Hi, does not make any sense!!!!! How do you want to take such decision when the impact of each HTTP request may be different on the server for different reason: - static / dynamic - object size - number of DB access - load on the server on the moment of the request - etc...
Using such method for load-balancing HTTP would result of moving all the load from server to server, so you're not load balancing, but "balancing the load", which makes a huge difference and which will be counter-productive in the end. Something nice would to be able to increase / decrease server weight in a farm when its load is to high after a certain amount of time. cheers On Tue, Dec 6, 2011 at 9:38 PM, Wout Mertens <wout.mert...@gmail.com> wrote: > So if you're doing HTTP load balancing for app servers, it seems to me that > the server that responded fastest last time should get the job. > > HAproxy is already capturing the response times at each request so I think > this would allow for really responsive fair load balancing. > > Any chance of HAproxy supporting that? > > Wout.
