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@2ndQuadrant.com www.2ndQuadrant.us
