[lkml]   [2006]   [Nov]   [13]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: unexplainable read errors, copy/diff-issue
Alan wrote:
>> Can anybody imagine that DMA could cause my problems? And if so,.. is it
>> likely that this would come from a hardware error or maybe from software?
> IDE DMA hits the hardware pretty heavily, so it may show up PCI
> arbitration bugs, software bugs handling PCI stalls in other drivers
> and/or BIOS misconfiguration of system parameters
And what should I do now?

Anyway here my current testing results:
As I told in the beginning I have the following configuration:

primary IDE controller:
master: my pata harddisk
slave: Plextor PX760A (DVD/CD)

secondary IDE controller (not usable with the board - no connectors at
all ;) )

SATA controller:
2x harddisks

Ok yesterday I've reported that when using_dma:0 for the PATA disk,..
the error doesn't occur (I did three or four diffs of the 30 GB).
I still don't know how to deactivate DMA for SATA... so wasn't able to
test the same thing on the SATA drives.

dmes says the following for my IDE devices:
Probing IDE interface ide0...
hda: IC35L120AVV207-1, ATA DISK drive
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
Probing IDE interface ide1...
Probing IDE interface ide1...
hda: max request size: 512KiB
hda: 241254720 sectors (123522 MB) w/7965KiB Cache, CHS=16383/255/63,
hda: cache flushes supported
hda: hda1 hda2 hda3 hda4 < hda5 hda6 >
hdb: ATAPI 40X DVD-ROM DVD-R CD-R/RW drive, 2048kB Cache, UDMA(66)
Uniform CD-ROM driver Revision: 3.20

As the CD/DVD runs in DMA, too (but a slower, UDMA66), I took a full
DualLayer Disk, created sha512sums of all files,.. and verified them
some times (4x).
No checksum mismatch was found, what does this mean now?

If I assume that the whole error is driver related, then wouldn't this
apply to the CD/DVD drive, too? The same if it would be an hardware error?

The driver I use is the AMD7XXX,... while it says that it work for some
nvidia (IIRC up to nforce 3) chipsets, too, does it also work for the
nforce professional?

Ok another idea was,.. that the errors come from some electro-magnetical
disturbances or something like that,... does this sound possible?
At least my IDE cables are shielded,...

Best wishes,
fn:Mitterer, Christoph Anton
n:Mitterer;Christoph Anton

 \ /
  Last update: 2006-11-13 22:01    [W:0.091 / U:32.268 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site