Across the whole cluster, 2 OSDs out of 12 failed to activate:
2014-07-11 06:18:46.948432 mon.0 10.108.7.3:6789/0 122 : [INF] osdmap e61: 12 osds: 10 up, 12 in
At the end of ceph.log on node-1, there's a number of slow requests:
2014-07-11 06:19:38.746562 osd.9 10.108.7.7:6800/24689 2 : [WRN] slow request 30.154477 seconds old, received at 2014-07-11 06:19:08.592017: osd_op(client.4777.0:1 00109b68-f1b2-4e8d-90e4-ebb4b5eeffe0.rbd [stat] 3.82587b08 e61) v4 currently reached pg
...
2014-07-11 06:21:09.288881 osd.10 10.108.7.8:6802/24827 4 : [WRN] slow request 60.062250 seconds old, received at 2014-07-11 06:20:09.226564: osd_op(client.4783.0:14 rbd_data.12af32850276.0000000000000000 [write 0~8388608] 3.29b77010 e61) v4 currently reached pg
Could be that Glance image upload timed out due to Ceph OSD cluster rebalance following failure of 2 OSDs.
Across the whole cluster, 2 OSDs out of 12 failed to activate:
2014-07-11 06:18:46.948432 mon.0 10.108.7.3:6789/0 122 : [INF] osdmap e61: 12 osds: 10 up, 12 in
At the end of ceph.log on node-1, there's a number of slow requests: 7.7:6800/ 24689 2 : [WRN] slow request 30.154477 seconds old, received at 2014-07-11 06:19:08.592017: osd_op( client. 4777.0: 1 00109b68- f1b2-4e8d- 90e4-ebb4b5eeff e0.rbd [stat] 3.82587b08 e61) v4 currently reached pg 7.8:6802/ 24827 4 : [WRN] slow request 60.062250 seconds old, received at 2014-07-11 06:20:09.226564: osd_op( client. 4783.0: 14 rbd_data. 12af32850276. 000000000000000 0 [write 0~8388608] 3.29b77010 e61) v4 currently reached pg
2014-07-11 06:19:38.746562 osd.9 10.108.
...
2014-07-11 06:21:09.288881 osd.10 10.108.
Could be that Glance image upload timed out due to Ceph OSD cluster rebalance following failure of 2 OSDs.