Cliff Woolley wrote: >On Thu, 11 Apr 2002, Aaron Bannert wrote: > >> Under typical conditions, long-running and short-running requests will >> be distributed throughout the children. In order for this scenario to >> occur, all M threads in a child would have to be in use by a long-lived >> connection. Assuming a random distribution of these clients, I don't >> see how this scenario can consistently occur except when all threads >> across all children are already being occupied by long-lived connections. >> > >Another thing of note is that this sort of problem will only happen (or >rather, will only be severe) when the server goes instantaneously from x >concurrent connections on average to x+y concurrent connections, where y >is large, which is what's happening when you suddenly ab pound a server, >because p_i_s_m doesn't have a chance to keep up. >
So far, so good, but... >Under production >circumstances, the number of concurrent connections would tend to have >less significant discontinuities. > On the contrary, production servers sometimes have *huge* discontinuities in the number of concurrent connections. Think about what happens to the connection rate at an online brokerage every day at the instant when the stock markets open, for example. Or a news site when there's major breaking news. Or a small site that's just been featured on Slashdot. A server that can't handle discontinuities in request volume just isn't suitable for general-purpose use in the real world. --Brian
