上週 Ceph cluster 掛掉,結果是某個 OSD 一直起不來。
在 /var/log/ceph/ceph-osd.X.log
裡面看到了以下錯誤訊息
1 2 3 4 5 6 7 8 9 10 11 12
| ceph version 0.80.5 (38b73c67d375a2552d8ed67843c8a65c2c0feba6) 1: (FileStore::lfn_open(coll_t, ghobject_t const&, bool, std::tr1::shared_ptr<FDCache::FD>*, std::tr1::shared_ptr<CollectionIndex::Path>*, std::tr1::shared_ptr<CollectionIndex>*)+0x4e6) [0x888926] 2: (FileStore::_touch(coll_t, ghobject_t const&)+0x18b) [0x88effb] 3: (FileStore::_do_transaction(ObjectStore::Transaction&, unsigned long, int, ThreadPool::TPHandle*)+0x48f6) [0x899856] 4: (FileStore::_do_transactions(std::list<ObjectStore::Transaction*, std::allocator<ObjectStore::Transaction*> >&, unsigned long, ThreadPool::TPHandle*)+0x74) [0x89b204] 5: (JournalingObjectStore::journal_replay(unsigned long)+0x886) [0x8af6e6] 6: (FileStore::mount()+0x30c2) [0x883052] 7: (OSD::do_convertfs(ObjectStore*)+0x1a) [0x61a11a] 8: (main()+0x1d88) [0x602f98] 9: (__libc_start_main()+0xed) [0x7f70e698276d] 10: /usr/bin/ceph-osd() [0x607229] NOTE: a copy of the executable, or `objdump -rdS <executable>` is needed to interpret this.
|
Continue reading