[sheepdog-users] cluster data distribution

[Liu Yuan]

On 05/09/2013 07:55 PM, Valerio Pachera wrote:
>> Yes, plugging the new disk doesn't trigger a data re-balance across the
>> > nodes but re-balance data between the disks in this node, which is not
>> > the same as adding a new node that trigger a data re-balance across the
>> > nodes.
> I've been writing more data on the cluster.
> Now it looks like this:
> 
> root at sheepdog004:~# collie node info
> Id      Size    Used    Use%
>  0      1.6 TB  846 GB   51%
>  1      1.6 TB  787 GB   46%
>  2      2.1 TB  191 GB    8%
> Total   5.4 TB  1.8 TB   33%
> Total virtual image size        1.2 TB
> 
> Calculating the difference of used space I get
> 86G written on id 0
> 64G written on id 1
> 16G written on id 2
> 
> Sheepdog doesn't seem to balance when writing.
> I mean, I thought that when it finds a situation like that, while
> writing new data was going to move more data on node 2.
> Is there a way to force balancing without adding a node?
>

Since we don't change weight by plugging/unplugging disks, there is no
way to rebalance data. If we allow weight-change for plug/unplug, we
have to pay price: plug/unplug one disk will trigger the whole cluster
recovery. If you really want to do this(data rebalance acrros nodes),
you can start a new sheep daemon on that disk instead of plugging it.

>>> >> root at sheepdog004:~# collie node md info --all
>>> >> Id      Size    Use     Path
>>> >> Node 0:
>>> >>  0      1.3 TB  544 GB  /mnt/ST2000DM001-1CH164_W1E2N5G6/obj
>>> >>  1      232 GB  233 GB  /mnt/wd_WMAYP0904279
>> >
>> > Looks like this node is full of space because disk 1 doesn't have enough
>> > space to hold more objects.
> I don't get this. "Node0 id1" is a 500G disk. 232 used and 233 free. Right?
> 
> Is it possible to change the label "Size" into "Free".

Ah, yeah, it is wrong. You are right, should be 'Size' --> 'Free' Or we
should really print 'Size' as total?

Thanks,
Yuan