Christian wrote:
quoted text
> I've tested multiple kernels (including -mm series) in the range of 2.6.19.7
> (before sata_nv adma support went in) up to 2.6.20-rc4.
> Every NCQ enabled kernel I've tested showed ata errors in dmesg. So I came to 
> the conclusion that my system was faulty. I ran memtest86+ for a long time, 
> but no errors were found. After some fiddling with my HW I discovered that 
> the nforce chipset fan induced some kind of electro magnetic interference to 
> the southbridge, which could clearly be heard as a low frequency noise if I 
> plugged in my speakers to the onboard sound. After replacing the fan, my 
> system is stable again. Now running 2.6.21-rc3-mm2+rsdlv31 without errors. 
> Really strange problem he ;-)

Man, that's the strangest way to solve ATA command failures I've ever 
heard of.  Kudos to you for finding it out.  :-)

-- 
tejun
-
unsubscribe notice
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/