On 10/06/11 11:25, Tejun Heo wrote: > Hello, > > On Thu, Jun 09, 2011 at 02:16:07PM +0100, Tim Small wrote: > >> ... if I then didn't power down the drive, but instead attached it >> to the Marvell controller, it didn't come back, so I'd guess the >> interaction with the 3124 has wedged the drive permanently. >> > Heh, that's interesting. The feature isn't very well tested and it > wouldn't be too surprising if there are some bugs on all sides > (driver, controller and drive firmware). Can you please try with a > drive from a different vendor and see whether it fares any > differently? > All tests with a Silicon Image port multiplier, plugged into the Intel H67 motherboard SATA port... I tried with a WD drive: 1783.276989] ata11.02: exception Emask 0x10 SAct 0x0 SErr 0x4050000 action 0xf 1783.277165] ata11.02: SError: { PHYRdyChg CommWake DevExch } 1783.277359] ata11.02: hard resetting link 1784.001050] ata11.02: SATA link up 3.0 Gbps (SStatus 123 SControl 320) 1788.999212] ata11.02: qc timeout (cmd 0xef) 1788.999375] ata11.02: failed to IDENTIFY (SPINUP failed, err_mask=0x4) 1788.999539] ata11.15: hard resetting link 1794.529376] ata11.15: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 1794.529709] ata11.00: hard resetting link 1794.849450] ata11.00: SATA link down (SStatus 0 SControl 320) 1794.849642] ata11.01: hard resetting link 1795.169358] ata11.01: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 1795.169538] ata11.02: hard resetting link 1795.489250] ata11.02: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 1795.489439] ata11.03: hard resetting link 1795.809146] ata11.03: SATA link down (SStatus 0 SControl 320) 1795.809347] ata11.04: hard resetting link 1796.129047] ata11.04: SATA link down (SStatus 0 SControl 320) 1796.129232] ata11.05: hard resetting link 1796.448936] ata11.05: SATA link up 1.5 Gbps (SStatus 113 SControl 320) 1796.545496] ata11.01: configured for UDMA/133 1796.556856] ata11.02: ATA-8: WDC WD5000AAKS-22YGA0, 12.01C02, max UDMA/133 1796.557038] ata11.02: 976773168 sectors, multi 0: LBA48 NCQ (depth 31/32), AA 1796.558414] ata11.02: configured for UDMA/133 1796.558760] ata11: EH complete 1796.559020] scsi 10:2:0:0: Direct-Access ATA WDC WD5000AAKS-2 12.0 PQ: 0 ANSI: 5 1796.559453] sd 10:2:0:0: [sdb] 976773168 512-byte logical blocks: (500 GB/465 GiB) 1796.559726] sd 10:2:0:0: [sdb] Write Protect is off 1796.559886] sd 10:2:0:0: [sdb] Mode Sense: 00 3a 00 00 1796.559910] sd 10:2:0:0: [sdb] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA 1796.590194] sdb: sdb1 sdb2 sdb4 < sdb5 sdb6 > 1796.590690] sd 10:2:0:0: [sdb] Attached SCSI disk ... looks OK - then I added in a different WD (few-year-old Hitachi Ultrastar "enterprise" 1TB drive): 3221.187324] ata10.03: exception Emask 0x10 SAct 0x0 SErr 0x4050000 action 0xf 3221.187495] ata10.03: SError: { PHYRdyChg CommWake DevExch } 3221.187690] ata10.03: hard resetting link 3221.908208] ata10.03: SATA link up 3.0 Gbps (SStatus 123 SControl 320) 3221.908405] ata10.03: failed to IDENTIFY (I/O error, err_mask=0x100) 3221.908580] ata10.15: hard resetting link 3227.438189] ata10.15: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 3227.438596] ata10.00: hard resetting link 3227.758285] ata10.00: SATA link down (SStatus 0 SControl 310) 3227.758481] ata10.01: hard resetting link 3228.078174] ata10.01: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 3228.078363] ata10.02: hard resetting link 3228.398069] ata10.02: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 