Skip to contentSkip to conversation

VIA silent disk corruption - fixed for me

DISCUSSION Petr Vandrovec 2 participants 2 messages Feb 7, 2001

lore
Share & tools
lore
#0 lore raw

I wrote on 6 Feb evening CET:

Quoted 12 lines · Udo A. Steinberg
Quoted 10 lines
Quoted 3 lines

So for today I'm back on [UMS]DMA disabled. I'll try downgrading BIOS today, but it looks to me like that something is severely broken here.

Are your drives connected to the VIA or the Promise controller? Mine are both connected to the PDC20265 and running in UDMA-100 mode. There have been several threads on lkml about corruption on disks connected to Via chipset IDE controllers, although I didn't follow them in great detail. Maybe your problem is not related to the host bridge, but to the IDE controller?

Quoted 10 lines

They are connected to Promise, I reserved VIA for CDROM drive. One HDD runs in UDMA5 mode, another in UDMA2. Corruption is often when I run md5sum in parallel on both HDDs - in that case almost no file generates same checksum which was generated using PIO4. When I run md5sum on only one HDD, there are about 4 checksum errors in 6GB of data. But I'm more and more inclined to throw this A7V away, as it is impossible to get datasheet from Promise, and for VIA host bridge I was just able to slow down normal system operation by factor of 3... but still with same corruption :-( Just if page could have 4092 and not 4096 bytes ;-)

After upgrading BIOS (it did not help) I decided to switch my secondary harddisk to master. And voila - hde running UDMA5, hdg running UDMA2 (hdf/hdh does not exist), whole night stresstests, no corruption.

So at least for me it means that Promise Linux driver does not support slave-only configuration. I did not checked whether master-slave pair works, but master alone for sure works for me.

That is, for me problem was not in VIA bridge, but in PDC20265 driver...
Best regards,
Petr Vandrovec [email protected]

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
Please read the FAQ at http://www.tux.org/lkml/

#1 lore raw
Quoted 3 lines · Petr Vandrovec

After upgrading BIOS (it did not help) I decided to switch my secondary harddisk to master. And voila - hde running UDMA5, hdg running UDMA2 (hdf/hdh does not exist), whole night stresstests, no corruption.

Excellent!

Quoted 3 lines

So at least for me it means that Promise Linux driver does not support slave-only configuration. I did not checked whether master-slave pair works, but master alone for sure works for me.

I have a master-slave configuration. Both are IBM DTLA-307030 in UDMA-5 mode, the master using vfat32, the slave using ext2. Works like a charm.

-Udo.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
Please read the FAQ at http://www.tux.org/lkml/