Hitoshi Mitake

@tmenjo could you work on deleting object cache?

@tankitty thanks for your report. Current `dog vdi check` believes location of objects calculated by vnode info provided by sheep. But in a case of corrupted cluster, `dog vdi check`...

You can enable/disable the auto recovery with `dog cluster recover enable|disable`. After disabling the auto recovery, `dog node kill` will purge a node from the cluster without involving recovery traffic.

Also `dog node recovery set-throttle|get-throttle` will be helpful for controlling resource consumption by the recovery process.

For the purpose, `dog node vnodes set` will be useful. You can reduce the number of vnodes of a specific node gradually. This process can migrate objects from the node...

Yes, it can be found in 1.0.x series.

@tmenjo could you work on it? Especially, employing a service of CI for testing PR is really helpful.

If I remember correctly, you created a table like this @sirio81 . Could you add it to our wiki?

Can this problem be reproduced with the fixed vnode mode? I believe the auto vnode is completely flawed stuff so should be removed in the future. If this problem is...

I'd like to report my experiment of etcd 5022: https://github.com/coreos/etcd/issues/5022 | w/ or w/o Namazu process inspector | Reproducibility | | --- | --- | | w/o | 0% |...