Hacker News Reader

Do they really care if any one of those servers loses its data though? At that scale, you need higher level redundancy so it makes sense to prioritize filesystems for other features than how well they actually retain your data.

For example, detecting corruption would be more important than never having any, so that you can get IO errors and immediately kill the server before it serves bad data.

Specifically BTRFS's RAID5/RAID6 implementation is unstable and susceptible to data loss. Facebook doesn't use those RAID levels in production.

https://www.phoronix.com/scan.php?page=news_item&px=Btrfs-Wa...

https://btrfs.wiki.kernel.org/index.php/Gotchas#Parity_RAID

So what you’re saying is, btrfs works if you can afford an ops/sre team on par with Facebook’s?