mfip and smartctl Re: smartctl / mpt on 9.0-RC1
Alex Samorukov
ml at os2.kiev.ua
Mon Nov 7 14:06:45 UTC 2011
On 11/07/2011 02:47 PM, Andrew Boyer wrote:
>
> [GLTSD (Global Logging Target Save Disable) set. Enable Save with '-S on']
> No self-tests have been logged
> Long (extended) Self Test duration: 1740 seconds [29.0 minutes]
>
> btw, 3dm can tell about reallocated sector count on sas somehow, while smartctl cannot, even on supported controller :(
> Notice how the device type is "<31>"? The mfip driver masks off the SCSI INQUIRY peripheral device type bits to prevent CAM from attached da* devices to the disks. See sys/dev/mfi/mfi_cam.c, search for T_DIRECT. That confuses smartctl and prevents it from displaying information like the Grown Defect List.
>
> I added a local hack to smartctl to interpret a peripheral device type of 0x1f (unknown or missing) to 0x0 (disk), but I don't think the hack is appropriate for general consumption. What we need is better way for mfi and aac to block CAM from attaching without corrupting the inquiry results
I can add hack to the sources with checking if underlying driver is mfi
(there are already some for buggy SAT fw implementation). It is probably
easiest way to do this. I just tested - firmware itself returns correct
(disk) status.
Of course in the feature its better to fix in mfi_cam to avoid such hacks.
More information about the freebsd-stable
mailing list