Hello, I'm using a server side replication on 6 servers. Glusterfsd crashes on a few hour basis: gdb -se /usr/sbin/glusterfsd -c /core.26947 GNU gdb Fedora (6.8-27.el5) Copyright (C) 2008 Free Software Foundation, Inc. License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html> This is free software: you are free to change and redistribute it. There is NO WARRANTY, to the extent permitted by law. Type "show copying" and "show warranty" for details. This GDB was configured as "x86_64-redhat-linux-gnu"... (no debugging symbols found) warning: .dynamic section for "/usr/lib64/libglusterfs.so.0" is not at the expected address warning: difference appears to be caused by prelink, adjusting expectations Reading symbols from /usr/lib64/libglusterfs.so.0...done. Loaded symbols for /usr/lib64/libglusterfs.so.0 Reading symbols from /lib64/libdl.so.2...done. Loaded symbols for /lib64/libdl.so.2 Reading symbols from /lib64/libpthread.so.0...done. Loaded symbols for /lib64/libpthread.so.0 Reading symbols from /lib64/libc.so.6...done. Loaded symbols for /lib64/libc.so.6 Reading symbols from /lib64/ld-linux-x86-64.so.2...done. Loaded symbols for /lib64/ld-linux-x86-64.so.2 Reading symbols from /usr/lib64/glusterfs/2.0.2/xlator/storage/posix.so...done. Loaded symbols for /usr/lib64/glusterfs/2.0.2/xlator/storage/posix.so Reading symbols from /usr/lib64/glusterfs/2.0.2/xlator/features/locks.so...done. Loaded symbols for /usr/lib64/glusterfs/2.0.2/xlator/features/locks.so Reading symbols from /usr/lib64/glusterfs/2.0.2/xlator/performance/io-threads.so...done. Loaded symbols for /usr/lib64/glusterfs/2.0.2/xlator/performance/io-threads.so Reading symbols from /usr/lib64/glusterfs/2.0.2/xlator/protocol/client.so...done. Loaded symbols for /usr/lib64/glusterfs/2.0.2/xlator/protocol/client.so Reading symbols from /usr/lib64/glusterfs/2.0.2/xlator/cluster/replicate.so...done. Loaded symbols for /usr/lib64/glusterfs/2.0.2/xlator/cluster/replicate.so Reading symbols from /usr/lib64/glusterfs/2.0.2/xlator/protocol/server.so...done. Loaded symbols for /usr/lib64/glusterfs/2.0.2/xlator/protocol/server.so Reading symbols from /usr/lib64/glusterfs/2.0.2/transport/socket.so...done. Loaded symbols for /usr/lib64/glusterfs/2.0.2/transport/socket.so Reading symbols from /usr/lib64/glusterfs/2.0.2/auth/addr.so...done. Loaded symbols for /usr/lib64/glusterfs/2.0.2/auth/addr.so Reading symbols from /lib64/libnss_files.so.2...done. Loaded symbols for /lib64/libnss_files.so.2 Reading symbols from /lib64/libgcc_s.so.1...done. Loaded symbols for /lib64/libgcc_s.so.1 Core was generated by `/usr/sbin/glusterfsd -f /etc/glusterfs/glusterfsd.vol'. Program terminated with signal 6, Aborted. [New process 26947] [New process 26956] [New process 26955] [New process 26954] [New process 26953] [New process 26952] [New process 26951] [New process 26950] [New process 26949] [New process 26948] #0 0x0000003040030215 in raise () from /lib64/libc.so.6 (gdb) bt #0 0x0000003040030215 in raise () from /lib64/libc.so.6 #1 0x0000003040031cc0 in abort () from /lib64/libc.so.6 #2 0x000000304006a7fb in __libc_message () from /lib64/libc.so.6 #3 0x0000003040071ce2 in _int_free () from /lib64/libc.so.6 #4 0x000000304007590c in free () from /lib64/libc.so.6 #5 0x00002aaaaaaadcc9 in __socket_ioq_entry_free (entry=0x2aaab001da30) at socket.c:331 #6 0x00002aaaaaaaf1c9 in __socket_ioq_churn_entry (this=<value optimized out>, entry=0x2aaab001da30) at socket.c:368 #7 0x00002aaaaaaaf8ec in socket_submit (this=0xae11a70, buf=0x2aaab00378c0 "", len=340, vector=0x0, count=<value optimized out>, iobref=<value optimized out>) at socket.c:1281 #8 0x00002b2e7c775bd3 in protocol_client_xfer (frame=0x2aaab0030ab0, this=0xae0ab00, trans=0xae11a70, type=1, op=40, hdr=0x2aaab00378c0, hdrlen=340, vector=0x0, count=0, iobref=0x0) at client-protocol.c:636 #9 0x00002b2e7c77bc1a in client_xattrop (frame=0x2aaab0030ab0, this=0xae0ab00, loc=0x2aaab4004238, flags=GF_XATTROP_ADD_ARRAY, dict=0x2aaab4031fc0) at client-protocol.c:1922 #10 0x00002b2e7c9a2cda in afr_changelog_pre_op (frame=0x2aaab401ea70, this=0xae0b280) at afr-transaction.c:782 #11 0x00002b2e7c9a2f31 in afr_lock_rec (frame=0x2aaab401ea70, this=0xae0b280, child_index=1) at afr-transaction.c:979 #12 0x00002b2e7c9a36a8 in afr_lock_cbk (frame=0x2aaab401ea70, cookie=<value optimized out>, this=0xae0b280, op_ret=0, op_errno=0) at afr-transaction.c:906 #13 0x00002b2e7b6a75f0 in default_inodelk_cbk (frame=<value optimized out>, cookie=<value optimized out>, this=<value optimized out>, op_ret=-1, op_errno=128) at defaults.c:1199 #14 0x00002b2e7c358182 in pl_inodelk (frame=0x2aaab4034c10, this=0xae08870, volume=<value optimized out>, loc=0x2aaab4032170, cmd=7, flock=0x0) at internal.c:194 #15 0x00002b2e7b6a815c in default_inodelk (frame=0x2aaab4017660, this=0xae09080, volume=0xae0b260 "replicate", loc=0x2aaab4004238, cmd=7, lock=0x7fff2f422f80) at defaults.c:1209 #16 0x00002b2e7c9a33ba in afr_lock_rec (frame=0x2aaab401ea70, this=0xae0b280, child_index=0) at afr-transaction.c:1006 #17 0x00002b2e7c9a35c2 in afr_transaction (frame=0x2aaab401ea70, this=0xae0b280, type=AFR_DATA_TRANSACTION) at afr-transaction.c:1170 #18 0x00002b2e7c9a07cd in afr_truncate (frame=0x2aaab403ac30, this=0xae0b280, loc=0x2aaab40174a0, offset=0) at afr-inode-write.c:1224 #19 0x00002b2e7cbc0969 in server_truncate_resume (frame=0x2aaab403acc0, this=<value optimized out>, loc=0x2aaab40174a0, offset=0) at server-protocol.c:4243 #20 0x00002b2e7b6b06f7 in call_resume (stub=0x2aaab4017470) at call-stub.c:2384 #21 0x00002b2e7cbc4125 in server_truncate (frame=0x2aaab403acc0, bound_xl=<value optimized out>, hdr=<value optimized out>, hdrlen=<value optimized out>, iobuf=<value optimized out>) at server-protocol.c:4291 #22 0x00002b2e7cbbfb20 in protocol_server_pollin (this=0xae0bdf0, trans=0xae17960) at server-protocol.c:7735 #23 0x00002b2e7cbbfbfb in notify (this=0xae0bdf0, event=<value optimized out>, data=0x6) at server-protocol.c:7791 #24 0x00002aaaaaaafb43 in socket_event_handler (fd=<value optimized out>, idx=11, data=0xae17960, poll_in=1, poll_out=0, poll_err=0) at socket.c:813 #25 0x00002b2e7b6ba2a5 in event_dispatch_epoll (event_pool=0xae02300) at event.c:804 #26 0x0000000000403899 in main () (gdb) bt full #0 0x0000003040030215 in raise () from /lib64/libc.so.6 No symbol table info available. #1 