HP dishes 24 hour party people blade
NonStop takes on modern touch
When HP talks about "blade everything", it means freaking everything. The hardware maker has pumped out a blade server running its NonStop operating system and software of all things.
The NonStop NB50000c BladeSystem will fail to shock loyal HP customers. We spotted the server on HP roadmaps almost a year ago. HP has been working away on making sure that the NonStop software would work well with the c-Class chassis that houses HP's other x86 and Itanium-based blades.
The new blade holds a pair of dual-core 1.66GHz Itanium 9100 Series chips, each with 18MB of Level 3 cache. The unit can also contain up to 48GB of memory and has all of the redundant bits - fans and power supplies - that you would expect of a NonStop system. In addition, the box can make use of the ServerNet switching technology used in the NonStop realm to combine up to 4,080 blades into a single system.
HP reckons that the NB50000c offers up twice as much performance per unit of floor space as the existing, bulky NS16000 box.
The company is pretty proud of itself for bringing the NonStop software loved by financial, telecommunications and government customers over to the c-Class chassis. It's a sign that HP is moving away from very specialized cases and innards in favor of a shared hardware base.
"Everything we did was custom designed - custom cabinets, power supplies, memory and disk drives," said Randy Meyer, director of NonStop systems at HP. "What we have been doing over the last period of years is moving toward industry standard hardware as it gets more and more reliable. Now we can drive down costs while maintaining the NonStop capabilities of fault tolerance and massive scale."
You can fit eight full-height NonStop blades in the c-Class chassis, running NonStop Operating System release J06. Customers will see a chassis plus two blades - each with one Itanium chip and 8GB of memory - start at around $300,000, including software licenses. HP emphasizes that the price comes in below the NS16000, which starts around $385,000.
In either case, you're obviously paying an awful lot for the NonStop software, since a normal C-class chassis with a couple of x86 blades will be in the tens of thousands of dollars range.
HP is hoping that the modernized NonStop system will prove enough to attract customers away from IBM's mainframes. To help encourage this shift, it's offering to waive the purchase price of the hardware and cover the software costs for one-year if you'll move a financial application over to the NonStop blade from a mainframe.
It's always refreshing to see HP and IBM play nice.
There's more information on the NonStop FREEdom campaign - how cute - here. ®
Yeah...so why did they disable 25% of the cache on the chip?
Seems to me you would expect Non-Stop hardware to get the best chips
If I hadn't been tweaking old COBOL and TAL code for decades in response to changing business conditions, I'd be inclined to agree. However, I ***have*** been looking at old Tandem programs, understanding enough to modify them, retest and send them back into battle: we're not talking orphan objects here. The complexity usually comes more from years of accumulated real world adjustments than spaghetti coding. I will grant that there must be pathological cases in which people won't go near a critical module for fear of breaking the system, but I don't see those because I don't get hired to work on them.
Would I rather rewrite the old Tandem apps completely? Yes. Would I choose different languages? Yes. Would my clients consider the total cost and associated risk justified? Almost never.
But speculating on variations in application code quality misses the point, which is: the Tandem architecture provides scalability, data integrity and uptime that other systems simply can't touch. When you consider that there has been only one major architectural change in the system since the late 70's (K-series to S-series) apart from the normal Moore's Law upgrades, that's pretty amazing.
Does rehosting on Itanium make a difference? Not to me as a legacy maintenance programmer. Neither did the move from proprietary CISC CPUs to MIPS RISC, or the failed attempt to move from MIPS RISC to the DEC Alpha of blessed memory. Since Pathway and SQL were put into place in the early eighties, Tandems have always programmed the same for the most part. System managers and the people who pay for the hardware care about the hardware changes in order to achieve their required Transactions Per Second capacity but are quite happy that they have never had to suffer through the software equivalent of a forklift upgrade. Tweaks and minor conversions, yes, but never a "bet your business" kind of upgrade.
Of course, I do other stuff on the side as well as on my own time, and I'm sure that truck drivers like to drive sports cars now and then as well.
As far as I know, the Tandem is the only long-lived commercial system designed from the get-go for NonStop operation, data integrity and extreme linear scalability (no SMP "knees" in the power versus CPUs curve). The architecture reflects these baked-in requirements, and the OS and middleware take advantage of them. Once you're used to this kind of engineering, almost everything else looks like improvisation.
so why did they disable 25% of the cache?