Current HPX master causes segfaults within Octo-Tiger
G-071 opened this issue · 1 comments
G-071 commented
Octo-Tiger currently does not work when using the current HPX master. We get a segfault, usually at the beginning of the application (for instance when loading of options or during the first timestep -- it varies). Note that this does not always happen and some few runs execute normally.
This does not seem to be a racing condition as I am able to reproduce this with --hpx:threads=1.
I did some digging when this problem started to occur. HPX 1.9.1 still works fine, of course! The problem seems to start occuring after #6050 was merged: I can reproduce the problem with 962288c , while the commit just before that ( 8edd9b3 ) still works without any issues.
To reproduce:
- I used a basic Octo-Tiger (master) build without CUDA / Kokkos / Networking on my laptop
- GCC/12
- Scenario
./build/octotiger/build/octotiger --hpx:threads=1 --config_file=src/octotiger/test_problems/rotating_star/rotating_star.ini --unigrid=0 --cuda_number_gpus=1 --max_kernels_fused=1 --stop_step=10 --max_gpu_executor_queue_length=5 --max_level=3 --correct_am_hydro=0 --monopole_host_kernel_type=LEGACY --multipole_host_kernel_type=LEGACY --theta=0.5 --monopole_device_kernel_type=OFF --multipole_device_kernel_type=OFF --hydro_device_kernel_type=OFF --hydro_host_kernel_type=LEGACY --amr_boundary_kernel_type=AMR_OPTIMIZED --disable_output=1
The backtrace of the segfault is:
#0 0x00007ffff71fc801 in hpx::util::extra_data_node::get<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > (this=0x8) at /home/daissgr/workshop/KokkosTiger/src/hpx/libs/core/type_support/include/hpx/type_support/extra_data.hpp:130
#1 hpx::util::extra_data::try_get<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > (this=0x7fffd000f8b0) at /home/daissgr/workshop/KokkosTiger/src/hpx/libs/core/type_support/include/hpx/type_support/extra_data.hpp:164
#2 hpx::lcos::detail::future_data<hpx::id_type>::try_get_extra_data<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > (this=0x7fffd000f840) at /home/daissgr/workshop/KokkosTiger/src/hpx/libs/full/components/include/hpx/components/client_base.hpp:246
#3 hpx::lcos::detail::future_data<hpx::id_type>::tidy (this=this@entry=0x7fffd000f840) at /home/daissgr/workshop/KokkosTiger/src/hpx/libs/full/components/src/client_base.cpp:48
#4 0x00007ffff710b6de in hpx::lcos::detail::future_data<hpx::id_type>::~future_data (this=0x7fffd000f840, __in_chrg=<optimized out>) at /home/daissgr/workshop/KokkosTiger/src/hpx/libs/full/components/include/hpx/components/client_base.hpp:226
#5 hpx::lcos::detail::future_data_allocator<hpx::id_type, hpx::util::thread_local_caching_allocator<char, std::allocator<char> >, void>::~future_data_allocator (this=0x7fffd000f840, __in_chrg=<optimized out>) at /home/daissgr/workshop/KokkosTiger/src/hpx/libs/core/futures/include/hpx/futures/detail/future_data.hpp:730
#6 0x00007ffff71193f0 in std::__new_allocator<hpx::lcos::detail::future_data_allocator<hpx::id_type, hpx::util::thread_local_caching_allocator<char, std::allocator<char> >, void> >::destroy<hpx::lcos::detail::future_data_allocator<hpx::id_type, hpx::util::thread_local_caching_allocator<char, std::allocator<char> >, void> > (__p=<optimized out>, this=<optimized out>) at /usr/include/c++/12/bits/new_allocator.h:181
#7 std::allocator_traits<std::allocator<hpx::lcos::detail::future_data_allocator<hpx::id_type, hpx::util::thread_local_caching_allocator<char, std::allocator<char> >, void> > >::destroy<hpx::lcos::detail::future_data_allocator<hpx::id_type, hpx::util::thread_local_caching_allocator<char, std::allocator<char> >, void> > (__p=<optimized out>, __a=...) at /usr/include/c++/12/bits/alloc_traits.h:535
#8 hpx::util::thread_local_caching_allocator<hpx::lcos::detail::future_data_allocator<hpx::id_type, hpx::util::thread_local_caching_allocator<char, std::allocator<char> >, void>, std::allocator<hpx::lcos::detail::future_data_allocator<hpx::id_type, hpx::util::thread_local_caching_allocator<char, std::allocator<char> >, void> > >::destroy<hpx::lcos::detail::future_data_allocator<hpx::id_type, hpx::util::thread_local_caching_allocator<char, std::allocator<char> >, void> > (p=<optimized out>, this=<optimized out>) at /home/daissgr/workshop/KokkosTiger/src/hpx/libs/core/allocator_support/include/hpx/allocator_support/thread_local_caching_allocator.hpp:183
