Description of problem: BlueStore OSD crashes in _do_read - BlueStore::_do_read 2019-02-15 21:42:51.930852 7fbc3ea6d700 -1 *** Caught signal (Aborted) ** in thread 7fbc3ea6d700 thread_name:tp_osd_tp ceph version 12.2.5-45redhat1xenial (d4b9f17b56b3348566926849313084dd6efc2ca2) luminous (stable) 1: (()+0xa7e5d4) [0x55dc7ecda5d4] 2: (()+0x11390) [0x7fbc57fd4390] 3: (pread64()+0x33) [0x7fbc57fd3d43] 4: (KernelDevice::read(unsigned long, unsigned long, ceph::buffer::list*, IOContext*, bool)+0x31d) [0x55dc7ecbb91d] 5: (BlueStore::_do_read(BlueStore::Collection*, boost::intrusive_ptr<BlueStore::Onode>, unsigned long, unsigned long, ceph::buffer::list&, unsigned int)+0x1b4a) [0x55dc7ebc85aa] 6: (BlueStore::read(boost::intrusive_ptr<ObjectStore::CollectionImpl>&, ghobject_t const&, unsigned long, unsigned long, ceph::buffer::list&, unsigned int)+0x4d7) [0x55dc7ebca377] 7: (ReplicatedBackend::be_deep_scrub(hobject_t const&, unsigned int, ScrubMap::object&, ThreadPool::TPHandle&, ScrubMap*)+0x204) [0x55dc7ea2b314] 8: (PGBackend::be_scan_list(ScrubMap&, std::vector<hobject_t, std::allocator<hobject_t> > const&, bool, unsigned int, ThreadPool::TPHandle&)+0x3ec) [0x55dc7e937b8c] 9: (PG::build_scrub_map_chunk(ScrubMap&, hobject_t, hobject_t, bool, unsigned int, ThreadPool::TPHandle&)+0x239) [0x55dc7e7d1759] 10: (PG::replica_scrub(boost::intrusive_ptr<OpRequest>, ThreadPool::TPHandle&)+0x65d) [0x55dc7e7d213d] 11: (PrimaryLogPG::do_request(boost::intrusive_ptr<OpRequest>&, ThreadPool::TPHandle&)+0x82d) [0x55dc7e89bc8d] 12: (OSD::dequeue_op(boost::intrusive_ptr<PG>, boost::intrusive_ptr<OpRequest>, ThreadPool::TPHandle&)+0x3a9) [0x55dc7e711fa9] 13: (PGQueueable::RunVis::operator()(boost::intrusive_ptr<OpRequest> const&)+0x57) [0x55dc7e9bc477] 14: (OSD::ShardedOpWQ::_process(unsigned int, ceph::heartbeat_handle_d*)+0x1047) [0x55dc7e740357] 15: (ShardedThreadPool::shardedthreadpool_worker(unsigned int)+0x884) [0x55dc7ed220a4] 16: (ShardedThreadPool::WorkThreadSharded::entry()+0x10) [0x55dc7ed250e0] 17: (()+0x76ba) [0x7fbc57fca6ba] 18: (clone()+0x6d) [0x7fbc5704141d] NOTE: a copy of the executable, or `objdump -rdS <executable>` is needed to interpret this. Version-Release number of selected component (if applicable): Red Hat Ceph Storage 3.1 12.2.5-45redhat1xenial
Matching: master - https://tracker.ceph.com/issues/36455 luminous - https://tracker.ceph.com/issues/37825 https://github.com/ceph/ceph/pull/25855
That sounds right.
Neha, Can you fill out the Doc Text? I will use this to write a description of the bug/fix for the 3.2z2 Release notes. The Doc Text field is on the right side of the details of the bug at the top. Please fill out the "Cause: Consequence: Fix: Result:"
Since the problem described in this bug report should be resolved in a recent advisory, it has been closed with a resolution of ERRATA. For information on the advisory, and where to find the updated files, follow the link below. If the solution does not work for you, open a new bug report. https://access.redhat.com/errata/RHSA-2019:0911