Re: mon timeout

黑铁柱 <kangqi1988@xxxxxxxxx> · Thu, 24 Sep 2015 11:01:35 +0800

我发现这个问题是mon的名字不可以是单纯的一个数字导致的

2015-09-24 10:22 GMT+08:00 黑铁柱 <kangqi1988@xxxxxxxxx>:
[root@10_123_5_29 /var/log/ceph]# ceph --admin-daemon /var/run/ceph/ceph-mon.0.asok mon_status 
{ "name": "0",
  "rank": -1,
  "state": "probing",
  "election_epoch": 0,
  "quorum": [],
  "outside_quorum": [],
  "extra_probe_peers": [
        "10.123.5.29:6789\/0"],
  "sync_provider": [],
  "monmap": { "epoch": 0,
      "fsid": "eeabaeaf-4eb0-468a-a0e0-a3a3bece28af",
      "modified": "2015-09-23 22:03:45.415605",
      "created": "2015-09-23 22:03:45.415605",
      "mons": [
            { "rank": 0,
              "name": "10_123_5_29",
              "addr": "0.0.0.0:0\/1"}]}}

[root@10_123_5_29 /var/log/ceph]#  ceph --admin-daemon /var/run/ceph/ceph-mon.0.asok quorum_status
{ "election_epoch": 0,
  "quorum": [],
  "quorum_names": [],
  "quorum_leader_name": "",
  "monmap": { "epoch": 0,
      "fsid": "eeabaeaf-4eb0-468a-a0e0-a3a3bece28af",
      "modified": "2015-09-23 22:03:45.415605",
      "created": "2015-09-23 22:03:45.415605",
      "mons": [
            { "rank": 0,
              "name": "10_123_5_29",
              "addr": "0.0.0.0:0\/1"}]}}

2015-09-24 10:19 GMT+08:00 黑铁柱 <kangqi1988@xxxxxxxxx>:
I can not connect my mon.0.   probe timeout!!

ceph version:0.80.7
I just have one mon server--->10.123.5.29:6789;
why it find other mon?

ceph.conf
///////////////////////////////////////////////
[global]
auth service required = cephx
filestore xattr use omap = true
auth client required = cephx
auth cluster required = cephx
mon host = 10.123.5.29
mon initial members = 10_123_5_29
fsid = eeabaeaf-4eb0-468a-a0e0-a3a3bece28af
debug ms = 1/5
[mon]
mon data = "">debug mon = 20
debug paxos = 1/5
debug auth = 2
[mon.0]
host = 10_123_5_29
mon addr = 10.123.5.29:6789
///////////////////////////////////////////////

ceph-mon.0.log:
2015-09-24 10:13:02.051630 7f5fbe06f700  4 mon.0@-1(probing) e0 probe_timeout 0x29201b0
2015-09-24 10:13:02.051651 7f5fbe06f700 10 mon.0@-1(probing) e0 bootstrap
2015-09-24 10:13:02.051653 7f5fbe06f700 10 mon.0@-1(probing) e0 sync_reset_requester
2015-09-24 10:13:02.051654 7f5fbe06f700 10 mon.0@-1(probing) e0 unregister_cluster_logger - not registered
2015-09-24 10:13:02.051656 7f5fbe06f700 10 mon.0@-1(probing) e0 cancel_probe_timeout (none scheduled)
2015-09-24 10:13:02.051658 7f5fbe06f700 10 mon.0@-1(probing) e0 _reset
2015-09-24 10:13:02.051659 7f5fbe06f700 10 mon.0@-1(probing) e0 cancel_probe_timeout (none scheduled)
2015-09-24 10:13:02.051661 7f5fbe06f700 10 mon.0@-1(probing) e0 timecheck_finish
2015-09-24 10:13:02.051663 7f5fbe06f700 10 mon.0@-1(probing) e0 scrub_reset
2015-09-24 10:13:02.051669 7f5fbe06f700 10 mon.0@-1(probing) e0 cancel_probe_timeout (none scheduled)
2015-09-24 10:13:02.051671 7f5fbe06f700 10 mon.0@-1(probing) e0 reset_probe_timeout 0x29201a0 after 2 seconds
2015-09-24 10:13:02.051679 7f5fbe06f700 10 mon.0@-1(probing) e0 probing other monitors
2015-09-24 10:13:02.051683 7f5fbe06f700  1 -- 10.123.5.29:6789/0 --> mon.0 0.0.0.0:0/1 -- mon_probe(probe eeabaeaf-4eb0-468a-a0e0-a3a3bece28af name 0 new) v6 -- ?+0 0x2d3b980
q12015-09-24 10:13:04.028927 7f5fbe06f700 11 mon.0@-1(probing) e0 tick
2015-09-24 10:13:04.028950 7f5fbe06f700 20 mon.0@-1(probing) e0 sync_trim_providers
2015-09-24 10:13:04.051741 7f5fbe06f700  4 mon.0@-1(probing) e0 probe_timeout 0x29201a0
2015-09-24 10:13:04.051753 7f5fbe06f700 10 mon.0@-1(probing) e0 bootstrap
2015-09-24 10:13:04.051755 7f5fbe06f700 10 mon.0@-1(probing) e0 sync_reset_requester
2015-09-24 10:13:04.051756 7f5fbe06f700 10 mon.0@-1(probing) e0 unregister_cluster_logger - not registered
2015-09-24 10:13:04.051758 7f5fbe06f700 10 mon.0@-1(probing) e0 cancel_probe_timeout (none scheduled)
2015-09-24 10:13:04.051760 7f5fbe06f700 10 mon.0@-1(probing) e0 _reset
2015-09-24 10:13:04.051761 7f5fbe06f700 10 mon.0@-1(probing) e0 cancel_probe_timeout (none scheduled)
2015-09-24 10:13:04.051762 7f5fbe06f700 10 mon.0@-1(probing) e0 timecheck_finish
2015-09-24 10:13:04.051765 7f5fbe06f700 10 mon.0@-1(probing) e0 scrub_reset
2015-09-24 10:13:04.051770 7f5fbe06f700 10 mon.0@-1(probing) e0 cancel_probe_timeout (none scheduled)
2015-09-24 10:13:04.051772 7f5fbe06f700 10 mon.0@-1(probing) e0 reset_probe_timeout 0x2920200 after 2 seconds
2015-09-24 10:13:04.051780 7f5fbe06f700 10 mon.0@-1(probing) e0 probing other monitors
2015-09-24 10:13:04.051783 7f5fbe06f700  1 -- 10.123.5.29:6789/0 --> mon.0 0.0.0.0:0/1 -- mon_probe(probe eeabaeaf-4eb0-468a-a0e0-a3a3bece28af name 0 new) v6 -- ?+0 0x2d3b700
///////////////////////////////////////////////
problem:
[root@10_123_5_29 /var/log/ceph]# ceph -w
2015-09-24 09:43:10.738514 7fb5e88ae700  0 monclient(hunting): authenticate timed out after 300
2015-09-24 09:43:10.738555 7fb5e88ae700  0 librados: client.admin authentication error (110) Connection timed out
Error connecting to cluster: TimedOut

_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com