#9 std::allocator_traits<hpx::util::thread_local_caching_allocator<hpx::lcos::detail::future_data_allocator<hpx::id_type, hpx::util::thread_local_caching_allocator<char, std::allocator<char> >, void>, std::allocator<hpx::lcos::detail::future_data_allocator<hpx::id_type, hpx::util::thread_local_caching_allocator<char, std::allocator<char> >, void> > > >::_S_destroy<hpx::util::thread_local_caching_allocator<hpx::lcos::detail::future_data_allocator<hpx::id_type, hpx::util::thread_local_caching_allocator<char, std::allocator<char> >, void>, std::allocator<hpx::lcos::detail::future_data_allocator<hpx::id_type, hpx::util::thread_local_caching_allocator<char, std::allocator<char> >, void> > >, hpx::lcos::detail::future_data_allocator<hpx::id_type, hpx::util::thread_local_caching_allocator<char, std::allocator<char> >, void> > (__p=<optimized out>, __a=...) at /usr/include/c++/12/bits/alloc_traits.h:272
#10 std::allocator_traits<hpx::util::thread_local_caching_allocator<hpx::lcos::detail::future_data_allocator<hpx::id_type, hpx::util::thread_local_caching_allocator<char, std::allocator<char> >, void>, std::allocator<hpx::lcos::detail::future_data_allocator<hpx::id_type, hpx::util::thread_local_caching_allocator<char, std::allocator<char> >, void> > > >::destroy<hpx::lcos::detail::future_data_allocator<hpx::id_type, hpx::util::thread_local_caching_allocator<char, std::allocator<char> >, void> > (__p=<optimized out>, __a=...) at /usr/include/c++/12/bits/alloc_traits.h:378
#11 hpx::lcos::detail::future_data_allocator<hpx::id_type, hpx::util::thread_local_caching_allocator<char, std::allocator<char> >, void>::destroy (this=0x7fffd000f840) at /home/daissgr/workshop/KokkosTiger/src/hpx/libs/core/futures/include/hpx/futures/detail/future_data.hpp:777
#12 0x00007ffff78c0f56 in hpx::lcos::detail::intrusive_ptr_release (p=<optimized out>) at /home/daissgr/workshop/KokkosTiger/build/hpx/include/hpx/futures/detail/future_data.hpp:145
#13 hpx::lcos::detail::intrusive_ptr_release (p=<optimized out>) at /home/daissgr/workshop/KokkosTiger/build/hpx/include/hpx/futures/detail/future_data.hpp:141
#14 hpx::intrusive_ptr<hpx::lcos::detail::future_data_base<hpx::id_type> >::~intrusive_ptr (this=<optimized out>, __in_chrg=<optimized out>) at /home/daissgr/workshop/KokkosTiger/build/hpx/include/hpx/memory/intrusive_ptr.hpp:88
#15 hpx::intrusive_ptr<hpx::lcos::detail::future_data_base<hpx::id_type> >::reset (this=0x7ffff6294e08) at /home/daissgr/workshop/KokkosTiger/build/hpx/include/hpx/memory/intrusive_ptr.hpp:152
#16 hpx::future<hpx::id_type>::invalidate::~invalidate (this=0x7ffff6294d38, __in_chrg=<optimized out>) at /home/daissgr/workshop/KokkosTiger/build/hpx/include/hpx/futures/future.hpp:560
#17 hpx::future<hpx::id_type>::get (this=0x7ffff6294e08) at /home/daissgr/workshop/KokkosTiger/build/hpx/include/hpx/futures/future.hpp:698
#18 0x00007ffff78eee02 in operator() (__closure=<optimized out>, fut=...) at /home/daissgr/workshop/KokkosTiger/src/octotiger/src/node_server_actions_2.cpp:641
#19 operator() (__closure=<optimized out>) at /home/daissgr/workshop/KokkosTiger/build/hpx/include/hpx/futures/packaged_continuation.hpp:69
#20 hpx::detail::try_catch_exception_ptr<hpx::lcos::detail::invoke_continuation_nounwrap<node_client::get_ptr() const::<lambda(future<long unsigned int>&&)>, hpx::future<long unsigned int>, continuation<hpx::future<long unsigned int>, node_client::get_ptr() const::<lambda(future<long unsigned int>&&)>, node_server*> >(node_client::get_ptr() const::<lambda(future<long unsigned int>&&)>&, hpx::future<long unsigned int>&&, continuation<hpx::future<long unsigned int>, node_client::get_ptr() const::<lambda(future<long unsigned int>&&)>, node_server*>&)::<lambda()>, hpx::lcos::detail::invoke_continuation_nounwrap<node_client::get_ptr() const::<lambda(future<long unsigned int>&&)>, hpx::future<long unsigned int>, continuation<hpx::future<long unsigned int>, node_client::get_ptr() const::<lambda(future<long unsigned int>&&)>, node_server*> >(node_client::get_ptr() const::<lambda(future<long unsigned int>&&)>&, hpx::future<long unsigned int>&&, continuation<hpx::future<long unsigned int>, node_client::get_ptr() const::<lambda(future<long unsigned int>&&)>, node_server*>&)::<lambda(std::__exception_ptr::exception_ptr)> > (c=..., t=...) at /home/daissgr/workshop/KokkosTiger/build/hpx/include/hpx/errors/try_catch_exception_ptr.hpp:37
