Disk corruption fault

[hammer]

In a recent LWN article [1], it was mentioned that "There has also been some work done using hdparm to corrupt individual sectors on disk to see how filesystems respond."

It would be interesting to inject corruption at different levels of the stack.

[1] http://lwn.net/Articles/399148/

[afeinberg]

Yes, this would be a very interesting feature to have. What's interesting is how well do failure detectors built into distributed databases pick up on disks faults as opposed to simple machine failures. This has bitten various heart-beat based systems I've worked with.