Nothing of this did't happen. After OSDs fell I found this file /var/lib/ceph/osd/ceph-4/current/3.2_head/rb.0.19f2e.238e1f29.000000000728__head_813E90A3__3. Location of this file seemed for me is very strange and I just remove it and then all osds was started up.
On Fri, Feb 26, 2016 at 7:03 PM, Alexey Sheplyakov <asheplya...@mirantis.com > wrote: > Alexander, > > > # ceph osd pool get-quota cache > > quotas for pool 'cache': > > max objects: N/A > > max bytes : N/A > > But I set target_max_bytes: > > # ceph osd pool set cache target_max_bytes 1000000000000 > > Can it serve as the reason? > > I've been unable to reproduce http://tracker.ceph.com/issues/13098 > without setting max_bytes. > Perhaps you hit a different bug. > > > Every time 2 of 18 OSDs are crashing. > > How have they got to that state? Were some of OSDs full/nearly full? > Has the cache pool ever reached its target_max_bytes? Anything else > which might be relevant? > > Best regards, > Alexey > > > On Wed, Feb 24, 2016 at 7:36 PM, Alexander Gubanov <sht...@gmail.com> > wrote: > > Hm. It seems that the cache pool qoutas have not been set. At least I'm > sure > > I didn't set them. > > > > # ceph osd pool get-quota cache > > quotas for pool 'cache': > > max objects: N/A > > max bytes : N/A > > > > Hmm. It seems that the cache pool quota have not been set. At least I'm > sure > > I didn't set it. Maybe it have default setting. > > > > # ceph osd pool get-quota cache > > quotas for pool 'cache': > > max objects: N/A > > max bytes : N/A > > > > But I set target_max_bytes: > > > > # ceph osd pool set cache target_max_bytes 1000000000000 > > > > Can it serve as the reason? > > > > On Wed, Feb 24, 2016 at 4:08 PM, Alexey Sheplyakov > > <asheplya...@mirantis.com> wrote: > >> > >> Hi, > >> > >> > 0> 2016-02-24 04:51:45.884445 7fd994825700 -1 osd/ReplicatedPG.cc: In > >> > function 'int ReplicatedPG::fill_in_copy_get(ReplicatedPG::OpContext*, > >> > ceph::buffer::list::iterator&, OSDOp&, ObjectContextRef&, bool)' > thread > >> > 7fd994825700 time 2016-02-24 04:51:45.870995 > >> osd/ReplicatedPG.cc: 5558: FAILED assert(cursor.data_complete) > >> > ceph version 0.80.11-8-g95c4287 > >> > (95c4287b5d24b762bc8538633c5bb2918ecfe4dd) > >> > >> This one looks familiar: http://tracker.ceph.com/issues/13098 > >> > >> A quick work around is to unset the cache pool quota: > >> > >> ceph osd pool set-quota $cache_pool_name max_bytes 0 > >> ceph osd pool set-quota $cache_pool_name max_objects 0 > >> > >> The problem has been properly fixed in infernalis v9.1.0, and > >> (partially) in hammer (v0.94.6 which will be released soon). > >> > >> Best regards, > >> Alexey > >> > >> > >> On Wed, Feb 24, 2016 at 5:37 AM, Alexander Gubanov <sht...