Project

General

Profile

Actions

Bug #15440

closed

msg/async: deadlock on delayed delivery?

Added by Sage Weil about 8 years ago. Updated almost 8 years ago.

Status:
Resolved
Priority:
Urgent
Assignee:
-
Category:
-
Target version:
-
% Done:

0%

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

Description

Thread 2 (Thread 0x7fa196ba9700 (LWP 6954)):
#0  __lll_lock_wait () at ../nptl/sysdeps/unix/sysv/linux/x86_64/lowlevellock.S:135
#1  0x00007fa19d6f2657 in _L_lock_909 () from /lib/x86_64-linux-gnu/libpthread.so.0
#2  0x00007fa19d6f2480 in __GI___pthread_mutex_lock (mutex=0x7fa1ab41daf0) at ../nptl/pthread_mutex_lock.c:79
#3  0x00007fa19f3ddf68 in Mutex::Lock(bool) ()
#4  0x00007fa19f53f07b in AsyncConnection::handle_connect_msg(ceph_msg_connect&, ceph::buffer::list&, ceph::buffer::list&) ()
#5  0x00007fa19f542b7c in AsyncConnection::_process_connection() ()
#6  0x00007fa19f548cd8 in AsyncConnection::process() ()
#7  0x00007fa19f4ed0a5 in EventCenter::process_events(int) ()
#8  0x00007fa19f4ce350 in Worker::entry() ()
#9  0x00007fa19d6f0182 in start_thread (arg=0x7fa196ba9700) at pthread_create.c:312
#10 0x00007fa19b81e47d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:111

Thread 4 (Thread 0x7fa1973aa700 (LWP 6953)):
#0  0x00007fa19d6f166b in pthread_join (threadid=140331299120896, thread_return=0x0) at pthread_join.c:92
#1  0x00007fa19f411c80 in Thread::join(void**) ()
#2  0x00007fa19f539c44 in AsyncConnection::_stop() ()
#3  0x00007fa19f53c8c6 in AsyncConnection::fault() ()
#4  0x00007fa19f548abd in AsyncConnection::process() ()
#5  0x00007fa19f4ed0a5 in EventCenter::process_events(int) ()
#6  0x00007fa19f4ce350 in Worker::entry() ()
#7  0x00007fa19d6f0182 in start_thread (arg=0x7fa1973aa700) at pthread_create.c:312
#8  0x00007fa19b81e47d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:111

Thread 8 (Thread 0x7fa1963a8700 (LWP 6955)):
#0  __lll_lock_wait () at ../nptl/sysdeps/unix/sysv/linux/x86_64/lowlevellock.S:135
#1  0x00007fa19d6f2657 in _L_lock_909 () from /lib/x86_64-linux-gnu/libpthread.so.0
#2  0x00007fa19d6f2480 in __GI___pthread_mutex_lock (mutex=0x7fa1ab2d6028) at ../nptl/pthread_mutex_lock.c:79
#3  0x00007fa19f3ddf68 in Mutex::Lock(bool) ()
#4  0x00007fa19edfb8b2 in OSD::ms_dispatch(Message*) ()
#5  0x00007fa19f54c8b7 in Messenger::ms_deliver_dispatch(Message*) ()
#6  0x00007fa19f54d011 in C_handle_dispatch::do_request(int) ()
#7  0x00007fa19f4ed76d in EventCenter::process_events(int) ()
#8  0x00007fa19f4ce350 in Worker::entry() ()
#9  0x00007fa19d6f0182 in start_thread (arg=0x7fa1963a8700) at pthread_create.c:312
#10 0x00007fa19b81e47d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:111

Thread 14 (Thread 0x7fa18fb9b700 (LWP 6968)):
#0  __lll_lock_wait () at ../nptl/sysdeps/unix/sysv/linux/x86_64/lowlevellock.S:135
#1  0x00007fa19d6f2657 in _L_lock_909 () from /lib/x86_64-linux-gnu/libpthread.so.0
#2  0x00007fa19d6f2480 in __GI___pthread_mutex_lock (mutex=0x7fa1ab6da530) at ../nptl/pthread_mutex_lock.c:79
#3  0x00007fa19f3ddf68 in Mutex::Lock(bool) ()
#4  0x00007fa19ee67cc0 in PG::lock(bool) const ()
#5  0x00007fa19edef8ce in OSD::consume_map() ()
#6  0x00007fa19edf2d7e in OSD::_committed_osd_maps(unsigned int, unsigned int, MOSDMap*) ()
#7  0x00007fa19ee03009 in Context::complete(int) ()
#8  0x00007fa19f3608b6 in Finisher::finisher_thread_entry() ()
#9  0x00007fa19d6f0182 in start_thread (arg=0x7fa18fb9b700) at pthread_create.c:312
#10 0x00007fa19b81e47d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:111

