FOCUS DCIM DISCUSSIONS


Issue 20, Feb/March


DATA CENTER DISCUSSIONS


Emerson’s Steve Hassell and Schneider’s Kevin Brown go head-to-head on Data Center Infrastructure Management


The Data Center Infrastructure Management (DCIM) market is moving full steam ahead, with Emerson Network Power and Schneider Electric placing themselves firmly at the front of the pack with two solutions that promise to envelope the entire data center.


Schneider Electric’s StruxureWare operations suite was announced last year. The product runs on server clusters with load balancing, unlimited scaling and optional server choice. Using StruxureWare, data center operators can carry out physical location


planning, airflow analysis, VMware vSphere and


Microsoft System Center VMM Communication for virtualized server management.


It also covers the standard space, power,


Steve Hassell, president of Emerson’s DCIM division, Avocent, and Kevin Brown, VP of Data Center Global Offer at Schneider Electric, put their top DCIM questions to each other in this Data Center Infrastructure Management (DCIM) discussion. Here is what they said:


Q. KEVIN BROWN (Schneider Electric): What is DCIM and, more importantly, what is it not?


A. STEVE HASSELL (Emerson Network Power): DCIM is getting the IT infrastructure layer and the physical infrastructure layer to operate as one. It’s essentially virtualizing the physical infrastructure, just like what has happened to the IT infrastructure layer. Covering this gap is very broad, so in order for that to happen you still need to draw boundaries.


DCIM does not extend past the hypervisor on the IT side. It’s in the hypervisor because you need to have an idea of what’s happening inside IT – this is the demand side of the equation. You need to understand what’s happening, so you can take the correct actions.


I don’t think a DCIM tool physically moves virtual loads. I also don’t think it’s an IT service management tool that is involved in SLAs. It really starts with where the demand is and extends into the physical infrastructure, and then overlaps a bit but stops short of where the building management system (BMS) is located. You end up with DCIM at the top end, with the BMS to the hypervisor, where you have an interface with the virtual management system and the configuration management database that can interact with the IT essentials.


Q. STEVE HASSELL (Emerson Network Power): What are you hearing from CIOs as to the critical needs driving them to better manage their physical infrastructure and integrate that with the logical systems infrastructure?


A. KEVIN BROWN (Schneider Electric): Most CIOs are being driven by the trend towards ‘do more with less’. In the context of a data center physical infrastructure, this creates a tension between getting more energy efficient and getting more aligned with the business while receiving no relief from availability requirements. To be more energy efficient, operationally efficient and efficient with use of capital, a data center must reduce its safety margins.


This safety margin reduction results in the need for three things: better planning and communication between facilities and IT; more flexible data


26 www.datacenterdynamics.com


STEVE HASSELL President


Avocent (Emerson’s) DCIM solution


KEVIN BROWN


VP of Data Center Global Offer


Schneider Electric


cooling and network functions, among other areas.


Emerson Network Power’s Trellis offering builds on its acquisition of Aperture and Avocent in 2009. With the release of Trellis, Emerson increases its standard monitoring toolset to include server, storage and network infrastructure and power consumption.


Both companies claim to be advancing the area of DCIM with their all-inclusive product offerings that come with the promise of control over the entire data center. Here we put both companies side to side to see how their views on the relatively new DCIM industry have been shaping up. (For background, see our past coverage on both products in our special DCIM edition of FOCUS, Issue 17).


center architectures; and better tools to manage the infrastructure. It’s myopic to think this is only a conversation about software tools – it’s about planning, communication, business processes and the software tools.


Q. KB: How does a customer get started with a DCIM implementation? A. SH: You need to take a maturity model approach. Step one: understand what you have. If you don’t know what you are starting with it’s useless discussing how to control it. At that point, you can move to step two, which is starting to apply real-time information monitoring across the data center. This is getting status information as to what’s happening. From that you can start flowing information across the data center.


Then you are ready for the next stage, which I call analyze and diagnose. You can begin asking analytical questions of the information that is flowing through, such as, ‘Do I have enough capacity? Where should I put the next device? How long until it runs out?’. Once you get those answers you can start to add in rules. Then you can automate the entire process and allow the human operators to step back and let the system operate in a more dynamic fashion.


The good news is that every step of this maturity model pays for itself from an ROI standpoint.


Q. SH: Traditional data center design practices have involved several levels of power margins resulting in stranded capacity and lower efficiency. How can DCIM help recapture some of that capacity without compromising availability?


A. KB: The real action in future is going to be simulation of potential changes. We can model a data center today and when properly implemented a DCIM solution should be able to fully simulate changes before they happen. This is the Holy Grail that will only come through a coordinated and well-planned physical infrastructure architecture, as well as a good understanding of IT requirements.


This simulation will become more critical as customers begin implementing ‘zones of availability’ instead of a Tier III data center. We believe customers will begin to think of certain zones in the data center that only require Tier I and others that require Tier II.


Finally, virtualization and machine migration requires better integration


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57  |  Page 58  |  Page 59  |  Page 60  |  Page 61  |  Page 62  |  Page 63  |  Page 64  |  Page 65  |  Page 66  |  Page 67  |  Page 68  |  Page 69  |  Page 70  |  Page 71  |  Page 72