Bug #17778: notional amount of data stored is greater than actual data in the cluster. - Ceph - Ceph

Actions

Copy link

Bug #17778

closed

notional amount of data stored is greater than actual data in the cluster.

Added by Parikshith B over 7 years ago. Updated almost 7 years ago.

Status:

Closed

Priority:

Normal

Assignee:

Category:

Target version:

% Done:

Source:

other

Tags:

Backport:

Regression:

Severity:

3 - minor

Reviewed:

Affected Versions:

v10.2.2

ceph-qa-suite:

Pull request ID:

Crash signature (v1):

Crash signature (v2):

Description

1. I was running IOs on cephfs and replicted pools and noticed that estimated data is more than actual data.

ceph -s
    cluster 54483280-809a-48f0-a657-a077f1f60100
     health HEALTH_WARN
            noscrub,nodeep-scrub,sortbitwise flag(s) set
     monmap e1: 1 mons at {rack3-ramp-9=10.242.43.35:6789/0}
            election epoch 11, quorum 0 rack3-ramp-9
      fsmap e9188: 1/1/1 up {0=rack3-ramp-9=up:active}
     osdmap e2017: 16 osds: 16 up, 16 in
            flags noscrub,nodeep-scrub,sortbitwise
      pgmap v220139: 2348 pgs, 3 pools, 22916 GB data, 9852 kobjects
            19864 GB used, 37179 GB / 57043 GB avail
                2348 active+clean

ceph df GLOBAL: SIZE AVAIL RAW USED %RAW USED 57043G 37179G 19864G 34.82 POOLS: NAME ID USED %USED MAX AVAIL OBJECTS cephfs_data 1 7688G 26.95 17763G 5091323 cephfs_metadata 2 312M 0 17763G 239 pool1 4 15228G 53.39 17763G 4997442

2. Replication size is 2 on all the pools. There are no clones or snapshots.

3. Ran the same test on just the replicated pools,here notional data was half of used data(as replication was 2)