Re: testing ProcArrayLock patches

On Mon, Nov 21, 2011 at 11:01 PM, Kevin Grittner
<Kevin(dot)Grittner(at)wicourts(dot)gov> wrote:
> Pavan Deolasee <pavan(dot)deolasee(at)gmail(dot)com> wrote:
>
>> It will be a great help if you could spare few minutes to also
>> test the patch to take out the frequently accessed PGPROC members
>> to a different array. We are seeing good improvements on HPUX IA
>> platform and the AMD Opteron and it will be interesting to know
>> what happens on the Intel platform too.
>>
>>
> http://archives.postgresql.org/message-id/4EB7C4C9.9070309@enterprisedb.com
>
> It's going to be hard to arrange more of the 20-hours runs I've been
> doing, but I can work in some more abbreviated tests.  What would be
> the best test for this?  (I would hate to try and find out I didn't
> exercise the right code path.)
>

I think 2-3 runs with 32 and 128 clients each with prepared statements
should suffice to quickly compare with the other numbers you posted
for the master.

Thanks,
Pavan

--
Pavan Deolasee
EnterpriseDB     http://www.enterprisedb.com