Bob La Quey wrote:
<quote>
The job of any filesystem boils down to this: when asked to read a
block, it should return the same data that was previously written to
that block. If it can't do that -- because the disk is offline or the
data has been damaged or tampered with -- it should detect this and
return an error.
Incredibly, most filesystems fail this test. They depend on the
underlying hardware to detect and report errors. If a disk simply
returns bad data, the average filesystem won't even detect it.
</quote>
http://blogs.sun.com/bonwick/entry/zfs_end_to_end_data
This just sounds right to me. I think I am ready to
drink the koolaid :)
Well, it's pretty safe Kool-Aid. The mainframe guys have believed this
for 20+ years now.
Some of the big processors (Sparc and POWER, IIRC) actually have special
validation units in processor units themselves. For example, every
multiply is accompanied by a faster, smaller ring field multiply. At
the end of the multiply, the result is check against the modulus
multiply and if they don't match a fault is generated.
-a
--
[email protected]
http://www.kernel-panic.org/cgi-bin/mailman/listinfo/kplug-list
