Re: Ceph Giant not fixed RepllicatedPG:NotStrimming?

[Ta Ba Tuan <tuantb@xxxxxxxxxx>]

Hi Sage Weil

Thank for your repling. Yes, I'm using Ceph v.0.86,
I report some related bugs, Hope you help me,

2014-10-31 15:34:52.927965 7f85efb6b700  0 osd.21 104744 do_command r=0
2014-10-31 15:34:53.105533 7f85f036c700 -1 *** Caught signal (Segmentation fault) **
 in thread 7f85f036c700
 ceph version 0.86-106-g6f8524e (6f8524ef7673ab4448de2e0ff76638deaf03cae8)
 1: /usr/bin/ceph-osd() [0x9b6655]
 2: (()+0xfcb0) [0x7f8615726cb0]
 3: (ReplicatedPG::trim_object(hobject_t const&)+0x395) [0x811c25]
 4: (ReplicatedPG::TrimmingObjects::react(ReplicatedPG::SnapTrim const&)+0x43e) [0x82baae]
 5: (boost::statechart::simple_state<ReplicatedPG::TrimmingObjects, ReplicatedPG::SnapTrimmer, boost::mpl::list<mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na>, (boost::statechart::history_mode)0>::react_impl(boost::statechart::event_base const&, void const*)+0xc0) [0x870c30]
 6: (boost::statechart::state_machine<ReplicatedPG::SnapTrimmer, ReplicatedPG::NotTrimming, std::allocator<void>, boost::statechart::null_exception_translator>::process_queued_events()+0xfb) [0x8560db]
 7: (boost::statechart::state_machine<ReplicatedPG::SnapTrimmer, ReplicatedPG::NotTrimming, std::allocator<void>, boost::statechart::null_exception_translator>::process_event(boost::statechart::event_base const&)+0x1e) [0x8562ae]
 8: (ReplicatedPG::snap_trimmer()+0x4f8) [0x7d5f48]
 9: (OSD::SnapTrimWQ::_process(PG*)+0x14) [0x6739b4]
 10: (ThreadPool::worker(ThreadPool::WorkThread*)+0x48e) [0xa8fa0e]
 11: (ThreadPool::WorkThread::entry()+0x10) [0xa927a0]
 12: (()+0x7e9a) [0x7f861571ee9a]
 13: (clone()+0x6d) [0x7f86140e931d]
 NOTE: a copy of the executable, or `objdump -rdS <executable>` is needed to interpret this.

 -9523> 2014-10-31 15:34:45.571962 7f85e3ee0700  5 -- op tracker -- seq: 6937, time: 2014-10-31 15:34:45.531887, event: header_read, op: MOSDPGPus
h(6.749 104744 [PushOp(d2106749/rbd_data.a2e6185b9a8ef8.0000000000000803/head//6, version: 104736'7736506, data_included: [0~4194304], data_size:
4194304, omap_header_size: 0, omap_entries_size: 0, attrset_size: 2, recovery_info: ObjectRecoveryInfo(d2106749/rbd_data.a2e6185b9a8ef8.0000000000
000803/head//6@104736'7736506, copy_subset: [0~4194304], clone_subset: {}), after_progress: ObjectRecoveryProgress(!first, data_recovered_to:41943
04, data_complete:true, omap_recovered_to:, omap_complete:true), before_progress: ObjectRecoveryProgress(first, data_recovered_to:0, data_complete
:false, omap_recovered_to:, omap_complete:false)),PushOp(60940749/rbd_data.3435875ff78f67.0000000000001408/head//6, version: 104736'7736579, data_
included: [0~335360], data_size: 335360, omap_header_size: 0, omap_entries_size: 0, attrset_size: 2, recovery_info: ObjectRecoveryInfo(60940749/rb
d_data.3435875ff78f67.0000000000001408/head//6@104736'7736579, copy_subset: [0~335360], clone_subset: {}), after_progress: ObjectRecoveryProgress(
!first, data_recovered_to:335360, data_complete:true, omap_recovered_to:, omap_complete:true), before_progress: ObjectRecoveryProgress(first, data
_recovered_to:0, data_complete:false, omap_recovered_to:, omap_complete:false)),PushOp(922b1749/rbd_data.1c3dade6cdc10.00000000000014c5/head//6, v
ersion: 104736'7736866, data_included: [0~4194304], data_size: 4194304, omap_header_size: 0, omap_entries_size: 0, attrset_size: 2, recovery_info:
 ObjectRecoveryInfo(922b1749/rbd_data.1c3dade6cdc10.00000000000014c5/head//6@104736'7736866, copy_subset: [0~4194304], clone_subset: {}), after_pr
ogress: ObjectRecoveryProgress(!first, data_recovered_to:4194304, data_complete:true, omap_recovered_to:, omap_complete:true), before_progress: Ob
jectRecoveryProgress(first, data_recovered_to:0, data_complete:false, omap_recovered_to:, omap_complete:false))])

