ADVERTORIAL FUTURE FACILITIES
Issue 18, October/November
CENTRE HEALTH ‘Supercharging’ DCIM with simulation is the ultimate way to improve data centre practices, says Alexandra Bannerman, Technical Marketing Engineer at Future Facilities Ltd.
CFD SIMULATION - THE FUTURE OF DCIM AND DATA D ata Centre Infrastructure Management has quickly
become a hot topic within the industry. Its rapidly growing popularity suggests that people are realising the severity of problems caused by a lack of communication
between IT and facilities management, and the difficulties arising from inadequate recognition of important details during the entire data centre lifespan.
WHY DCIM?
From the very start of a data centre’s lifecycle, the various key parties involved work separately towards different goals, and do so with varying degrees of care and accuracy.
• Many data centre design specifications have long been based on speculative ‘rules of thumb’ that have no real relation to the behaviour of the facility in operation. For example, the watts per square unit ‘rule’ used for capacity planning is irrelevant and erroneous in the majority of cases, as facility load distributions are rarely uniform, and usually change multiple times during a facility lifecycle. However, designers have for years been using these near meaningless metrics as guidelines for a permanent structure, and imagining their assets will thrive within the resulting unsuitable atmosphere.
• Facility managers provide layouts and specifications for cabinets, ACUs and PDUs within the completed facility shell without full knowledge of the equipment to be catered for. Despite this, the layout is expected to support the requirements of that equipment for the remainder of the facility’s operational life.
• IT managers regularly require new servers that may not fit into the predefined layout.
• Equipment manufacturers are constantly changing and upgrading models, increasing power densities and adapting airflow characteristics. While this satisfies the objective of the manufacturer to improve processing power, it complicates the data centre puzzle further by introducing variables.
Independent changes like these are hardwired into the facility for the long term, with very definite effects; the inconsistencies between design aims and results can be highly detrimental to a facility’s longevity.
A data centre is, in itself, a transient entity; its contents are continually changing. Load capacities change in response to client needs, IT equipment is continually evolving both in terms of power density and airflow characteristics, and changes like these affect everything else within the facility - airflow, power and networking being perfect important examples. It therefore follows that a sensible approach to designing, optimising and managing a data centre must take every detail
76
www.datacenterdynamics.com
Snapshot of a 6SigmaDC Virtual Facility of its workings into account - however, this is easier said than done!
It must be noted that every change to a data centre, no matter how small, could potentially have a devastating effect on its workings. For example a damaging hotspot at one end of a facility could have been brought about by something as simple as a new blanking panel in a cabinet at the other end, or a server ramping up temporarily to provide required processing power. It is rare that the causes of such problems can immediately be seen. While it is possible to attempt quick fixes or apply blanket changes to combat problems, the underlying problem remains; the workings of data centres are often unknown, or misunderstood. Working reactively to solve problems that have already occurred does nothing to reclaim the resulting lost capacity and lifespan, and does nothing to ensure problems won’t recur.
By bridging the communications gap that separates each sector of the data centre workforce, DCIM will essentially reduce the likelihood of negative effects by promoting proactive improvements to data centres throughout its lifecycle.
TAKING DCIM TO THE NEXT LEVEL
According to Gartner, DCIM is likely to have been adopted by 60% of the market by 2014, and this can only be a positive development. However, DCIM tools currently revolve around asset management and real-time monitoring only. While these activities are a great way to increase information dissemination within facilities, they are only a small part of the data centre conundrum. The ultimate form of DCIM would be a tool that encompasses these activities while facilitating experimentation, analysis and therefore the complete understanding of the data centre’s workings - airflow,
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 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96