Hi, Is there a known issue with using 64K Kernel PAGE_SIZE? I am using ARM64 systems, and I upgraded from 0.94.4 to 9.2.1 today. The system which was on 4K page size, came up OK and OSDs are all online. Systems with 64K Page size are all seeing the OSDs crash with following stack: Begin dump of recent events --- -54> 2016-03-01 20:52:56.489752 ffff97e38f10 5 asok(0xaaaaff6c0000) register_command perfcounters_dump hook 0xaaaaff63c030 -53> 2016-03-01 20:52:56.489798 ffff97e38f10 5 asok(0xaaaaff6c0000) register_command 1 hook 0xaaaaff63c030 -52> 2016-03-01 20:52:56.489809 ffff97e38f10 5 asok(0xaaaaff6c0000) register_command perf dump hook 0xaaaaff63c030 -51> 2016-03-01 20:52:56.489819 ffff97e38f10 5 asok(0xaaaaff6c0000) register_command perfcounters_schema hook 0xaaaaff63c030 -50> 2016-03-01 20:52:56.489829 ffff97e38f10 5 asok(0xaaaaff6c0000) register_command 2 hook 0xaaaaff63c030 -49> 2016-03-01 20:52:56.489839 ffff97e38f10 5 asok(0xaaaaff6c0000) register_command perf schema hook 0xaaaaff63c030 -48> 2016-03-01 20:52:56.489849 ffff97e38f10 5 asok(0xaaaaff6c0000) register_command perf reset hook 0xaaaaff63c030 -47> 2016-03-01 20:52:56.489858 ffff97e38f10 5 asok(0xaaaaff6c0000) register_command config show hook 0xaaaaff63c030 -46> 2016-03-01 20:52:56.489868 ffff97e38f10 5 asok(0xaaaaff6c0000) register_command config set hook 0xaaaaff63c030 -45> 2016-03-01 20:52:56.489877 ffff97e38f10 5 asok(0xaaaaff6c0000) register_command config get hook 0xaaaaff63c030 -44> 2016-03-01 20:52:56.489886 ffff97e38f10 5 asok(0xaaaaff6c0000) register_command config diff hook 0xaaaaff63c030 -43> 2016-03-01 20:52:56.489896 ffff97e38f10 5 asok(0xaaaaff6c0000) register_command log flush hook 0xaaaaff63c030 -42> 2016-03-01 20:52:56.489905 ffff97e38f10 5 asok(0xaaaaff6c0000) register_command log dump hook 0xaaaaff63c030 -41> 2016-03-01 20:52:56.489914 ffff97e38f10 5 asok(0xaaaaff6c0000) register_command log reopen hook 0xaaaaff63c030 -40> 2016-03-01 20:52:56.497924 ffff97e38f10 0 set uid:gid to 64045:64045 -39> 2016-03-01 20:52:56.498074 ffff97e38f10 0 ceph version 9.2.1 (752b6a3020c3de74e07d2a8b4c5e48dab5a6b6fd), process ceph-osd, pid 17095 -38> 2016-03-01 20:52:56.499547 ffff97e38f10 1 -- 10.18.240.124:0/0 learned my addr 10.18.240.124:0/0 -37> 2016-03-01 20:52:56.499572 ffff97e38f10 1 accepter.accepter.bind my_inst.addr is 10.18.240.124:6802/17095 need_addr=0 -36> 2016-03-01 20:52:56.499620 ffff97e38f10 1 -- 192.168.240.124:0/0 learned my addr 192.168.240.124:0/0 -35> 2016-03-01 20:52:56.499638 ffff97e38f10 1 accepter.accepter.bind my_inst.addr is 192.168.240.124:6802/17095 need_addr=0 -34> 2016-03-01 20:52:56.499673 ffff97e38f10 1 -- 192.168.240.124:0/0 learned my addr 192.168.240.124:0/0 -33> 2016-03-01 20:52:56.499690 ffff97e38f10 1 accepter.accepter.bind my_inst.addr is 192.168.240.124:6803/17095 need_addr=0 -32> 2016-03-01 20:52:56.499724 ffff97e38f10 1 -- 10.18.240.124:0/0 learned my addr 10.18.240.124:0/0 -31> 2016-03-01 20:52:56.499741 ffff97e38f10 1 accepter.accepter.bind my_inst.addr is 10.18.240.124:6803/17095 need_addr=0 -30> 2016-03-01 20:52:56.503307 ffff97e38f10 5 asok(0xaaaaff6c0000) init /var/run/ceph/ceph-osd.100.asok -29> 2016-03-01 20:52:56.503329 ffff97e38f10 5 asok(0xaaaaff6c0000) bind_and_listen /var/run/ceph/ceph-osd.100.asok -28> 2016-03-01 20:52:56.503460 ffff97e38f10 5 asok(0xaaaaff6c0000) register_command 0 hook 0xaaaaff6380c0 -27> 2016-03-01 20:52:56.503479 