Joshua it looks like you got Ceph from EPEL (that version has the '-2' slapped on it). And it is why you are seeing this for ceph: ceph-0.80.1-2.el6.x86_64 And this for others: libcephfs1-0.80.1-0.el6.x86_64 Make sure that you do get Ceph from our repos. Newer versions of ceph-deploy fix this by installing the priority plugin and making sure the ceph.repo file will have higher priority than EPEL. On Fri, Jul 11, 2014 at 1:31 AM, Joshua McClintock <joshua at gravityedge.com> wrote: > [root at chefwks01 ~]# ceph --cluster us-west01 osd crush dump > > { "devices": [ > > { "id": 0, > > "name": "osd.0"}, > > { "id": 1, > > "name": "osd.1"}, > > { "id": 2, > > "name": "osd.2"}, > > { "id": 3, > > "name": "osd.3"}, > > { "id": 4, > > "name": "osd.4"}], > > "types": [ > > { "type_id": 0, > > "name": "osd"}, > > { "type_id": 1, > > "name": "host"}, > > { "type_id": 2, > > "name": "chassis"}, > > { "type_id": 3, > > "name": "rack"}, > > { "type_id": 4, > > "name": "row"}, > > { "type_id": 5, > > "name": "pdu"}, > > { "type_id": 6, > > "name": "pod"}, > > { "type_id": 7, > > "name": "room"}, > > { "type_id": 8, > > "name": "datacenter"}, > > { "type_id": 9, > > "name": "region"}, > > { "type_id": 10, > > "name": "root"}], > > "buckets": [ > > { "id": -1, > > "name": "default", > > "type_id": 10, > > "type_name": "root", > > "weight": 147455, > > "alg": "straw", > > "hash": "rjenkins1", > > "items": [ > > { "id": -2, > > "weight": 29491, > > "pos": 0}, > > { "id": -3, > > "weight": 29491, > > "pos": 1}, > > { "id": -4, > > "weight": 29491, > > "pos": 2}, > > { "id": -5, > > "weight": 29491, > > "pos": 3}, > > { "id": -6, > > "weight": 29491, > > "pos": 4}]}, > > { "id": -2, > > "name": "ceph-node20", > > "type_id": 1, > > "type_name": "host", > > "weight": 29491, > > "alg": "straw", > > "hash": "rjenkins1", > > "items": [ > > { "id": 0, > > "weight": 29491, > > "pos": 0}]}, > > { "id": -3, > > "name": "ceph-node22", > > "type_id": 1, > > "type_name": "host", > > "weight": 29491, > > "alg": "straw", > > "hash": "rjenkins1", > > "items": [ > > { "id": 2, > > "weight": 29491, > > "pos": 0}]}, > > { "id": -4, > > "name": "ceph-node24", > > "type_id": 1, > > "type_name": "host", > > "weight": 29491, > > "alg": "straw", > > "hash": "rjenkins1", > > "items": [ > > { "id": 4, > > "weight": 29491, > > "pos": 0}]}, > > { "id": -5, > > "name": "ceph-node21", > > "type_id": 1, > > "type_name": "host", > > "weight": 29491, > > "alg": "straw", > > "hash": "rjenkins1", > > "items": [ > > { "id": 1, > > "weight": 29491, > > "pos": 0}]}, > > { "id": -6, > > "name": "ceph-node23", > > "type_id": 1, > > "type_name": "host", > > "weight": 29491, > > "alg": "straw", > > "hash": "rjenkins1", > > "items": [ > > { "id": 3, > > "weight": 29491, > > "pos": 0}]}], > > "rules": [ > > { "rule_id": 0, > > "rule_name": "replicated_ruleset", > > "ruleset": 0, > > "type": 1, > > "min_size": 1, > > "max_size": 10, > > "steps": [ > > { "op": "take", > > "item": -1, > > "item_name": "default"}, > > { "op": "chooseleaf_firstn", > > "num": 0, > > "type": "host"}, > > { "op": "emit"}]}, > > { "rule_id": 1, > > "rule_name": "erasure-code", > > "ruleset": 1, > > "type": 3, > > "min_size": 3, > > "max_size": 20, > > "steps": [ > > { "op": "set_chooseleaf_tries", > > "num": 5}, > > { "op": "take", > > "item": -1, > > "item_name": "default"}, > > { "op": "chooseleaf_indep", > > "num": 0, > > "type": "host"}, > > { "op": "emit"}]}, > > { "rule_id": 2, > > "rule_name": "ecpool", > > "ruleset": 2, > > "type": 3, > > "min_size": 3, > > "max_size": 20, > > "steps": [ > > { "op": "set_chooseleaf_tries", > > "num": 5}, > > { "op": "take", > > "item": -1, > > "item_name": "default"}, > > { "op": "choose_indep", > > "num": 0, > > "type": "osd"}, > > { "op": "emit"}]}], > > "tunables": { "choose_local_tries": 0, > > "choose_local_fallback_tries": 0, > > "choose_total_tries": 50, > > "chooseleaf_descend_once": 1, > > "profile": "bobtail", > > "optimal_tunables": 0, > > "legacy_tunables": 0, > > "require_feature_tunables": 1, > > "require_feature_tunables2": 1}} > > > > On Thu, Jul 10, 2014 at 8:16 PM, Sage Weil <sweil at redhat.com> wrote: >> >> That is CEPH_FEATURE_CRUSH_V2. Can you attach teh output of >> >> ceph osd crush dump >> >> Thanks! >> sage >> >> >> On Thu, 10 Jul 2014, Joshua McClintock wrote: >> >> > Yes, I change some