Hi all, Thanks for you all. Like Mark's information this problem is releate to CRUSH Map. After create 2 OSDs on 2 different host, healthy check is OK. Appreciate the information again~
Best wishes, Mika 2014-10-29 17:19 GMT+08:00 Vickie CH <[email protected]>: > Hi： > -----------------------------ceph osd > tree----------------------------------- > # id weight type name up/down reweight > -1 1.82 root default > -2 1.82 host storage1 > 0 0.91 osd.0 up 1 > 1 0.91 osd.1 up 1 > > Best wishes, > Mika > > 2014-10-29 17:05 GMT+08:00 Irek Fasikhov <[email protected]>: > >> ceph osd tree please :) >> >> 2014-10-29 12:03 GMT+03:00 Vickie CH <[email protected]>: >> >>> Dear all, >>> Thanks for the reply. >>> Pool replicated size is 2. Because the replicated size parameter already >>> write into ceph.conf before deploy. >>> Because not familiar crush map. I will according Mark's information to >>> do a test that change the crush map to see the result. >>> >>> -----------ceph.conf------------------ >>> [global] >>> fsid = c404ded6-4086-4f0b-b479- >>> 89bc018af954 >>> mon_initial_members = storage0 >>> mon_host = 192.168.1.10 >>> auth_cluster_required = cephx >>> auth_service_required = cephx >>> auth_client_required = cephx >>> filestore_xattr_use_omap = true >>> >>> *osd_pool_default_size = 2osd_pool_default_min_size = 1* >>> osd_pool_default_pg_num = 128 >>> osd_journal_size = 2048 >>> osd_pool_default_pgp_num = 128 >>> osd_mkfs_type = xfs >>> ------------------------------------------- >>> >>> ----------------------ceph osd dump result ----------------------------- >>> pool 0 'data' replicated size 2 min_size 1 crush_ruleset 0 object_hash >>> rjenkins pg_num 64 pgp_num 64 last_change 14 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 15 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 16 flags hashpspool stripe_width 0 >>> max_osd 2 >>> >>> ------------------------------------------------------------------------------ >>> >>> Best wishes, >>> Mika >>> >>> Best wishes, >>> Mika >>> >>> 2014-10-29 16:56 GMT+08:00 Mark Kirkwood <[email protected]> >>> : >>> >>>> That is not my experience: >>>> >>>> $ ceph -v >>>> ceph version 0.86-579-g06a73c3 (06a73c39169f2f332dec760f56d3ec >>>> 20455b1646) >>>> >>>> $ cat /etc/ceph/ceph.conf >>>> [global] >>>> ... >>>> osd pool default size = 2 >>>> >>>> $ ceph osd dump|grep size >>>> pool 2 'hot' replicated size 2 min_size 1 crush_ruleset 0 object_hash >>>> rjenkins pg_num 128 pgp_num 128 last_change 47 flags >>>> hashpspool,incomplete_clones tier_of 1 cache_mode writeback target_bytes >>>> 2000000000 hit_set bloom{false_positive_probability: 0.05, >>>> target_size: 0, seed: 0} 3600s x1 stripe_width 0 >>>> pool 10 '.rgw.root' replicated size 2 min_size 1 crush_ruleset 0 >>>> object_hash rjenkins pg_num 8 pgp_num 8 last_change 102 owner >>>> 18446744073709551615 flags hashpspool stripe_width 0 >>>> pool 11 '.rgw.control' replicated size 2 min_size 1 crush_ruleset 0 >>>> object_hash rjenkins pg_num 8 pgp_num 8 last_change 104 owner >>>> 18446744073709551615 flags hashpspool stripe_width 0 >>>> pool 12 '.rgw' replicated size 2 min_size 1 crush_ruleset 0 object_hash >>>> rjenkins pg_num 8 pgp_num 8 last_change 106 owner 18446744073709551615 >>>> flags hashpspool stripe_width 0 >>>> pool 13 '.rgw.gc' replicated size 2 min_size 1 crush_ruleset 0 >>>> object_hash rjenkins pg_num 8 pgp_num 8 last_change 107 owner >>>> 18446744073709551615 flags hashpspool stripe_width 0 >>>> pool 14 '.users.uid' replicated size 2 min_size 1 crush_ruleset 0 >>>> object_hash rjenkins pg_num 8 pgp_num 8 last_change 108 owner >>>> 18446744073709551615 flags hashpspool