Can the wall time be considered constant if it depends on the magnitude of the numbers to sort? A list of numbers between 1 and 1000 will be much faster to sort than a list of numbers between 1 and 10^100. EDIT: I did get the joke when I read your post, and laughed to myself, so well done :)
The constant is the biggest number in the list multiplied by the sleep multiplicand. That plus overhead gets you the approximate runtime of the function.
If you just repeat the same number a million times, then the threads will all be scheduled to run at the same time, but of course, your computer doesn't have a million cores, so the threads will have to be executed partially in sequence. That means, even if you assume the largest integer is a constant (valid for some integer types, but notably not Integer in Haskell), the runtime will be proportional to the number of elements in the list.
Yeah, but technically that doesn't qualify as a constant since it depends on the input. If you explicitly constrain the problem space such that the magnitude of the numbers in the list is bounded by a fixed upper bound, then it works out. That's fine though, but then it's not a fully general sorting algorithm, like e.g quicksort