ffff97e38f10 5 asok(0xaaaaff6c0000) register_command version hook 0xaaaaff6380c0 -26> 2016-03-01 20:52:56.503490 ffff97e38f10 5 asok(0xaaaaff6c0000) register_command git_version hook 0xaaaaff6380c0 -25> 2016-03-01 20:52:56.503500 ffff97e38f10 5 asok(0xaaaaff6c0000) register_command help hook 0xaaaaff63c1e0 -24> 2016-03-01 20:52:56.503510 ffff97e38f10 5 asok(0xaaaaff6c0000) register_command get_command_descriptions hook 0xaaaaff63c1f0 -23> 2016-03-01 20:52:56.503566 ffff9643f030 5 asok(0xaaaaff6c0000) entry start -22> 2016-03-01 20:52:56.503635 ffff97e38f10 10 monclient(hunting): build_initial_monmap -21> 2016-03-01 20:52:56.520227 ffff97e38f10 5 adding auth protocol: cephx -20> 2016-03-01 20:52:56.520244 ffff97e38f10 5 adding auth protocol: cephx -19> 2016-03-01 20:52:56.520427 ffff97e38f10 5 asok(0xaaaaff6c0000) register_command objecter_requests hook 0xaaaaff63c2b0 -18> 2016-03-01 20:52:56.520538 ffff97e38f10 1 -- 10.18.240.124:6802/17095 messenger.start -17> 2016-03-01 20:52:56.520601 ffff97e38f10 1 -- :/0 messenger.start -16> 2016-03-01 20:52:56.520655 ffff97e38f10 1 -- 10.18.240.124:6803/17095 messenger.start -15> 2016-03-01 20:52:56.520712 ffff97e38f10 1 -- 192.168.240.124:6803/17095 messenger.start -14> 2016-03-01 20:52:56.520768 ffff97e38f10 1 -- 192.168.240.124:6802/17095 messenger.start -13> 2016-03-01 20:52:56.520824 ffff97e38f10 1 -- :/0 messenger.start -12> 2016-03-01 20:52:56.520973 ffff97e38f10 2 osd.100 0 mounting /var/lib/ceph/osd/ceph-100 /var/lib/ceph/osd/ceph-100/journal -11> 2016-03-01 20:52:56.521095 ffff97e38f10 0 filestore(/var/lib/ceph/osd/ceph-100) backend xfs (magic 0x58465342) -10> 2016-03-01 20:52:56.521640 ffff97e38f10 0 genericfilestorebackend(/var/lib/ceph/osd/ceph-100) detect_features: FIEMAP ioctl is disabled via 'filestore fiemap' config option -9> 2016-03-01 20:52:56.521659 ffff97e38f10 0 genericfilestorebackend(/var/lib/ceph/osd/ceph-100) detect_features: SEEK_DATA/SEEK_HOLE is disabled via 'filestore seek data hole' config option -8> 2016-03-01 20:52:56.521696 ffff97e38f10 0 genericfilestorebackend(/var/lib/ceph/osd/ceph-100) detect_features: splice is supported -7> 2016-03-01 20:52:56.542459 ffff97e38f10 0 genericfilestorebackend(/var/lib/ceph/osd/ceph-100) detect_features: syncfs(2) syscall fully supported (by glibc and kernel) -6> 2016-03-01 20:52:56.542582 ffff97e38f10 0 xfsfilestorebackend(/var/lib/ceph/osd/ceph-100) detect_features: extsize is supported and your kernel >= 3.5 -5> 2016-03-01 20:52:56.602688 ffff97e38f10 0 filestore(/var/lib/ceph/osd/ceph-100) mount: enabling WRITEAHEAD journal mode: checkpoint is not enabled -4> 2016-03-01 20:52:56.649576 ffff97e38f10 2 journal open /var/lib/ceph/osd/ceph-100/journal fsid 20ef1e17-8c52-42fe-ae82-ddb094220f48 fs_op_seq 300803 -3> 2016-03-01 20:52:56.649687 ffff97e38f10 1 journal _open /var/lib/ceph/osd/ceph-100/journal fd 19: 6291456000 bytes, block size 4096 bytes, directio = 1, aio = 1 -2> 2016-03-01 20:52:56.650394 ffff97e38f10 2 journal open journal block size 65536 != current 4096 -1> 2016-03-01 20:52:56.650412 ffff97e38f10 3 journal journal_replay open failed with (22) Invalid argument 0> 2016-03-01 20:52:56.654595 ffff97e38f10 -1 os/FileJournal.h: In function 'virtual FileJournal::~FileJournal()' thread ffff97e38f10 time 2016-03-01 20:52:56.650433 os/FileJournal.h: 406: FAILED assert(fd == -1) thanks Pankaj |
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com