Re: MDS damaged after mimic 13.2.1 to 13.2.2 upgrade

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



I was able to start MDS and mount the fs with broken ownership/permissions and 8k out of millions files in lost+found.


On 7.10.2018, at 02:04, Sergey Malinin <hell@xxxxxxxxxxx> wrote:

I'm at scan_links now, will post an update once it has finished.
Have you reset the journal after fs recovery as suggested in the doc?

quote:

If the damaged filesystem contains dirty journal data, it may be recovered next with:

cephfs-journal-tool --rank=<original filesystem name>:0 event recover_dentries list --alternate-pool recovery
cephfs-journal-tool --rank recovery-fs:0 journal reset --force


On 7.10.2018, at 00:36, Alfredo Daniel Rezinovsky <alfrenovsky@xxxxxxxxx> wrote:

I did something wrong in the upgrade restart also...

after rescaning with:

cephfs-data-scan scan_extents cephfs_data (with threads)

cephfs-data-scan scan_inodes cephfs_data (with threads)

cephfs-data-scan scan_links

My MDS still crashes and wont replay.
 1: (()+0x3ec320) [0x55b0e2bd2320]
 2: (()+0x12890) [0x7fc3adce3890]
 3: (gsignal()+0xc7) [0x7fc3acddbe97]
 4: (abort()+0x141) [0x7fc3acddd801]
 5: (ceph::__ceph_assert_fail(char const*, char const*, int, char const*)+0x250) [0x7fc3ae3cc080]
 6: (()+0x26c0f7) [0x7fc3ae3cc0f7]
 7: (()+0x21eb27) [0x55b0e2a04b27]
 8: (MDCache::journal_dirty_inode(MutationImpl*, EMetaBlob*, CInode*, snapid_t)+0xc0) [0x55b0e2a04d40]
 9: (Locker::check_inode_max_size(CInode*, bool, unsigned long, unsigned long, utime_t)+0x91d) [0x55b0e2a6a0fd]
 10: (RecoveryQueue::_recovered(CInode*, int, unsigned long, utime_t)+0x39f) [0x55b0e2a3ca2f]
 11: (MDSIOContextBase::complete(int)+0x119) [0x55b0e2b54ab9]
 12: (Filer::C_Probe::finish(int)+0xe7) [0x55b0e2bd94e7]
 13: (Context::complete(int)+0x9) [0x55b0e28e9719]
 14: (Finisher::finisher_thread_entry()+0x12e) [0x7fc3ae3ca4ce]
 15: (()+0x76db) [0x7fc3adcd86db]
 16: (clone()+0x3f) [0x7fc3acebe88f]

Did you do somenthing else before starting the MDSs again?


On 05/10/18 21:17, Sergey Malinin wrote:
I ended up rescanning the entire fs using alternate metadata pool approach as in http://docs.ceph.com/docs/mimic/cephfs/disaster-recovery/
The process has not competed yet because during the recovery our cluster encountered another problem with OSDs that I got fixed yesterday (thanks to Igor Fedotov @ SUSE).
The first stage (scan_extents) completed in 84 hours (120M objects in data pool on 8 hdd OSDs on 4 hosts). The second (scan_inodes) was interrupted by OSDs failure so I have no timing stats but it seems to be runing 2-3 times faster than extents scan.
As to root cause -- in my case I recall that during upgrade I had forgotten to restart 3 OSDs, one of which was holding metadata pool contents, before restarting MDS daemons and that seemed to had an impact on MDS journal corruption, because when I restarted those OSDs, MDS was able to start up but soon failed throwing lots of 'loaded dup inode' errors.


On 6.10.2018, at 00:41, Alfredo Daniel Rezinovsky <alfrenovsky@xxxxxxxxx> wrote:

Same problem...

# cephfs-journal-tool --journal=purge_queue journal inspect
2018-10-05 18:37:10.704 7f01f60a9bc0 -1 Missing object 500.0000016c
Overall journal integrity: DAMAGED
Objects missing:
  0x16c
Corrupt regions:
  0x5b000000-ffffffffffffffff

Just after upgrade to 13.2.2

Did you fixed it?


