BTW, what -B setting were you running the postmaster with? While poking
at this, I was reminded that having adequate buffer space really makes
a considerable difference ... especially under WAL, where it's not
necessary to flush dirty buffers to disk at the end of each transaction.
The default -B 64 is certainly too small to get reasonable performance.
I got roughly twice the tps reading (pgbench -t 1000, with -F) at -B 1024.
regards, tom lane