Cost of purchase for most HPC users

… is the biggest non-sunk cost aspect for an HPC system, outside any software licensing costs, which have a habit of often dwarfing the system cost.
At InsideHPC.com, John West does an analysis of the RedHat HPC announcement.

While the Hat’s HPC solution is evidently cheaper per node at street price than Windows, it’s still not cheap (see the comment on the original post at this site by a reader who was considering dumping a $50/node OS in favor of something cheaper). To be fair I hadn’t given much thought to the issue of price for the OS, and I think that my (mistaken) indifference is probably an issue for the broader market. In a word, yes. It is very much an issue for the broader market. Remember, HPC at the top, is shrinking in relative terms as a fraction of the HPC market. I haven’t looked at the numbers recently, but it wouldn’t surprise me to see an absolute shrinkage as well. I suspect a large segement of the low-end to middle of the HPC market is getting into this without planning for an OS purchase. That would be accurate. The OS doesn’t have to cost you anything. It is your choice if you wish to pay for it. Apart from Windows that is, where you must pay for it. So the additional OS cost is modeled as Cost(OS) = N(licenses) * Cost(per-license) For N~32, and Cost(per-license) of about$200 USD, this adds $6.4k USD to the purchase cost of the system. For 32 nodes of about$2500 USD/unit, this is the difference between an $80k USD cluster and an$86k USD cluster.
For Cost(per-license) of about $469 USD (Windows server 2008 HPC), this is an additional$15k USD cost.
So now your typical user will do a cost benefit analysis. And ask themselves what, precisely, is the benefit that they should realize from this additional expenditure.

They’re focused on the hardware and the apps, but not the OS.

Yes. Exactly. Precisely. The OS (well the most common cluster OSes) do not cost *anything* to purchase. So adding cost means, for most companies purchasing HPC gear, giving up something else.

It will be interesting to see if they recognize the value of an integrated OS stack right off the bat, or if they’ll have to spend 18 months as a market trying to roll their own before they are willing to spend the cash.

Er … I disagree with this. Lots of end users already have integrated OS stacks with HPC tools. And Redhat’s hasn’t been … well … all that good for HPC in large part due to its missing features and kernel issues. To get good stability/performance out of the systems, you usually have to start out by replacing the kernel. Since that breaks the Redhat support agreement, this is troublesome for many HPC shops that might like to use a pure Redhat load.
Currently, the most integrated HPC stack I am aware of is the Rocks stack. It (sadly) is tied to Redhat in ways that make it hard to use anywhere else. There is a long (negative) history between Platform and the Rocks team as well. There are other stacks as well. This is a solved problem, has been for a while. This is a new entrant into the solved problem arena.
As it is a non-zero cost entrant, it would be important to understand what the cost per node buys you. We have spoken to many customers whom have no interest whatsoever of paying OS cost per compute node. Many are opting out of paying OS cost per desktop/laptop by adopting alternative OSes to what traditionally shows up there.
The question is, fundamentally, what will the adoption rates look like. I don’t think they will be all that good, but I am guessing. I reserve the right to change my mind (could be that this new thing is the best thing since sliced bread, but honestly, I doubt it).

6 thoughts on “Cost of purchase for most HPC users”

1. Going from free to anything is a hard sell. To quote Homer Simpson, “Free…yeah, I can swing that.”

2. Well, if the stack does add real value, it is possible. Ignoring the marketeers for a moment, will it? That is the question. If they genuinely make a significant difference in the ease of use of a system, and it doesn’t negatively impact other areas (due to the ancient Redhat kernels and missing features) it would be interesting to see if they get traction. If it is little more than a bundling arrangement, I would be hard pressed to see it take serious hold.

3. I think this also begs an interesting question – is a fully integrated stack, ala’ ROCKS, better than a cluster tool that is layered on top of an OS? I have my own personal view… 🙂 But I’m interested in what other people think.

4. I personally prefer the latter than the former. Most customers (at least in the commercial space) don’t care, it is a detail to them. I’d love to hear comments about this as well though, even given my own particular biases.

5. I think the above discussion shows clearly – why M\$ tries to get native apps to run on ‘their hpc product’.
By creating apps, which absolutely won’t run on Linux – you can force people to pay for the OS. (and ISVs for the dev/debug-tools)
And interestingly enough – a lot of ISVs seem to blindly take the bait (and the gallow!) Redmont is currently offering them …
I 100% agree, that redhat’s success is exactly based on providing the MINIMUM set of software, which ‘runs the node’.
No bells, no whistles => no bloat !
But THIS is IMHO the whole ‘secret’ to success!
Don’t enforce anything – and the free market forces (smart folks) will after a while automatically find the optimal set of bits+pieces.
you can’t do that with the bloatware from redmont. – You’re forced to stick to their rules and understanding of the world.
(for example: boot 100% diskless over IB)
(or chose whether you want an NFS-root, or a ramdisk-root-fs, etc etc.)