On 26/09/18 13:05, Sergey Malinin wrote:
Hello,
Followed standard upgrade procedure to upgrade from 13.2.1 to 13.2.2.
After upgrade MDS cluster is down, mds rank 0 and purge_queue journal are damaged. Resetting purge_queue does not seem to work well as journal still appears to be damaged.
Can anybody help?

mds log:

  -789> 2018-09-26 18:42:32.527 7f70f78b1700  1 mds.mds2 Updating MDS map to version 586 from mon.2
  -788> 2018-09-26 18:42:32.527 7f70f78b1700  1 mds.0.583 handle_mds_map i am now mds.0.583
  -787> 2018-09-26 18:42:32.527 7f70f78b1700  1 mds.0.583 handle_mds_map state change up:rejoin --> up:active
  -786> 2018-09-26 18:42:32.527 7f70f78b1700  1 mds.0.583 recovery_done -- successful recovery!
<skip>
   -38> 2018-09-26 18:42:32.707 7f70f28a7700 -1 mds.0.purge_queue _consume: Decode error at read_pos=0x322ec6636
   -37> 2018-09-26 18:42:32.707 7f70f28a7700  5 mds.beacon.mds2 set_want_state: up:active -> down:damaged
   -36> 2018-09-26 18:42:32.707 7f70f28a7700  5 mds.beacon.mds2 _send down:damaged seq 137
   -35> 2018-09-26 18:42:32.707 7f70f28a7700 10 monclient: _send_mon_message to mon.ceph3 at mon:6789/0
   -34> 2018-09-26 18:42:32.707 7f70f28a7700  1 -- mds:6800/e4cc09cf --> mon:6789/0 -- mdsbeacon(14c72/mds2 down:damaged seq 137 v24a) v7 -- 0x563b321ad480 con 0
<skip>
    -3> 2018-09-26 18:42:32.743 7f70f98b5700  5 -- mds:6800/3838577103 >> mon:6789/0 conn(0x563b3213e000 :-1 s=STATE_OPEN_MESSAGE_READ_FOOTER_AND_DISPATCH pgs=8 cs=1 l=1). rx mon.2 seq 29 0x563b321ab880 mdsbeaco
n(85106/mds2 down:damaged seq 311 v587) v7
    -2> 2018-09-26 18:42:32.743 7f70f98b5700  1 -- mds:6800/3838577103 <== mon.2 mon:6789/0 29 ==== mdsbeacon(85106/mds2 down:damaged seq 311 v587) v7 ==== 129+0+0 (3296573291 0 0) 0x563b321ab880 con 0x563b3213e
000
    -1> 2018-09-26 18:42:32.743 7f70f98b5700  5 mds.beacon.mds2 handle_mds_beacon down:damaged seq 311 rtt 0.038261
     0> 2018-09-26 18:42:32.743 7f70f28a7700  1 mds.mds2 respawn!

# cephfs-journal-tool --journal=purge_queue journal inspect
Overall journal integrity: DAMAGED
Corrupt regions:
  0x322ec65d9-ffffffffffffffff

# cephfs-journal-tool --journal=purge_queue journal reset
old journal was 13470819801~8463
new journal start will be 13472104448 (1276184 bytes past old end)
writing journal head
done

# cephfs-journal-tool --journal=purge_queue journal inspect
2018-09-26 19:00:52.848 7f3f9fa50bc0 -1 Missing object 500.00000c8c
Overall journal integrity: DAMAGED
Objects missing:
  0xc8c
Corrupt regions:
  0x323000000-ffffffffffffffff
_______________________________________________
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

[Index of Archives]     [Information on CEPH]     [Linux Filesystem Development]     [Ceph Development]     [Ceph Large]     [Ceph Dev]     [Linux USB Development]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]     [xfs]


  Powered by Linux