Project

General

Profile

Bug #1679

Updated by Sage Weil over 12 years ago


 3 boxes, 12 osds per box.    4 osds (9,11,20,24) crashed at the following assertion.    This was triggered by first setting the crush map (ceph mon setcrushmap), and then setting the replication factor (ceph osd pool set [meta]data size 3): 

 osd/PG.cc: In function 'void PG::proc_primary_info(ObjectStore::Transaction&, const PG::Info&)', in thread '0x7f2bf0614700' 
 osd/PG.cc: 3728: FAILED assert(is_replica()) 
  ceph version 0.37 (commit:a6f3bbb744a6faea95ae48317f0b838edb16a896) 
  1: (PG::proc_primary_info(ObjectStore::Transaction&, PG::Info const&)+0x678) [0x64db48] 
  2: (PG::RecoveryState::ReplicaActive::react(PG::RecoveryState::MInfoRec const&)+0x81) [0x64dc11] 
  3: (boost::statechart::detail::reaction_result boost::statechart::simple_state<PG::RecoveryState::ReplicaActive, PG::RecoveryState::Started, 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>::local_react_impl_non_empty::local_react_impl<boost::mpl::list2<boost::statechart::custom_reaction<PG::RecoveryState::MQuery>, boost::statechart::custom_reaction<PG::RecoveryState::MInfoRec> >, boost::statechart::simple_state<PG::RecoveryState::ReplicaActive, PG::RecoveryState::Started, 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> >(boost::statechart::simple_state<PG::RecoveryState::ReplicaActive, PG::RecoveryState::Started, 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>&, boost::statechart::event_base const&, void const*)+0x106) [0x668f36] 
  4: (boost::statechart::simple_state<PG::RecoveryState::ReplicaActive, PG::RecoveryState::Started, 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*)+0x5a) [0x668fea] 
  5: (boost::statechart::state_machine<PG::RecoveryState::RecoveryMachine, PG::RecoveryState::Initial, std::allocator<void>, boost::statechart::null_exception_translator>::send_event(boost::statechart::event_base const&)+0x5f) [0x6561af] 
  6: (PG::RecoveryState::handle_info(int, PG::Info&, PG::RecoveryCtx*)+0x143) [0x625243] 
  7: (OSD::handle_pg_info(MOSDPGInfo*)+0x380) [0x55e470] 
  8: (OSD::_dispatch(Message*)+0x4ab) [0x56d25b] 
  9: (OSD::ms_dispatch(Message*)+0xf6) [0x56e1c6] 
  10: (SimpleMessenger::dispatch_entry()+0x88b) [0x5e461b] 
  11: (SimpleMessenger::DispatchThread::entry()+0x1c) [0x4bd55c] 
  12: (()+0x6d8c) [0x7f2bfc8e7d8c] 
  13: (clone()+0x6d) [0x7f2bfb12904d] 
  ceph version 0.37 (commit:a6f3bbb744a6faea95ae48317f0b838edb16a896) 
  1: (PG::proc_primary_info(ObjectStore::Transaction&, PG::Info const&)+0x678) [0x64db48] 
  2: (PG::RecoveryState::ReplicaActive::react(PG::RecoveryState::MInfoRec const&)+0x81) [0x64dc11] 
  3: (boost::statechart::detail::reaction_result boost::statechart::simple_state<PG::RecoveryState::ReplicaActive, PG::RecoveryState::Started, 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>::local_react_impl_non_empty::local_react_impl<boost::mpl::list2<boost::statechart::custom_reaction<PG::RecoveryState::MQuery>, boost::statechart::custom_reaction<PG::RecoveryState::MInfoRec> >, boost::statechart::simple_state<PG::RecoveryState::ReplicaActive, PG::RecoveryState::Started, 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> >(boost::statechart::simple_state<PG::RecoveryState::ReplicaActive, PG::RecoveryState::Started, 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>&, boost::statechart::event_base const&, void const*)+0x106) [0x668f36] 
