On Mon, 2004-12-06 at 17:43, Josh Berkus wrote:
> Mark,
>
> > Ok, here are a series of three tests varying the bgwriter_delay at 1,
> > 50, and 100:
> > http://www.osdl.org/projects/dbt2dev/results/pgsql/bgwriter_delay/
>
> Hmmm. Looks inconclusive. The differences between the runs are < 0.3%,
> which is a margin of error by anyone's definition.
>
> Will have to develop better tests ...
Josh is right - these are inconclusive. That usually means the other
settings are still very sub-optimal.
The graphs show the effect of checkpointing is still very large, so it
looks like the bgwriter is ineffective.
Varying bgwriter_maxpages upwards should take performance higher.
--
Best Regards, Simon Riggs