Hi Haomai, Hmm, one other thing: I'm testing the fix in wip-8701 and it is tripping over the KeyValueStore test. This
./ceph_test_objectstore --gtest_filter=ObjectStore/StoreTest.BigRGWObjectName/1 fails with 0> 2014-07-22 08:45:25.640932 7fe617fff700 -1 *** Caught signal (Segmentation fault) ** in thread 7fe617fff700 ceph version 0.82-649-gc5732e4 (c5732e4aefbd80f29b766756478d79808f0245d7) 1: (ceph::BackTrace::BackTrace(int)+0x2d) [0xa09a7b] 2: ./ceph_test_objectstore() [0xb145b6] 3: (()+0x10340) [0x7fe621313340] 4: (std::pair<unsigned long const, ghobject_t>::pair(unsigned long const&, ghobject_t const&)+0x18) [0xadb710] 5: (std::map<unsigned long, ghobject_t, std::less<unsigned long>, std::allocator<std::pair<unsigned long const, ghobject_t> > >::operator[](unsigned long const&)+0x109) [0xad957f] 6: (RandomCache<ghobject_t, std::pair<coll_t, std::tr1::shared_ptr<StripObjectMap::StripObjectHeader> > >::trim_cache(unsigned long)+0xc2) [0xad7218] 7: (RandomCache<ghobject_t, std::pair<coll_t, std::tr1::shared_ptr<StripObjectMap::StripObjectHeader> > >::add(ghobject_t, std::pair<coll_t, std::tr1::shared_ptr<StripObjectMap::StripObjectHeader> >)+0x70) [0xad53a2] 8: (StripObjectMap::lookup_strip_header(coll_t const&, ghobject_t const&, std::tr1::shared_ptr<StripObjectMap::StripObjectHeader>*)+0x4d3) [0xab1fb1] 9: (KeyValueStore::BufferTransaction::lookup_cached_header(coll_t const&, ghobject_t const&, std::tr1::shared_ptr<StripObjectMap::StripObjectHeader>*, bool)+0x1dc) [0xab32c0] 10: (KeyValueStore::_remove(coll_t, ghobject_t const&, KeyValueStore::BufferTransaction&)+0x188) [0xac0472] 11: (KeyValueStore::_do_transaction(ObjectStore::Transaction&, KeyValueStore::BufferTransaction&, ThreadPool::TPHandle*)+0x632) [0xabba0c] 12: (KeyValueStore::_do_transactions(std::list<ObjectStore::Transaction*, std::allocator<ObjectStore::Transaction*> >&, unsigned long, ThreadPool::TPHandle*)+0x138) [0xabb2ee] 13: (KeyValueStore::_do_op(KeyValueStore::OpSequencer*, ThreadPool::TPHandle&)+0x1f5) [0xabac11] 14: (KeyValueStore::OpWQ::_process(KeyValueStore::OpSequencer*, ThreadPool::TPHandle&)+0x2f) [0xad3f23] 15: (ThreadPool::WorkQueue<KeyValueStore::OpSequencer>::_void_process(void*, ThreadPool::TPHandle&)+0x33) [0xadf645] 16: (ThreadPool::worker(ThreadPool::WorkThread*)+0x734) [0xb28f7c] 17: (ThreadPool::WorkThread::entry()+0x23) [0xb2d031] 18: (Thread::entry_wrapper()+0x79) [0xb21647] 19: (Thread::_entry_func(void*)+0x18) [0xb215c4] 20: (()+0x8182) [0x7fe62130b182] 21: (clone()+0x6d) [0x7fe61fc8330d] NOTE: a copy of the executable, or `objdump -rdS <executable>` is needed to interpret this. It's a new test (long file names and collection_move) that addresses an issue with the FileStore, but KeyValueStore doesn't seem to like it either... Thanks! sage On Tue, 22 Jul 2014, Sage Weil wrote: > Hi Haomai, > > Do you mind looking at wip-memstore at > > https://github.com/ceph/ceph/pull/2125 > > A couple minor fixes and then we can enable it in ceph_test_objectstore. > > Also, I would love any feedback on wip-objectstore > > https://github.com/ceph/ceph/pull/2124 > > That one is RFC at this point. I'm trying to simplify the ObjectStore > interface as much as possible. > > Thanks! > sage > > > -- > To unsubscribe from this list: send the line "unsubscribe ceph-devel" in > the body of a message to majord...@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html > > -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html