Released recently: a research report, conducted by Futuriom, spanning medium to large enterprises across China, the USA and UK provides a detailed analysis of how today’s data center professionals are addressing the challenge of supporting high-power applications such as artificial intelligence and big data analytics across public, private and hybrid clouds. The study reveals high interest in software-defined virtualization and network optimization strategies. It shows that processor offload and SmartNICs are now the favoured solution for improving data center performance – while deploying more servers is least favoured. Above all it concludes that the network, a key engine of performance to the cloud, needs specific adaptations to keep up with data centers that have ambitions to be cloud-scale.
“If you want to cut through hype and rumour to find out what is really happening, you ask the people at the coal face” says Kevin Deierling, VP of Marketing, Mellanox Technologies, sponsors of the research study. “Over 200 director level or higher data center professionals – from US, UK and China-based cloud, telecommunications and enterprise IT – were screened by country and company size by analyst firm, Futuriom, to dig deeper into actual working practice and the key trends. There was a lot of interest in SmartNICs – a bare 10% did not know what they were. Their applications included improving the efficiency of VMs and/or containers (56%), virtualizing and sharing flash storage more efficiently (55%), isolating and stopping security threats (47%), accelerating hyperconverged infrastructure (50%), and enabling SDN (54%).”
Other findings include: the recognition that network optimization technologies are a key way to improve DC performance; potential benefits in upgrading the network include faster application performance (64%), stronger security (59%), greater flexibility (57%), and application reliability (57%); and that 84% of respondents thought network infrastructure was either “very important” or “important” to delivering artificial intelligence and machine learning. Highly efficient utilization of servers and storage topped the list when asked which aspect of hyper-scale cloud operations they would most like to emulate. The next tier of results included use of flexible, converged 25/50/100Gb Ethernet networking for everything (19%), automated infrastructure deployment, management and monitoring (17%), and simplified resource provisioning, reporting and billing (15%).
The US, UK and China were selected in order to garner a diverse global outlook from three regions where data-center infrastructure is being deployed most aggressively, and the report includes both aggregated data from these geographic regions and broken down results where appropriate. The report also provides further detail on the biggest perceived challenges around virtualization and containers; on developments in data center storage strategy; on the future of Moore’s Law and its strategic relevance for data center strategy; on developing network requirements for data centers; and key technologies to watch, including hyperconverged infrastructure, domain specific processors and application code efficiency. Full report is now available to download - bit.ly/2IooSRH
“The data center is being reinvented” according to Scott Raynovich, Chief Analyst, Futuriom. “It’s a real challenge to build a cloud infrastructure that can scale to support demanding applications that can embrace big data, analytics, self-driving cars, and artificial intelligence. The very techniques developed by hyperscale cloud giants are now migrating to the enterprise, where distributed applications now rule. There’s more pressure than ever for networks to perform, and new technologies are beginning to be deployed to make sure that networks don’t become the bottleneck for the cloud. This report provides the most detailed insight into why this matters, and how key players are re-shaping the road map.”