Turns out it is probably orphans. We are running ceph luminous : 12.2.12 And the orphans find is stuck in the stage : "iterate_bucket_index" on shard "0" for 2 days now. Anyone is facing this issue ? Regards, De : ceph-users <ceph-users-bounces@xxxxxxxxxxxxxx<mailto:ceph-users-bounces@xxxxxxxxxxxxxx>> Envoyé : 21 January 2020 10:10 À : ceph-users@xxxxxxxxxxxxxx<mailto:ceph-users@xxxxxxxxxxxxxx> Objet : Understand ceph df details Hi everyone, I'm trying to understand where is the difference between the command : ceph df details And the result I'm getting when I run this script : total_bytes=0 while read user; do echo $user bytes=$(radosgw-admin user stats --uid=${user} | grep total_bytes_rounded | tr -dc "0-9") if [ ! -z ${bytes} ]; then total_bytes=$((total_bytes + bytes)) pretty_bytes=$(echo "scale=2; $bytes / 1000^4" | bc) echo " ($bytes B) $pretty_bytes TiB" fi pretty_total_bytes=$(echo "scale=2; $total_bytes / 1000^4" | bc) done <<< "$(radosgw-admin user list | jq -r .[])" echo "" echo "Total : ($total_bytes B) $pretty_total_bytes TiB" When I run df I get this : default.rgw.buckets.data 70 N/A N/A 226TiB 89.23 27.2TiB 61676992 61.68M 2.05GiB 726MiB 677TiB And when I use my script I don't have the same result : Total : (207579728699392 B) 207.57 TiB It means that I have 20 TiB somewhere but I can't find and must of all understand where this 20 TiB. Does anyone have an explanation ? Fi : [root@ceph_monitor01 ~]# radosgw-admin gc list -include-all | grep oid | wc -l 23 _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
 |