Hello list, this bug is filed as: https://tracker.ceph.com/issues/23891
>From my point of this is a bug, probably others are experiencing also this problem and can provide additional details. I would like to map a rbd using rbd-nbd. Without adding the foreground flag it is not possible to map the device. The command listed beyond, are executed on a mon server (same thing happens on other servers) ################################################################################## ### Not working scenario: running rbd-nbd as background proccess Shell 1: # rmmod nbd rmmod: ERROR: Module nbd is not currently loaded # rbd-nbd map --nbds_max 16 RBD_XenStorage-07449252-bf96-4daa-b0a6-687b7f1c369c/RBD-17efad10-6807-433f-879a-c59b511f895c -> it blocks probably forever Strace of the problem situation # strace -frvT -s128 -o /tmp/fail.strace rbd-nbd map --nbds_max 16 RBD_XenStorage-07449252-bf96-4daa-b0a6-687b7f1c369c/RBD-17efad10-6807-433f-879a-c59b511f895c (see https://tracker.ceph.com/issues/23891) Shell 2: # rbd-nbd list-mapped -> no output # lsmod |grep nbd -> no output ################################################################################## ### Working scenario running rbd-nbd in foreground: Shell 1: # rbd-nbd map -d --nbds_max 16 RBD_XenStorage-07449252-bf96-4daa-b0a6-687b7f1c369c/RBD-17efad10-6807-433f-879a-c59b511f895c 2018-04-26 23:22:19.681903 7fde4b442e80 0 ceph version 12.2.5 (cad919881333ac92274171586c827e01f554a70a) luminous (stable), process (unknown), pid 326958 2018-04-26 23:22:19.681919 7fde4b442e80 0 pidfile_write: ignore empty --pid-file /dev/nbd0 -> Blocking, because its running as foreeground proccess Shell 2: # rbd-nbd list-mapped pid pool image snap device 326958 RBD_XenStorage-07449252-bf96-4daa-b0a6-687b7f1c369c RBD-17efad10-6807-433f-879a-c59b511f895c - /dev/nbd0 # blockdev --getsize64 /dev/nbd0 21474836480 # blockdev --setra 1024 /dev/nbd0 # blockdev --getra /dev/nbd0 1024 # rbd-nbd unmap /dev/nbd0 Shell 1: -> terminates in unmap 2018-04-26 23:24:55.660478 7fdded7ba700 0 rbd-nbd: disconnect request received ################################################################################### ### Our System: * Luminous/12.2.5 * Ubuntu 16.04 * 5 OSD Nodes (24*8 TB HDD OSDs, 48*1TB SSD OSDS, Bluestore, 6Gb Cache per OSD) * Size per OSD, 192GB RAM, 56 HT CPUs) * 3 Mons (64 GB RAM, 200GB SSD, 4 visible CPUs) * 2 * 10 GBIT, SFP+, bonded xmit_hash_policy layer3+4
_______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com