Thanks for the great overview !
> Of course, servers are a rather different ballgame. Here, actual memory > performance doesn't rate high on the priority scale at all, while often > the more GB of memory that can be stuffed into the system, the better > performance gets, due to a working data set often tens of GBs in size, the > more of which can be cached in memory, the better. It's HERE that a > quad opteron system (8 cores if dual-cored, tho that doesn't affect > memory), with quad chips and therefore quad mmu, each of which can access > 8GB in 4 slots of memory off the local controller, therefore totalling > 32GB of physical memory, <WHAT a system! drool, drool>, can /still/ be > minimally adequate to do the job. 4 CPU/32 gig is my machine ! And memory performance is important for me (more than saving 700 Mb, the question was whether memory hole remapping interferes with the performance). Most university servers are number crunching machines, which run codes utilizing all available memory, or run bunch of CPU/memory intensive serial jobs. And many vendors are optimizing quad opterons for that. > > -- > Duncan - List replies preferred. No HTML msgs. > "Every nonfree program has a lord, a master -- > and if you use the program, he is your master." Richard Stallman in > http://www.linuxdevcenter.com/pub/a/linux/2004/12/22/rms_interview.html > > -- > [email protected] mailing list -- Dmitri Pogosyan Department of Physics Associate Professor University of Alberta tel 1-780-492-2150 412 Avadh Bhatia Physics Labs fax 1-780-492-0714 Edmonton, AB, T6G 2J1, CANADA -- [email protected] mailing list
