Project

General

Profile

Actions

Bug #19503

closed

mgr: segv in tcmalloc via ClusterState::set_fsmap, FSMap::operator=

Added by Sage Weil about 7 years ago. Updated almost 7 years ago.

Status:
Can't reproduce
Priority:
Urgent
Assignee:
-
Category:
-
Target version:
-
% Done:

0%

Source:
Tags:
Backport:
Regression:
No
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Pull request ID:
Crash signature (v1):
Crash signature (v2):

Description

(gdb) bt
#0  0x00007f8affa9b923 in tcmalloc::ThreadCache::ReleaseToCentralCache(tcmalloc::ThreadCache::FreeList*, unsigned long, int) () from /usr/lib/libtcmalloc.so.4
#1  0x00007f8affa9b9db in tcmalloc::ThreadCache::ListTooLong(tcmalloc::ThreadCache::FreeList*, unsigned long) () from /usr/lib/libtcmalloc.so.4
#2  0x00007f8affaa92c8 in tc_free () from /usr/lib/libtcmalloc.so.4
#3  0x00007f8b0091667d in ceph::BackTrace::print (this=this@entry=0x7f8afaab6360, out=...) at /build/ceph-12.0.0-2242-ge651c30/src/common/BackTrace.cc:68
#4  0x00007f8b008ff6ac in handle_fatal_signal (signum=11) at /build/ceph-12.0.0-2242-ge651c30/src/global/signal_handler.cc:119
#5  <signal handler called>
#6  0x00007f8affa9b923 in tcmalloc::ThreadCache::ReleaseToCentralCache(tcmalloc::ThreadCache::FreeList*, unsigned long, int) () from /usr/lib/libtcmalloc.so.4
#7  0x00007f8affa9b9db in tcmalloc::ThreadCache::ListTooLong(tcmalloc::ThreadCache::FreeList*, unsigned long) () from /usr/lib/libtcmalloc.so.4
#8  0x00007f8affaaae08 in tc_delete () from /usr/lib/libtcmalloc.so.4
#9  0x00007f8b0088f8fb in deallocate (this=0x7f8b0b4ee588, __p=0x7f8b0a9df5f0) at /usr/include/c++/4.8/ext/new_allocator.h:110
#10 _M_put_node (this=0x7f8b0b4ee588, __p=0x7f8b0a9df5f0) at /usr/include/c++/4.8/bits/stl_tree.h:374
#11 _M_destroy_node (this=0x7f8b0b4ee588, __p=0x7f8b0a9df5f0) at /usr/include/c++/4.8/bits/stl_tree.h:422
#12 std::_Rb_tree<unsigned long, std::pair<unsigned long const, std::string>, std::_Select1st<std::pair<unsigned long const, std::string> >, std::less<unsigned long>, std::allocator<std::pair<unsigned long const, std::string> > >::_M_erase (this=this@entry=0x7f8b0b4ee588, __x=0x7f8b0a9df5f0)
    at /usr/include/c++/4.8/bits/stl_tree.h:1127
#13 0x00007f8b0088f8df in std::_Rb_tree<unsigned long, std::pair<unsigned long const, std::string>, std::_Select1st<std::pair<unsigned long const, std::string> >, std::less<unsigned long>, std::allocator<std::pair<unsigned long const, std::string> > >::_M_erase (this=this@entry=0x7f8b0b4ee588, __x=0x7f8b0a873510)
    at /usr/include/c++/4.8/bits/stl_tree.h:1125
#14 0x00007f8b0088f8df in std::_Rb_tree<unsigned long, std::pair<unsigned long const, std::string>, std::_Select1st<std::pair<unsigned long const, std::string> >, std::less<unsigned long>, std::allocator<std::pair<unsigned long const, std::string> > >::_M_erase (this=this@entry=0x7f8b0b4ee588, __x=0x7f8b0a9df320)
    at /usr/include/c++/4.8/bits/stl_tree.h:1125
#15 0x00007f8b0088fdfa in clear (this=0x7f8b0b4ee588) at /usr/include/c++/4.8/bits/stl_tree.h:860
#16 std::_Rb_tree<unsigned long, std::pair<unsigned long const, std::string>, std::_Select1st<std::pair<unsigned long const, std::string> >, std::less<unsigned long>, std::allocator<std::pair<unsigned long const, std::string> > >::operator= (this=this@entry=0x7f8b0b4ee588, __x=...)
    at /usr/include/c++/4.8/bits/stl_tree.h:993
#17 0x00007f8b0089155a in operator= (__x=..., this=<optimized out>) at /usr/include/c++/4.8/bits/stl_map.h:266
#18 operator= (this=<optimized out>) at /build/ceph-12.0.0-2242-ge651c30/src/include/CompatSet.h:29
#19 operator= (this=<optimized out>) at /build/ceph-12.0.0-2242-ge651c30/src/include/CompatSet.h:20
#20 FSMap::operator= (this=this@entry=0x7f8b0b4ee4f8, rhs=...) at /build/ceph-12.0.0-2242-ge651c30/src/mds/FSMap.h:145
#21 0x00007f8b0088f807 in ClusterState::set_fsmap (this=this@entry=0x7f8b0b4ee4e8, new_fsmap=...) at /build/ceph-12.0.0-2242-ge651c30/src/mgr/ClusterState.cc:39
#22 0x00007f8b008ac664 in Mgr::handle_fs_map (this=this@entry=0x7f8b0b4ee000, m=m@entry=0x7f8b0af36780) at /build/ceph-12.0.0-2242-ge651c30/src/mgr/Mgr.cc:495
#23 0x00007f8b008ad6a7 in Mgr::ms_dispatch (this=0x7f8b0b4ee000, m=m@entry=0x7f8b0af36780) at /build/ceph-12.0.0-2242-ge651c30/src/mgr/Mgr.cc:457
#24 0x00007f8b008a39c9 in MgrStandby::ms_dispatch (this=0x7ffd8ea4f390, m=0x7f8b0af36780) at /build/ceph-12.0.0-2242-ge651c30/src/mgr/MgrStandby.cc:259
#25 0x00007f8b00b3ddab in ms_deliver_dispatch (m=0x7f8b0af36780, this=0x7f8b0a8da000) at /build/ceph-12.0.0-2242-ge651c30/src/msg/Messenger.h:602
#26 DispatchQueue::entry (this=0x7f8b0a8da178) at /build/ceph-12.0.0-2242-ge651c30/src/msg/DispatchQueue.cc:197
#27 0x00007f8b009f23ed in DispatchQueue::DispatchThread::entry (this=<optimized out>) at /build/ceph-12.0.0-2242-ge651c30/src/msg/DispatchQueue.h:102
#28 0x00007f8afeec5184 in start_thread (arg=0x7f8afaab9700) at pthread_create.c:312
#29 0x00007f8afdfab37d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:111

