Forcing full file read in ZFS even when checksum error encountered

[Andrei Kolu]

On Wednesday 06 February 2008 12:06:42 Dag-Erling Smørgrav wrote:
> Jeremy Chadwick <koitsu at freebsd.org> writes:
> > I realise I classify pretty much everything as "priority 0" (of utmost
> > importance), but there doesn't appear to be any indication of anyone
> > caring about this problem.
>
> Most likely, nobody with the ability to find and fix the cause of your
> problem has been able to reproduce it.  It's really hard to fix a bug
> you can't reproduce; you're basically flying blind, unless the person
> who reported the issue is very experienced and can cooperate in
> diagnosing the problem (which is very rare).
>
> > I want to do more to help, but I don't know what I *can* do, besides
> > offer to buy people identical hardware for attempted reproduction, or
> > put up a test box with serial console access for developers to beat up
> > on.
>
> Several developers already *have* identical hardware, or nearly so.
>
> (speaking for myself, all my Seagate disks are dead, and I use Western
> Digital exclusively these days, as they tend to live longer in my
> experience; sometimes they don't even fail until *after* the warranty
> runs out!)

I have exactly opposite experience- all my WD drives are dead and only Seagate 
survived. Actually I'd recommend to use as many different manufacturers as 
possible. For example in NAS with 4-8 hard drives I got at least two 
different drives- Seagate and Hitachi- in case of some bad model (or bad day 
in manufacturer plant) you'll not loose all drives in short period of time... 
There is no such a thing like bad brand- there is bad models or bad days...