Re: Pooling in Core WAS: Need help in performance tuning.

Looks like ,

pgbench cannot be used for testing with pgbouncer if number of
pgbench clients exceeds pool_size + reserve_pool_size of pgbouncer.
pgbench keeps waiting doing nothing. I am using pgbench of postgresql 8.1.
Are there changes to pgbench in this aspect ?

regds
Rajesh Kumar Mallah.

On Sun, Jul 18, 2010 at 11:38 PM, Rajesh Kumar Mallah <
mallah(dot)rajesh(at)gmail(dot)com> wrote:

>
>
> On Sun, Jul 18, 2010 at 10:55 PM, Greg Smith <greg(at)2ndquadrant(dot)com> wrote:
>
>> Rajesh Kumar Mallah wrote:
>>
>>> the no of clients was 10 ( -c 10) carrying out 10000 transactions each
>>> (-t 10000) .
>>> pgbench db was initilised with scaling factor -s 100.
>>>
>>> since client count was less there was no queuing of requests in pgbouncer
>>> i would prefer to say it was in 'passthrough' mode.
>>>
>>
>> Of course pgbouncer is going decrease performance in this situation.
>> You've added a whole layer to things that all traffic has to pass through,
>> without a setup that gains any benefit from the connection pooling. Try
>> making the client count 1000 instead if you want a useful test.
>>
>
> Dear Greg,
>
> my max_client is 300 shall i test with client count 250 ?
> if so what should be the scaling factor while initializing
> the pgbench db?
>
>
>> --
>> Greg Smith 2ndQuadrant US Baltimore, MD
>> PostgreSQL Training, Services and Support
>> greg(at)2ndQuadrant(dot)com www.2ndQuadrant.us
>>
>>
>