I am getting a lot of these errors in the syslog whenever I run the parity checks/builds:

 

Dec 24 19:44:28 Meatlocker kernel: ata5.00: configured for UDMA/133

Dec 24 19:44:28 Meatlocker kernel: ata5.01: configured for UDMA/133

Dec 24 19:44:28 Meatlocker kernel: ata5: EH complete

Dec 24 19:44:28 Meatlocker kernel: sd 5:0:0:0: [sde] 1465149168 512-byte hardware sectors (750156 MB)

Dec 24 19:44:28 Meatlocker kernel: sd 5:0:0:0: [sde] Write Protect is off

Dec 24 19:44:28 Meatlocker kernel: sd 5:0:0:0: [sde] Mode Sense: 00 3a 00 00

Dec 24 19:44:28 Meatlocker kernel: sd 5:0:0:0: [sde] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA

Dec 24 19:44:28 Meatlocker kernel: sd 5:0:1:0: [sdf] 976773168 512-byte hardware sectors (500108 MB)

Dec 24 19:44:28 Meatlocker kernel: sd 5:0:1:0: [sdf] Write Protect is off

Dec 24 19:44:28 Meatlocker kernel: sd 5:0:1:0: [sdf] Mode Sense: 00 3a 00 00

Dec 24 19:44:28 Meatlocker kernel: sd 5:0:1:0: [sdf] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA

Dec 24 19:44:28 Meatlocker kernel: sd 5:0:0:0: [sde] 1465149168 512-byte hardware sectors (750156 MB)

Dec 24 19:44:28 Meatlocker kernel: sd 5:0:0:0: [sde] Write Protect is off

Dec 24 19:44:28 Meatlocker kernel: sd 5:0:0:0: [sde] Mode Sense: 00 3a 00 00

Dec 24 19:44:28 Meatlocker kernel: sd 5:0:0:0: [sde] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA

Dec 24 19:44:28 Meatlocker kernel: sd 5:0:1:0: [sdf] 976773168 512-byte hardware sectors (500108 MB)

Dec 24 19:44:28 Meatlocker kernel: sd 5:0:1:0: [sdf] Write Protect is off

Dec 24 19:44:28 Meatlocker kernel: sd 5:0:1:0: [sdf] Mode Sense: 00 3a 00 00

Dec 24 19:44:28 Meatlocker kernel: sd 5:0:1:0: [sdf] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA

Dec 24 19:46:48 Meatlocker kernel: ata2.00: exception Emask 0x12 SAct 0x0 SErr 0x1300500 action 0x6

Dec 24 19:46:48 Meatlocker kernel: ata2.00: BMDMA stat 0x5

Dec 24 19:46:48 Meatlocker kernel: ata2: SError: { UnrecovData Proto Dispar BadCRC TrStaTrns }

Dec 24 19:46:48 Meatlocker kernel: ata2.00: cmd 25/00:00:87:83:9e/00:04:12:00:00/e0 tag 0 dma 524288 in

Dec 24 19:46:48 Meatlocker kernel: res 51/84:1f:68:85:9e/84:02:12:00:00/e0 Emask 0x12 (ATA bus error)

Dec 24 19:46:48 Meatlocker kernel: ata2.00: status: { DRDY ERR }

Dec 24 19:46:48 Meatlocker kernel: ata2.00: error: { ICRC ABRT }

Dec 24 19:46:48 Meatlocker kernel: ata2: hard resetting link

Dec 24 19:46:48 Meatlocker kernel: ata2: SATA link up 1.5 Gbps (SStatus 113 SControl 310)

Dec 24 19:46:48 Meatlocker kernel: ata2.00: configured for UDMA/133

Dec 24 19:46:48 Meatlocker kernel: ata2: EH complete

Dec 24 19:46:48 Meatlocker kernel: sd 2:0:0:0: [sdb] 1953525168 512-byte hardware sectors (1000205 MB)

Dec 24 19:46:48 Meatlocker kernel: sd 2:0:0:0: [sdb] Write Protect is off

Dec 24 19:46:48 Meatlocker kernel: sd 2:0:0:0: [sdb] Mode Sense: 00 3a 00 00

Dec 24 19:46:48 Meatlocker kernel: sd 2:0:0:0: [sdb] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA

Dec 24 19:47:37 Meatlocker kernel: ata5.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6

Dec 24 19:47:37 Meatlocker kernel: ata5.00: BMDMA stat 0x66

Dec 24 19:47:37 Meatlocker kernel: ata5.00: cmd 25/00:00:cf:03:e4/00:04:12:00:00/e0 tag 0 dma 524288 in

Dec 24 19:47:37 Meatlocker kernel: res 51/84:6f:60:06:e4/84:01:12:00:00/e0 Emask 0x30 (host bus error)

Dec 24 19:47:37 Meatlocker kernel: ata5.00: status: { DRDY ERR }

Dec 24 19:47:37 Meatlocker kernel: ata5.00: error: { ICRC ABRT }

Dec 24 19:47:37 Meatlocker kernel: ata5: soft resetting link

 

This error repeats over and over.  The system is a Foxconn 45GMX ICH7 board.  There 4xSATAII using onboard with a 2xSATAI on a PCI card.  I rechecked all the cables, swapped cables, moved the drives around to different ports, etc etc multiple times now.  I still get the same errors, although the /dev will change sometimes.

 

The PSU is an Enermax 550Watt.  There is sufficient cooling.  These drives otherwise check out flawlessly.  Rebuilding parity is chugging along at 35-45 kbs/s.  When I had a certain configuration in the past, the errors would happen every sec or so which brought the spped down to 1.4 kb/s.  I have sinced found this "optimal" configuration and removed 2 old PATA drives.

 

I usually get these errors when I'm parity checking or building.  I read in a thread someone while googling these emask problems that it might be that the PCI bus is getting hammered.  Is this the case?  Will upgrading to another MB help?

 

Thanks in advance.

In my experience, both of these errors are from a loose or bad cable, or bad cable connections, not from the drives or PCI bus (although I could be wrong).  A bad cable connection could also be from a bad backplane or tray connection.  With this small a syslog excerpt, I don't have much to go on, I can't tell you which drives have the bad connection(s).

It turned out that it WAS a bad cable.  It was a brand spanking new cable from Monoprice too. 

 

After much more intensive testing, almost 20% of my SATA cables are bad somehow.  Go figure.