/a/sage-2017-04-05_05:26:00-rados-wip-sage-testing---basic-smithi/989922

Related issues 1 (0 open1 closed)

Related to Ceph - Bug #19595: mgr: segv in msgr thread, with no coreResolved04/12/2017

Actions
Actions #1

Updated by Kefu Chai almost 7 years ago

i have another bt:

#0  0x00007f75aba64096 in tc_newarray () from /usr/lib/libtcmalloc.so.4
#1  0x000055c1be9511bd in ?? ()
#2  0x000055c1be95154c in pretty_version_to_str[abi:cxx11]() ()
#3  0x000055c1be770006 in ceph::BackTrace::print(std::ostream&) const ()
#4  0x000055c1be756777 in ?? ()
#5  <signal handler called>
#6  0x00007f75aba64096 in tc_newarray () from /usr/lib/libtcmalloc.so.4
#7  0x000055c1be7e4a12 in void std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, ceph_mon_subscribe_item>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, ceph_mon_subscribe_item> >, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, ceph_mon_subscribe_item> > >::_M_insert_unique<std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, ceph_mon_subscribe_item> > >(std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, ceph_mon_subscribe_item> >, std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, ceph_mon_subscribe_item> >) ()
#8  0x000055c1be7dcdcb in MonClient::_renew_subs() ()
#9  0x000055c1be719088 in Objecter::_maybe_request_map() ()
#10 0x000055c1be719398 in Objecter::maybe_request_map() ()
#11 0x000055c1be702dd6 in Mgr::ms_dispatch(Message*) ()
#12 0x000055c1be6fa224 in MgrStandby::ms_dispatch(Message*) ()
#13 0x000055c1be9cba0a in DispatchQueue::entry() ()
#14 0x000055c1be865f7d in DispatchQueue::DispatchThread::entry() ()
#15 0x00007f75aae706ba in start_thread (arg=0x7f75a69bf700) at pthread_create.c:333
#16 0x00007f75a9edc82d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:109

/a/kchai-2017-04-18_05:51:22-rados-wip-kefu-testing---basic-mira/1039837

mgr.x crashed while dumping the backtrace. so the bt is not included in the log file.

Actions #2

Updated by Kefu Chai almost 7 years ago

  • Related to Bug #19595: mgr: segv in msgr thread, with no core added
Actions #3

Updated by Sage Weil almost 7 years ago

  • Status changed from New to Can't reproduce
Actions

Also available in: Atom PDF