# tail -f /var/log/ceph/ceph-osd.3.log
...
2018-10-02 03:49:48.552686 7ffa10b6bd00 1 bluestore(/var/lib/ceph/osd/ceph-3) _open_db opened rocksdb path db options compression=kNoCompression,max_write_buffer_number=4,min_write_buffer_number_to
_merge=1,recycle_log_file_num=4,write_buffer_size=268435456,writable_file_max_buffer_size=0,compaction_readahead_size=2097152
2018-10-02 03:49:48.568184 7ffa10b6bd00 1 freelist init
2018-10-02 03:49:48.579042 7ffa10b6bd00 1 bluestore(/var/lib/ceph/osd/ceph-3) _open_alloc opening allocation metadata
2018-10-02 03:49:48.767642 7ffa10b6bd00 1 bluestore(/var/lib/ceph/osd/ceph-3) _open_alloc loaded 599 G in 1055 extents
2018-10-02 03:58:46.061109 7ffa10b6bd00 2 osd.3 0 journal looks like hdd
2018-10-02 03:58:46.061146 7ffa10b6bd00 2 osd.3 0 boot
2018-10-02 03:58:46.061236 7ffa10b6bd00 20 osd.3 0 configured osd_max_object_name[space]_len looks ok
2018-10-02 03:58:46.062040 7ffa10b6bd00 10 osd.3 0 read_superblock sb(4c9eb31c-b6a9-4b46-a8a2-cbbfaf56444b osd.3 656ca1d3-7e50-4bcc-bbfe-27b88a28dcf6 e7019 [5862,7019] lci=[7015,7019])
2018-10-02 03:58:46.086503 7ffa10b6bd00 10 open_all_classes
...
As above, the "bluestore(/var/lib/ceph/osd/ceph-3) _open_alloc loaded xxx" took 8 minutes, and at this time, top to see a cpu core iowait 80% ~ 100%, as follow
"%Cpu3 : 3.6 us, 4.2 sy, 0.0 ni, 0.0 id, 92.2 wa, 0.0 hi, 0.0 si, 0.0 st"
I tested the disk with `dd` cmd, the disk itself is fine. So I am confused, what is the cause?
-------------------
ceph version 12.2.4 luminous (stable)
Linux 4.4.0-116-generic #140-Ubuntu SMP Mon Feb 12 21:23:04 UTC 2018 x86_64 x86_64 x86_64 GNU/Linux
-------------------
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
