ceph osd para baixo e rgw Tempo limite de inicialização, falha ao inicializar após a reinicialização

Question

Centos7.2, Ceph com 3 OSD, 1 MON em execução no mesmo nó. radosgw e todos os daemons estão rodando no mesmo nó, e tudo estava funcionando bem. Depois de reiniciar o servidor, todos os osd não podem se comunicar (parece) e o radosgw não funciona corretamente, diz o log:

2016-03-09 17:03:30.916678 7fc71bbce880  0 ceph version 0.94.6 (e832001feaf8c176593e0325c8298e3f16dfb403), process radosgw, pid 24181
2016-03-09 17:08:30.919245 7fc712da8700 -1 Initialization timeout, failed to initialize

ceph health mostra:

HEALTH_WARN 1760 pgs stale; 1760 pgs stuck stale; too many PGs per OSD (1760 > max 300); 2/2 in osds are down

e ceph osd tree dar:

ID WEIGHT  TYPE NAME               UP/DOWN REWEIGHT PRIMARY-AFFINITY
-1 2.01999 root default
-2 1.01999     host app112
 0 1.00000         osd.0              down  1.00000          1.00000
 1 0.01999         osd.1              down        0          1.00000
-3 1.00000     host node146
 2 1.00000         osd.2              down  1.00000          1.00000

e service ceph status resultados:

=== mon.app112 ===
mon.app112: running {"version":"0.94.6"}
=== osd.0 ===
osd.0: running {"version":"0.94.6"}
=== osd.1 ===
osd.1: running {"version":"0.94.6"}
=== osd.2 ===
osd.2: running {"version":"0.94.6"}
=== osd.0 ===
osd.0: running {"version":"0.94.6"}
=== osd.1 ===
osd.1: running {"version":"0.94.6"}
=== osd.2 ===
osd.2: running {"version":"0.94.6"}

e isso é service radosgw status :

Redirecting to /bin/systemctl status  radosgw.service
● ceph-radosgw.service - LSB: radosgw RESTful rados gateway
   Loaded: loaded (/etc/rc.d/init.d/ceph-radosgw)
   Active: active (exited) since Wed 2016-03-09 17:03:30 CST; 1 day 23h ago
     Docs: man:systemd-sysv-generator(8)
  Process: 24134 ExecStop=/etc/rc.d/init.d/ceph-radosgw stop (code=exited, status=0/SUCCESS)
  Process: 2890 ExecReload=/etc/rc.d/init.d/ceph-radosgw reload (code=exited, status=0/SUCCESS)
  Process: 24153 ExecStart=/etc/rc.d/init.d/ceph-radosgw start (code=exited, status=0/SUCCESS)

Vendo isso, eu tentei o sudo /etc/init.d/ceph -a start osd.1 e parei por algumas vezes, mas o resultado é o mesmo que acima.

sudo /etc/init.d/ceph -a stop osd.1
=== osd.1 ===
Stopping Ceph osd.1 on open-kvm-app92...kill 12688...kill 12688...done

sudo /etc/init.d/ceph -a start osd.1
=== osd.1 ===
create-or-move updated item name 'osd.1' weight 0.02 at location {host=open-kvm-app92,root=default} to crush map
Starting Ceph osd.1 on open-kvm-app92...
Running as unit ceph-osd.1.1457684205.040980737.service.

Por favor ajude. obrigado

EDITAR: parece que mon não pode falar com osd. mas ambos daemons estão rodando ok. o log do osd mostra:

2016-03-11 17:35:21.649712 7f003c633700  5 osd.0 234 tick
2016-03-11 17:35:22.649982 7f003c633700  5 osd.0 234 tick
2016-03-11 17:35:23.650262 7f003c633700  5 osd.0 234 tick
2016-03-11 17:35:24.650538 7f003c633700  5 osd.0 234 tick
2016-03-11 17:35:25.650807 7f003c633700  5 osd.0 234 tick
2016-03-11 17:35:25.779693 7f0024c96700  5 osd.0 234 heartbeat: osd_stat(6741 MB used, 9119 MB avail, 15861 MB total, peers []/[] op hist [])
2016-03-11 17:35:26.651059 7f003c633700  5 osd.0 234 tick
2016-03-11 17:35:27.651314 7f003c633700  5 osd.0 234 tick
2016-03-11 17:35:28.080165 7f0024c96700  5 osd.0 234 heartbeat: osd_stat(6741 MB used, 9119 MB avail, 15861 MB total, peers []/[] op hist [])