Thanks for reply,
>>ceph df
GLOBAL:
SIZE AVAIL RAW USED %RAW USED
13910G 2472G 11437G 82.22
POOLS:
NAME ID USED %USED MAX AVAIL OBJECTS
rbd 0 3792G 27.26 615G 971526
How to free raw used space?
From: ceph-users [mailto:ceph-users-bounces@xxxxxxxxxxxxxx] On Behalf Of Henrik Korkuc
Sent: Tuesday, March 10, 2015 10:13 AM
To: ceph-users@xxxxxxxxxxxxxx
Subject: Re: Ceph free space
On 3/10/15 11:06, Mateusz Skała wrote:
Hi,
In my cluster is something wrong with free space. In cluster with 10OSD (5*1TB + 5*2TB) ‘ceph –s’ shows:
11425 GB used, 2485 GB / 13910 GB avail
But I have only 2 rbd disks in one pool (‘rbd’):
>>rados df
pool name category KB objects clones degraded unfound rd rd KB wr wr KB
rbd - 3976154023 971434 0 6474 0 11542224 1391869743 742847 385900453
total used 11988041672 971434
total avail 2598378648
total space 14586420320
>>rbd ls
vm-100-disk-1
vm-100-disk-2
>>rbd info vm-100-disk-1
rbd image 'vm-100-disk-1':
size 16384 MB in 4096 objects
order 22 (4096 kB objects)
block_name_prefix: rbd_data.14ef2ae8944a
format: 2
features: layering
>>rbd info vm-100-disk-2
rbd image 'vm-100-disk-2':
size 4096 GB in 1048576 objects
order 22 (4096 kB objects)
block_name_prefix: rbd_data.15682ae8944a
format: 2
features: layering
So my rbd disks use only 4112GB. Default size of cluster is 2 so used space should be ca 8224GB, why ceph –s shows 11425 GB ?
Can someone explain this situation?
Thanks, Mateusz
Hey,
what does "ceph df" show?
ceph -s shows raw disk usage so there will be some overhead from file system, also maybe you left some files there?
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
