[MESOS-393] Forking at an unlucky time on OS X can cause the C++ library to deadlock.

• Type: Bug
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 0.13.0
• Assignee: Vinod Kone
• Reporter: Benjamin Hindman
• Created: 14/Mar/13 07:14
• Updated: 10/Jun/13 18:07
• Resolved: 10/Jun/13 18:07

Description

Thread 1 (process 91631):
#0 0x00007fff85893bf2 in __psynch_mutexwait ()
#1 0x00007fff8711a1a1 in pthread_mutex_lock ()
#2 0x00007fff8f6d5af5 in _gnu_cxx::_mutex::lock ()
#3 0x00007fff8f6dc903 in std::locale::locale ()
#4 0x00007fff8f6e6582 in std::basic_ios<char, std::char_traits<char> >::basic_ios ()
#5 0x00007fff8f6febe4 in std::basic_ostringstream<char, std::char_traits<char>, std::allocator<char> >::basic_ostringstream ()
#6 0x00000001014216d5 in process::UPID::operator std::string () at stl_deque.h:441
#7 0x000000010125130c in mesos::internal::slave::ProcessBasedIsolationModule::createExecutorLauncher (this=0x7fc19a5062c0, slaveId=@0x7fc19a536438, frameworkId=@0x7fc19a536458, frameworkInfo=@0x7fc19a536478, executorInfo=@0x2060, directory=@0x10233f6b0) at process_based_isolation_module.cpp:293
#8 0x000000010125200c in mesos::internal::slave::ProcessBasedIsolationModule::launchExecutor (this=0x10233fbc0, slaveId=@0x10233fbc0, frameworkId=@0x10233fbc0, frameworkInfo=@0x10233fbc0, executorInfo=@0x10233fbc0, _=@0x7fc19a536548, directory=@0x7fc19a536548, resources=@0x7fc19a536550, path=@0x7fc19a536588) at process_based_isolation_module.cpp:213
#9 0x000000010122597c in std::tr1::Function_handler<void ()(mesos::internal::slave::IsolationModule*), std::tr1::_Bind<std::tr1::_Mem_fn<void (mesos::internal::slave::IsolationModule::*)(mesos::SlaveID const&, mesos::FrameworkID const&, mesos::FrameworkInfo const&, mesos::ExecutorInfo const&, UUID const&, std::string const&, mesos::internal::Resources const&, Option<std::string> const&)> ()(std::tr1::_Placeholder<1>, mesos::SlaveID, mesos::FrameworkID, mesos::FrameworkInfo, mesos::ExecutorInfo, UUID, std::string, mesos::internal::Resources, Option<std::string>)> >::_M_invoke (_functor=@0x10233f670, __a1=0x7fc19a536438) at functional_iterate.h:214
#10 0x000000010122b466 in std::tr1::_shared_count<(gnu_cxx::_Lock_policy)2>::~_shared_count () at boost_shared_ptr.h:133
#11 0x000000010122b466 in std::tr1::_shared_ptr<std::tr1::function<void ()(mesos::internal::slave::IsolationModule*)>, (gnu_cxx::_Lock_policy)2>::~_shared_ptr () at /usr/include/c++/4.2.1/tr1/boost_shared_ptr.h:504
#12 0x000000010122b466 in std::tr1::_Bind<void (()(std::tr1::_Placeholder<1>, std::tr1::shared_ptr<std::tr1::function<void ()(mesos::internal::slave::IsolationModule)> >))(process::ProcessBase*, std::tr1::shared_ptr<std::tr1::function<void ()(mesos::internal::slave::IsolationModule*)> >)>::operator()<process::ProcessBase*> (this=0x10233f670, __u1=@0x7fc19a536438) at boost_shared_ptr.h:974
#13 0x0000000101229f28 in std::tr1::Function_handler<void ()(process::ProcessBase*), std::tr1::_Bind<void (()(std::tr1::_Placeholder<1>, std::tr1::shared_ptr<std::tr1::function<void ()(mesos::internal::slave::IsolationModule)> >))(process::ProcessBase*, std::tr1::shared_ptr<std::tr1::function<void ()(mesos::internal::slave::IsolationModule*)> >)> >::_M_invoke (_a1=0x7fc19a5063f0, __functor=@0x10233f670) at functional_iterate.h:502
#14 0x00000001013e2d4a in std::tr1::function<void ()(process::ProcessBase*)>::operator() () at stl_deque.h:441
#15 0x0000000101360ccc in process::ProcessBase::visit () at boost_shared_ptr.h:152
#16 0x00000001013895df in process::DispatchEvent::visit () at boost_shared_ptr.h:152
#17 0x0000000101374ec0 in process::ProcessManager::resume () at boost_shared_ptr.h:152
#18 0x0000000101375f06 in process::schedule () at boost_shared_ptr.h:152
#19 0x00007fff8711b8bf in _pthread_start ()
#20 0x00007fff8711eb75 in thread_start ()