Comment by tmountain
9 hours ago
Floppy disks were ubiquitous when I was in college. When I got into Linux, I did an experiment raw writing zeros to floppies with dd to see what percentage of them had I/O errors. I tested with a stack of about 50 of them that were left in our computer lab over the years (different brands). The failure rate was staggering. Something like 30-40% of them had bad sectors. After that, I realized that I could never rely on them as a storage medium for anything important without regular backups.
Floppy reliability dropped of a cliff in the mid-90s. It came to a point where it wasn't unusual to see I/O errors even on completely new floppies.
But with older drives and older media, produced to a higher standard, they were pretty reliable. (After all, IBM invented them to store CPU microcode, they had to be.)
I wonder if anyone made an error correcting driver or file format for unreliable data storage like this. Did anyone ever implement RAId (redundant array of independent diskettes)? Edit: apparently RAR had an option to add internal error correction data to the archive, and you can also use PAR2 files for another layer (I think that's able to reconstruct the archive if one file is totally unreadable)
. . . simultaneously over-writing the last remaining copy of the original Linux!