On Tue, Mar 7, 2017 at 10:27 AM, Francois Blondel <fblondel at intelliad.de> wrote:
> Hi all,
>
> I have been triyng to use RBD devices on a Erasure Coded data-pool on Ubuntu
> Xenial.
>
> I created my block device "blockec2" with :
> rbd create blockec2 --size 300G --data-pool ecpool --image-feature
> layering,data-pool
> (same issue with "rbd create blockec2 --size 300G --data-pool ecpool" )
>
> I maped this block device to a "4.4.0-65-generic #86-Ubuntu SMP Thu Feb 23
> 17:49:58 UTC 2017 x86_64" Kernel using "rbd-nbd map rbd/blockec2"
>
> Wenn using the block device (mkfs.ext4 for example), i get following errors
> in dmesg:
>
> [Fri Mar 3 10:05:25 2017] nbd: registered device at major 43
> [Fri Mar 3 10:05:53 2017] block nbd0: Other side returned error (95)
> [Fri Mar 3 10:05:53 2017] blk_update_request: I/O error, dev nbd0, sector 0
> [Fri Mar 3 10:05:56 2017] block nbd0: Other side returned error (95)
> [Fri Mar 3 10:05:56 2017] blk_update_request: I/O error, dev nbd0, sector
> 8388607
> [Fri Mar 3 10:06:06 2017] block nbd0: Other side returned error (95)
> [Fri Mar 3 10:06:06 2017] blk_update_request: I/O error, dev nbd0, sector
> 16777214
Be aware that this functionality is experimental and may eat your data.
If you still want to try it, you need to whitelist it in ceph.conf:
enable experimental unrecoverable data corrupting features =
debug_white_box_testing_ec_overwrites
and do
$ ceph osd pool set ecpool debug_white_box_testing_ec_overwrites true
Thanks,
Ilya
