salhelper/source/timer.cxx | 4 ++++
1 file changed, 4 insertions(+)
New commits:
commit a27a5dda1cb92b0eb46f41dfad596e34988737cd
Author: Mike Kaganski <mike.kagan...@collabora.com>
AuthorDate: Tue Aug 20 11:32:03 2024 +0500
Commit: Mike Kaganski <mike.kagan...@collabora.com>
CommitDate: Tue Aug 20 11:14:01 2024 +0200
Do not try to notify, if the thread is already killed
On a particular system, I see unit tests reliably hung at the exit time
(at a DLL unload), when it waits indefinitely in notify_all. It is the
only thread in the process left; TimerManager thread was likely killed
by that time.
This is the call stack of the hung state:
ntdll.dll!ZwReleaseKeyedEvent()
ntdll.dll!string "Enabling heap debug options
"()
msvcp140d.dll!Concurrency::details::stl_condition_variable_win7::notify_all()
Line 178
msvcp140d.dll!_Cnd_broadcast(_Cnd_internal_imp_t * cond) Line 93
salhelper3MSC.dll!std::condition_variable::notify_all() Line 590
salhelper3MSC.dll!salhelper::TimerManager::~TimerManager() Line 221
salhelper3MSC.dll!``anonymous namespace'::getTimerManager'::`2'::`dynamic
atexit destructor for 'aManager''()
ucrtbased.dll!_execute_onexit_table::__l2::<lambda>() Line 206
ucrtbased.dll!__crt_seh_guarded_call<int>::operator()<void
<lambda>(void),int <lambda>(void) &,void
<lambda>(void)>(__acrt_lock_and_call::__l2::void <lambda>(void) && setup,
_execute_onexit_table::__l2::int <lambda>(void) & action,
__acrt_lock_and_call::__l2::void <lambda>(void) && cleanup) Line 204
ucrtbased.dll!__acrt_lock_and_call<int <lambda>(void)>(const
__acrt_lock_id lock_id, _execute_onexit_table::__l2::int <lambda>(void) &&
action) Line 974
ucrtbased.dll!_execute_onexit_table(_onexit_table_t * table) Line 231
salhelper3MSC.dll!__scrt_dllmain_uninitialize_c() Line 399
salhelper3MSC.dll!dllmain_crt_process_detach(const bool is_terminating)
Line 182
salhelper3MSC.dll!dllmain_crt_dispatch(HINSTANCE__ * const instance, const
unsigned long reason, void * const reserved) Line 220
salhelper3MSC.dll!dllmain_dispatch(HINSTANCE__ * const instance, const
unsigned long reason, void * const reserved) Line 293
salhelper3MSC.dll!_DllMainCRTStartup(HINSTANCE__ * const instance, const
unsigned long reason, void * const reserved) Line 335
ntdll.dll!LdrShutdownProcess()
ntdll.dll!RtlExitUserProcess()
ucrtbased.dll!exit_or_terminate_process(const unsigned int return_code)
Line 144
ucrtbased.dll!common_exit(const int return_code, const
_crt_exit_cleanup_mode cleanup_mode, const _crt_exit_return_mode return_mode)
Line 280
ucrtbased.dll!exit(int return_code) Line 294
cppunittester.exe!__scrt_common_main_seh() Line 297
cppunittester.exe!__scrt_common_main() Line 331
cppunittester.exe!mainCRTStartup(void * __formal) Line 17
kernel32.dll!BaseThreadInitThunk()
ntdll.dll!RtlUserThreadStart()
This check prevents that hang.
The behavior is *possibly* related to my commit
8a0c43fa86bd32b4d47fd7e46d3ed414c9282ffa (Use _beginthreadex instead of
CreateThread, 2023-08-09), which put the threads under control of CRT;
and also to the specific version of CRT on the affected system, which
might affect the order of statics destruction and thread termination.
Change-Id: I6da95ea369ac9433a426a12d62cbd2a09cb4ce4a
Reviewed-on: https://gerrit.libreoffice.org/c/core/+/172093
Reviewed-by: Mike Kaganski <mike.kagan...@collabora.com>
Tested-by: Jenkins
diff --git a/salhelper/source/timer.cxx b/salhelper/source/timer.cxx
index 3c6c0a00d922..07510f228cde 100644
--- a/salhelper/source/timer.cxx
+++ b/salhelper/source/timer.cxx
@@ -215,6 +215,10 @@ TimerManager::TimerManager() :
TimerManager::~TimerManager() {
{
std::scoped_lock g(m_Lock);
+ // Sometimes, the TimerManager thread gets killed before the static's
destruction;
+ // in that case, notify_all could hang in unit tests
+ if (!isRunning())
+ return;
m_terminate = true;
}
m_notEmpty.notify_all();
