It is well known in queueing theory that having a monolithic server performs better than having a number of smaller servers, with same total capacity, that each are dedicated to one client. If the clients all share one server and jobs arrive more or less at random, the system can be more efficient in terms of service delay and overall buffer space needed. The same effect applies to buffer allocation: having a central pool requires less overall RAM, to meet a statistical peak demand, than having the RAM split around the various devices.
| 3: (C) 2012-16, DJ Greaves, University of Cambridge, Computer Laboratory. |