The documentation for leastconn says "The server with the lowest number of connections receives the connection" -- does this mean a new HTTP connection, or a new request on an existing connection (e.g. with HTTP keep-alive)?
In our use case, we have a relatively small (a few thousand) number of very long lived keep-alive sessions (100s of requests per second per connection), so the distinction is very important for us. It's not important that subsequent requests on a keep-alive session go to the same backend node that the previous ones did, each request is independent. Actually, for that matter, I have the same question about roundrobin and static-rr -- do they balance connections or requests? And, if the former, is there a way to make HAProxy balance requests rather than connections? Thanks, - Dan Crosta
