News for hackers. Stuff that matters.

A comment on HFS+ Bit Rot. Parent comment

Re:HFS+ Bit Rot by XorNot on Wednesday June 11, 2014 @11:14AM (#7878402)
The design doesn't assume ECC RAM. It's recommended because you can't talk about end-to-end checksumming and then not explain that it can't proof you against unreliable memory.

All other filesystems are equally susceptible - if your memory is getting errors, they'll happily write those to disk too.

[ Parent | on HN ]
Re:HFS+ Bit Rot by rodgerd on Wednesday June 11, 2014 @06:59PM (#7880928)
Actually, XFS checksumming will alert on errors caused by bad RAM.
[ Parent | on HN ]
Re:HFS+ Bit Rot by XorNot on Wednesday June 11, 2014 @08:54PM (#7881277)
Depends what you mean by this. ZFS will alert if it reads data into ram that then doesn't match the checksum during verification.

But it can't prevent a bitflip of data in memory from getting written to disk before the checksum is calculated. Nor can it prevent data being bitflipped after its been verified and handed off to the application.

Which I'm pretty sure XFS can't do either.

[ Parent | on HN ]