On 20/02/17 18:27, Martin Bosner wrote:

quoted

On 20 Feb 2017, at 19:11, Phil Turmel [off-list ref] wrote:

Of the 36 original disks, you have 34.  You have one incomplete
rebuild, meaning it is still technically a spare. One of the still
active 34 is also showing pending relocations, meaning that disk will
not be able to supply all sectors to complete any recovery.
{ /dev/sdah, serial # S1F0FPYR }

If you have any access to the two "dead" drives, there might be
a slight chance. Since they were likely kicked out due to timeout
mismatch, not a complete failure, this could be possible.

Otherwise, you are utterly screwed.  Sorry.

The disks are dead. I already tried different boards but that did not help.

If it had been the timeout problem, you would probably have been able to
recover the array. As it isn't :-(

What would happen if i recreate the array with —assume-clean ? Would i be able to start the array? Can I mark disks as clean? I actually have one failed disks, one nearly recovered disk and one that has been copied by 2/3 ...

You can try "--assemble --force". It sounds like you might well get away
with it.

BUT! DO NOT ATTEMPT TO USE THE ARRAY IF IT LOOKS LIKE IT'S OKAY. Are all
the disks the same age? In which case, all the other drives are on the
verge of failure, too!

I don't know whether to suggest you use smartctl to see what state the
drives are in (I've seen too many reports of allegedly healthy drives
failing, so I wouldn't trust it, especially with this particular drive.)

ddrescue your remaining drives *now*, and hope you're okay. You say you
have 35GB, across 36 drives, so you should only be using the first 1GB
of each drive. We hope ...

Martin 

Cheers,
Wol