Project

General

Profile

Actions

Bug #39087

open

ec_lost_unfound: a EC shard has missing object after `osd lost`

Added by Chang Liu about 5 years ago. Updated about 5 years ago.

Status:
New
Priority:
Normal
Assignee:
-
Category:
-
Target version:
-
% Done:

0%

Source:
Tags:
Backport:
Regression:
No
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Component(RADOS):
Pull request ID:
Crash signature (v1):
Crash signature (v2):

Description

http://pulpito.ceph.com/kchai-2019-04-01_10:38:29-rados-wip-kefu-testing-2019-04-01-1531-distro-basic-mira/3797065/

16729 2019-04-01T14:49:52.035 INFO:tasks.ec_lost_unfound:listing missing/lost in 2.4 state active+recovery_unfound+undersized+degraded
  16730 2019-04-01T14:49:52.035 INFO:teuthology.orchestra.run.mira111:Running:
  16731 2019-04-01T14:49:52.035 INFO:teuthology.orchestra.run.mira111:> sudo adjust-ulimits ceph-coverage /home/ubuntu/cephtest/archive/coverage timeout 120 ceph --cluster ceph -- pg 2.4 list_unfound '{}'
  16732 2019-04-01T14:49:52.309 INFO:tasks.ec_lost_unfound.radosbench.client.admin.mira111.stdout:   13      20      6191      6171   3.70606   1.88281   0.0225818   0.0421165
  16733 2019-04-01T14:49:52.505 INFO:teuthology.orchestra.run.mira111.stdout:{
  16734 2019-04-01T14:49:52.506 INFO:teuthology.orchestra.run.mira111.stdout:    "offset": {
  16735 2019-04-01T14:49:52.506 INFO:teuthology.orchestra.run.mira111.stdout:        "oid": "",
  16736 2019-04-01T14:49:52.506 INFO:teuthology.orchestra.run.mira111.stdout:        "key": "",
  16737 2019-04-01T14:49:52.506 INFO:teuthology.orchestra.run.mira111.stdout:        "snapid": 0,
  16738 2019-04-01T14:49:52.506 INFO:teuthology.orchestra.run.mira111.stdout:        "hash": 0,
  16739 2019-04-01T14:49:52.506 INFO:teuthology.orchestra.run.mira111.stdout:        "max": 0,
  16740 2019-04-01T14:49:52.506 INFO:teuthology.orchestra.run.mira111.stdout:        "pool": -9223372036854775808,
  16741 2019-04-01T14:49:52.507 INFO:teuthology.orchestra.run.mira111.stdout:        "namespace": "" 
  16742 2019-04-01T14:49:52.507 INFO:teuthology.orchestra.run.mira111.stdout:    },
  16743 2019-04-01T14:49:52.507 INFO:teuthology.orchestra.run.mira111.stdout:    "num_missing": 3,
  16744 2019-04-01T14:49:52.507 INFO:teuthology.orchestra.run.mira111.stdout:    "num_unfound": 3,
  16745 2019-04-01T14:49:52.507 INFO:teuthology.orchestra.run.mira111.stdout:    "objects": [
  16746 2019-04-01T14:49:52.507 INFO:teuthology.orchestra.run.mira111.stdout:        {
  16747 2019-04-01T14:49:52.507 INFO:teuthology.orchestra.run.mira111.stdout:            "oid": {
  16748 2019-04-01T14:49:52.508 INFO:teuthology.orchestra.run.mira111.stdout:                "oid": "existed_4",
  16749 2019-04-01T14:49:52.508 INFO:teuthology.orchestra.run.mira111.stdout:                "key": "",
  16750 2019-04-01T14:49:52.508 INFO:teuthology.orchestra.run.mira111.stdout:                "snapid": -2,
  16751 2019-04-01T14:49:52.508 INFO:teuthology.orchestra.run.mira111.stdout:                "hash": 873891716,
  16752 2019-04-01T14:49:52.508 INFO:teuthology.orchestra.run.mira111.stdout:                "max": 0,
  16753 2019-04-01T14:49:52.508 INFO:teuthology.orchestra.run.mira111.stdout:                "pool": 2,
  16754 2019-04-01T14:49:52.508 INFO:teuthology.orchestra.run.mira111.stdout:                "namespace": "" 
  16755 2019-04-01T14:49:52.509 INFO:teuthology.orchestra.run.mira111.stdout:            },
  16756 2019-04-01T14:49:52.509 INFO:teuthology.orchestra.run.mira111.stdout:            "need": "21'8",
  16757 2019-04-01T14:49:52.509 INFO:teuthology.orchestra.run.mira111.stdout:            "have": "0'0",
  16758 2019-04-01T14:49:52.509 INFO:teuthology.orchestra.run.mira111.stdout:            "flags": "none",
  16759 2019-04-01T14:49:52.509 INFO:teuthology.orchestra.run.mira111.stdout:            "locations": [
  16760 2019-04-01T14:49:52.509 INFO:teuthology.orchestra.run.mira111.stdout:                "2(2)" 
  16761 2019-04-01T14:49:52.509 INFO:teuthology.orchestra.run.mira111.stdout:            ]
  16762 2019-04-01T14:49:52.509 INFO:teuthology.orchestra.run.mira111.stdout:        },
  16763 2019-04-01T14:49:52.510 INFO:teuthology.orchestra.run.mira111.stdout:        {
  16764 2019-04-01T14:49:52.510 INFO:teuthology.orchestra.run.mira111.stdout:            "oid": {
  16765 2019-04-01T14:49:52.510 INFO:teuthology.orchestra.run.mira111.stdout:                "oid": "existing_7",
