[bane]

Great comment. IBM is as IBM wants to be. I don't think there's a mystery to it and they've ended up on an evolutionary path that can't be reversed.

To wit, I just watched a long form video [1] on the passion that goes into IBM mainframes including some interesting clips of various physical robustness tests of the assembled systems. It reminded me of watching clips from various space programs where a largely full-up untested rocket had to put humans into orbit without blowing up.

Another revolution that's occurred, but IBM chose not to really follow (asterisk) is the idea that you assume some percentage of your hardware will fail (instead of trying to make it never die) -- then you engineer around that. I'm not sure what will win in the end, but right now the entire industry is telling us to have failover into different availability zones in Amazon, or even across clouds -- one of which IBM offers.

1 - https://youtu.be/ouAG4vXFORc (asterisk) - IBM does sort of have an understanding of this of course, they have a cloud after all.

[ngcc_hk]

Recall the token ring not falling and error management way, compared with the Ethernet assume possibly failure. It is such a headache to manage token ring and sna network. At least sna is reliable. Token ring is actually no. Suprisng. But at least sna assume there might be issues in the other end. Not token ring. And that is the problem of assuming all problem is managed.