Hi everyone! I've encountered situation I cannot even google. In a nutshell, rbd map test/kek --id test hags forever on ```futex(0x7ffdfa73d748, FUTEX_WAIT_BITSET_PRIVATE|FUTEX_CLOCK_REALTIME, 0, NULL, FUTEX_BITSET_MATCH_ANY``` instruction in strace. Of course, I have all the keyrings and ceph.conf on site.
I would think about network related problem however there is neither firewall not iptables filtering rules. Tcpdump show that packages fly both ends (i don't know what is inside). The trick is when I bring admin keyring onto client - ```ceph -s``` command works perfect. Thare are no mentions about connection attemp in systemd service of monitors. No mentions at all in any logs. I've been fighting for three days now and no result. So ANY advice is very appreciated and you will receive quants of love from me personally :) Ubuntu 22.04.4 LTS on both client and ceph nodes with kernel 5.15.0-112-generic There is no firewall and no iptables rules filtering rules on client and the same (excluding rules added by docker) on cluster nodes. There is a ping between client and any of cluster nodes. By netcat I can see that OSD and MON ports are open. I am totally lost here. Please, give me a hint what to check and where to find? root@ceph1:/tmp/nfs# ceph -s cluster: id: ceph-fsid health: HEALTH_OK services: mon: 3 daemons, quorum ceph10,ceph6,ceph1 (age 46h) mgr: ceph1.rynror(active, since 46h), standbys: ceph2.nxpjmd osd: 109 osds: 108 up (since 44h), 108 in (since 43h) flags noautoscale data: pools: 6 pools, 6401 pgs objects: 38 objects, 65 MiB usage: 105 TiB used, 1.7 PiB / 1.8 PiB avail pgs: 6401 active+clean Thanks in advance This is ceph v18.2.2 _______________________________________________ ceph-users mailing list -- ceph-users@ceph.io To unsubscribe send an email to ceph-users-le...@ceph.io