Created
July 27, 2020 21:27
-
-
Save froody/ecc8bc849b8a95f89218fd5b6dc2ecd6 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
(gdb) thread apply all bt | |
Thread 18 (Thread 0x7f4b2a5d5700 (LWP 11702)): | |
#0 0x00007f4c096c8f85 in futex_abstimed_wait_cancelable (private=<optimized out>, abstime=0x7f4b2a5d4e00, expected=0, futex_word=0x56462ad3c93c <_PyRuntime+1340>) at ../sysdeps/unix/sysv/linux/futex-internal.h:205 | |
#1 __pthread_cond_wait_common (abstime=0x7f4b2a5d4e00, mutex=0x56462ad3c940 <_PyRuntime+1344>, cond=0x56462ad3c910 <_PyRuntime+1296>) at pthread_cond_wait.c:539 | |
#2 __pthread_cond_timedwait (cond=0x56462ad3c910 <_PyRuntime+1296>, mutex=0x56462ad3c940 <_PyRuntime+1344>, abstime=0x7f4b2a5d4e00) at pthread_cond_wait.c:667 | |
#3 0x000056462abd965e in PyCOND_TIMEDWAIT (cond=0x56462ad3c910 <_PyRuntime+1296>, mut=0x56462ad3c940 <_PyRuntime+1344>, us=5000) at /home/conda/feedstock_root/build_artifacts/python_1591034797817/work/Python/condvar.h:90 | |
#4 take_gil () at /home/conda/feedstock_root/build_artifacts/python_1591034797817/work/Python/ceval_gil.h:208 | |
#5 0x000056462ab03be4 in PyEval_RestoreThread () at /home/conda/feedstock_root/build_artifacts/python_1591034797817/work/Python/ceval.c:271 | |
#6 0x00007f4bedcabb16 in torch::autograd::python::PythonEngine::thread_init(int, std::shared_ptr<torch::autograd::ReadyQueue> const&, bool) () | |
from /private/home/tbirch/.conda/envs/torch16/lib/python3.7/site-packages/torch/lib/libtorch_python.so | |
#7 0x00007f4bf07d3163 in std::execute_native_thread_routine (__p=0x5646951bdce0) at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/src/gcc/libstdc++-v3/src/c++11/thread.cc:80 | |
#8 0x00007f4c096c26db in start_thread (arg=0x7f4b2a5d5700) at pthread_create.c:463 | |
#9 0x00007f4c093eb88f in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95 | |
Thread 17 (Thread 0x7f4b2bc21700 (LWP 11701)): | |
#0 0x00007f4c096c8f85 in futex_abstimed_wait_cancelable (private=<optimized out>, abstime=0x7f4b2bc20e00, expected=0, futex_word=0x56462ad3c93c <_PyRuntime+1340>) at ../sysdeps/unix/sysv/linux/futex-internal.h:205 | |
#1 __pthread_cond_wait_common (abstime=0x7f4b2bc20e00, mutex=0x56462ad3c940 <_PyRuntime+1344>, cond=0x56462ad3c910 <_PyRuntime+1296>) at pthread_cond_wait.c:539 | |
#2 __pthread_cond_timedwait (cond=0x56462ad3c910 <_PyRuntime+1296>, mutex=0x56462ad3c940 <_PyRuntime+1344>, abstime=0x7f4b2bc20e00) at pthread_cond_wait.c:667 | |
#3 0x000056462abd965e in PyCOND_TIMEDWAIT (cond=0x56462ad3c910 <_PyRuntime+1296>, mut=0x56462ad3c940 <_PyRuntime+1344>, us=5000) at /home/conda/feedstock_root/build_artifacts/python_1591034797817/work/Python/condvar.h:90 | |
#4 take_gil () at /home/conda/feedstock_root/build_artifacts/python_1591034797817/work/Python/ceval_gil.h:208 | |
#5 0x000056462ab03be4 in PyEval_RestoreThread () at /home/conda/feedstock_root/build_artifacts/python_1591034797817/work/Python/ceval.c:271 | |
#6 0x00007f4bedcabb16 in torch::autograd::python::PythonEngine::thread_init(int, std::shared_ptr<torch::autograd::ReadyQueue> const&, bool) () | |
from /private/home/tbirch/.conda/envs/torch16/lib/python3.7/site-packages/torch/lib/libtorch_python.so | |
