Thing is Google does not use commodity hardware for their DCs as far as I can tell. They got famous for that back in the early 2000s but I think they abandoned that approach a long time ago.
They may design their own hardware, but their approach to scaling and fault tolerance is still the same: not a low number of fast and very expensive enterprise grade hardware that is unlikely to fail, but a huge fleet of servers that scale horizontally and that can tolerate the loss of a machine.
Which is the Mainframe vs commodity server dichotomy.
