On Wed, Nov 21, 2012 at 8:14 AM, Vlad <marchenko(at)gmail(dot)com> wrote:
>
>
> '-M prepared' produces normal results, while '-M simple' results in 40% sys
> cpu. '-M extended' is somewhere in between.
> I'm running it as 60 clients, 2 threads.
2 threads is pretty low for 60 clients. What happens if you increase
-j to either 30 or 60? (What I'm wondering here is if perhaps in this
case it is pgbench which is triggering the scheduling issue)
Also, what happens if you channel pgbench through pgbouncer?
Cheers,
Jeff