[Sheepdog] Sheepdog 0.3.0 schedule and 0.4.0 plan

Liu Yuan namei.unix at gmail.com
Tue Nov 15 03:48:31 CET 2011


On 11/15/2011 10:05 AM, MORITA Kazutaka wrote:

> Hi,
> 
> I finished all of the cluster driver implementation we planed, so I
> think of releasing 0.3.0 this weekend.  If you have pending patches
> for 0.3.0, please send them until Nov 18th.  I'll spend this week
> testing Sheepdog.
> 
> The planned big features for 0.4.0 are as follows:
> 
>  - add write-cache support
>    http://lists.wpkg.org/pipermail/sheepdog/2011-October/001480.html
> 
>  - support larger object size
>    http://lists.wpkg.org/pipermail/sheepdog/2011-November/001914.html
> 
>  - use differential copy for fast object recovery
>    http://lists.wpkg.org/pipermail/sheepdog/2011-July/001131.html
> 
>  - add hierarchical zones support
>  - reclaim unused objects automatically
>    http://lists.wpkg.org/pipermail/sheepdog/2011-October/001587.html
> 
> Let me know if there are others you want to include in the 0.4.0
> release.
> 
> 


Hi Kazum,

   I think "farm" can be ready for .4.0, the new kv-store which will
support

 - cluster wide snapshot. (both customized time and at the point of
epoch change)

 - node-wide data sharing for snapshot objects with the same content. so
snapshoting is very cheap operation.

 - support 'collie checkout epoch' to restore fully to the state of
history epoch and customized time.

 - differential data change between subsequent epoches (for faster
nested recovery, that node failure happens at recovery stage)

 - auto checksumed snapshot objects

 - no stale objects that are found in current implementation, that will
waste storage a lot.

Thanks,
Yuan



More information about the sheepdog mailing list