On Tue, 17 Oct 2000, Vojtech Pavlik wrote:
> But does this give any benchmarking benefit over traditional access via
> /dev/hda?
Sure, I can make it slip revs that the elevator can not correct.
Hop platters, if we know where they begin/end.
I can do write_verify_read that can never be done in a filesystem.
Pick any sector, write to it, and read it back and verify that the in and
out of that sector is identical.
More than that it could be expanded to recover bad block of data once it
is understood how to do that in more detail.
All the raid devices that report smaller capacity than max to protect the
signature can be recovered now. Thus reading beyond reported geometry.
Junk like this will be more useful.
Cheers,
Andre Hedrick
The Linux ATA/IDE guy
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Mon Oct 23 2000 - 21:00:11 EST