Corruption Stats: Suggested Blacklist from the data

Alan Cox (
Wed, 29 Jul 1998 21:03:33 +0100 (BST)

> > WD has a non-announced bug with UDMA support on certain models,
> > which I just found out about from reading some "semi-secret"
> > material sent to me from a vendor of IDE-interface boards.
> THANK YOU THANK YOU THANK YOU, for finally admitting what people have been
> trying to tell you all along.

Is there a recognizable symptom (other than it broke)

Also I have an Ingo project - Ingo can you write a PCI bus speed measurer
for the kernel - is it possible.

The first thing both WDC and Quantum told me when poking about these reports
was 'if you have 75/83Mhz set check your motherboard PCI bus is set to 33MHz

My ASUS SP97XV arrived with me with the PCI bus at 37.5Mhz so this occurs.

I'd say the starting blacklist should be

WDC AC22100H
WDC AC36400L [also 'it work fine' reports too 8)]

[maybe some firmware revs only ?]

FUJITSU M1638TAU (2 times)

Quantum Fireball ST (2 times, both with other drives) on the cable also seeing
problems. Other drive was 'unknown' in one case '1.6 gig WD' in the other

That covers about 40% of the reports - it also and I never noticed it before
covers 90% of the uniprocessor cases.

Ok Linus - I'd say there's an SMP bug somewhere maybe, but the uniprocessor
one you are probably right about.

And folks: please send me more reports about corruptions, even SCSI ones now.

Also if you have a WDC AC36400L send me a Yes/No and also a firmware revision
(see man hdparm).


To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to
Please read the FAQ at