of the mount options on my osds (xfs mount options), >> > but >> > I think this may be the answer from dmesg, sorta looks like a version >> > mismatch: >> > >> > libceph: loaded (mon/osd proto 15/24) >> > >> > ceph: loaded (mds proto 32) >> > >> > libceph: mon0 192.168.0.14:6789 feature set mismatch, my 4a042aca < >> > server's >> > 104a042aca, missing 1000000000 >> > >> > libceph: mon0 192.168.0.14:6789 socket error on read >> > >> > libceph: mon2 192.168.0.16:6789 feature set mismatch, my 4a042aca < >> > server's >> > 104a042aca, missing 1000000000 >> > >> > libceph: mon2 192.168.0.16:6789 socket error on read >> > >> > libceph: mon1 192.168.0.15:6789 feature set mismatch, my 4a042aca < >> > server's >> > 104a042aca, missing 1000000000 >> > >> > libceph: mon1 192.168.0.15:6789 socket error on read >> > >> > libceph: mon0 192.168.0.14:6789 feature set mismatch, my 4a042aca < >> > server's >> > 104a042aca, missing 1000000000 >> > >> > libceph: mon0 192.168.0.14:6789 socket error on read >> > >> > libceph: mon2 192.168.0.16:6789 feature set mismatch, my 4a042aca < >> > server's >> > 104a042aca, missing 1000000000 >> > >> > libceph: mon2 192.168.0.16:6789 socket error on read >> > >> > libceph: mon1 192.168.0.15:6789 feature set mismatch, my 4a042aca < >> > server's >> > 104a042aca, missing 1000000000 >> > >> > libceph: mon1 192.168.0.15:6789 socket error on read >> > >> > >> > I maybe I didn't update as well as I thought it did. I did hit every >> > mon, >> > but I remember I couldn't upgrade to the new 'ceph' package because it >> > conflicted with 'python-ceph', so I uninstalled it (python-ceph), and >> > then >> > upgraded to .80.1-2. Maybe there's a subcomponent I missed? >> > >> > >> > Here's rpm -qa from the client: >> > >> > >> > [root at chefwks01 ~]# rpm -qa|grep ceph >> > >> > ceph-deploy-1.5.2-0.noarch >> > >> > ceph-release-1-0.el6.noarch >> > >> > ceph-0.80.1-2.el6.x86_64 >> > >> > libcephfs1-0.80.1-0.el6.x86_64 >> > >> > >> > Here's rpm -qa from the mons: >> > >> > >> > [root at ceph-mon01 ~]# rpm -qa|grep ceph >> > >> > ceph-0.80.1-2.el6.x86_64 >> > >> > ceph-release-1-0.el6.noarch >> > >> > libcephfs1-0.80.1-0.el6.x86_64 >> > >> > [root at ceph-mon01 ~]# >> > >> > >> > [root at ceph-mon02 ~]# rpm -qa|grep ceph >> > >> > libcephfs1-0.80.1-0.el6.x86_64 >> > >> > ceph-0.80.1-2.el6.x86_64 >> > >> > ceph-release-1-0.el6.noarch >> > >> > [root at ceph-mon02 ~]# >> > >> > >> > [root at ceph-mon03 ~]# rpm -qa|grep ceph >> > >> > libcephfs1-0.80.1-0.el6.x86_64 >> > >> > ceph-0.80.1-2.el6.x86_64 >> > >> > ceph-release-1-0.el6.noarch >> > >> > [root at ceph-mon03 ~]# >> > >> > >> > Joshua >> > >> > >> > >> > On Thu, Jul 10, 2014 at 6:04 PM, Sage Weil <sweil at redhat.com> wrote: >> > Have you made any other changes after the upgrade? (Like >> > adjusting >> > tunables, or creating EC pools?) >> > >> > See if there is anything in 'dmesg' output. >> > >> > sage >> > >> > On Thu, 10 Jul 2014, Joshua McClintock wrote: >> > >> > > I upgraded my cluster to .80.1-2 (CentOS). My mount command >> > just freezes >> > > and outputs an error: >> > > >> > > mount.ceph 192.168.0.14,192.168.0.15,192.168.0.16:/ /us-west01 >> > -o >> > > name=chefwks01,secret=`ceph-authtool -p -n client.admin >> > > /etc/ceph/us-west01.client.admin.keyring` >> > > >> > > mount error 5 = Input/output error >> > > >> > > >> > > Here's the output from 'ceph -s' >> > > >> > > >> > > cluster xxxxxxxxxxxxxxxxxxxxxx >> > > >> > > health HEALTH_OK >> > > >> > > monmap e1: 3 >> > monsat{ceph-mon01=192.168.0.14:6789/0,ceph-mon02=192.168.0.15:6789/0,ceph-mon03 >> > =1 >> > > 92.168.0.16:6789/0}, election epoch 88, quorum 0,1,2 >> > > ceph-mon01,ceph-mon02,ceph-mon03 >> > > >> > > mdsmap e26: 1/1/1 up {0=0=up:active} >> > > >> > > osdmap e1371: 5 osds: 5 up, 5 in >> > > >> > > pgmap v49431: 192 pgs, 3 pools, 135 GB data, 34733 >> > objects >> > > >> > > 406 GB used, 1874 GB / 2281 GB avail >> > > >> > > 192 active+clean >> > > >> > > >> > > I can see some packets being exchanged between the client and >> > the mon, but >> > > it's a pretty short exchange. >> > > >> > > Any ideas where to look next? >> > > >> > > Joshua >> > > >> > > >> > > >> > >> > >> > >> > > > > > _______________________________________________ > ceph-users mailing list > ceph-users at lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >