- for convenience it's easier if persistent storage is on first node
  of allocation to create and destroy pools

- differentiate file names by rank to allow single node tests
- use fallocate instead of fopen/fwrite to generate file
- error checking

- also normalize test order and labels with other platforms

- also normalize labels for test runs with bebop scripts

- to pick up latest progress mode updates

- the purpose is to test the new wait_fd capability in verbs;ofi_rxm