RAS on not-a-mainframe servers is about being able to disable faulty components and being able to swap them out without turning off the power. eg your data center gets hit by lightning and your UPS doesn't fully protect the hardware, with the result that 3 of your 8 CPUs, 41 of your 256 dimms, and 3 of your 8 ethernet cards fail. A mainframe level RAS server will detect the errors and disable the faulty components automatically and keep running at reduced performance until the needed replacements are shipped in and installed in the running system. IBM's been doing that for something like 50 years. Intel initially acquired the same capabilities for the Itanic, but once it became clear that cluster-elephant had no future started migrating them all over to its most expensive Xeons.
Did you ever see history portrayed as an old man with a wise brow and pulseless heart, waging all things in the balance of reason? Is not rather the genius of history like an eternal, imploring maiden, full of fire, with a burning heart and flaming soul, humanly warm and humanly beautiful? --Zachris Topelius Training a telescope on one’s own belly button will only reveal lint. You like that? You go right on staring at it. I prefer looking at galaxies. -- Sarah Hoyt