> I have examined my syslog files and this is what I have found.
> Dec 15 20:44:14 osmeh kernel: hdc: QUANTUM FIREBALL SE4.3A, ATA DISK drive
> Dec 15 20:44:14 osmeh kernel: hdc: QUANTUM FIREBALL SE4.3A, 4110MB w/80kB
> Cache, CHS=14848/9/63, UDMA
> Since some peolehave expirienced problems with dma I have decided to turn
> off DMA. Before I have expirienced complete ext2fs demolition on /dev/hdc2
> thi is what was in log files:
> Dec 15 18:33:34 osmeh kernel: ide1: reset: success
> Dec 15 18:33:34 osmeh kernel: hdc: status error: status=0x10 { SeekComplete }
> Dec 15 18:33:38 osmeh kernel: hdc: no DRQ after issuing WRITE
> Dec 15 18:33:38 osmeh kernel: hdc: status error: status=0x50 { DriveReady SeekComplete }
> Dec 15 18:33:38 osmeh kernel: hdc: no DRQ after issuing WRITE
> Dec 15 18:33:38 osmeh kernel: hdc: status error: status=0x50 { DriveReady SeekComplete }
I have seen these errors when the PIO mode is too fast for the
drive or too heavy optimizations in transfer mode are used.
If you run your mainboard / PCI bus 'overclocked' the PIO modes
resulting may be overclocked as well, resulting in serious
miscommunication with the drive.
Try turning off _all_ nice features that hdparm can turn off.
Then the problems should go away and you can experiment with
what features can be turned on again without causing trouble.
(and if a certain feature doesn't help performance enough,
LEAVE IT OFF just out of paranoia -- data integrity is usually
more important than performance)
succes,
Rik -- the flu hits, the flu hits, the flu hits -- MORE
+-------------------------------------------------------------------+
| Linux memory management tour guide. H.H.vanRiel@phys.uu.nl |
| Scouting Vries cubscout leader. http://www.phys.uu.nl/~riel/ |
+-------------------------------------------------------------------+
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/