 -6933> 2014-10-31 15:34tha7.611229 7f85f737a700  5 osd.21 pg_epoch: 104744 pg[6.749( v 104744'7741801 (104665'7732106,104744'7741801] lb 14886749/rbd_data.3955b9640616f2.000000000000f5e2/head//6 local-les=104661 n=1780 ec=164 les/c 104742/104735 104740/104741/103210) [74,112,21]/[74,112] r=-1 lpr=104741 pi=64005-104740/278 luod=0'0 crt=104744'7741798 active+remapped] enter Started/ReplicaActive/RepNotRecovering

I think having some missing objects, I can't start one osd  that above objects be pushed to that osd. Ceph'versions are slower 0.86 then appear this bug?
Should I upgrade to Giant o resolve this bug?,


Thank you,
--
Tuan
HaNoi-VietNam

On 10/30/2014 10:02 PM, Sage Weil wrote:

On Thu, 30 Oct 2014, Ta Ba Tuan wrote:

Hi Everyone,

I upgraded Ceph to Giant by installing *tar.gz package, but appeared some
errors related Object Trimming or Snap Trimming:
I think having some missing objects and be not recovered.

Note that this isn't giant, which is 0.87, but something a few weeks 
older.  There were a few bugs fixed in this code, but we can't tell if 
this was one of them without the log leading up to this message, which 
should include either a failed assertion message or segmentation fault or 
similar.

Thanks!
sage

 ceph version 0.86-106-g6f8524e (6f8524ef7673ab4448de2e0ff76638deaf03cae8)
 1: /usr/bin/ceph-osd() [0x9b6655]
 2: (()+0xfcb0) [0x7fa52c471cb0]
 3: (ReplicatedPG::trim_object(hobject_t const&)+0x395) [0x811c25]
 4: (ReplicatedPG::TrimmingObjects::react(ReplicatedPG::SnapTrim
const&)+0x43e) [0x82baae]
 5: (boost::statechart::simple_state<ReplicatedPG::TrimmingObjects,
ReplicatedPG::SnapTrimmer, boost::mpl::list<mpl_::na, mpl_::na, mpl_::na,
mpl
_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na,
mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na, mpl_::na
, mpl_::na, mpl_::na>,(boost::statechart::history_mode)0>::react_impl(boost::statechart::event_ba
se const&, void const*)+0xc0) [0x870c30]
 6: (boost::statechart::state_machine<ReplicatedPG::SnapTrimmer,
ReplicatedPG::NotTrimming, std::allocator<void>,
boost::statechart::null_excepti
on_translator>::process_queued_events()+0xfb) [0x8560db]
 7: (boost::statechart::state_machine<ReplicatedPG::SnapTrimmer,
ReplicatedPG::NotTrimming, std::allocator<void>,
boost::statechart::null_excepti
on_translator>::process_event(boost::statechart::event_base const&)+0x1e)
[0x8562ae]
 8: (ReplicatedPG::snap_trimmer()+0x4f8) [0x7d5f48]
 9: (OSD::SnapTrimWQ::_process(PG*)+0x14) [0x6739b4]
 10: (ThreadPool::worker(ThreadPool::WorkThread*)+0x48e) [0xa8fa0e]
 11: (ThreadPool::WorkThread::entry()+0x10) [0xa927a0]
 12: (()+0x7e9a) [0x7fa52c469e9a]
 13: (clone()+0x6d) [0x7fa52ae3431d]
 NOTE: a copy of the executable, or `objdump -rdS <executable>` is needed to
interpret this.


  -128> 2014-10-29 13:51:23.049357 7fa50ed9d700  5 osd.21 pg_epoch: 104445
pg[6.9d8( v 104445'7857889 (103730'7852406,104445'7857889] local-les=104444
n=4345 ec=164 les/c 104444/104272 104443/104443/104443) [21,93,49] r=0
lpr=104443 pi=103787-104442/16 crt=104442'7857887 mlcod 104445'7857888
active snaptrimq=[1907~1,1941~4,1946~1,19ef~2,19f2~1,19f4~3,19fa~5]] exit
Started/Primary/Active/Recovered 0.000084 0 0.000000
  -127> 2014-10-29 13:51:23.049392 7fa50ed9d700  5 osd.21 pg_epoch: 104445
pg[6.9d8( v 104445'7857889 (103730'7852406,104445'7857889] local-les=104444
n=4345 ec=164 les/c 104444/104272 104443/104443/104443) [21,93,49] r=0
lpr=104443 pi=103787-104442/16 crt=104442'7857887 mlcod 104445'7857888
active snaptrimq=[1907~1,1941~4,1946~1,19ef~2,19f2~1,19f4~3,19fa~5]] enter
Started/Primary/Active/Clean
  -126> 2014-10-29 13:51:23.049582 7fa50ed9d700  1 -- 172.30.5.2:6838/22980
--> 172.30.5.4:6859/8884 -- pg_info(1 pgs e104445:6.9d8) v4 -- ?+0
0x30d41c00 con 0x26c6ac60


Thank you!
--
Tuan
HaNoi-VietNam

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