stripe_width 0 >>>> pool 15 '.rgw.buckets.index' replicated size 2 min_size 1 crush_ruleset >>>> 0 object_hash rjenkins pg_num 8 pgp_num 8 last_change 110 owner >>>> 18446744073709551615 flags hashpspool stripe_width 0 >>>> pool 16 '.rgw.buckets' replicated size 2 min_size 1 crush_ruleset 0 >>>> object_hash rjenkins pg_num 8 pgp_num 8 last_change 112 owner >>>> 18446744073709551615 flags hashpspool stripe_width 0 >>>> pool 17 'rbd' replicated size 2 min_size 1 crush_ruleset 0 object_hash >>>> rjenkins pg_num 1024 pgp_num 1024 last_change 186 flags hashpspool >>>> stripe_width 0 >>>> >>>> >>>> >>>> >>>> >>>> >>>> On 29/10/14 21:46, Irek Fasikhov wrote: >>>> >>>>> Hi. >>>>> This parameter does not apply to pools by default. >>>>> ceph osd dump | grep pool. see size=? >>>>> >>>>> >>>>> 2014-10-29 11:40 GMT+03:00 Vickie CH <[email protected] >>>>> <mailto:[email protected]>>: >>>>> >>>>> Der Irek： >>>>> >>>>> Thanks for your reply. >>>>> Even already set "osd_pool_default_size = 2" the cluster still need >>>>> 3 different hosts right？ >>>>> Is this default number can be changed by user and write into >>>>> ceph.conf before deploy？ >>>>> >>>>> >>>>> Best wishes, >>>>> Mika >>>>> >>>>> 2014-10-29 16:29 GMT+08:00 Irek Fasikhov <[email protected] >>>>> <mailto:[email protected]>>: >>>>> >>>>> Hi. >>>>> >>>>> Because the disc requires three different hosts, the default >>>>> number of replications 3. >>>>> >>>>> 2014-10-29 10:56 GMT+03:00 Vickie CH <[email protected] >>>>> <mailto:[email protected]>>: >>>>> >>>>> >>>>> Hi all, >>>>> Try to use two OSDs to create a cluster. After the >>>>> deply finished, I found the health status is "88 >>>>> active+degraded" "104 active+remapped". Before use 2 osds >>>>> to >>>>> create cluster the result is ok. I'm confuse why this >>>>> situation happened. Do I need to set crush map to fix this >>>>> problem？ >>>>> >>>>> >>>>> ----------ceph.conf--------------------------------- >>>>> [global] >>>>> fsid = c404ded6-4086-4f0b-b479-89bc018af954 >>>>> mon_initial_members = storage0 >>>>> mon_host = 192.168.1.10 >>>>> auth_cluster_required = cephx >>>>> auth_service_required = cephx >>>>> auth_client_required = cephx >>>>> filestore_xattr_use_omap = true >>>>> osd_pool_default_size = 2 >>>>> osd_pool_default_min_size = 1 >>>>> osd_pool_default_pg_num = 128 >>>>> osd_journal_size = 2048 >>>>> osd_pool_default_pgp_num = 128 >>>>> osd_mkfs_type = xfs >>>>> --------------------------------------------------------- >>>>> >>>>> -----------ceph -s----------------------------------- >>>>> cluster c404ded6-4086-4f0b-b479-89bc018af954 >>>>> health HEALTH_WARN 88 pgs degraded; 192 pgs stuck >>>>> unclean >>>>> monmap e1: 1 mons at {storage0=192.168.10.10:6789/0 >>>>> <http://192.168.10.10:6789/0>}, election epoch 2, quorum 0 >>>>> storage0 >>>>> osdmap e20: 2 osds: 2 up, 2 in >>>>> pgmap v45: 192 pgs, 3 pools, 0 bytes data, 0 objects >>>>> 79752 kB used, 1858 GB / 1858 GB avail >>>>> 88 active+degraded >>>>> 104 active+remapped >>>>> -------------------------------------------------------- >>>>> >>>>> >>>>> Best wishes, >>>>> Mika >>>>> >>>>> _______________________________________________ >>>>> ceph-users mailing list >>>>> [email protected] <mailto:[email protected]. >>>>> com> >>>>> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >>>>> >>>>> >>>>> >>>>> >>>>> -- >>>>> С уважением, Фасихов Ирек Нургаязович >>>>> Моб.: +79229045757 >>>>> >>>>> >>>>> >>>>> >>>>> >>>>> -- >>>>> С уважением, Фасихов Ирек Нургаязович >>>>> Моб.: +79229045757 >>>>> >>>>> >>>>> _______________________________________________ >>>>> 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
