I assume the cluster is used in roughly the same way as before the
upgrade and the load has not increased since, correct? What is the
usual load, can you share some 'ceph daemonperf mds.<MDS>' output? It
might be unrelated but have you tried to compact the OSDs belonging to
this pool, online or offline?
Zitat von Denis Polom <denispolom@xxxxxxxxx>:
Hi
any help here, please? I observe the same behavior on cluster I just
updated with latest Octopus.
Any help will be appreciated
thx
On 8/6/21 14:41, Denis Polom wrote:
Hi,
I observe strange behavior on my Ceph MDS cluster, where
cephfs_metadata pool is filling out without obvious reason. It's
getting +15% by day even when there are no I/O on the cluster. I
have separate SSD disks for metadata pool, each 112G with pool
replica size 3.
`ceph fs status` shows only about 1,5G is used by metadata but only
19.9G available:
POOL TYPE USED AVAIL
cephfs_metadata metadata 1446M 19.9G
on other site `ceph osd df` shows that each device is 77% utilized
(was 9% 5 days ago) and there are 85G of data:
ID CLASS WEIGHT REWEIGHT SIZE RAW USE DATA OMAP META AVAIL %USE VAR
PGS STATUS
119 ssd 0.10918 1.00000 112 GiB 86 GiB 85 GiB 317 MiB 590 MiB 26
GiB 77.09 1.11 128 up
100 ssd 0.10918 1.00000 112 GiB 86 GiB 85 GiB 309 MiB 658 MiB 26
GiB 77.14 1.11 128 up
82 ssd 0.10918 1.00000 112 GiB 86 GiB 85 GiB 393 MiB 617 MiB 26 GiB
77.17 1.11 128 up
`ceph df` output is also a bit different:
CLASS SIZE AVAIL USED RAW USED %RAW USED
ssd 335 GiB 76 GiB 259 GiB 259 GiB 77.20
POOL ID PGS STORED OBJECTS USED %USED MAX AVAIL
cephfs_metadata 2 128 492 MiB 1.78k 1.4 GiB 2.37 20 GiB
I don't know what data are consuming so much space there. This
happend after upgrade from nautilus to pacific release. Before
upgrade cephfs_metadata utilization was always about 9%.
Any idea what can be wrong and how to fix it?
Thank you
Denis
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx
