It is possible that it is valid.. Till you reach the limits of your server , the throughput will increase, then flatten(saturation point) , then fall (buckle point) see for e.g. http://books.google.com/books?id=HTX8DyD0WzkC&pg=PA12&lpg=PA12&dq=throughput+curve&source=bl&ots=7qYRIZiPX9&sig=7UoxT-8gpbmqWwwUcu0aROe_QWA&hl=en&ei=1X6mSqLyHpDK_gbMgvC-CQ&sa=X&oi=book_result&ct=result&resnum=5#v=onepage&q=throughput%20curve&f=false
However its just as possible , especially if your tests dont have assertions, that the system errors and returns quickly, your test doesnt check for errors and you keep getting good results regards deepak On Mon, Dec 28, 2009 at 12:53 PM, Maria Alejandra Trozzi <[email protected] > wrote: > Hi ! > I'm getting better throughput with more concurrent users (same test run > with > 20, 50 and 100 concurrent users) > Can you tell me if it is a valid output or if it there could be some bad > results.... ?? > > Thanks ! >
