[sheepdog] [PATCH v1] sheep/md: leave cluster if disk number equals zero in handling EIO

[Hitoshi Mitake]

At Fri, 12 Sep 2014 15:54:26 +0200,
Valerio Pachera wrote:
> 
> I confirm such wrong behaviour in Sheepdog daemon version 0.8.0_331_gecc533e.
> More than leaving the cluster, the node should get weight 0 and become
> a gateway only.
> This way guests can continue working.

Thanks for your reporting. BTW, I don't like the current way of
handling -EIO (not limited to md, and not works well
currently). Because if sheep has no disks, it means it cannot store
log. It will make trouble shooting almost impossible. Rather than
calling leave_cluster(), simply calling panic() or exit() would be
enough. How do you think, Valerio and Bingpeng?

Thanks,
Hitoshi

> 
> root at test007:~# dog node list
>   Id   Host:Port         V-Nodes       Zone
>    0   192.168.10.4:7000        126   67807424
>    1   192.168.10.5:7000        129   84584640
>    2   192.168.10.6:7000        129  101361856
>    3   192.168.10.7:7000        129  118139072
> 
> root at test007:~# dog node md info --all
> Id      Size    Used    Avail   Use%    Path
> Node 0:
>  0      216 GB  5.7 GB  210 GB    2%    /mnt/sheep/0
> Node 1:
>  0      219 GB  4.8 GB  215 GB    2%    /mnt/sheep/0
> Node 2:
>  0      220 GB  5.2 GB  215 GB    2%    /mnt/sheep/0
> Node 3:
>  0      220 GB  5.2 GB  215 GB    2%    /mnt/sheep/0
> 
> root at test007:~# dog node md unplug /mnt/sheep/0
>     __
>    ()'`;
>    /\|`
>   /  |   Caution! Recovery will be triggered after unplugging.
> (/_)_|_  Are you sure you want to continue? [yes/no]: yes
> 
> root at test007:~# dog node list
>   Id   Host:Port         V-Nodes       Zone
>    0   192.168.10.4:7000        126   67807424
>    1   192.168.10.5:7000        129   84584640
>    2   192.168.10.6:7000        129  101361856
>    3   192.168.10.7:7000        129  118139072
> root at test007:~# dog node recovery
> Nodes In Recovery:
>   Id   Host:Port         V-Nodes       Zone       Progress
>    3   192.168.10.7:7000     129  118139072        0.0%
> 
> root at test007:~# dog node info
> Id      Size    Used    Avail   Use%
>  0      216 GB  5.7 GB  210 GB    2%
>  1      219 GB  4.8 GB  215 GB    2%
>  2      220 GB  5.2 GB  215 GB    2%
>  3      0.0 MB  0.0 MB  0.0 MB    0%
> (It hangs...I had to press ctrl+c)
> -- 
> sheepdog mailing list
> sheepdog at lists.wpkg.org
> http://lists.wpkg.org/mailman/listinfo/sheepdog