3228.398249] ata10.03: hard resetting link 3228.717949] ata10.03: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 3228.718129] ata10.04: hard resetting link 3229.037845] ata10.04: SATA link down (SStatus 0 SControl 320) 3229.053513] ata10.05: hard resetting link 3229.373739] ata10.05: SATA link up 1.5 Gbps (SStatus 113 SControl 320) 3229.471776] ata10.01: configured for UDMA/133 3229.485021] ata10.02: configured for UDMA/133 3234.479859] ata10.03: qc timeout (cmd 0xef) 3234.480019] ata10.03: failed to IDENTIFY (SPINUP failed, err_mask=0x4) 3234.480182] ata10.15: hard resetting link 3240.010031] ata10.15: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 3240.010404] ata10.00: hard resetting link 3240.330128] ata10.00: SATA link down (SStatus 0 SControl 310) 3240.330334] ata10.01: hard resetting link 3240.650005] ata10.01: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 3240.650190] ata10.02: hard resetting link 3240.969924] ata10.02: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 3240.970105] ata10.03: hard resetting link 3241.289820] ata10.03: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 3241.289997] ata10.05: hard resetting link 3241.609677] ata10.05: SATA link up 1.5 Gbps (SStatus 113 SControl 320) 3241.711873] ata10.01: configured for UDMA/133 3241.728940] ata10.02: configured for UDMA/133 3241.729112] ata10.03: failed to IDENTIFY (I/O error, err_mask=0x100) 3241.729270] ata10.03: failed to recover link after 3 tries, disabling 3241.729437] ata10.15: hard resetting link 3247.259626] ata10.15: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 3247.579625] ata10.00: hard resetting link 3247.899626] ata10.00: SATA link down (SStatus 0 SControl 310) 3247.899826] ata10.01: hard resetting link 3248.219520] ata10.01: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 3248.219701] ata10.02: hard resetting link 3248.539376] ata10.02: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 3248.539553] ata10.04: hard resetting link 3248.859283] ata10.04: SATA link down (SStatus 0 SControl 320) 3248.859486] ata10.05: hard resetting link 3249.179167] ata10.05: SATA link up 1.5 Gbps (SStatus 113 SControl 320) 3249.280756] ata10.01: configured for UDMA/133 3249.294319] ata10.02: configured for UDMA/133 3249.611012] ata10: EH complete 3250.388324] ata10.00: failed to read SCR 1 (Emask=0x40) 3250.388490] ata10.01: failed to read SCR 1 (Emask=0x40) 3250.388644] ata10.02: failed to read SCR 1 (Emask=0x40) 3250.388800] ata10.03: failed to read SCR 1 (Emask=0x40) 3250.388955] ata10.04: failed to read SCR 1 (Emask=0x40) 3250.389112] ata10.05: failed to read SCR 1 (Emask=0x40) 3250.389274] ata10.15: exception Emask 0x2 SAct 0x0 SErr 0x0 action 0x6 frozen 3250.389447] ata10.15: irq_stat 0x00800000, incorrect PMP 3250.389608] ata10.00: exception Emask 0x100 SAct 0x0 SErr 0x0 action 0x6 frozen 3250.389842] ata10.01: exception Emask 0x100 SAct 0x0 SErr 0x0 action 0x6 frozen 3250.390072] ata10.02: exception Emask 0x100 SAct 0x0 SErr 0x0 action 0x6 frozen 3250.390300] ata10.03: exception Emask 0x100 SAct 0x0 SErr 0x0 action 0x6 frozen 3250.390525] ata10.04: exception Emask 0x100 SAct 0x0 SErr 0x0 action 0x6 frozen 3250.390763] ata10.05: exception Emask 0x100 SAct 0x0 SErr 0x0 action 0x6 frozen 3250.390993] ata10.15: hard resetting link 3255.920751] ata10.15: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 3256.240698] ata10.03: failed to write SCR 1 (Emask=0x100) 3256.240862] ata10.03: COMRESET