Re:Of Course not! (Score 1)

The add that the server can't dynamically create more utilization capacity (extra hardware) dynamically. If anyone out there were selling a box that could do that, I'd buy it in a heartbeat. First we'd need some good nanobots, or maybe a replicator.....

Actually, he was comparing two alternatives
1) a single IBM mainframe running multiple Linux images.
2) a Linux server farm.

In the second alternative, a load balancer distributes traffic evenly across all of the servers. To increase the capacity of your server farm, you can add a new server and reconfigure your load balancer. This can be done while the rest of the farm is still up and running.

However, dynamically increasing the capacity of a single mainframe would be more difficult. (Maybe impossible, but I admit I don't know much about mainframes) How would you do that? Add more processors? More memory? Add a faster disk? All of these options would require some disruption. (Again, I am not a mainframe expert, but adding cpu/memory while the thing is running seems difficult to me. Disks can be hot-swapable of course...)

Anyway, it seems to me that Linux server farms work pretty good. Why move everything onto one really expensive mainframe? There don't seem to be many benefits to justify the added expense.