I’ve just returned from spending two days in Barcelona, attending the HP Converged Infrastructure Event.
Disclaimer: HP paid for my flights, hotels and meals during this trip. I was otherwise not remunerated for my time or required to blog about the event.
The event was more a media/press session rather than a technical deep dive, although technical product managers were on hand and the assembled bloggers did exercise the product managers’ knowledge. We were presented to on the new P9500 (the HP model of the HDS VSP) and on new blade systems.
Having seen the P9500 in a different skin only a week before, there weren’t any major surprises in the hardware. For those of you who are interested in the hardware, Calvin Zito has a video here. However we were shown a new software feature called APEX (Application Performance Extender) that enables QOS to be applied to servers (and on HP-UX, applications) for I/O on the P9500. APEX seems like a great idea; a centralised server collects performance statistics on each server (using agents, unfortunately), then makes decisions on workload prioritisation that are then fed to the P9500 array in order to implement the QOS policies.
I do think however that APEX has some issues. Firstly, response time is measured on the basis of the view of the host of that I/O. Now I know it’s notoriously difficult (nay, impossible) to measure end-to-end performance in a SAN network and to determine how each component influences the I/O latency. There could be multiple Fibre Channel switch hops, buffer credit congestion (especially in stretched fabrics), latency introduced by replication and so on. Consequently the view the host sees of an I/O could be vastly different to the way the array believes it is servicing that I/O. This could result in skewed I/O balancing, which isn’t good. Hopefully as more information is made available, I will be able to provide more insight, suffice to say for now, that the concept is good; the proof will be in the detail.
Day 2 of the CI event was a 3Par roadshow. 3PAR is being pushed as the saviour for HP Storage and that can be seen by the fact that Dave Scott, who headed up 3Par, has been appointed General Manager for the StorageWorks business. I personally believe 3Par is a great product, and with the momentum they’ve achieved so far with their R&D spend, it can only get better as HP publicly committed to significant increased R&D in the platform. HP stated that only 11% of the external storage market comes their way and they intend to use 3Par to go after the other 89%.
The positioning of 3Par seems like a great move for HP. The acquisition wasn’t a direct response to the Dell bid, but rather HP had been planning for some time to acquire 3Par and changes in management made that more easy to achieve as part of a Dell counter-offer. But the confusing part of the day’s presentation was the omission of the P9500 array from the discussion. A slide was displayed showing the evolution of the platforms for both traditional and service provider customers. 3Par is the only choice for service providers and is the major choice at Enterprise, mid and low-range. XP (now P9000) is moved to the side and presumably only retained for mainframe or existing/specialist customers.
If 3Par is to become the premier HP storage product, there is going to need to be some serious thinking put in to converting customers. Management (alerting, provisioning, billing etc) will all be different; there’s a whole set of migration strategies that will need to be developed; business models will change (new ways to calculate ROI/TCO). Getting this information to customers rather than just discussing the tin will be HP’s greatest challenge and one I look forward to observing.
Meanwhile, here are a few pictures from the event.