Hm, it seems we are victim of a SATA NCQ HORKAGE: http://www.mail-archive.com/[EMAIL PROTECTED]/msg08936.html
Disableing NCQ seems to work on the sb600. Samsung already ships a newer edition ("403" instead of "401") but there is no fix for the NCQ in the 401 edition. With Samsungs HUTIL you cannot disbale NCQ on the disk itself. Sadly we have about 20 pcs SAMSUNG HD401LJ of the broken one here :/ Interstingly the ncq horkage does not affect the platforms which are ICH7-based. We replugged both harddisks to some core2quad/ICH7-based system without any change in software - and it works without lockups. Is that simply luck? According to dmesg NCQ is activated on the ICH7. Is it currently only possible to ATA_HORKAGE_NONCQ generally? Or can that be done per chipset? Best Regards, Andreas @Ulrich: On what kind of chipset did you observe the horkage? Andreas John schrieb: > Hi, > as requested by Tejun here comes dmesg and lspci -nn. Additionally I > found something dmesg (See 1.), probably caused by the low-level error. > > Best Regards, > Andreas > > 1.) > [81739.060000] sd 1:0:0:0: [sdb] Result: hostbyte=DID_BAD_TARGET > driverbyte=DRIVER_OK,SUGGEST_OK > [81739.060000] end_request: I/O error, dev sdb, sector 0 > > 2.) lspci -nn > [EMAIL PROTECTED]:~# lspci -nn > 00:00.0 Host bridge [0600]: ATI Technologies Inc Unknown device [1002:7910] > 00:01.0 PCI bridge [0604]: ATI Technologies Inc Unknown device [1002:7912] > 00:12.0 SATA controller [0106]: ATI Technologies Inc SB600 Non-Raid-5 > SATA [1002:4380] > 00:13.0 USB Controller [0c03]: ATI Technologies Inc SB600 USB (OHCI0) > [1002:4387] > 00:13.1 USB Controller [0c03]: ATI Technologies Inc SB600 USB (OHCI1) [SNIP] - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/