  16766 2019-04-01T14:49:52.510 INFO:teuthology.orchestra.run.mira111.stdout:                "key": "",
  16767 2019-04-01T14:49:52.510 INFO:teuthology.orchestra.run.mira111.stdout:                "snapid": -2,
  16768 2019-04-01T14:49:52.510 INFO:teuthology.orchestra.run.mira111.stdout:                "hash": 3996155460,
  16769 2019-04-01T14:49:52.510 INFO:teuthology.orchestra.run.mira111.stdout:                "max": 0,
  16770 2019-04-01T14:49:52.510 INFO:teuthology.orchestra.run.mira111.stdout:                "pool": 2,
  16771 2019-04-01T14:49:52.511 INFO:teuthology.orchestra.run.mira111.stdout:                "namespace": "" 
  16772 2019-04-01T14:49:52.511 INFO:teuthology.orchestra.run.mira111.stdout:            },
  16773 2019-04-01T14:49:52.511 INFO:teuthology.orchestra.run.mira111.stdout:            "need": "21'9",
  16774 2019-04-01T14:49:52.511 INFO:teuthology.orchestra.run.mira111.stdout:            "have": "18'6",
  16775 2019-04-01T14:49:52.511 INFO:teuthology.orchestra.run.mira111.stdout:            "flags": "none",
  16776 2019-04-01T14:49:52.511 INFO:teuthology.orchestra.run.mira111.stdout:            "locations": [
  16777 2019-04-01T14:49:52.511 INFO:teuthology.orchestra.run.mira111.stdout:                "2(2)" 
  16778 2019-04-01T14:49:52.511 INFO:teuthology.orchestra.run.mira111.stdout:            ]
  16779 2019-04-01T14:49:52.512 INFO:teuthology.orchestra.run.mira111.stdout:        },
  16780 2019-04-01T14:49:52.512 INFO:teuthology.orchestra.run.mira111.stdout:        {
  16781 2019-04-01T14:49:52.512 INFO:teuthology.orchestra.run.mira111.stdout:            "oid": {
  16782 2019-04-01T14:49:52.512 INFO:teuthology.orchestra.run.mira111.stdout:                "oid": "existed_2",
  16783 2019-04-01T14:49:52.512 INFO:teuthology.orchestra.run.mira111.stdout:                "key": "",
  16784 2019-04-01T14:49:52.512 INFO:teuthology.orchestra.run.mira111.stdout:                "snapid": -2,
  16785 2019-04-01T14:49:52.512 INFO:teuthology.orchestra.run.mira111.stdout:                "hash": 1767667508,
  16786 2019-04-01T14:49:52.513 INFO:teuthology.orchestra.run.mira111.stdout:                "max": 0,
  16787 2019-04-01T14:49:52.513 INFO:teuthology.orchestra.run.mira111.stdout:                "pool": 2,
  16788 2019-04-01T14:49:52.513 INFO:teuthology.orchestra.run.mira111.stdout:                "namespace": "" 
  16789 2019-04-01T14:49:52.513 INFO:teuthology.orchestra.run.mira111.stdout:            },
  16790 2019-04-01T14:49:52.513 INFO:teuthology.orchestra.run.mira111.stdout:            "need": "21'7",
  16791 2019-04-01T14:49:52.513 INFO:teuthology.orchestra.run.mira111.stdout:            "have": "0'0",
  16792 2019-04-01T14:49:52.513 INFO:teuthology.orchestra.run.mira111.stdout:            "flags": "none",
  16793 2019-04-01T14:49:52.513 INFO:teuthology.orchestra.run.mira111.stdout:            "locations": [
  16794 2019-04-01T14:49:52.514 INFO:teuthology.orchestra.run.mira111.stdout:                "2(2)" 
  16795 2019-04-01T14:49:52.514 INFO:teuthology.orchestra.run.mira111.stdout:            ]
  16796 2019-04-01T14:49:52.514 INFO:teuthology.orchestra.run.mira111.stdout:        }
  16797 2019-04-01T14:49:52.514 INFO:teuthology.orchestra.run.mira111.stdout:    ],
  16798 2019-04-01T14:49:52.514 INFO:teuthology.orchestra.run.mira111.stdout:    "more": false
  16799 2019-04-01T14:49:52.514 INFO:teuthology.orchestra.run.mira111.stdout:}
  16800 2019-04-01T14:49:52.519 INFO:tasks.ec_lost_unfound:{u'num_unfound': 3, u'objects': [{u'need': u"21'8", u'oid': {u'hash': 873891716, u'max': 0, u'oid': u'existed_4', u'namespace': u'', u'snapid': -        2, u'key': u'', u'pool': 2}, u'flags': u'none', u'locations': [u'2(2)'], u'have': u"0'0"}, {u'need': u"21'9", u'oid': {u'hash': 3996155460, u'max': 0, u'oid': u'existing_7', u'namespace': u'', u's        napid': -2, u'key': u'', u'pool': 2}, u'flags': u'none', u'locations': [u'2(2)'], u'have': u"18'6"}, {u'need': u"21'7", u'oid': {u'hash': 1767667508, u'max': 0, u'oid': u'existed_2', u'namespace':         u'', u'snapid': -2, u'key': u'', u'pool': 2}, u'flags': u'none', u'locations': [u'2(2)'], u'have': u"0'0"}], u'num_missing': 3, u'offset': {u'hash': 0, u'max': 0, u'oid': u'', u'namespace': u'',         u'snapid': 0, u'key': u'', u'pool': -9223372036854775808}}
  16801 2019-04-01T14:49:52.519 INFO:tasks.ec_lost_unfound:reverting unfound in 2.4