#7 0x00007f4bf07d3163 in std::execute_native_thread_routine (__p=0x564694fd6be0) at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/src/gcc/libstdc++-v3/src/c++11/thread.cc:80 | |
#8 0x00007f4c096c26db in start_thread (arg=0x7f4b2bc21700) at pthread_create.c:463 | |
#9 0x00007f4c093eb88f in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95 | |
Thread 16 (Thread 0x7f4b2dfff700 (LWP 11692)): | |
#0 0x00007f4c096cc384 in __libc_read (fd=49, buf=buf@entry=0x7f4b2dffee70, nbytes=nbytes@entry=16) at ../sysdeps/unix/sysv/linux/read.c:27 | |
#1 0x00007f4b69df1d5f in read (__nbytes=16, __buf=0x7f4b2dffee70, __fd=<optimized out>) at /usr/include/x86_64-linux-gnu/bits/unistd.h:44 | |
#2 __ibv_get_async_event (context=0x564694fd8300, event=0x7f4b2dffeed0) at src/device.c:770 | |
#3 0x00007f4bb84a5932 in wrap_ibv_get_async_event (context=context@entry=0x564694fd8300, event=event@entry=0x7f4b2dffeed0) at misc/ibvwrap.cc:220 | |
#4 0x00007f4bb845f563 in ncclIbAsyncThreadMain (args=0x564694fd8300) at transport/net_ib.cc:69 | |
#5 0x00007f4c096c26db in start_thread (arg=0x7f4b2dfff700) at pthread_create.c:463 | |
#6 0x00007f4c093eb88f in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95 | |
Thread 15 (Thread 0x7f4b757fa700 (LWP 11690)): | |
---Type <return> to continue, or q <return> to quit--- | |
#0 0x00007f4c096c89f3 in futex_wait_cancelable (private=<optimized out>, expected=0, futex_word=0x7f4b60000b88) at ../sysdeps/unix/sysv/linux/futex-internal.h:88 | |
#1 __pthread_cond_wait_common (abstime=0x0, mutex=0x56462e201bd8, cond=0x7f4b60000b60) at pthread_cond_wait.c:502 | |
#2 __pthread_cond_wait (cond=0x7f4b60000b60, mutex=0x56462e201bd8) at pthread_cond_wait.c:655 | |
#3 0x00007f4ba5ddbb8d in ?? () from /usr/lib/x86_64-linux-gnu/libcuda.so.1 | |
#4 0x00007f4ba5d81155 in ?? () from /usr/lib/x86_64-linux-gnu/libcuda.so.1 | |
#5 0x00007f4ba5ddadc8 in ?? () from /usr/lib/x86_64-linux-gnu/libcuda.so.1 | |
#6 0x00007f4c096c26db in start_thread (arg=0x7f4b757fa700) at pthread_create.c:463 | |
#7 0x00007f4c093eb88f in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95 | |
Thread 14 (Thread 0x7f4b75ffb700 (LWP 11689)): | |
#0 0x00007f4c093debf9 in __GI___poll (fds=0x7f4b64000bd0, nfds=11, timeout=100) at ../sysdeps/unix/sysv/linux/poll.c:29 | |
#1 0x00007f4ba5dd8733 in ?? () from /usr/lib/x86_64-linux-gnu/libcuda.so.1 | |
#2 0x00007f4ba5e674dd in ?? () from /usr/lib/x86_64-linux-gnu/libcuda.so.1 | |
#3 0x00007f4ba5ddadc8 in ?? () from /usr/lib/x86_64-linux-gnu/libcuda.so.1 | |
#4 0x00007f4c096c26db in start_thread (arg=0x7f4b75ffb700) at pthread_create.c:463 | |
#5 0x00007f4c093eb88f in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95 | |
Thread 13 (Thread 0x7f4b77fff700 (LWP 11680)): | |
#0 0x00007f4c096c8f85 in futex_abstimed_wait_cancelable (private=<optimized out>, abstime=0x7f4b77ffeb60, expected=0, futex_word=0x56462e271190) at ../sysdeps/unix/sysv/linux/futex-internal.h:205 | |
#1 __pthread_cond_wait_common (abstime=0x7f4b77ffeb60, mutex=0x56462e271110, cond=0x56462e271168) at pthread_cond_wait.c:539 | |
#2 __pthread_cond_timedwait (cond=0x56462e271168, mutex=0x56462e271110, abstime=0x7f4b77ffeb60) at pthread_cond_wait.c:667 | |
#3 0x00007f4bee248ba7 in torch::distributed::rpc::ProcessGroupAgent::pollTimedOutRPCs() () from /private/home/tbirch/.conda/envs/torch16/lib/python3.7/site-packages/torch/lib/libtorch_python.so | |
#4 0x00007f4bf07d3163 in std::execute_native_thread_routine (__p=0x56462e268130) at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/src/gcc/libstdc++-v3/src/c++11/thread.cc:80 | |
#5 0x00007f4c096c26db in start_thread (arg=0x7f4b77fff700) at pthread_create.c:463 | |
#6 0x00007f4c093eb88f in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95 | |
Thread 12 (Thread 0x7f4b7cff9700 (LWP 11678)): | |
#0 0x00007f4c096c8f85 in futex_abstimed_wait_cancelable (private=<optimized out>, abstime=0x7f4b7cff8b50, expected=0, futex_word=0x7f4b6c001358) at ../sysdeps/unix/sysv/linux/futex-internal.h:205 | |
#1 __pthread_cond_wait_common (abstime=0x7f4b7cff8b50, mutex=0x7f4b6c001308, cond=0x7f4b6c001330) at pthread_cond_wait.c:539 | |
#2 __pthread_cond_timedwait (cond=0x7f4b6c001330, mutex=0x7f4b6c001308, abstime=0x7f4b7cff8b50) at pthread_cond_wait.c:667 | |
#3 0x00007f4beaad2ed3 in gloo::transport::tcp::UnboundBuffer::waitRecv(int*, std::chrono::duration<long, std::ratio<1l, 1000l> >) () from /private/home/tbirch/.conda/envs/torch16/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so | |
#4 0x00007f4bee2b2c69 in c10d::ProcessGroupGloo::RecvWork::wait(std::chrono::duration<long, std::ratio<1l, 1000l> >) () from /private/home/tbirch/.conda/envs/torch16/lib/python3.7/site-packages/torch/lib/libtorch_python.so | |
#5 0x00007f4bee24b662 in torch::distributed::rpc::ProcessGroupAgent::listenLoopInternal() () from /private/home/tbirch/.conda/envs/torch16/lib/python3.7/site-packages/torch/lib/libtorch_python.so | |
#6 0x00007f4bee24bd25 in torch::distributed::rpc::ProcessGroupAgent::listenLoop() () from /private/home/tbirch/.conda/envs/torch16/lib/python3.7/site-packages/torch/lib/libtorch_python.so | |
#7 0x00007f4bf07d3163 in std::execute_native_thread_routine (__p=0x56462e271430) at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/src/gcc/libstdc++-v3/src/c++11/thread.cc:80 | |
#8 0x00007f4c096c26db in start_thread (arg=0x7f4b7cff9700) at pthread_create.c:463 | |
#9 0x00007f4c093eb88f in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95 | |
---Type <return> to continue, or q <return> to quit--- | |
Thread 11 (Thread 0x7f4b7d7fa700 (LWP 11676)): | |
#0 0x00007f4c096c8f85 in futex_abstimed_wait_cancelable (private=<optimized out>, abstime=0x7f4b7d7f9dc0, expected=0, futex_word=0x56462e270d80) at ../sysdeps/unix/sysv/linux/futex-internal.h:205 | |
#1 __pthread_cond_wait_common (abstime=0x7f4b7d7f9dc0, mutex=0x56462e270d88, cond=0x56462e270d58) at pthread_cond_wait.c:539 | |
#2 __pthread_cond_timedwait (cond=0x56462e270d58, mutex=0x56462e270d88, abstime=0x7f4b7d7f9dc0) at pthread_cond_wait.c:667 | |
#3 0x00007f4be977fb79 in torch::distributed::rpc::RpcAgent::retryExpiredRpcs() () from /private/home/tbirch/.conda/envs/torch16/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so | |
#4 0x00007f4bf07d3163 in std::execute_native_thread_routine (__p=0x56462e270450) at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/src/gcc/libstdc++-v3/src/c++11/thread.cc:80 | |
#5 0x00007f4c096c26db in start_thread (arg=0x7f4b7d7fa700) at pthread_create.c:463 | |
#6 0x00007f4c093eb88f in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95 | |
Thread 10 (Thread 0x7f4b7dffb700 (LWP 11672)): | |
#0 0x00007f4c096c89f3 in futex_wait_cancelable (private=<optimized out>, expected=0, futex_word=0x56462e271048) at ../sysdeps/unix/sysv/linux/futex-internal.h:88 | |
#1 __pthread_cond_wait_common (abstime=0x0, mutex=0x56462e270ff8, cond=0x56462e271020) at pthread_cond_wait.c:502 | |
#2 __pthread_cond_wait (cond=0x56462e271020, mutex=0x56462e270ff8) at pthread_cond_wait.c:655 | |
#3 0x00007f4bf07cf48b in __gthread_cond_wait (__mutex=<optimized out>, __cond=<optimized out>) | |
at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/build/build-cc-gcc-final/x86_64-conda_cos6-linux-gnu/libstdc++-v3/include/x86_64-conda_cos6-linux-gnu/bits/gthr-default.h:878 | |
#4 std::condition_variable::wait (this=<optimized out>, __lock=...) at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/src/gcc/libstdc++-v3/src/c++11/condition_variable.cc:53 | |
#5 0x00007f4bb441b97f in c10::ThreadPool::main_loop(unsigned long) () from /private/home/tbirch/.conda/envs/torch16/lib/python3.7/site-packages/torch/lib/libc10.so | |
#6 0x00007f4bf07d3163 in std::execute_native_thread_routine (__p=0x56462e270160) at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/src/gcc/libstdc++-v3/src/c++11/thread.cc:80 | |
#7 0x00007f4c096c26db in start_thread (arg=0x7f4b7dffb700) at pthread_create.c:463 | |
#8 0x00007f4c093eb88f in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95 | |
Thread 9 (Thread 0x7f4b7e7fc700 (LWP 11670)): | |
#0 0x00007f4c096c89f3 in futex_wait_cancelable (private=<optimized out>, expected=0, futex_word=0x56462e271048) at ../sysdeps/unix/sysv/linux/futex-internal.h:88 | |
#1 __pthread_cond_wait_common (abstime=0x0, mutex=0x56462e270ff8, cond=0x56462e271020) at pthread_cond_wait.c:502 | |
#2 __pthread_cond_wait (cond=0x56462e271020, mutex=0x56462e270ff8) at pthread_cond_wait.c:655 | |
#3 0x00007f4bf07cf48b in __gthread_cond_wait (__mutex=<optimized out>, __cond=<optimized out>) | |
at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/build/build-cc-gcc-final/x86_64-conda_cos6-linux-gnu/libstdc++-v3/include/x86_64-conda_cos6-linux-gnu/bits/gthr-default.h:878 | |
#4 std::condition_variable::wait (this=<optimized out>, __lock=...) at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/src/gcc/libstdc++-v3/src/c++11/condition_variable.cc:53 | |
#5 0x00007f4bb441b97f in c10::ThreadPool::main_loop(unsigned long) () from /private/home/tbirch/.conda/envs/torch16/lib/python3.7/site-packages/torch/lib/libc10.so | |
#6 0x00007f4bf07d3163 in std::execute_native_thread_routine (__p=0x56462e26ff00) at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/src/gcc/libstdc++-v3/src/c++11/thread.cc:80 | |
#7 0x00007f4c096c26db in start_thread (arg=0x7f4b7e7fc700) at pthread_create.c:463 | |
#8 0x00007f4c093eb88f in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95 | |
Thread 8 (Thread 0x7f4b7effd700 (LWP 11669)): | |
---Type <return> to continue, or q <return> to quit--- | |
#0 0x00007f4c096c89f3 in futex_wait_cancelable (private=<optimized out>, expected=0, futex_word=0x56462e271048) at ../sysdeps/unix/sysv/linux/futex-internal.h:88 | |
#1 __pthread_cond_wait_common (abstime=0x0, mutex=0x56462e270ff8, cond=0x56462e271020) at pthread_cond_wait.c:502 | |
#2 __pthread_cond_wait (cond=0x56462e271020, mutex=0x56462e270ff8) at pthread_cond_wait.c:655 | |
#3 0x00007f4bf07cf48b in __gthread_cond_wait (__mutex=<optimized out>, __cond=<optimized out>) | |
at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/build/build-cc-gcc-final/x86_64-conda_cos6-linux-gnu/libstdc++-v3/include/x86_64-conda_cos6-linux-gnu/bits/gthr-default.h:878 | |
#4 std::condition_variable::wait (this=<optimized out>, __lock=...) at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/src/gcc/libstdc++-v3/src/c++11/condition_variable.cc:53 | |
#5 0x00007f4bb441b97f in c10::ThreadPool::main_loop(unsigned long) () from /private/home/tbirch/.conda/envs/torch16/lib/python3.7/site-packages/torch/lib/libc10.so | |
#6 0x00007f4bf07d3163 in std::execute_native_thread_routine (__p=0x56462e26fca0) at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/src/gcc/libstdc++-v3/src/c++11/thread.cc:80 | |
#7 0x00007f4c096c26db in start_thread (arg=0x7f4b7effd700) at pthread_create.c:463 | |
#8 0x00007f4c093eb88f in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95 | |
Thread 7 (Thread 0x7f4b7f7fe700 (LWP 11668)): | |
#0 0x00007f4c096c89f3 in futex_wait_cancelable (private=<optimized out>, expected=0, futex_word=0x56462e271048) at ../sysdeps/unix/sysv/linux/futex-internal.h:88 | |
#1 __pthread_cond_wait_common (abstime=0x0, mutex=0x56462e270ff8, cond=0x56462e271020) at pthread_cond_wait.c:502 | |
#2 __pthread_cond_wait (cond=0x56462e271020, mutex=0x56462e270ff8) at pthread_cond_wait.c:655 | |
#3 0x00007f4bf07cf48b in __gthread_cond_wait (__mutex=<optimized out>, __cond=<optimized out>) | |
at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/build/build-cc-gcc-final/x86_64-conda_cos6-linux-gnu/libstdc++-v3/include/x86_64-conda_cos6-linux-gnu/bits/gthr-default.h:878 | |
#4 std::condition_variable::wait (this=<optimized out>, __lock=...) at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/src/gcc/libstdc++-v3/src/c++11/condition_variable.cc:53 | |
#5 0x00007f4bb441b97f in c10::ThreadPool::main_loop(unsigned long) () from /private/home/tbirch/.conda/envs/torch16/lib/python3.7/site-packages/torch/lib/libc10.so | |
#6 0x00007f4bf07d3163 in std::execute_native_thread_routine (__p=0x56462e2713f0) at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/src/gcc/libstdc++-v3/src/c++11/thread.cc:80 | |
#7 0x00007f4c096c26db in start_thread (arg=0x7f4b7f7fe700) at pthread_create.c:463 | |
#8 0x00007f4c093eb88f in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95 | |
Thread 6 (Thread 0x7f4b7ffff700 (LWP 11665)): | |
#0 0x00007f4c096c89f3 in futex_wait_cancelable (private=<optimized out>, expected=0, futex_word=0x56462e270978) at ../sysdeps/unix/sysv/linux/futex-internal.h:88 | |
#1 __pthread_cond_wait_common (abstime=0x0, mutex=0x56462e270928, cond=0x56462e270950) at pthread_cond_wait.c:502 | |
#2 __pthread_cond_wait (cond=0x56462e270950, mutex=0x56462e270928) at pthread_cond_wait.c:655 | |
#3 0x00007f4bf07cf48b in __gthread_cond_wait (__mutex=<optimized out>, __cond=<optimized out>) | |
at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/build/build-cc-gcc-final/x86_64-conda_cos6-linux-gnu/libstdc++-v3/include/x86_64-conda_cos6-linux-gnu/bits/gthr-default.h:878 | |