@gmail.com> > >> wrote: > >> > Hi, > >> > > >> > Every time 2 of 18 OSDs are crashing. I think it's happening when run > PG > >> > replication because crashing only 2 OSDs and every time they're are > the > >> > same. > >> > > >> > 0> 2016-02-24 04:51:45.884445 7fd994825700 -1 osd/ReplicatedPG.cc: In > >> > function 'int ReplicatedPG::fill_in_copy_get(ReplicatedPG::OpContext*, > >> > ceph::buffer::list::iterator&, OSDOp&, ObjectContextRef&, bool)' > thread > >> > 7fd994825700 time 2016-02-24 04:51:45.870995 > >> > osd/ReplicatedPG.cc: 5558: FAILED assert(cursor.data_complete) > >> > > >> > ceph version 0.80.11-8-g95c4287 > >> > (95c4287b5d24b762bc8538633c5bb2918ecfe4dd) > >> > 1: (ReplicatedPG::fill_in_copy_get(ReplicatedPG::OpContext*, > >> > ceph::buffer::list::iterator&, OSDOp&, > >> > std::tr1::shared_ptr<ObjectContext>&, > >> > bool)+0xffc) [0x7c1f7c] > >> > 2: (ReplicatedPG::do_osd_ops(ReplicatedPG::OpContext*, > >> > std::vector<OSDOp, > >> > std::allocator<OSDOp> >&)+0x4171) [0x809f21] > >> > 3: (ReplicatedPG::prepare_transaction(ReplicatedPG::OpContext*)+0x62) > >> > [0x814622] > >> > 4: (ReplicatedPG::execute_ctx(ReplicatedPG::OpContext*)+0x5f8) > >> > [0x815098] > >> > 5: (ReplicatedPG::do_op(std::tr1::shared_ptr<OpRequest>)+0x3dd4) > >> > [0x81a3f4] > >> > 6: (ReplicatedPG::do_request(std::tr1::shared_ptr<OpRequest>, > >> > ThreadPool::TPHandle&)+0x66d) [0x7b4ecd] > >> > 7: (OSD::dequeue_op(boost::intrusive_ptr<PG>, > >> > std::tr1::shared_ptr<OpRequest>, ThreadPool::TPHandle&)+0x3a5) > >> > [0x600ee5] > >> > 8: (OSD::OpWQ::_process(boost::intrusive_ptr<PG>, > >> > ThreadPool::TPHandle&)+0x203) [0x61cba3] > >> > 9: (ThreadPool::WorkQueueVal<std::pair<boost::intrusive_ptr<PG>, > >> > std::tr1::shared_ptr<OpRequest> >, boost::intrusive_ptr<PG> > >> >>::_void_process(void*, ThreadPool::TPHandle&)+0xac) [0x660f2c] > >> > 10: (ThreadPool::worker(ThreadPool::WorkThread*)+0xb20) [0xa7def0] > >> > 11: (ThreadPool::WorkThread::entry()+0x10) [0xa7ede0] > >> > 12: (()+0x7dc5) [0x7fd9ad03edc5] > >> > 13: (clone()+0x6d) [0x7fd9abd2828d] > >> > NOTE: a copy of the executable, or `objdump -rdS <executable>` is > >> > needed to > >> > interpret this. > >> > > >> > --- logging levels --- > >> > 0/ 5 none > >> > 0/ 1 lockdep > >> > 0/ 1 context > >> > 1/ 1 crush > >> > 1/ 5 mds > >> > 1/ 5 mds_balancer > >> > 1/ 5 mds_locker > >> > 1/ 5 mds_log > >> > 1/ 5 mds_log_expire > >> > 1/ 5 mds_migrator > >> > 0/ 1 buffer > >> > 0/ 1 timer > >> > 0/ 1 filer > >> > 0/ 1 striper > >> > 0/ 1 objecter > >> > 0/ 5 rados > >> > 0/ 5 rbd > >> > 0/ 5 journaler > >> > 0/ 5 objectcacher > >> > 0/ 5 client > >> > 0/ 5 osd > >> > 0/ 5 optracker > >> > 0/ 5 objclass > >> > 1/ 3 filestore > >> > 1/ 3 