Just back from Budapest where I attended a training event for Sun’s EMEA, Government, Education and Healthcare team. My work on NESSI has opened my eyes to the tremendous innovation occurring in parts of these sectors; I was really looking forward to it.
A colleague of mine, Philipe Trautman presented on winning High Performance Computing deals. He produced some fascinating figures to describe the opportunity. Both Storage and Systems are forecast to grow at double digit rates for the next few years, where as commercial IT is expected to standstill at best. Over 30% of CPUs are going to be bought by HPC solutions during this period and at the moment, 65% of the HPC market is educational and/or research institutes. He outlined Sun’s product portfolio consisting of systems, storage, operating systems and interconnects, which can be supplemented by partner products and people. He made the assertion that the real pain is no longer FLOPS, but elsewhere
- Power & Cooling
- Cluster Management
- Application Scalability & Utilization
- Data Access including Filesystem selection
and presumably interconnect architecture and selection. Some of these are problems we have been confronting in commercial data centres for a while, albeit on a smaller scale but the last two are new.
Philipe introduced Dr Wolfgang Hafeman, of “Solutions for Research”, a subsidiary of T-Systems and thus Deutsche Telekom, who have built and manage an HPC system for researchers in German commerce and academia, using Sun’s products. I wonder if I can get the picture he showed, its quite dramatic. Again, this is an example of the right thing done well. Certainly T-System’s people have added massive value to the proposition, although often the success of such a piece of business is based on the quality, drive and determination of the project teams. The relationship between the project teams supersedes the relationship between the companies. Its a great example of partnering for the end customer’s success.
In discussing virtualisation, a speaker this morning suggested that the two biggest inhibitors to using virtualisation technology are security and scalability. Both of these are opportunities for Solaris. A number of security conscious customers use Solaris 10 with trusted extensions, to run a container, with a virtual box instance, hosting windows. They’re delighted because it allows them to protect their network from windows vulnerabilities (It also allows them to protect their data from windows vulnerabilities; you can prohibit the container from acquiring data via any i/o device). The new scalability problem is to scale on a CPU. Sun’s Niagara processors are the most threaded CPUs in common use, but Intel and AMD are also pursuing multi-threaded CPU designs. They and their customers need an operating system that scales across the new architectures. Some users/customers are now evaluating work/kwatt, and thus being busy helps you score high in these tests. Scalability = Performance, and Performance = Eco. You still draw power even when not busy.
On the penultimate day, I walked down the hill from the castle heights, towards the Magrit Hid. There’s a number of small alleys with steps as its quite steep. The views from the heights are quite dramatic as central Budapest is quite low and the old, i.e. very old, ‘buildings of power’ dominate the skyline. You can see the Parliament building(?) in the background here.
Originally posted on my sun/oracle blog, and reposted here in July 2016.