When I first created a test cluster, I used 1 GiB disks.  That causes
problems.

Ceph has a CRUSH weight.  By default, the weight is the size of the disk in
TiB, truncated to 2 decimal places.  ie, any disk smaller than 10 GiB will
have a weight of 0.00.

I increased all of my virtual disks to 10 GiB.  After rebooting the nodes
(to see the changes), everything healed.


On Tue, Dec 9, 2014 at 9:45 AM, Gregory Farnum <[email protected]> wrote:

> It looks like your OSDs all have weight zero for some reason. I'd fix
> that. :)
> -Greg
>
> On Tue, Dec 9, 2014 at 6:24 AM Giuseppe Civitella <
> [email protected]> wrote:
>
>> Hi,
>>
>> thanks for the quick answer.
>> I did try the force_create_pg on a pg but is stuck on "creating":
>> root@ceph-mon1:/home/ceph# ceph pg dump |grep creating
>> dumped all in format plain
>> 2.2f    0       0       0       0       0       0       0       creating
>>        2014-12-09 13:11:37.384808      0'0     0:0     []      -1      []
>>    -1      0'0     0.0000000'0      0.000000
>>
>> root@ceph-mon1:/home/ceph# ceph pg 2.2f query
>> { "state": "active+degraded",
>>   "epoch": 105,
>>   "up": [
>>         0],
>>   "acting": [
>>         0],
>>   "actingbackfill": [
>>         "0"],
>>   "info": { "pgid": "2.2f",
>>       "last_update": "0'0",
>>       "last_complete": "0'0",
>>       "log_tail": "0'0",
>>       "last_user_version": 0,
>>       "last_backfill": "MAX",
>>       "purged_snaps": "[]",
>>           "last_scrub": "0'0",
>>           "last_scrub_stamp": "2014-12-06 14:15:11.499769",
>>           "last_deep_scrub": "0'0",
>>           "last_deep_scrub_stamp": "2014-12-06 14:15:11.499769",
>>           "last_clean_scrub_stamp": "0.000000",
>>           "log_size": 0,
>>           "ondisk_log_size": 0,
>>           "stats_invalid": "0",
>>           "stat_sum": { "num_bytes": 0,
>>               "num_objects": 0,
>>               "num_object_clones": 0,
>>               "num_object_copies": 0,
>>               "num_objects_missing_on_primary": 0,
>>               "num_objects_degraded": 0,
>>               "num_objects_unfound": 0,
>>               "num_objects_dirty": 0,
>>               "num_whiteouts": 0,
>>               "num_read": 0,
>>               "num_read_kb": 0,
>>               "num_write": 0,
>>               "num_write_kb": 0,
>>               "num_scrub_errors": 0,
>>               "num_shallow_scrub_errors": 0,
>>               "num_deep_scrub_errors": 0,
>>               "num_objects_recovered": 0,
>>               "num_bytes_recovered": 0,
>>               "num_keys_recovered": 0,
>>               "num_objects_omap": 0,
>>               "num_objects_hit_set_archive": 0},
>>           "stat_cat_sum": {},
>>           "up": [
>>                 0],
>>           "acting": [
>>                 0],
>>           "up_primary": 0,
>>           "acting_primary": 0},
>>       "empty": 1,
>>       "dne": 0,
>>       "incomplete": 0,
>>       "last_epoch_started": 104,
>>       "hit_set_history": { "current_last_update": "0'0",
>>           "current_last_stamp": "0.000000",
>>           "current_info": { "begin": "0.000000",
>>               "end": "0.000000",
>>               "version": "0'0"},
>>           "history": []}},
>>   "peer_info": [],
>>   "recovery_state": [
>>         { "name": "Started\/Primary\/Active",
>>           "enter_time": "2014-12-09 12:12:52.760384",
>>           "might_have_unfound": [],
>>           "recovery_progress": { "backfill_targets": [],
>>               "waiting_on_backfill": [],
>>               "last_backfill_started": "0\/\/0\/\/-1",
>>               "backfill_info": { "begin": "0\/\/0\/\/-1",
>>                   "end": "0\/\/0\/\/-1",
>>                   "objects": []},
>>               "peer_backfill_info": [],
>>               "backfills_in_flight": [],
>>               "recovering": [],
>>               "pg_backend": { "pull_from_peer": [],
>>                   "pushing": []}},
>>           "scrub": { "scrubber.epoch_start": "0",
>>               "scrubber.active": 0,
>>               "scrubber.block_writes": 0,
>>               "scrubber.finalizing": 0,
>>               "scrubber.waiting_on": 0,
>>               "scrubber.waiting_on_whom": []}},
>>         { "name": "Started",
>>           "enter_time": "2014-12-09 12:12:51.845686"}],
>>   "agent_state": {}}root@ceph-mon1:/home/ceph#
>>
>>
>>
>> 2014-12-09 13:01 GMT+01:00 Irek Fasikhov <[email protected]>:
>>
>>> Hi.
>>>
>>> http://ceph.com/docs/master/rados/troubleshooting/troubleshooting-pg/
