[fancyfredbot]

Your average HFT algorithm will not have time to access storage at all, let alone 10 PB of it.

Back testing an HFT algo could very plausibly need 10PB, but I don't see that being co-located with the exchange.

[rbanffy]

What would be good cases for data-heavy applications in expensive places?

[fancyfredbot]

I'm not sure but I suspect that people who've run out of space in an existing data centre will be willing to pay for increased density rather than relocating.

[rbanffy]

Unless latency is at a premium. This is why I thought about HFT.