failed (errno=-5) 3256.241021] ata10.03: failed to write SCR 1 (Emask=0x40) 3256.241182] ata10.03: failed to clear SError.N (errno=-5) 3256.241341] ata10.15: hard resetting link 3261.770807] ata10.15: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 3262.090762] ata10.03: failed to write SCR 1 (Emask=0x100) 3262.090922] ata10.03: COMRESET failed (errno=-5) 3262.091076] ata10.03: failed to write SCR 1 (Emask=0x40) 3262.091236] ata10.03: failed to clear SError.N (errno=-5) 3262.091397] ata10.15: hard resetting link 3267.620864] ata10.15: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 3267.940817] ata10.03: failed to write SCR 1 (Emask=0x100) 3267.956355] ata10.03: COMRESET failed (errno=-5) 3267.956511] ata10.03: failed to write SCR 1 (Emask=0x40) 3267.956669] ata10.03: failed to clear SError.N (errno=-5) 3267.956672] ata10.15: hard resetting link 3273.482932] ata10.15: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 3273.802873] ata10.03: failed to write SCR 1 (Emask=0x100) 3273.803037] ata10.03: COMRESET failed (errno=-5) 3273.803190] ata10.03: failed to write SCR 1 (Emask=0x40) 3273.803348] ata10.03: failed to clear SError.N (errno=-5) 3273.803507] ata10.15: hard resetting link 3279.332984] ata10.15: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 3279.652933] ata10.03: failed to write SCR 1 (Emask=0x100) 3279.653097] ata10.03: COMRESET failed (errno=-5) 3279.653255] ata10.03: failed to write SCR 1 (Emask=0x40) 3279.653411] ata10.03: failed to clear SError.N (errno=-5) 3279.653569] ata10: failed to recover PMP after 5 tries, giving up 3279.653729] ata10.15: Port Multiplier detaching 3279.653884] ata10.01: disabled 3279.654024] ata10.02: disabled 3279.654185] ata10.00: disabled 3279.654335] ata10: exception Emask 0x2 SAct 0x0 SErr 0x0 action 0x6 frozen t4 3279.654507] ata10: irq_stat 0x00800001, incorrect PMP 3279.654666] ata10: hard resetting link 3285.183040] ata10: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 3285.183223] ata10: EH complete 3285.183371] ata10.01: detaching (SCSI 9:1:0:0) 3285.207124] sd 9:1:0:0: [sdb] Synchronizing SCSI cache 3285.207304] sd 9:1:0:0: [sdb] Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK 3285.207599] sd 9:1:0:0: [sdb] Stopping disk 3285.207754] sd 9:1:0:0: [sdb] START_STOP FAILED 3285.207908] sd 9:1:0:0: [sdb] Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK 3285.208233] ata10.02: detaching (SCSI 9:2:0:0) 3285.223124] sd 9:2:0:0: [sdc] Synchronizing SCSI cache 3285.223313] sd 9:2:0:0: [sdc] Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK 3285.223614] sd 9:2:0:0: [sdc] Stopping disk 3285.223771] sd 9:2:0:0: [sdc] START_STOP FAILED 3285.223927] sd 9:2:0:0: [sdc] Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK ... and then there were no drives visible the other side of the port multiplier at all - not so good.... Unplugging the port multiplier from the motherboard SATA port (a different port on this occasion, but I think the same thing happens if I pick the same one), and replugging it makes the disappeared drives reappear, along with the (now spun up) Hitachi: 3374.238416] ata10: exception Emask 0x10 SAct 0x0 SErr 0x4090000 action 0xe frozen 3374.238652] ata10: irq_stat 0x00400040, connection status changed 3374.238814] ata10: SError: { PHYRdyChg 10B8B DevExch } 3374.238972] ata10: hard resetting link 3374.961277] ata10: SATA link down (SStatus 0 SControl 300) 3374.961453] ata10: EH complete 3381.497602] ata11: exception Emask 0x10 SAct 