Avago LSI SAS 3008 & Intel SSD Timeouts

[Borja Marcos]

> On 07 Jun 2016, at 00:19, list-news <list-news at mindpackstudios.com> wrote:
> 
> *# sysctl vfs.zfs.vdev.bio_delete_disable=1*
> (a few minutes later)

So trim is not causing it.

> 
> *Error:*
> Jun  6 13:36:15 s18 kernel: (da6:mpr0:0:16:0): WRITE(10). CDB: 2a 00 30 65 13 90 00 00 10 00
> Jun  6 13:36:15 s18 kernel: (da6:mpr0:0:16:0): CAM status: SCSI Status Error
> Jun  6 13:36:15 s18 kernel: (da6:mpr0:0:16:0): SCSI status: Check Condition
> Jun  6 13:36:15 s18 kernel: (da6:mpr0:0:16:0): SCSI sense: UNIT ATTENTION asc:29,0 (Power on, reset, or bus device reset occurred)
> Jun  6 13:36:15 s18 kernel: (da6:mpr0:0:16:0): Retrying command (per sense data)
> ...
> 
> *And again 2 minutes later:*
> 
> Jun  6 13:38:43 s18 kernel: (da2:mpr0:0:12:0): WRITE(10). CDB: 2a 00 21 66 63 58 00 00 10 00
> Jun  6 13:38:43 s18 kernel: (da2:mpr0:0:12:0): CAM status: SCSI Status Error
> Jun  6 13:38:43 s18 kernel: (da2:mpr0:0:12:0): SCSI status: Check Condition
> Jun  6 13:38:43 s18 kernel: (da2:mpr0:0:12:0): SCSI sense: UNIT ATTENTION asc:29,0 (Power on, reset, or bus device reset occurred)
> Jun  6 13:38:43 s18 kernel: (da2:mpr0:0:12:0): Retrying command (per sense data)


I suffered this particular symptom because, it seems of a broken LSI3008 card. Finally I replaced it with a LSI2008 (I didn’t have a spare
LSI3008 handy) and the errors vanished. In my case it is a NFS storage based on ZFS and Samsung SSD disks serving several Xen 
hosts.

In my case the disks are SATA.

I know that it was a defective card and not a problem with the LSI3008 cards or driver because I have a twin system working like a charm
from day zero.

I would try, if possible, to swap the controller. 






Borja.