Like extreme skiing, without the helicopters.
On Wednesday HP announced its new Extreme Scale Out (ExSO) Portfolio, a collection of hardware, software, and services aimed at provisioning datacenters with requirements for 1000s to 10s of thousands of servers.
With the announcement HP introduced the ProLiant SL line of servers that use standard 19″ components in regular 42U racks (unlike IBM’s iDataPlex or SGI’s CloudRack, the obvious competitors for this offering) and mount servers on cookie sheets rather than enclosed metal boxes. These sheets also have holes cut in them to further reduce weight, all of which results in systems that are 31% lighter. The systems also consolidate fans and high efficiency power supplies on a per tray basis, shaving what the company estimates to be 28% off the top of your power bill on a per server basis. From the release
At the core of the HP ExSO portfolio is the HP ProLiant SL server family, which uses a ”skinless” systems architecture that replaces the traditional chassis and rack form factors with an extremely lightweight rail and tray design. As a result, customers can dramatically reduce capital, facilities and shipping costs while using a fraction of the space normally required in a data center. Additionally, its ultra-efficient, modular design enables customers to quickly and easily build solutions that meet extreme scale-out workload requirements.
One of the features that I really like in the new portfolio, but that doesn’t get much air time in the release or in other feature coverage of the announcement, is HP’s Environmental Edge offering
HP Data Center Environmental Edge uses a system of wireless sensors placed throughout a data center to monitor a variety of variables, such as temperature, humidity, air pressure and power utilization. The system provides real-time visualization of environmental variables so administrators can perform root cause analysis to eliminate excess operational costs.
Although draconian security requirements will make the wireless bit a little sticky in some settings, it’s ideal in existing, busy datacenters where a fixed wire infrastructure would be very disruptive to install. I cover this announcement in some detail for a feature piece at HPCwire that will run sometime this week. In that piece I point to the future joining of the stream of data about the data center itself and user jobs
But once centers are more commonly instrumented and interfaces to those data are more widely accepted, HP sees a future in which environmental data are taken into account in routine operations. For example, if a job scheduler was aware of the power utilization of all the machines in a center it could move jobs to machines with lower energy use, or even delay running those jobs until off-peak power rates made running a particularly power-intensive job cheaper. HP isn’t ready to talk much about this, other than to say that they are working on it now. It will certainly allow us to take a much more integrated approach to sustainable computing practices while still getting the scale we need to do our jobs.