0x0 SErr 0x4050002 action 0xe frozen 3381.497838] ata11: irq_stat 0x00400040, connection status changed 3381.498002] ata11: SError: { RecovComm PHYRdyChg CommWake DevExch } 3381.498172] ata11: hard resetting link 3387.429132] ata11: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 3387.429520] ata11.15: Port Multiplier 1.1, 0x1095:0x3726 r23, 6 ports, feat 0x1/0x9 3387.429944] ata11.00: hard resetting link 3387.749226] ata11.00: SATA link down (SStatus 0 SControl 310) 3387.749427] ata11.01: hard resetting link 3388.069106] ata11.01: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 3388.069287] ata11.02: hard resetting link 3388.389018] ata11.02: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 3388.389195] ata11.03: hard resetting link 3388.708866] ata11.03: SATA link up 3.0 Gbps (SStatus 123 SControl 300) 3388.709047] ata11.04: hard resetting link 3389.028796] ata11.04: SATA link down (SStatus 0 SControl 320) 3389.028996] ata11.05: hard resetting link 3389.348681] ata11.05: SATA link up 1.5 Gbps (SStatus 113 SControl 320) 3389.384254] ata11.01: ATA-7: ST3500641AS, 3.AAD, max UDMA/133 3389.384428] ata11.01: 976773168 sectors, multi 0: LBA48 NCQ (depth 31/32) 3389.450869] ata11.01: configured for UDMA/133 3389.467745] ata11.02: ATA-8: WDC WD5000AAKS-22YGA0, 12.01C02, max UDMA/133 3389.467916] ata11.02: 976773168 sectors, multi 0: LBA48 NCQ (depth 31/32), AA 3389.469215] ata11.02: configured for UDMA/133 3389.478644] ata11.03: ATA-7: Hitachi HUA721010KLA330, GKAOAB0A, max UDMA/133 3389.478818] ata11.03: 1953525168 sectors, multi 0: LBA48 NCQ (depth 31/32), AA 3389.480158] ata11.03: configured for UDMA/133 3389.480508] ata11: EH complete 3389.480702] scsi 10:1:0:0: Direct-Access ATA ST3500641AS 3.AA PQ: 0 ANSI: 5 3389.480831] sd 10:1:0:0: [sdb] 976773168 512-byte logical blocks: (500 GB/465 GiB) 3389.480878] sd 10:1:0:0: [sdb] Write Protect is off 3389.480881] sd 10:1:0:0: [sdb] Mode Sense: 00 3a 00 00 3389.480903] sd 10:1:0:0: [sdb] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA 3389.481290] scsi 10:2:0:0: Direct-Access ATA WDC WD5000AAKS-2 12.0 PQ: 0 ANSI: 5 3389.481453] sd 10:2:0:0: [sdc] 976773168 512-byte logical blocks: (500 GB/465 GiB) 3389.481503] sd 10:2:0:0: [sdc] Write Protect is off 3389.481506] sd 10:2:0:0: [sdc] Mode Sense: 00 3a 00 00 3389.481526] sd 10:2:0:0: [sdc] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA 3389.481532] scsi 10:3:0:0: Direct-Access ATA Hitachi HUA72101 GKAO PQ: 0 ANSI: 5 3389.499135] sdb: sdb1 3389.499412] sd 10:3:0:0: [sdd] 1953525168 512-byte logical blocks: (1.00 TB/931 GiB) 3389.499618] sd 10:1:0:0: [sdb] Attached SCSI disk 3389.499834] sd 10:3:0:0: [sdd] Write Protect is off 3389.499987] sd 10:3:0:0: [sdd] Mode Sense: 00 3a 00 00 3389.500007] sd 10:3:0:0: [sdd] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA 3389.542656] sdc: sdc1 sdc2 sdc4 < sdc5 sdc6 > 3389.557103] sdd: sdd1 sdd2 < sdd5 > 3389.574742] sd 10:2:0:0: [sdc] Attached SCSI disk 3389.574789] sd 10:3:0:0: [sdd] Attached SCSI disk Is this any use? Lots of other permutations for me to try out - I'll try and get some time to do that tomorrow. Tim. -- South East Open Source Solutions Limited Registered in England and Wales with company number 06134732. Registered Office: 2 Powell Gardens, Redhill, Surrey, RH1 1TQ VAT number: 900 6633 53 http://seoss.co.uk/ +44-(0)1273-808309 -- To unsubscribe from this list: send the line "unsubscribe linux-ide" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html