[sobriquet9]

If you use multiple computers doing the same calculation and then take the answer from the quorum, how do you ensure the computer that does the comparison is not affected by memory failures? Remember that all queries have to through it, so it has to be comparable in scale and power.

[rovr138]

> how do you ensure the computer that does the comparison is not affected by memory failures?

You do the comparison on multiple nodes too. Get the calculations. Pass them to multiple nodes, validate again and if it all matches, you use it.

[sobriquet9]

> validate again

Recursion, see recursion.

[wtallis]

See also Byzantine fault tolerance: https://scholar.harvard.edu/files/mickens/files/thesaddestmo...

[Guvante]

I mean raft and similar algorithms run multiple verification machines because a single point of failure is a single point of failure.

[sobriquet9]

Raft, Paxos, and other consensus algorithms add even more overhead. Imagine running every Google query through Raft and think how long it will take and how much extra hardware would be needed.

ECC memory is just as fast as non-ECC memory, and only cost a little more.

[Guvante]

Your comment sounded like "your recursive definition is impossible".

I am totally for ECC and was flabbergasted when it went away. But the article makes sense since I remember Intel pushing hard to keep it out of the consumer space. The freaking QX6800 didn't support ECC and it retailed for over a grand.