>>>
>>> ceph pg force_create_pg <pgid>
>>>
>>>
>>> 2014-12-09 14:50 GMT+03:00 Giuseppe Civitella <
>>> [email protected]>:
>>>
>>>> Hi all,
>>>>
>>>> last week I installed a new ceph cluster on 3 vm running Ubuntu 14.04
>>>> with default kernel.
>>>> There is a ceph monitor a two osd hosts. Here are some datails:
>>>> ceph -s
>>>>     cluster c46d5b02-dab1-40bf-8a3d-f8e4a77b79da
>>>>      health HEALTH_WARN 192 pgs degraded; 192 pgs stuck unclean
>>>>      monmap e1: 1 mons at {ceph-mon1=10.1.1.83:6789/0}, election epoch
>>>> 1, quorum 0 ceph-mon1
>>>>      osdmap e83: 6 osds: 6 up, 6 in
>>>>       pgmap v231: 192 pgs, 3 pools, 0 bytes data, 0 objects
>>>>             207 MB used, 30446 MB / 30653 MB avail
>>>>                  192 active+degraded
>>>>
>>>> root@ceph-mon1:/home/ceph# ceph osd dump
>>>> epoch 99
>>>> fsid c46d5b02-dab1-40bf-8a3d-f8e4a77b79da
>>>> created 2014-12-06 13:15:06.418843
>>>> modified 2014-12-09 11:38:04.353279
>>>> flags
>>>> pool 0 'data' replicated size 2 min_size 1 crush_ruleset 0 object_hash
>>>> rjenkins pg_num 64 pgp_num 64 last_change 18 flags hashpspool
>>>> crash_replay_interval 45 stripe_width 0
>>>> pool 1 'metadata' replicated size 2 min_size 1 crush_ruleset 0
>>>> object_hash rjenkins pg_num 64 pgp_num 64 last_change 19 flags hashpspool
>>>> stripe_width 0
>>>> pool 2 'rbd' replicated size 2 min_size 1 crush_ruleset 0 object_hash
>>>> rjenkins pg_num 64 pgp_num 64 last_change 20 flags hashpspool stripe_width >>>> 0
>>>> max_osd 6
>>>> osd.0 up   in  weight 1 up_from 90 up_thru 90 down_at 89
>>>> last_clean_interval [58,89) 10.1.1.84:6805/995 10.1.1.84:6806/4000995
>>>> 10.1.1.84:6807/4000995 10.1.1.84:6808/4000995 exists,up
>>>> e3895075-614d-48e2-b956-96e13dbd87fe
>>>> osd.1 up   in  weight 1 up_from 88 up_thru 0 down_at 87
>>>> last_clean_interval [8,87) 10.1.1.85:6800/23146 10.1.1.85:6815/7023146
>>>> 10.1.1.85:6816/7023146 10.1.1.85:6817/7023146 exists,up
>>>> 144bc6ee-2e3d-4118-a460-8cc2bb3ec3e8
>>>> osd.2 up   in  weight 1 up_from 61 up_thru 0 down_at 60
>>>> last_clean_interval [11,60) 10.1.1.85:6805/26784 10.1.1.85:6802/5026784
>>>> 10.1.1.85:6811/5026784 10.1.1.85:6812/5026784 exists,up
>>>> 8d5c7108-ef11-4947-b28c-8e20371d6d78
>>>> osd.3 up   in  weight 1 up_from 95 up_thru 0 down_at 94
>>>> last_clean_interval [57,94) 10.1.1.84:6800/810 10.1.1.84:6810/3000810
>>>> 10.1.1.84:6811/3000810 10.1.1.84:6812/3000810 exists,up
>>>> bd762b2d-f94c-4879-8865-cecd63895557
>>>> osd.4 up   in  weight 1 up_from 97 up_thru 0 down_at 96
>>>> last_clean_interval [74,96) 10.1.1.84:6801/9304 10.1.1.84:6802/2009304
>>>> 10.1.1.84:6803/2009304 10.1.1.84:6813/2009304 exists,up
>>>> 7d28a54b-b474-4369-b958-9e6bf6c856aa
>>>> osd.5 up   in  weight 1 up_from 99 up_thru 0 down_at 98
>>>> last_clean_interval [79,98) 10.1.1.85:6801/19513 10.1.1.85:6808/2019513
>>>> 10.1.1.85:6810/2019513 10.1.1.85:6813/2019513 exists,up
>>>> f4d76875-0e40-487c-a26d-320f8b8d60c5
>>>>
>>>> root@ceph-mon1:/home/ceph# ceph osd tree
>>>> # id    weight  type name       up/down reweight
>>>> -1      0       root default
>>>> -2      0               host ceph-osd1
>>>> 0       0                       osd.0   up      1
>>>> 3       0                       osd.3   up      1
>>>> 4       0                       osd.4   up      1
>>>> -3      0               host ceph-osd2
>>>> 1       0                       osd.1   up      1
>>>> 2       0                       osd.2   up      1
>>>> 5       0                       osd.5   up      1
>>>>
>>>> Current HEALTH_WARN state says "192 active+degraded" since I rebooted
>>>> an osd host. Previously it was "incomplete". It never reached a HEALTH_OK
>>>> state.
>>>> Any hint about what to do next to have an healthy cluster?
>>>>
>>>>
>>>> _______________________________________________
>>>> ceph-users mailing list
>>>> [email protected]
>>>> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
>>>>
>>>>
>>>
>>>
>>> --
>>> С уважением, Фасихов Ирек Нургаязович
>>> Моб.: +79229045757
>>>
>>
>> _______________________________________________
>> ceph-users mailing list
>> [email protected]
>> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
>>
>
> _______________________________________________
> ceph-users mailing list
> [email protected]
> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
>
>
_______________________________________________
ceph-users mailing list
[email protected]
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com

Reply via email to