#21 hpx::lcos::detail::invoke_continuation_nounwrap<node_client::get_ptr() const::<lambda(future<long unsigned int>&&)>, hpx::future<long unsigned int>, hpx::lcos::detail::continuation<hpx::future<long unsigned int>, node_client::get_ptr() const::<lambda(future<long unsigned int>&&)>, node_server*> >(struct {...} &, hpx::future<unsigned long> &&, hpx::lcos::detail::continuation<hpx::future<long unsigned int>, node_client::get_ptr() const::<lambda(future<long unsigned int>&&)>, node_server*> &) (func=..., future=..., cont=warning: RTTI symbol not found for class 'hpx::lcos::detail::continuation_allocator<hpx::util::thread_local_caching_allocator<char, std::allocator<char> >, hpx::future<unsigned long>, node_client::get_ptr() const::{lambda(hpx::future<unsigned long>&&)#1}, node_server*>'
...) at /home/daissgr/workshop/KokkosTiger/build/hpx/include/hpx/futures/packaged_continuation.hpp:57
#22 0x00007ffff78e6ece in hpx::lcos::detail::invoke_continuation<node_client::get_ptr() const::<lambda(future<long unsigned int>&&)>, hpx::future<long unsigned int>, hpx::lcos::detail::continuation<hpx::future<long unsigned int>, node_client::get_ptr() const::<lambda(future<long unsigned int>&&)>, node_server*> > (cont=..., future=..., func=...) at /home/daissgr/workshop/KokkosTiger/build/hpx/include/hpx/futures/packaged_continuation.hpp:85
#23 hpx::lcos::detail::continuation<hpx::future<long unsigned int>, node_client::get_ptr() const::<lambda(future<long unsigned int>&&)>, node_server*>::run_impl<true> (f=..., this=<optimized out>) at /home/daissgr/workshop/KokkosTiger/build/hpx/include/hpx/futures/packaged_continuation.hpp:215
#24 operator() (__closure=<optimized out>) at /home/daissgr/workshop/KokkosTiger/build/hpx/include/hpx/futures/packaged_continuation.hpp:242
#25 hpx::threads::detail::thread_function_nullary<hpx::lcos::detail::continuation<hpx::future<long unsigned int>, node_client::get_ptr() const::<lambda(future<long unsigned int>&&)>, node_server*>::async<true, hpx::lcos::detail::post_policy_spawner>(hpx::traits::detail::shared_state_ptr_for_t<hpx::future<long unsigned int> >&&, hpx::lcos::detail::post_policy_spawner&&)::<lambda()> >::operator() (this=<optimized out>) at /home/daissgr/workshop/KokkosTiger/build/hpx/include/hpx/threading_base/register_thread.hpp:50
#26 hpx::util::detail::callable_vtable<std::pair<hpx::threads::thread_schedule_state, hpx::threads::thread_id>(hpx::threads::thread_restart_state)>::_invoke<hpx::threads::detail::thread_function_nullary<hpx::lcos::detail::continuation<hpx::future<long unsigned int>, node_client::get_ptr() const::<lambda(future<long unsigned int>&&)>, node_server*>::async<true, hpx::lcos::detail::post_policy_spawner>(hpx::traits::detail::shared_state_ptr_for_t<hpx::future<long unsigned int> >&&, hpx::lcos::detail::post_policy_spawner&&)::<lambda()> > >(void *, hpx::threads::thread_restart_state &&) (f=<optimized out>, vs#0=<optimized out>) at /home/daissgr/workshop/KokkosTiger/build/hpx/include/hpx/functional/detail/vtable/callable_vtable.hpp:88
#27 0x00007ffff6d31f49 in hpx::util::detail::basic_function<std::pair<hpx::threads::thread_schedule_state, hpx::threads::thread_id> (hpx::threads::thread_restart_state), false, false>::operator()(hpx::threads::thread_restart_state) const (vs#0=<optimized out>, this=0x7fffa400cea8) at /home/daissgr/workshop/KokkosTiger/src/hpx/libs/core/functional/include/hpx/functional/detail/basic_function.hpp:236
#28 hpx::threads::coroutines::detail::coroutine_impl::operator() (this=0x7fffa400ce40) at /home/daissgr/workshop/KokkosTiger/src/hpx/libs/core/coroutines/src/detail/coroutine_impl.cpp:77
#29 0x00007ffff6d313af in hpx::threads::coroutines::detail::lx::trampoline<hpx::threads::coroutines::detail::coroutine_impl> (fun=<optimized out>) at /home/daissgr/workshop/KokkosTiger/src/hpx/libs/core/coroutines/include/hpx/coroutines/detail/context_linux_x86.hpp:181
#30 0x0000000000000000 in ?? ()
@hkaiser: Do you have any idea what could cause this?