Hi,
We are running Ceph Reef 18.2.7, and we noticed an inconsistency when
checking RGW usage statistics with radosgw-admin usage show.
Cluster environment:
- 3 MONs, 36 OSDs (HDD + SSD mixed)
- RGW daemons: 3
- Deployment method: cephadm
When querying a specific UID, the totals look correct:
# radosgw-admin usage show --uid 0249bd92a6804133bf8e81f41da928cb | grep
total -A5
"total": {
"bytes_sent": 468098,
"bytes_received": 35998026,
"ops": 80,
"successful_ops": 77
}
But when dumping all usage and filtering for the same UID, the totals are
exactly doubled:
# radosgw-admin usage show | grep 0249bd92a6804133bf8e81f41da928cb -A100 |
grep total -A5
"total": {
"bytes_sent": 936196,
"bytes_received": 71996052,
"ops": 160,
"successful_ops": 154
}
Interestingly, if we specify a date filter, the numbers return to normal
again:
# radosgw-admin usage show --date=2025-09-24 | grep
0249bd92a6804133bf8e81f41da928cb -A100 | grep total -A5
"total": {
"bytes_sent": 468098,
"bytes_received": 35998026,
"ops": 80,
"successful_ops": 77
}
This issue does not affect all UIDs, only some of them.
Why does radosgw-admin usage show report doubled totals for certain UIDs
when dumping all usage, while --uid or --date shows correct values?
Is this expected behavior or a bug?
Thanks,
Jack
_______________________________________________
ceph-users mailing list -- [email protected]
To unsubscribe send an email to [email protected]
