1

My Ubuntu server has nine Silicon Image powered "5-to-1 Sata Port Multiplier" cards. I am getting the following messages in the syslog. These messages are being repeated every minute or so. From what I understand, one of the cards has some issues, and the port to it is being reset. And the reset is taking about 4-5 seconds for the whole process.

Can someone please tell me what can one make out from these errors. Do I have to replace the card? Or is it the cable that is faulty? I could have just replaced the cable, but with this particular server design (its custom made), to change the cable would take a lot of effort (almost equal to replacing the card itself).

Someone told me that it could be one of the hard drives connected to this particular card that might be the culprit (taking too long to spin, or something). Is that true?

Additionally a smartctl on all the hard drives on this card, shows a high number of UDMA_CRC_Error_Count errors.

Sep 28 20:54:26 zapdb1 kernel: [56523.744913] ata15.00: failed to read SCR 1 (Emask=0x40)
Sep 28 20:54:26 zapdb1 kernel: [56523.744921] ata15.00: failed to read SCR 0 (Emask=0x40)
Sep 28 20:54:26 zapdb1 kernel: [56523.744924] ata15.01: failed to read SCR 1 (Emask=0x40)
Sep 28 20:54:26 zapdb1 kernel: [56523.744929] ata15.01: failed to read SCR 0 (Emask=0x40)
Sep 28 20:54:26 zapdb1 kernel: [56523.744932] ata15.02: failed to read SCR 1 (Emask=0x40)
Sep 28 20:54:26 zapdb1 kernel: [56523.744936] ata15.02: failed to read SCR 0 (Emask=0x40)
Sep 28 20:54:26 zapdb1 kernel: [56523.744939] ata15.03: failed to read SCR 1 (Emask=0x40)
Sep 28 20:54:26 zapdb1 kernel: [56523.744943] ata15.03: failed to read SCR 0 (Emask=0x40)
Sep 28 20:54:26 zapdb1 kernel: [56523.744946] ata15.04: failed to read SCR 1 (Emask=0x40)
Sep 28 20:54:26 zapdb1 kernel: [56523.744950] ata15.04: failed to read SCR 0 (Emask=0x40)
Sep 28 20:54:26 zapdb1 kernel: [56523.744953] ata15.05: failed to read SCR 1 (Emask=0x40)
Sep 28 20:54:26 zapdb1 kernel: [56523.744960] ata15.15: exception Emask 0x100 SAct 0x0 SErr 0x0 action 0x6 frozen
Sep 28 20:54:26 zapdb1 kernel: [56523.745009] ata15.15: irq_stat 0x00060002, PMP DMA CS errata
Sep 28 20:54:26 zapdb1 kernel: [56523.745040] ata15.00: exception Emask 0x100 SAct 0x0 SErr 0x0 action 0x6 frozen
Sep 28 20:54:26 zapdb1 kernel: [56523.745088] ata15.00: failed command: READ DMA EXT
Sep 28 20:54:26 zapdb1 kernel: [56523.745120] ata15.00: cmd 25/00:00:80:9e:91/00:04:52:00:00/e0 tag 1 dma 524288 in
Sep 28 20:54:26 zapdb1 kernel: [56523.745122]          res 86/15:06:06:00:00/00:00:c0:12:86/00 Emask 0x2 (HSM violation)
Sep 28 20:54:26 zapdb1 kernel: [56523.745212] ata15.00: status: { Busy }
Sep 28 20:54:26 zapdb1 kernel: [56523.745237] ata15.00: error: { IDNF ABRT }
Sep 28 20:54:26 zapdb1 kernel: [56523.745265] ata15.01: exception Emask 0x100 SAct 0x0 SErr 0x0 action 0x6 frozen
Sep 28 20:54:26 zapdb1 kernel: [56523.745311] ata15.01: irq_stat 0x00060002, device error via D2H FIS
Sep 28 20:54:26 zapdb1 kernel: [56523.745341] ata15.01: failed command: READ DMA EXT
Sep 28 20:54:26 zapdb1 kernel: [56523.745373] ata15.01: cmd 25/00:00:78:9e:91/00:04:52:00:00/e0 tag 2 dma 524288 in
Sep 28 20:54:26 zapdb1 kernel: [56523.745375]          res 51/84:61:17:a0:91/00:02:52:00:00/02 Emask 0x10 (ATA bus error)
Sep 28 20:54:26 zapdb1 kernel: [56523.745466] ata15.01: status: { DRDY ERR }
Sep 28 20:54:26 zapdb1 kernel: [56523.745492] ata15.01: error: { ICRC ABRT }
Sep 28 20:54:26 zapdb1 kernel: [56523.745519] ata15.02: exception Emask 0x100 SAct 0x0 SErr 0x0 action 0x6 frozen
Sep 28 20:54:26 zapdb1 kernel: [56523.745565] ata15.02: failed command: READ DMA EXT
Sep 28 20:54:26 zapdb1 kernel: [56523.745597] ata15.02: cmd 25/00:00:78:9e:91/00:04:52:00:00/e0 tag 0 dma 524288 in
Sep 28 20:54:26 zapdb1 kernel: [56523.745599]          res 86/15:06:06:00:00/00:00:00:01:86/00 Emask 0x2 (HSM violation)
