SAS Error 8d

Hello,

I was recently browsing my syslog, and I noticed that I've been getting some drive-related errors over the past month.  I haven't noticed anything behaving unusually, and in fact I just passed a parity check a few days ago.  I have a Supermicro aoc-saslp-mv8 that a number of drives are connected to, which must be the SAS device that's mentioned here.

This happens once or twice a week, it appears.  Here's the most recent occurance (complete log is also attached):

Apr  2 19:31:42 Hyperion kernel: sas: command 0xf74e66c0, task 0xdf87c000, timed out: BLK_EH_NOT_HANDLED (Drive related)
Apr  2 19:31:42 Hyperion kernel: sas: Enter sas_scsi_recover_host (Drive related)
Apr  2 19:31:42 Hyperion kernel: sas: trying to find task 0xdf87c000 (Drive related)
Apr  2 19:31:42 Hyperion kernel: sas: sas_scsi_find_task: aborting task 0xdf87c000 (Drive related)
Apr  2 19:31:42 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 1703:<7>mv_abort_task() mvi=dfb20000 task=df87c000 slot=dfb3163c slot_idx=x2 (System)
Apr  2 19:31:42 Hyperion kernel: sas: sas_scsi_find_task: querying task 0xdf87c000 (Drive related)
Apr  2 19:31:42 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 1632:mvs_query_task:rc= 5 (System)
Apr  2 19:31:42 Hyperion kernel: sas: sas_scsi_find_task: task 0xdf87c000 failed to abort (Minor Issues)
Apr  2 19:31:42 Hyperion kernel: sas: task 0xdf87c000 is not at LU: I_T recover (Drive related)
Apr  2 19:31:42 Hyperion kernel: sas: I_T nexus reset for dev 0000000000000000 (Drive related)
Apr  2 19:31:42 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 2083:port 0 ctrl sts=0x89800. (System)
Apr  2 19:31:42 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 2085:Port 0 irq sts = 0x1001 (System)
Apr  2 19:31:42 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 2111:phy0 Unplug Notice (System)
Apr  2 19:31:42 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 2083:port 0 ctrl sts=0x199800. (System)
Apr  2 19:31:42 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 2085:Port 0 irq sts = 0x11081 (System)
Apr  2 19:31:42 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 2138:notify plug in on phy[0] (System)
Apr  2 19:31:42 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 2163:plugin interrupt but phy0 is gone (System)
Apr  2 19:31:44 Hyperion kernel: mvsas 0000:01:00.0: Phy0 : No sig fis (Drive related)
Apr  2 19:31:44 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 2024:phy0 Attached Device (System)
Apr  2 19:31:44 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 2083:port 0 ctrl sts=0x89800. (System)
Apr  2 19:31:44 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 2085:Port 0 irq sts = 0x1001001 (System)
Apr  2 19:31:44 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 2111:phy0 Unplug Notice (System)
Apr  2 19:31:44 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 2083:port 0 ctrl sts=0x199800. (System)
Apr  2 19:31:44 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 2085:Port 0 irq sts = 0x81 (System)
Apr  2 19:31:44 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 2083:port 0 ctrl sts=0x199800. (System)
Apr  2 19:31:44 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 2085:Port 0 irq sts = 0x10000 (System)
Apr  2 19:31:44 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 2138:notify plug in on phy[0] (System)
Apr  2 19:31:44 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 1224:port 0 attach dev info is 0 (System)
Apr  2 19:31:44 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 1226:port 0 attach sas addr is 0 (System)
Apr  2 19:31:44 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 378:phy 0 byte dmaded. (System)
Apr  2 19:31:44 Hyperion kernel: sas: sas_form_port: phy0 belongs to port0 already(1)! (Drive related)
Apr  2 19:31:45 Hyperion kernel: drivers/scsi/mvsas/mv_sas.c 1586:mvs_I_T_nexus_reset for device[0]:rc= 0 (System)
Apr  2 19:31:45 Hyperion kernel: sas: I_T 0000000000000000 recovered (Drive related)
Apr  2 19:31:45 Hyperion kernel: sas: sas_ata_task_done: SAS error 8d (Errors)
Apr  2 19:31:45 Hyperion kernel: ata11: translated ATA stat/err 0x01/04 to SCSI SK/ASC/ASCQ 0xb/00/00 (Drive related)
Apr  2 19:31:45 Hyperion kernel: ata11: status=0x01 { Error } (Errors)
Apr  2 19:31:45 Hyperion kernel: ata11: error=0x04 { DriveStatusError } (Errors)
Apr  2 19:31:45 Hyperion kernel: sas: --- Exit sas_scsi_recover_host (Drive related)

Any idea what is going on or how to debug?  Is a drive failing?  Is the SAS controller failing?  I don't know how to tell.

I am still back on the last "stable" beta, 5.0 beta 6a.  I've been afraid to update due to the issues with both SAS cards and Realtek network drivers in the more recent builds, which had both been working fine for me on 6a.

Thanks for any ideas you may have.

syslog-2012-04-07.txt.zip