0x0000003040031cc0 in abort () from /lib64/libc.so.6 No symbol table info available. #2 0x000000304006a7fb in __libc_message () from /lib64/libc.so.6 No symbol table info available. #3 0x0000003040071ce2 in _int_free () from /lib64/libc.so.6 No symbol table info available. #4 0x000000304007590c in free () from /lib64/libc.so.6 No symbol table info available. #5 0x00002aaaaaaadcc9 in __socket_ioq_entry_free (entry=0x2aaab001da30) at socket.c:331 No locals. #6 0x00002aaaaaaaf1c9 in __socket_ioq_churn_entry (this=<value optimized out>, entry=0x2aaab001da30) at socket.c:368 ret = 0 __PRETTY_FUNCTION__ = "__socket_ioq_churn_entry" #7 0x00002aaaaaaaf8ec in socket_submit (this=0xae11a70, buf=0x2aaab00378c0 "", len=340, vector=0x0, count=<value optimized out>, iobref=<value optimized out>) at socket.c:1281 priv = (socket_private_t *) 0xae11ec0 ret = <value optimized out> need_poll_out = <value optimized out> entry = (struct ioq *) 0x2aaab001da30 ctx = (glusterfs_ctx_t *) 0xae02010 __FUNCTION__ = "socket_submit" #8 0x00002b2e7c775bd3 in protocol_client_xfer (frame=0x2aaab0030ab0, this=0xae0ab00, trans=0xae11a70, type=1, op=40, hdr=0x2aaab00378c0, hdrlen=340, vector=0x0, count=0, iobref=0x0) at client-protocol.c:636 conf = (client_conf_t *) 0xae113c0 conn = (client_connection_t *) 0xae11f90 callid = 309893 ret = <value optimized out> rsphdr = {callid = 0, type = 0, op = 0, size = 0, {req = {pid = 0, uid = 0, gid = 0}, rsp = {op_ret = 0, op_errno = 0}}} forget = {hdr = 0x0, hdrlen = 0, frame = 0x0} #9 0x00002b2e7c77bc1a in client_xattrop (frame=0x2aaab0030ab0, this=0xae0ab00, loc=0x2aaab4004238, flags=GF_XATTROP_ADD_ARRAY, dict=0x2aaab4031fc0) at client-protocol.c:1922 hdr = (gf_hdr_common_t *) 0x101010101010101 req = <value optimized out> dict_len = 242 ret = <value optimized out> pathlen = <value optimized out> ino = 13893685 __FUNCTION__ = "client_xattrop" #10 0x00002b2e7c9a2cda in afr_changelog_pre_op (frame=0x2aaab401ea70, this=0xae0b280) at afr-transaction.c:782 _new = (call_frame_t *) 0x6943 priv = (afr_private_t *) 0xae13740 ret = <value optimized out> call_count = 1 xattr = (dict_t *) 0x2aaab4031fc0 local = (afr_local_t *) 0x2aaab4004200 __FUNCTION__ = "afr_changelog_pre_op" #11 0x00002b2e7c9a2f31 in afr_lock_rec (frame=0x2aaab401ea70, this=0xae0b280, child_index=1) at afr-transaction.c:979 local = (afr_local_t *) 0x2aaab4004200 priv = (afr_private_t *) 0xae13740 flock = {l_type = 1, l_whence = 12098, l_start = 0, l_len = 0, l_pid = 792866320} lower = <value optimized out> higher = <value optimized out> lower_name = <value optimized out> higher_name = <value optimized out> __FUNCTION__ = "afr_lock_rec" #12 0x00002b2e7c9a36a8 in afr_lock_cbk (frame=0x2aaab401ea70, cookie=<value optimized out>, this=0xae0b280, op_ret=0, op_errno=0) at afr-transaction.c:906 ---Type <return> to continue, or q <return> to quit--- local = (afr_local_t *) 0x2aaab4004200 child_index = 0 call_count = 0 __FUNCTION__ = "afr_lock_cbk" #13 0x00002b2e7b6a75f0 in default_inodelk_cbk (frame=<value optimized out>, cookie=<value optimized out>, this=<value optimized out>, op_ret=-1, op_errno=128) at defaults.c:1199 fn = (ret_fn_t) 0x101010101010101 _parent = (call_frame_t *) 0x6943 #14 0x00002b2e7c358182 in pl_inodelk (frame=0x2aaab4034c10, this=0xae08870, volume=<value optimized out>, loc=0x2aaab4032170, cmd=7, flock=0x0) at internal.c:194 fn = (ret_fn_t) 0x101010101010101 _parent = (call_frame_t *) 0x6943 op_ret = -1 op_errno = 128 ret = 0 can_block = 1 transport = <value optimized out> client_pid = 1 pinode = (pl_inode_t *) 0x2aaab0032810 reqlock = (posix_lock_t *) 0x2aaab4032170 __FUNCTION__ = "pl_inodelk" #15 0x00002b2e7b6a815c in default_inodelk (frame=0x2aaab4017660, this=0xae09080, volume=0xae0b260 "replicate", loc=0x2aaab4004238, cmd=7, lock=0x7fff2f422f80) at defaults.c:1209 _new = (call_frame_t *) 0x6943 #16 0x00002b2e7c9a33ba in afr_lock_rec (frame=0x2aaab401ea70, this=0xae0b280, child_index=0) at afr-transaction.c:1006 _new = (call_frame_t *) 0x6943 local = (afr_local_t *) 0x2aaab4004200 priv = (afr_private_t *) 0xae13740 flock = {l_type = 1, l_whence = 1, l_start = 0, l_len = 0, l_pid = 1074216160} lower = <value optimized out> higher = <value optimized out> lower_name = <value optimized out> higher_name = <value optimized out> __FUNCTION__ = "afr_lock_rec" #17 0x00002b2e7c9a35c2 in afr_transaction (frame=0x2aaab401ea70, this=0xae0b280, type=AFR_DATA_TRANSACTION) at afr-transaction.c:1170 local = (afr_local_t *) 0x2aaab4004200 priv = (afr_private_t *) 0xae13740 #18 0x00002b2e7c9a07cd in afr_truncate (frame=0x2aaab403ac30, this=0xae0b280, loc=0x2aaab40174a0, offset=0) at afr-inode-write.c:1224 transaction_frame = (call_frame_t *) 0x2aaab401ea70 op_errno = 107 __FUNCTION__ = "afr_truncate" #19 0x00002b2e7cbc0969 in server_truncate_resume (frame=0x2aaab403acc0, this=<value optimized out>, loc=0x2aaab40174a0, offset=0) at server-protocol.c:4243 _new = (call_frame_t *) 0x6943 __FUNCTION__ = "server_truncate_resume" #20 0x00002b2e7b6b06f7 in call_resume (stub=0x2aaab4017470) at call-stub.c:2384 __FUNCTION__ = "call_resume" #21 0x00002b2e7cbc4125 in server_truncate (frame=0x2aaab403acc0, bound_xl=<value optimized out>, hdr=<value optimized out>, hdrlen=<value optimized out>, iobuf=<value optimized out>) at server-protocol.c:4291 truncate_stub = (call_stub_t *) 0x0 state = (server_state_t *) 0x2aaab4032000 #22 0x00002b2e7cbbfb20 in protocol_server_pollin (this=0xae0bdf0, trans=0xae17960) at server-protocol.c:7735 hdr = 0x2aaab4017330 "" hdrlen = 98 ret = 0 iobuf = (struct iobuf *) 0x0 #23 0x00002b2e7cbbfbfb in notify (this=0xae0bdf0, event=<value optimized out>, data=0x6) at server-protocol.c:7791 ret = <value optimized out> trans = (transport_t *) 0x6943 ---Type <return> to continue, or q <return> to quit--- peerinfo = (peer_info_t *) 0xae179d0 myinfo = (peer_info_t *) 0xae17ac0 __FUNCTION__ = "notify" #24 0x00002aaaaaaafb43 in socket_event_handler (fd=<value optimized out>, idx=11, data=0xae17960, poll_in=1, poll_out=0, poll_err=0) at socket.c:813 this = (transport_t *) 0x6943 priv = (socket_private_t *) 0xae16ce0 ret = 0 #25 0x00002b2e7b6ba2a5 in event_dispatch_epoll (event_pool=0xae02300) at event.c:804 events = (struct epoll_event *) 0xae15990 i = 0 ret = 1 __FUNCTION__ = "event_dispatch_epoll" #26 0x0000000000403899 in main () No symbol table info available.
