DCN June 2017 | Page 17

big data & IoT
scalable , powerful processing and storage , high speed low latency connectivity , security , and abundant power .
Putting this into focus , just imagine the consequences of driverless cars hurtling along the M4 motorway and the data centre housing the control equipment going offline .
For some time data volumes have been doubling every 18 months but modern data centres with sufficient power on tap for running high density servers that can support highly virtualised environments have been coping . But this is just the tip of the iceberg . According to the mobile industry group , GSMA , by 2020 there will be 24 billion ‘ things ’
Just like the cloud , Big Data and the Internet of Things ( IoT ) ultimately require physical elements to sustain them .
‘ The main areas for concern when choosing a data centre provider are around power and cooling .’
connected to the Internet of which half will be mobile devices . A different study by Cisco puts the number of devices connected to the Internet at 50 billion by 2020 or over six ‘ connected devices ’ per person on this planet .
Clearly , the IoT is no longer just talk about some fanciful glimpse of how things will be in the future . It ’ s already here and a booming business . Gartner ’ s latest IoT Global Forecast predicts total IoT services spending this year will be $ 273bn on professional , consumer and connectivity services .
The Big Data landscape is dominated by operational and analytical systems , the former being real time interactive systems where data is primarily captured and stored . Latency for these applications must be very low and availability must be high in order to meet SLAs and user expectations for modern application performance . Analytical systems , on the other hand , demand high throughput to provide capabilities for complex analysis of large batches of retrospective data . Quite often both Big Data approaches are deployed together , and in any event , demand clustering of multiple servers comprising thousands of terabytes for the storing and processing of billions of files .
So how can we expect Big Data and the IoT to impact on the data centre ?
Older data centres housing IT systems typically doubling in performance every two years in accordance with Moore ’ s law , will likely struggle to support the new unprecedented compute demands of the IoT age . The only way forward is to have a highly flexible infrastructure that can adapt and grow to deliver the increasing power , cooling and connectivity
necessary . A typical rack in a data centre used to consume under 2kW of power and older data centres were built to support this level . However , expecting customers to now use two , three , four or more times the space to support increased IoT power requirements will not be acceptable practice .
Ultimately , IoT fuelled Big Data is accelerating the demand for high performance computing ( HPC ). They are inextricably linked . But the answer does not have to mean a return to building expensive inhouse data centres that will rapidly age and fail to keep pace with the power and cooling demands of such high density environments .
HPC ready
Enter the HPC ready colocation data centre with the space , power , cooling and connectivity necessary to support clusters of very high density server racks , some pulling as much 60kWs . By choosing the right colocation provider , an organisation can grow or shrink its HPC platform as required with the knowledge that the facility provider will not be a constraint on their needs . This solution must not only offer a future proofed data centre infrastructure to accommodate rapid expansion , but also provide the essential engineering skills necessary for the design and build of highly bespoke environments .
Power and cooling
The main areas for concern when choosing a data centre provider are around power and cooling – HPC , by its very nature , requires large amounts of power , and a suitable facility provider should be able to tap into the grid for not only what it needs now , but also for what it predicts will be required for the foreseeable future . However , grid power is not a guaranteed service – outages will occur . Therefore ,
June 2017 | 17