News for hackers. Stuff that matters.

A comment on ECC matters. Parent comment

Re:ECC matters by rovr138 on Sunday January 03, 2021 @03:35PM (#25624978)
> 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.

[ Parent | on HN ]
Re:ECC matters by sobriquet9 on Sunday January 03, 2021 @03:44PM (#25625057)
> validate again

Recursion, see recursion.

[ Parent | on HN ]
Re:ECC matters by wtallis on Sunday January 03, 2021 @04:45PM (#25625551)
See also Byzantine fault tolerance: https://scholar.harvard.edu/files/mickens/files/thesaddestmo...
[ Parent | on HN ]
Re:ECC matters by Guvante on Sunday January 03, 2021 @05:49PM (#25625998)
I mean raft and similar algorithms run multiple verification machines because a single point of failure is a single point of failure.
[ Parent | on HN ]
Re:ECC matters by sobriquet9 on Sunday January 03, 2021 @07:06PM (#25626546)
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.

[ Parent | on HN ]
Re:ECC matters by Guvante on Sunday January 03, 2021 @07:40PM (#25626760)
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.

[ Parent | on HN ]