Always in earlier PostgreSQL versions and still by default, the pgbench program itself runs as a single process on the system. It queues up statements for each client to execute, then feeds them new ones as they report they're finished responding to the previous one. In all situations, it is possible to have that process slow if you have a large number of clients active. A common approach to work around that has been to run the pgbench program itself on another system, which does unfortunately add its own overhead, too.
The situation is particularly bad on Linux systems running kernel 2.6.23 or later. The Completely Fair Scheduler (CFS) introduced in that version is not very fair to pgbench
