Jan Wieck <JanWieck@Yahoo.com> writes:
> Well, it turned out that pgbench does a terrible job with runtimes below
> 30 minutes. Seems that one checkpoint more or less can have a
> significant impact on the numbers reported by such run.
Yeah, it is *very* painful to get reproducible numbers out of pgbench.
> Using the above, the discussed change to the tuple header shows less
> than 1% difference.
So the bottom line is that there is probably no measurable performance
difference, but a 3% space savings, at least for average row lengths
comparable to those used in pgbench. (Obviously the space savings is
going to depend on average row length...)
regards, tom lane