  4: (boost::statechart::simple_state<PG::RecoveryState::ReplicaActive, PG::RecoveryState::Started, 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*)+0x5a) [0x668fea] 
  5: (boost::statechart::state_machine<PG::RecoveryState::RecoveryMachine, PG::RecoveryState::Initial, std::allocator<void>, boost::statechart::null_exception_translator>::send_event(boost::statechart::event_base const&)+0x5f) [0x6561af] 
  6: (PG::RecoveryState::handle_info(int, PG::Info&, PG::RecoveryCtx*)+0x143) [0x625243] 
  7: (OSD::handle_pg_info(MOSDPGInfo*)+0x380) [0x55e470] 
  8: (OSD::_dispatch(Message*)+0x4ab) [0x56d25b] 
  9: (OSD::ms_dispatch(Message*)+0xf6) [0x56e1c6] 
  10: (SimpleMessenger::dispatch_entry()+0x88b) [0x5e461b] 
  11: (SimpleMessenger::DispatchThread::entry()+0x1c) [0x4bd55c] 
  12: (()+0x6d8c) [0x7f2bfc8e7d8c] 
  13: (clone()+0x6d) [0x7f2bfb12904d] 
 *** Caught signal (Aborted) ** 
  in thread 0x7f2bf0614700 
  ceph version 0.37 (commit:a6f3bbb744a6faea95ae48317f0b838edb16a896) 
  1: /usr/bin/ceph-osd() [0x59f6d2] 
  2: (()+0xfc60) [0x7f2bfc8f0c60] 
  3: (gsignal()+0x35) [0x7f2bfb076d05] 
  4: (abort()+0x186) [0x7f2bfb07aab6] 
  5: (__gnu_cxx::__verbose_terminate_handler()+0x11d) [0x7f2bfb92d6dd] 
  6: (()+0xb9926) [0x7f2bfb92b926] 
  7: (()+0xb9953) [0x7f2bfb92b953] 
  8: (()+0xb9a5e) [0x7f2bfb92ba5e] 
  9: (ceph::__ceph_assert_fail(char const*, char const*, int, char const*)+0x396) [0x5a8e16] 
  10: (PG::proc_primary_info(ObjectStore::Transaction&, PG::Info const&)+0x678) [0x64db48] 
  11: (PG::RecoveryState::ReplicaActive::react(PG::RecoveryState::MInfoRec const&)+0x81) [0x64dc11] 
  12: (boost::statechart::detail::reaction_result boost::statechart::simple_state<PG::RecoveryState::ReplicaActive, PG::RecoveryState::Started, 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>::local_react_impl_non_empty::local_react_impl<boost::mpl::list2<boost::statechart::custom_reaction<PG::RecoveryState::MQuery>, boost::statechart::custom_reaction<PG::RecoveryState::MInfoRec> >, boost::statechart::simple_state<PG::RecoveryState::ReplicaActive, PG::RecoveryState::Started, 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> >(boost::statechart::simple_state<PG::RecoveryState::ReplicaActive, PG::RecoveryState::Started, 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>&, boost::statechart::event_base const&, void const*)+0x106) [0x668f36] 
  13: (boost::statechart::simple_state<PG::RecoveryState::ReplicaActive, PG::RecoveryState::Started, 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*)+0x5a) [0x668fea] 
  14: (boost::statechart::state_machine<PG::RecoveryState::RecoveryMachine, PG::RecoveryState::Initial, std::allocator<void>, boost::statechart::null_exception_translator>::send_event(boost::statechart::event_base const&)+0x5f) [0x6561af] 
  15: (PG::RecoveryState::handle_info(int, PG::Info&, PG::RecoveryCtx*)+0x143) [0x625243] 
  16: (OSD::handle_pg_info(MOSDPGInfo*)+0x380) [0x55e470] 
  17: (OSD::_dispatch(Message*)+0x4ab) [0x56d25b] 
  18: (OSD::ms_dispatch(Message*)+0xf6) [0x56e1c6] 
  19: (SimpleMessenger::dispatch_entry()+0x88b) [0x5e461b] 
  20: (SimpleMessenger::DispatchThread::entry()+0x1c) [0x4bd55c] 
  21: (()+0x6d8c) [0x7f2bfc8e7d8c] 

Back