1924724 2019-04-01T15:40:40.758 INFO:tasks.ceph.osd.1.mira111.stderr:2019-04-01 15:40:40.758 7fbcb881f700 -1 log_channel(cluster) log [ERR] : 2.4s0 shard 0(1) 2:29be9562:::dummy:head : missing
1924725 2019-04-01T15:40:40.758 INFO:tasks.ceph.osd.1.mira111.stderr:2019-04-01 15:40:40.758 7fbcb881f700 -1 log_channel(cluster) log [ERR] : 2.4s0 scrub 1 missing, 0 inconsistent objects

{"pgid":"2.4","version":"30'5134","report        ed_seq":"5352","reported_epoch":"61","state":"active+clean","last_fresh":"2019-04-01 15:40:33.883225","last_change":"2019-04-01 15:12:49.501106","last_active":"2019-04-01 15:40:33.883225","last_pe        ered":"2019-04-01 15:40:33.883225","last_clean":"2019-04-01 15:40:33.883225","last_became_active":"2019-04-01 15:12:49.437988","last_became_peered":"2019-04-01 15:12:49.437988","last_unstale":"201        9-04-01 15:40:33.883225","last_undegraded":"2019-04-01 15:40:33.883225","last_fullsized":"2019-04-01 15:40:33.883225","mapping_epoch":41,"log_start":"30'2100","ondisk_log_start":"30'2100","created        ":15,"last_epoch_clean":42,"parent":"0.0","parent_split_bits":0,"last_scrub":"0'0","last_scrub_stamp":"2019-04-01 14:48:53.857396","last_deep_scrub":"0'0","last_deep_scrub_stamp":"2019-04-01 14:48        :53.857396","last_clean_scrub_stamp":"2019-04-01 14:48:53.857396","log_size":3034,"ondisk_log_size":3034,"stats_invalid":true,"dirty_stats_invalid":false,"omap_stats_invalid":false,"hitset_stats_i        nvalid":false,"hitset_bytes_stats_invalid":false,"pin_stats_invalid":false,"manifest_stats_invalid":false,"snaptrimq_len":0,"stat_sum":{"num_bytes":12676,"num_objects":4,"num_object_clones":0,"num        _object_copies":16,"num_objects_missing_on_primary":0,"num_objects_missing":0,"num_objects_degraded":0,"num_objects_misplaced":0,"num_objects_unfound":0,"num_objects_dirty":4,"num_whiteouts":0,"nu        m_read":0,"num_read_kb":0,"num_write":5131,"num_write_kb":20516,"num_scrub_errors":0,"num_shallow_scrub_errors":0,"num_deep_scrub_errors":0,"num_objects_recovered":1578,"num_bytes_recovered":0,"nu        m_keys_recovered":0,"num_objects_omap":0,"num_objects_hit_set_archive":0,"num_bytes_hit_set_archive":0,"num_flush":0,"num_flush_kb":0,"num_evict":0,"num_evict_kb":0,"num_promote":0,"num_flush_mode        _high":0,"num_flush_mode_low":0,"num_evict_mode_some":0,"num_evict_mode_full":0,"num_objects_pinned":0,"num_legacy_snapsets":0,"num_large_omap_objects":0,"num_objects_manifest":0,"num_omap_bytes":        0,"num_omap_keys":0,"num_objects_repaired":0},"up":[1,0,2,3],"acting":[1,0,2,3],"blocked_by":[],"up_primary":1,"acting_primary":1,"purged_snaps":[]}
Actions #1

Updated by Chang Liu about 5 years ago

is this `scrub error` we expect? what we should do is to find out why ceph doesn't recovery PG 2.4s0 ?

Actions #2

Updated by Neha Ojha about 5 years ago

/a/yuriw-2019-04-02_20:09:55-rados-wip-yuri3-testing-2019-04-02-1623-mimic-distro-basic-smithi/3801955/ - looks like a similar failure in mimic

Actions #3

Updated by Greg Farnum about 5 years ago

  • Project changed from Ceph to RADOS
Actions

Also available in: Atom PDF