keyvaluestore > >> > 1/ 3 journal > >> > 0/ 5 ms > >> > 1/ 5 mon > >> > 0/10 monc > >> > 1/ 5 paxos > >> > 0/ 5 tp > >> > 1/ 5 auth > >> > 1/ 5 crypto > >> > 1/ 1 finisher > >> > 1/ 5 heartbeatmap > >> > 1/ 5 perfcounter > >> > 1/ 5 rgw > >> > 1/10 civetweb > >> > 1/ 5 javaclient > >> > 1/ 5 asok > >> > 1/ 1 throttle > >> > -2/-2 (syslog threshold) > >> > -1/-1 (stderr threshold) > >> > max_recent 10000 > >> > max_new 1000 > >> > log_file /var/log/ceph/ceph-osd.3.log > >> > --- end dump of recent events --- > >> > 2016-02-24 04:51:45.944447 7fd994825700 -1 *** Caught signal (Aborted) > >> > ** > >> > in thread 7fd994825700 > >> > > >> > ceph version 0.80.11-8-g95c4287 > >> > (95c4287b5d24b762bc8538633c5bb2918ecfe4dd) > >> > 1: /usr/bin/ceph-osd() [0x9a24f6] > >> > 2: (()+0xf100) [0x7fd9ad046100] > >> > 3: (gsignal()+0x37) [0x7fd9abc675f7] > >> > 4: (abort()+0x148) [0x7fd9abc68ce8] > >> > 5: (__gnu_cxx::__verbose_terminate_handler()+0x165) [0x7fd9ac56b9d5] > >> > 6: (()+0x5e946) [0x7fd9ac569946] > >> > 7: (()+0x5e973) [0x7fd9ac569973] > >> > 8: (()+0x5eb93) [0x7fd9ac569b93] > >> > 9: (ceph::__ceph_assert_fail(char const*, char const*, int, char > >> > const*)+0x1ef) [0xa8d9df] > >> > 10: (ReplicatedPG::fill_in_copy_get(ReplicatedPG::OpContext*, > >> > ceph::buffer::list::iterator&, OSDOp&, > >> > std::tr1::shared_ptr<ObjectContext>&, > >> > bool)+0xffc) [0x7c1f7c] > >> > 11: (ReplicatedPG::do_osd_ops(ReplicatedPG::OpContext*, > >> > std::vector<OSDOp, > >> > std::allocator<OSDOp> >&)+0x4171) [0x809f21] > >> > 12: > (ReplicatedPG::prepare_transaction(ReplicatedPG::OpContext*)+0x62) > >> > [0x814622] > >> > 13: (ReplicatedPG::execute_ctx(ReplicatedPG::OpContext*)+0x5f8) > >> > [0x815098] > >> > 14: (ReplicatedPG::do_op(std::tr1::shared_ptr<OpRequest>)+0x3dd4) > >> > [0x81a3f4] > >> > 15: (ReplicatedPG::do_request(std::tr1::shared_ptr<OpRequest>, > >> > ThreadPool::TPHandle&)+0x66d) [0x7b4ecd] > >> > 16: (OSD::dequeue_op(boost::intrusive_ptr<PG>, > >> > std::tr1::shared_ptr<OpRequest>, ThreadPool::TPHandle&)+0x3a5) > >> > [0x600ee5] > >> > 17: (OSD::OpWQ::_process(boost::intrusive_ptr<PG>, > >> > ThreadPool::TPHandle&)+0x203) [0x61cba3] > >> > 18: (ThreadPool::WorkQueueVal<std::pair<boost::intrusive_ptr<PG>, > >> > std::tr1::shared_ptr<OpRequest> >, boost::intrusive_ptr<PG> > >> >>::_void_process(void*, ThreadPool::TPHandle&)+0xac) [0x660f2c] > >> > 19: (ThreadPool::worker(ThreadPool::WorkThread*)+0xb20) [0xa7def0] > >> > 20: (ThreadPool::WorkThread::entry()+0x10) [0xa7ede0] > >> > 21: (()+0x7dc5) [0x7fd9ad03edc5] > >> > 22: (clone()+0x6d) [0x7fd9abd2828d] > >> > NOTE: a copy of the executable, or `objdump -rdS <executable>` is > >> > needed to > >> > interpret this. > >> > > >> > --- begin