Project

General

Profile

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:

0%

Source:
other
Tags:
Backport:
Regression:
No
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)

Actions
Copy link

Also available in: Atom PDF