Sep 28 20:54:26 zapdb1 kernel: [56523.745689] ata15.02: status: { Busy }
Sep 28 20:54:26 zapdb1 kernel: [56523.745714] ata15.02: error: { IDNF ABRT }
Sep 28 20:54:26 zapdb1 kernel: [56523.745741] ata15.03: exception Emask 0x100 SAct 0x0 SErr 0x0 action 0x6 frozen
Sep 28 20:54:26 zapdb1 kernel: [56523.745788] ata15.03: failed command: READ DMA EXT
Sep 28 20:54:26 zapdb1 kernel: [56523.745819] ata15.03: cmd 25/00:d8:98:9a:91/00:03:52:00:00/e0 tag 4 dma 503808 in
Sep 28 20:54:26 zapdb1 kernel: [56523.745821]          res 86/15:06:06:00:00/00:00:00:47:86/00 Emask 0x2 (HSM violation)
Sep 28 20:54:26 zapdb1 kernel: [56523.745911] ata15.03: status: { Busy }
Sep 28 20:54:26 zapdb1 kernel: [56523.745936] ata15.03: error: { IDNF ABRT }
Sep 28 20:54:26 zapdb1 kernel: [56523.745963] ata15.04: exception Emask 0x100 SAct 0x0 SErr 0x0 action 0x6 frozen
Sep 28 20:54:26 zapdb1 kernel: [56523.746010] ata15.04: failed command: READ DMA EXT
Sep 28 20:54:26 zapdb1 kernel: [56523.746041] ata15.04: cmd 25/00:d8:98:9a:91/00:03:52:00:00/e0 tag 3 dma 503808 in
Sep 28 20:54:26 zapdb1 kernel: [56523.746043]          res 86/15:06:06:00:00/00:00:80:37:86/00 Emask 0x2 (HSM violation)
Sep 28 20:54:26 zapdb1 kernel: [56523.746133] ata15.04: status: { Busy }
Sep 28 20:54:26 zapdb1 kernel: [56523.746158] ata15.04: error: { IDNF ABRT }
Sep 28 20:54:26 zapdb1 kernel: [56523.746185] ata15.05: exception Emask 0x100 SAct 0x0 SErr 0x0 action 0x6 frozen
Sep 28 20:54:26 zapdb1 kernel: [56523.746234] ata15.15: hard resetting link
Sep 28 20:54:26 zapdb1 kernel: [56523.746237] ata15: controller in dubious state, performing PORT_RST
Sep 28 20:54:29 zapdb1 kernel: [56525.973515] ata15.15: SATA link up 3.0 Gbps (SStatus 123 SControl 0)
Sep 28 20:54:29 zapdb1 kernel: [56525.974240] ata15.00: hard resetting link
Sep 28 20:54:29 zapdb1 kernel: [56526.293478] ata15.00: SATA link up 1.5 Gbps (SStatus 113 SControl 310)
Sep 28 20:54:29 zapdb1 kernel: [56526.293625] ata15.01: hard resetting link
Sep 28 20:54:29 zapdb1 kernel: [56526.613082] ata15.01: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
Sep 28 20:54:29 zapdb1 kernel: [56526.613131] ata15.02: hard resetting link
Sep 28 20:54:30 zapdb1 kernel: [56526.932262] ata15.02: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
Sep 28 20:54:30 zapdb1 kernel: [56526.932304] ata15.03: hard resetting link
Sep 28 20:54:30 zapdb1 kernel: [56527.252366] ata15.03: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
Sep 28 20:54:30 zapdb1 kernel: [56527.252417] ata15.04: hard resetting link
Sep 28 20:54:30 zapdb1 kernel: [56527.572270] ata15.04: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
Sep 28 20:54:30 zapdb1 kernel: [56527.572346] ata15.05: hard resetting link
Sep 28 20:54:31 zapdb1 kernel: [56527.891317] ata15.05: SATA link up 1.5 Gbps (SStatus 113 SControl 320)
Sep 28 20:54:31 zapdb1 kernel: [56527.894471] ata15.00: configured for UDMA/33
Sep 28 20:54:31 zapdb1 kernel: [56527.897816] ata15.01: configured for UDMA/33
Sep 28 20:54:31 zapdb1 kernel: [56527.901165] ata15.02: configured for UDMA/33
Sep 28 20:54:31 zapdb1 kernel: [56527.904446] ata15.03: configured for UDMA/33
Sep 28 20:54:31 zapdb1 kernel: [56527.907628] ata15.04: configured for UDMA/33
Sep 28 20:54:31 zapdb1 kernel: [56527.908096] ata15: EH complete

1 Answer 1

1

I have often found this to be a power issue. not enough power being supplied to the drive.

1
  • While assembling the server, I tried to see the amount of power going to these cards (note: the drives are being powered by the card, which is being powered directly by the power supply unit). The server has 2 PSUs. PSU1 powers the motherboard and 4 cards, PSU2 powers the remaining 5 cards. I noticed that the cards powered by PSU2 had a slightly lower voltage on the 5v pins (it was 4.2 I think). Voltage on 12v pins was 12.2v. And this particular card is powered by PSU2. Sep 29, 2012 at 5:00

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .