Allow up to 3 "-P 1" reports per thread in pgbench run of 2 seconds.
authorTom Lane <tgl@sss.pgh.pa.us>
Fri, 22 Sep 2017 16:59:44 +0000 (12:59 -0400)
committerTom Lane <tgl@sss.pgh.pa.us>
Fri, 22 Sep 2017 16:59:44 +0000 (12:59 -0400)
commit0f574a7afb5c998d19dc3d981e45cb10267286ed
treeae585922f256a8d809f5c87a0a4179140ff3f126
parent5d3cad564729f64d972c5c803ff34f0eb40bfd0c
Allow up to 3 "-P 1" reports per thread in pgbench run of 2 seconds.

There seems to be some considerable imprecision in the timing of -P
progress reports.  Nominally each thread ought to produce 2 reports
in this test, but about 10% of the time we only get one, and 1% of
the time we get three, as per buildfarm results so far.  Pending
further investigation, treat the last case as a "pass".  (I, tgl,
am suspicious that this still might not be lax enough, now that it's
obvious that the behavior is load-dependent; but there's not yet
buildfarm evidence to confirm that suspicion.)

Fabien Coelho

Discussion: https://postgr.es/m/26654.1505232433@sss.pgh.pa.us
src/bin/pgbench/t/001_pgbench_with_server.pl