Hi,

I have a problem with large amounts of dark data/orphans on cephfs data pool. Data is stored mostly on a 8+3 EC pool (cephfs_data_echdd).

There is ~5.6PiB stored on /ceph, shown by ceph.dir.rbytes with 132M files and 139M rentries. The pool shows 7PiB stored and 9.7PiB used consistent with 8+3 EC.
The layout for most files:
ceph.dir.layout="stripe_unit=16777216 stripe_count=1 object_size=16777216 pool=cephfs_data_echdd"

But there is 1.4PiB discrepancy between the pool and the filesystem which I cannot explain and I suspect there are a lot of orphan objects there. I have run mds scrub on / and ~mdsdir as well. There is some mds damage on some old small files (~400 files), which I do not think it's relevant here.

ceph was created with 17.2.6 and runs 19.2.3.

Do you might have any suggestions how to fix this?

Thanks,
Andrej

spod01 ~# ceph df
--- RAW STORAGE ---
CLASS     SIZE    AVAIL     USED  RAW USED  %RAW USED
hdd     11 PiB  1.5 PiB  9.7 PiB   9.7 PiB      86.28
nvme   363 TiB  356 TiB  6.8 TiB   6.8 TiB       1.87
ssd    3.5 TiB  3.0 TiB  478 GiB   478 GiB      13.37
TOTAL   12 PiB  1.9 PiB  9.7 PiB   9.7 PiB      83.68

--- POOLS ---
POOL                        ID   PGS   STORED  OBJECTS     USED %USED  MAX AVAIL .mgr                         1     1  850 MiB      213  2.5 GiB   0    178 TiB cephfs_data                  2   256   28 GiB  134.71M   86 GiB  2.86    972 GiB cephfs_metadata              3    64   66 GiB    6.66M  199 GiB  6.38    972 GiB cephfs_data_echdd           19  4096  7.0 PiB  594.70M  9.7 PiB 94.90    388 TiB cephfs_data_ecnvme          26    64  1.2 TiB    2.84M  1.7 TiB  0.48    251 TiB
...


--
_____________________________________________________________
   prof. dr. Andrej Filipcic,   E-mail: [email protected]
   Department of Experimental High Energy Physics - F9
   Jozef Stefan Institute, Jamova 39, P.o.Box 3000
   SI-1001 Ljubljana, Slovenia
   Tel.: +386-1-477-3674    Fax: +386-1-477-3166
-------------------------------------------------------------
_______________________________________________
ceph-users mailing list -- [email protected]
To unsubscribe send an email to [email protected]

Reply via email to