On 06/25/2015 10:47 AM, Peter Geoghegan wrote:
> On Wed, Jun 24, 2015 at 2:52 PM, Josh Berkus <josh(at)agliodbs(dot)com> wrote:
>> OK, this is pretty bad in its real performance effects. On a workload
>> which is dominated by new connection creation, we've lost about 17%
>> throughput.
>
> Mistakes happen, but this is the kind of regression that automated
> performance testing could have caught. That's another area of testing
> that needs considerable improvement IMV.
Well, I have a pgbench test script for it now. If only I had some place
to check it in ...
--
Josh Berkus
PostgreSQL Experts Inc.
http://pgexperts.com