dump of recent events --- > >> > -5> 2016-02-24 04:51:45.904559 7fd995026700 5 -- op tracker -- , > >> > seq: > >> > 19230, time: 2016-02-24 04:51:45.904559, event: started, request: > >> > osd_op(osd.13.12097:806246 rb.0.218d6.238e1f29.000000010db3@snapdir > >> > [list-snaps] 3.94c2bed2 > >> > ack+read+ignore_cache+ignore_overlay+map_snap_clone > >> > e13252) v4 > >> > -4> 2016-02-24 04:51:45.904598 7fd995026700 1 -- > >> > 172.16.0.1:6801/419703 > >> > --> 172.16.0.3:6844/12260 -- osd_op_reply(806246 > >> > rb.0.218d6.238e1f29.000000010db3 [list-snaps] v0'0 uv27683057 ondisk = > >> > 0) v6 > >> > -- ?+0 0x9f90800 con 0x1b7838c0 > >> > -3> 2016-02-24 04:51:45.904616 7fd995026700 5 -- op tracker -- , > >> > seq: > >> > 19230, time: 2016-02-24 04:51:45.904616, event: done, request: > >> > osd_op(osd.13.12097:806246 rb.0.218d6.238e1f29.000000010db3@snapdir > >> > [list-snaps] 3.94c2bed2 > >> > ack+read+ignore_cache+ignore_overlay+map_snap_clone > >> > e13252) v4 > >> > -2> 2016-02-24 04:51:45.904637 7fd995026700 5 -- op tracker -- , > >> > seq: > >> > 19231, time: 2016-02-24 04:51:45.904637, event: reached_pg, request: > >> > osd_op(osd.13.12097:806247 rb.0.218d6.238e1f29.000000010db3 [copy-get > >> > max > >> > 8388608] 3.94c2bed2 > ack+read+ignore_cache+ignore_overlay+map_snap_clone > >> > e13252) v4 > >> > -1> 2016-02-24 04:51:45.904673 7fd995026700 5 -- op tracker -- , > >> > seq: > >> > 19231, time: 2016-02-24 04:51:45.904673, event: started, request: > >> > osd_op(osd.13.12097:806247 rb.0.218d6.238e1f29.000000010db3 [copy-get > >> > max > >> > 8388608] 3.94c2bed2 > ack+read+ignore_cache+ignore_overlay+map_snap_clone > >> > e13252) v4 > >> > 0> 2016-02-24 04:51:45.944447 7fd994825700 -1 *** Caught signal > >> > (Aborted) ** > >> > in thread 7fd994825700 > >> > > >> > ceph version 0.80.11-8-g95c4287 > >> > (95c4287b5d24b762bc8538633c5bb2918ecfe4dd) > >> > 1: /usr/bin/ceph-osd() [0x9a24f6] > >> > 2: (()+0xf100) [0x7fd9ad046100] > >> > 3: (gsignal()+0x37) [0x7fd9abc675f7] > >> > 4: (abort()+0x148) [0x7fd9abc68ce8] > >> > 5: (__gnu_cxx::__verbose_terminate_handler()+0x165) [0x7fd9ac56b9d5] > >> > 6: (()+0x5e946) [0x7fd9ac569946] > >> > 7: (()+0x5e973) [0x7fd9ac569973] > >> > 8: (()+0x5eb93) [0x7fd9ac569b93] > >> > 9: (ceph::__ceph_assert_fail(char const*, char const*, int, char > >> > const*)+0x1ef) [0xa8d9df] > >> > 10: (ReplicatedPG::fill_in_copy_get(ReplicatedPG::OpContext*, > >> > ceph::buffer::list::iterator&, OSDOp&, > >> > std::tr1::shared_ptr<ObjectContext>&, > >> > bool)+0xffc) [0x7c1f7c] > >> > 11: (ReplicatedPG::do_osd_ops(ReplicatedPG::OpContext*, > >> > std::vector<OSDOp, > >> > std::allocator<OSDOp> >&)+0x4171) [0x809f21] > >> > 12: > (ReplicatedPG::prepare_transaction(ReplicatedPG::OpContext*)+0x62) > >> > [0x814622] > >> > 13: (ReplicatedPG::execute_ctx(ReplicatedPG::OpContext*)+0x5f8) > >> > [0x815098] > >> > 14: (ReplicatedPG::do_op(std::tr1::shared_ptr<OpRequest>)+0x3dd4) > >> > [0x81a3f4] > >> > 15: (ReplicatedPG::do_request(std::tr1::shared_ptr<OpRequest>, > >> > ThreadPool::TPHandle&)+0x66d) [0x7b4ecd] > >> > 16: (OSD::dequeue_op(boost::intrusive_ptr<PG>, > >> > std::tr1::shared_ptr<OpRequest>, ThreadPool::TPHandle&)+0x3a5) > >> > [0x600ee5] > >> > 17: (OSD::OpWQ::_process(boost::intrusive_ptr<PG>, > >> > ThreadPool::TPHandle&)+0x203) [0x61cba3] > >> > 18: (ThreadPool::WorkQueueVal<std::pair<boost::intrusive_ptr<PG>, > >> > std::tr1::shared_ptr<OpRequest> >, boost::intrusive_ptr<PG> > >> >>::_void_process(void*, ThreadPool::TPHandle&)+0xac) [0x660f2c] > >> > 19: (ThreadPool::worker(ThreadPool::WorkThread*)+0xb20) [0xa7def0] > >> > 20: (ThreadPool::WorkThread::entry()+0x10) [0xa7ede0] > >> > 21: (()+0x7dc5) [0x7fd9ad03edc5] > >> > 22: (clone()+0x6d) [0x7fd9abd2828d] > >> > NOTE: a copy of the executable, or `objdump -rdS <executable>` is > >> > needed to > >> > interpret this. > >> > > >> > --- logging levels --- > >> > 0/ 5 none > >> > 0/ 1 lockdep > >> > 0/ 1 context > >> > 1/ 1 crush > >> > 1/ 5 mds > >> > 1/ 5 mds_balancer > >> > 1/ 5 mds_locker > >> > 1/ 5 mds_log > >> > 1/ 5 mds_log_expire > >> > 1/ 5 mds_migrator > >> > 0/ 1 buffer > >> > 0/ 1 timer > >> > 0/ 1 filer > >> > 0/ 1 striper > >> > 0/ 1 objecter > >> > 0/ 5 rados > >> > 0/ 5 rbd > >> > 0/ 5 journaler > >> > 0/ 5 objectcacher > >> > 0/ 5 client > >> > 0/ 5 osd > >> > 0/ 5 optracker > >> > 0/ 5 objclass > >> > 1/ 3 filestore > >> > 1/ 3 keyvaluestore > >> > 1/ 3 journal > >> > 0/ 5 ms > >> > 1/ 5 mon > >> > 0/10 monc > >> > 1/ 5 paxos > >> > 0/ 5 tp > >> > 1/ 5 auth > >> > 1/ 5 crypto > >> > 1/ 1 finisher > >> > 1/ 5 heartbeatmap > >> > 1/ 5 perfcounter > >> > 1/ 5 rgw > >> > 1/10 civetweb > >> > 1/ 5 javaclient > >> > 1/ 5 asok > >> > 1/ 1 throttle > >> > -2/-2 (syslog threshold) > >> > -1/-1 (stderr threshold) > >> > max_recent 10000 > >> > max_new 1000 > >> > log_file /var/log/ceph/ceph-osd.3.log > >> > --- end dump of recent events --- > >> > > >> > -- > >> > Alexander Gubanov > >> > > >> > _______________________________________________ > >> > ceph-users mailing list > >> > ceph-users@lists.ceph.com > >> > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > >> > > > > > > > > > > > -- > > Alexander Gubanov > > > > _______________________________________________ > > ceph-users mailing list > > ceph-users@lists.ceph.com > > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > > > -- Alexander Gubanov
_______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
