Submission 10:
- per thread throttling instead of a global process with a mutex. this avoids a mutex, and the process is shared
betweenclients of a given thread.
- ISTM that there "thread start time" should be initialized at the beginning of threadRun instead of in the loop
*before*thread creation, otherwise the thread creation delays are incorporated in the performance measure, but ISTM
thatthe point of pgbench is not to measure thread creation performance...
I've added a comment suggesting where it should be put instead, first thing in threadRun.
--
Fabien.