Why Is Next Month's Compute Capacity Easier to Sell?

Evan Conrad says capacity that starts a month from now can be bought and sold all the time, so liquidity shows up easily. Capacity right now sells only by interrupting the workload already running on it, and the seller has to decide whether that interruption is acceptable. Worrying about capacity next month is a different problem from cutting a job that is already running.

The way an interruption lands depends on storage. A Weka or Vast system, and how large it is, changes how a job handles being preempted or pulled off the cluster. If data can move quickly from one cluster to another, he leaves open whether a job spreads across several clusters, drops on one, and starts again on another. The fast path is usually a wide area network: cables that tie the clusters together, a private internet. Most clusters being built do not necessarily have that link.

Traditional central processing unit clusters sat next to the customer to keep latency low. Graphics processing unit clusters sit next to the power. Data centers are going up in places that never expected them, so a transit path from one site to another is not guaranteed to be excellent.