ceph rebalance osd

[ilia987]

Seems quite well balanced.
But if you want to extract a little bit of extra space on a , the ceph balancer plugin did miracles for me on a cluster with a mix of very random drive sizes

https://docs.ceph.com/docs/mimic/mgr/balancer/

ceph mgr module enable balancer
ceph balancer on
ceph balancer mode upmap

Good luck

i just got rid of the old jewel clients and run the commands
but it did not make any change see the image: one of the osd is very full and once it got fuller the ceph got frozen

ceph balancer status
{
"last_optimize_duration": "0:00:00.005535",
"plans": [],
"mode": "upmap",
"active": true,
"optimize_result": "Unable to find further optimization, or pool(s) pg_num is decreasing, or distribution is already perfect",
"last_optimize_started": "Sun Feb 21 11:27:12 2021"
}

update: just needed to wait few minutes, it started to re-balance
it improved , (second image after balanced finished) better but far from ideal