Re: ceph-mds failure replaying journal

"Yan, Zheng" <ukernel@xxxxxxxxx> · Mon, 29 Oct 2018 16:19:39 +0800

We backported a wrong patch to 13.2.2.  downgrade ceph to 13.2.1, then run 'ceph mds repaired fido_fs:1" .
Sorry for the trouble
Yan, Zheng

On Mon, Oct 29, 2018 at 7:48 AM Jon Morby <jon@xxxxxxxx> wrote:

We accidentally found ourselves upgraded from 12.2.8 to 13.2.2 after a ceph-deploy install went awry (we were expecting it to upgrade to 12.2.9 and not jump a major release without warning)

Anyway .. as a result, we ended up with an mds journal error and 1 daemon reporting as damaged

Having got nowhere trying to ask for help on irc, we've followed various forum posts and disaster recovery guides, we ended up resetting the journal which left the daemon as no longer “damaged” however we’re now seeing mds segfault whilst trying to replay 

https://pastebin.com/iSLdvu0b

/build/ceph-13.2.2/src/mds/journal.cc: 1572: FAILED assert(g_conf->mds_wipe_sessions)

 ceph version 13.2.2 (02899bfda814146b021136e9d8e80eba494e1126) mimic (stable)
 1: (ceph::__ceph_assert_fail(char const*, char const*, int, char const*)+0x102) [0x7fad637f70f2]
 2: (()+0x3162b7) [0x7fad637f72b7]
 3: (EMetaBlob::replay(MDSRank*, LogSegment*, MDSlaveUpdate*)+0x5f4b) [0x7a7a6b]
 4: (EUpdate::replay(MDSRank*)+0x39) [0x7a8fa9]
 5: (MDLog::_replay_thread()+0x864) [0x752164]
 6: (MDLog::ReplayThread::entry()+0xd) [0x4f021d]
 7: (()+0x76ba) [0x7fad6305a6ba]
 8: (clone()+0x6d) [0x7fad6288341d]
 NOTE: a copy of the executable, or `objdump -rdS <executable>` is needed to interpret this.

full logs

https://pastebin.com/X5UG9vT2

We’ve been unable to access the cephfs file system since all of this started …. attempts to mount fail with reports that “mds probably not available” 

Oct 28 23:47:02 mirrors kernel: [115602.911193] ceph: probably no mds server is up

root@mds02:~# ceph -s
  cluster:
    id:     78d5bf7d-b074-47ab-8d73-bd4d99df98a5
    health: HEALTH_WARN
            1 filesystem is degraded
            insufficient standby MDS daemons available
            too many PGs per OSD (276 > max 250)

  services:
    mon: 3 daemons, quorum mon01,mon02,mon03
    mgr: mon01(active), standbys: mon02, mon03
    mds: fido_fs-2/2/1 up  {0=mds01=up:resolve,1=mds02=up:replay(laggy or crashed)}
    osd: 27 osds: 27 up, 27 in

  data:
    pools:   15 pools, 3168 pgs
    objects: 16.97 M objects, 30 TiB
    usage:   71 TiB used, 27 TiB / 98 TiB avail
    pgs:     3168 active+clean

  io:
    client:   680 B/s rd, 1.1 MiB/s wr, 0 op/s rd, 345 op/s wr

Before I just trash the entire fs and give up on ceph, does anyone have any suggestions as to how we can fix this?

root@mds02:~# ceph versions
{
    "mon": {
        "ceph version 13.2.2 (02899bfda814146b021136e9d8e80eba494e1126) mimic (stable)": 3
    },
    "mgr": {
        "ceph version 13.2.2 (02899bfda814146b021136e9d8e80eba494e1126) mimic (stable)": 3
    },
    "osd": {
        "ceph version 12.2.8 (ae699615bac534ea496ee965ac6192cb7e0e07c0) luminous (stable)": 27
    },
    "mds": {
        "ceph version 13.2.2 (02899bfda814146b021136e9d8e80eba494e1126) mimic (stable)": 2
    },
    "overall": {
        "ceph version 12.2.8 (ae699615bac534ea496ee965ac6192cb7e0e07c0) luminous (stable)": 27,
        "ceph version 13.2.2 (02899bfda814146b021136e9d8e80eba494e1126) mimic (stable)": 8
    }
}

_______________________________________________

ceph-users mailing list

ceph-users@xxxxxxxxxxxxxx

http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com

_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com