[cperciva]

Maybe I misunderstood the article -- it sounded to me like requests were being distributed between Mongrel processes and queued on the individual processes rather than being queued centrally and only allocated to individual processes when a process is free (like Apache does).

[davidw]

The problem with Mongrel is that you allocate N mongrel instances at setup time. Apache, on the other hand, can dynamically allocate new processes (up to a limit) in order to meet increased demand. This is especially important for people like me, who host more than one site on a machine, and want to be able to handle load up to a certain point without fiddling with config files every time there is a spike in traffic.

[rantfoil]

That's correct -- the load balancer passes the traffic directly to Mongrel, and each mongrel has its own internal queue / mutex.

That's why you run like 4 or 8 or 12 or N many mongrels to handle additional load.