Re: mdadm creating raid5 with all spare disks

[Andre Tomt <andre@tomt.net>]

On 11.12.2009 02:01, Matt Tehonica wrote:
> On Dec 10, 2009, at 7:47 PM, Richard Scobie <richard@sauce.co.nz> wrote:
<snip>
>> Looks like the drives are being dropped by the controller.
>>
>> I believe there was some recent discussion here about mv_sas, md and
>> failures under heavy I/O load.
>
> Thanks Richard! After some more review I found many people with this
> problem and appears the linux-scsi devs submitted patches mid last
> month. Building the latest kernel as we speak!

FYI; The fixes has not made it to mainline yet so 2.6.32 and 2.6.33-git 
is still broken with this driver. Not sure if they've landed in some 
scsi tree yet but manually applying patches 1-6 from the linux-scsi 
mailing list worked for me, at least to the point that it is now usable 
(patch 7 is for some libsas change not in 2.6.32).

On a related note, mptsas driver also seems to have issues with newer 
HBA's. Non-RAID SAS HBA's doesn't seem to be in a very good shape in 
Linux nowadays. Might give a mpt2sas driven controller a spin soon, 
curious on how that pans out..

-- 
André
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html