obviates the need for manual readings, on a once-in-a-while basis. You have more accurate and granular data, without expending labor to take measurements.
- Maximizing capacity. Cascading conservative assumptions lead to inefficient allocation of power at each level of the power chain. This results in inefficient loading, but also oodles of “stranded power” (and ditto space, cooling and cabling). Many data centers operate at 20-40% of their design capacity. A DCIM solution should allow you to unlock this unused capacity, installing additional equipment in your data center. In some cases, this means you can defer or cancel planned new build-outs, saving perhaps hundreds of millions of dollars!
- Higher reliability. For some data centers, having a tool which can predict problems, identify weaknesses, and being able to fix issues quickly and effectively means you will have less costly downtime. Some operators can even quantify the business value of increased reliability.
DCIM is for all types of data centers
DCIM fits “owner operator” data centers, where a single entity is responsible for operating the building, the facilities infrastructure and the IT. But it also fits the multi-tenant data center (MTDC) aka “colocation” or “third-party managed” model where one party is responsible for the facility and for providing the power and the connectivity, while the tenants (or third parties) may be responsible for the equipment. And then there are the cloud data centers, many of which operate at hyperscale and who compete for customers on the basis of cost, service levels and performance; DCIM tools can help on all of these accounts.
If you have not yet embarked on your journey into the realm of DCIM, the question isn’t whether you should — the question should be: Where do I start?
I attended too and was glad to see...