Buzbee, James wrote:
Sorry for the long post, but I'm wrestling with several issues related
to manufacturing flaws that are (evidently) commonly found with IDE drives.
[...]
Last question, if this -really- is normal, and it is something that has
to be dealt with, what is the proper solution? I know that leaving
Write Verify turned on is not the solution. It cuts drive performance
in half. One proposed solution (for us at least) is to turn Write Verify
on for "critical" data and off for "non-critical" data. This seems like
a hack. <RANT> If I write the data to the drive, and the drive says
"OK" shouldn't the data be there? </RANT
I agree with your rant - and I also know that the trick the drive
makers use works for Windows systems because the "format" operation
(well older Windows) would write to every sector of the drive.
What I have done is to take new drives and put them on-line (powered)
and set the write verify on and then use a simple tool that wrote
random data over the whole disk (or just /dev/zero using something
like 'dd if=/dev/zero of=/dev/scsi/host0/bus0/target0/lun0/disc')
to make sure every block gets hit. I actually run multiple of
these commands at the same time (started a few seconds apart) such
that the head seaks are tested too.
Now, we generally don't use the super-cheap IDE drives for the critical
systems.
BTW - I think the drive makers are getting really pushed into the
lower testing levels due to the price points. It is hard to justify
a long and complex test process when you sell the product at todays
hard drive prices. Plus the manufacturing yield is high enough that
it does not justify it either, especially if there is a solution that
gets you better than 99% coverage. (The write verify solution trick)
--
Michael Sinz -- Director, Systems Engineering -- Worldgate Communications
A master's secrets are only as good as
the master's ability to explain them to others.
|