Thread 28 (Thread 0x7fa184203700 (LWP 7032)):
#0  __lll_lock_wait () at ../nptl/sysdeps/unix/sysv/linux/x86_64/lowlevellock.S:135
#1  0x00007fa19d6f2657 in _L_lock_909 () from /lib/x86_64-linux-gnu/libpthread.so.0
---Type <return> to continue, or q <return> to quit---
#2  0x00007fa19d6f2480 in __GI___pthread_mutex_lock (mutex=0x7fa1ab41daf0) at ../nptl/pthread_mutex_lock.c:79
#3  0x00007fa19f3ddf68 in Mutex::Lock(bool) ()
#4  0x00007fa19f54c2aa in AsyncConnection::is_connected() ()
#5  0x00007fa19edaf636 in OSD::op_is_discardable(MOSDOp*) ()
#6  0x00007fa19ee7b809 in PG::can_discard_op(std::shared_ptr<OpRequest>&) ()
#7  0x00007fa19ee7bef5 in PG::can_discard_request(std::shared_ptr<OpRequest>&) ()
#8  0x00007fa19ef15766 in ReplicatedPG::do_request(std::shared_ptr<OpRequest>&, ThreadPool::TPHandle&) ()
#9  0x00007fa19edd6415 in OSD::dequeue_op(boost::intrusive_ptr<PG>, std::shared_ptr<OpRequest>, ThreadPool::TPHandle&) ()
#10 0x00007fa19edd663d in PGQueueable::RunVis::operator()(std::shared_ptr<OpRequest>&) ()
#11 0x00007fa19eddb049 in OSD::ShardedOpWQ::_process(unsigned int, ceph::heartbeat_handle_d*) ()
#12 0x00007fa19f41e8f7 in ShardedThreadPool::shardedthreadpool_worker(unsigned int) ()
#13 0x00007fa19f420820 in ShardedThreadPool::WorkThreadSharded::entry() ()
#14 0x00007fa19d6f0182 in start_thread (arg=0x7fa184203700) at pthread_create.c:312
#15 0x00007fa19b81e47d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:111

Thread 32 (Thread 0x7fa16d3c2700 (LWP 8876)):
#0  __lll_lock_wait () at ../nptl/sysdeps/unix/sysv/linux/x86_64/lowlevellock.S:135
#1  0x00007fa19d6f2657 in _L_lock_909 () from /lib/x86_64-linux-gnu/libpthread.so.0
#2  0x00007fa19d6f2480 in __GI___pthread_mutex_lock (mutex=0x7fa1ab41daf0) at ../nptl/pthread_mutex_lock.c:79
#3  0x00007fa19f3ddf68 in Mutex::Lock(bool) ()
#4  0x00007fa19f54c2aa in AsyncConnection::is_connected() ()
#5  0x00007fa19edaf636 in OSD::op_is_discardable(MOSDOp*) ()
#6  0x00007fa19ede2eba in OSD::handle_op(std::shared_ptr<OpRequest>&, std::shared_ptr<OSDMap const>&) ()
#7  0x00007fa19ede40de in OSD::dispatch_op_fast(std::shared_ptr<OpRequest>&, std::shared_ptr<OSDMap const>&) ()
#8  0x00007fa19ede43d8 in OSD::dispatch_session_waiting(OSD::Session*, std::shared_ptr<OSDMap const>) ()
#9  0x00007fa19ede4724 in OSD::ms_fast_dispatch(Message*) ()
#10 0x00007fa19f535f55 in AsyncConnection::DelayedDelivery::entry() ()
#11 0x00007fa19d6f0182 in start_thread (arg=0x7fa16d3c2700) at pthread_create.c:312
#12 0x00007fa19b81e47d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:111

Thread 102 (Thread 0x7fa186a08700 (LWP 7027)):
#0  __lll_lock_wait () at ../nptl/sysdeps/unix/sysv/linux/x86_64/lowlevellock.S:135
#1  0x00007fa19d6f2657 in _L_lock_909 () from /lib/x86_64-linux-gnu/libpthread.so.0
#2  0x00007fa19d6f2480 in __GI___pthread_mutex_lock (mutex=0x7fa1ab6da530) at ../nptl/pthread_mutex_lock.c:79
#3  0x00007fa19f3ddf68 in Mutex::Lock(bool) ()
#4  0x00007fa19ee67cc0 in PG::lock(bool) const ()
#5  0x00007fa19ee67e4e in PG::lock_suspend_timeout(ThreadPool::TPHandle&) ()
#6  0x00007fa19eddaabe in OSD::ShardedOpWQ::_process(unsigned int, ceph::heartbeat_handle_d*) ()
#7  0x00007fa19f41e8f7 in ShardedThreadPool::shardedthreadpool_worker(unsigned int) ()
#8  0x00007fa19f420820 in ShardedThreadPool::WorkThreadSharded::entry() ()
#9  0x00007fa19d6f0182 in start_thread (arg=0x7fa186a08700) at pthread_create.c:312
#10 0x00007fa19b81e47d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:111

/a/sage-2016-04-07_14:41:26-rados-wip-sage-testing-distro-basic-smithi/114688

Actions

Also available in: Atom PDF