#4 std::condition_variable::wait (this=<optimized out>, __lock=...) at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/src/gcc/libstdc++-v3/src/c++11/condition_variable.cc:53 | |
#5 0x00007f4bee2b8af1 in c10d::ProcessGroupGloo::runLoop(int) () from /private/home/tbirch/.conda/envs/torch16/lib/python3.7/site-packages/torch/lib/libtorch_python.so | |
#6 0x00007f4bf07d3163 in std::execute_native_thread_routine (__p=0x56462e2673e0) at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/src/gcc/libstdc++-v3/src/c++11/thread.cc:80 | |
#7 0x00007f4c096c26db in start_thread (arg=0x7f4b7ffff700) at pthread_create.c:463 | |
#8 0x00007f4c093eb88f in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95 | |
---Type <return> to continue, or q <return> to quit--- | |
Thread 5 (Thread 0x7f4b9cf1a700 (LWP 11664)): | |
#0 0x00007f4c096c89f3 in futex_wait_cancelable (private=<optimized out>, expected=0, futex_word=0x56462e27097c) at ../sysdeps/unix/sysv/linux/futex-internal.h:88 | |
#1 __pthread_cond_wait_common (abstime=0x0, mutex=0x56462e270928, cond=0x56462e270950) at pthread_cond_wait.c:502 | |
#2 __pthread_cond_wait (cond=0x56462e270950, mutex=0x56462e270928) at pthread_cond_wait.c:655 | |
#3 0x00007f4bf07cf48b in __gthread_cond_wait (__mutex=<optimized out>, __cond=<optimized out>) | |
at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/build/build-cc-gcc-final/x86_64-conda_cos6-linux-gnu/libstdc++-v3/include/x86_64-conda_cos6-linux-gnu/bits/gthr-default.h:878 | |
#4 std::condition_variable::wait (this=<optimized out>, __lock=...) at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/src/gcc/libstdc++-v3/src/c++11/condition_variable.cc:53 | |
#5 0x00007f4bee2b8af1 in c10d::ProcessGroupGloo::runLoop(int) () from /private/home/tbirch/.conda/envs/torch16/lib/python3.7/site-packages/torch/lib/libtorch_python.so | |
#6 0x00007f4bf07d3163 in std::execute_native_thread_routine (__p=0x56462e25eb70) at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/src/gcc/libstdc++-v3/src/c++11/thread.cc:80 | |
#7 0x00007f4c096c26db in start_thread (arg=0x7f4b9cf1a700) at pthread_create.c:463 | |
#8 0x00007f4c093eb88f in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95 | |
Thread 4 (Thread 0x7f4b9d71b700 (LWP 11663)): | |
#0 0x00007f4c093ebbb7 in epoll_wait (epfd=31, events=0x7f4b9d71aba0, maxevents=64, timeout=10) at ../sysdeps/unix/sysv/linux/epoll_wait.c:30 | |
#1 0x00007f4beaabd265 in gloo::transport::tcp::Loop::run() () from /private/home/tbirch/.conda/envs/torch16/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so | |
#2 0x00007f4bf07d3163 in std::execute_native_thread_routine (__p=0x56462e25d270) at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/src/gcc/libstdc++-v3/src/c++11/thread.cc:80 | |
#3 0x00007f4c096c26db in start_thread (arg=0x7f4b9d71b700) at pthread_create.c:463 | |
#4 0x00007f4c093eb88f in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95 | |
Thread 3 (Thread 0x7f4b9df1c700 (LWP 11661)): | |
#0 0x00007f4c093debf9 in __GI___poll (fds=0x7f4b94000b60, nfds=4, timeout=-1) at ../sysdeps/unix/sysv/linux/poll.c:29 | |
#1 0x00007f4bee29c2a8 in c10d::TCPStoreDaemon::run() () from /private/home/tbirch/.conda/envs/torch16/lib/python3.7/site-packages/torch/lib/libtorch_python.so | |
#2 0x00007f4bf07d3163 in std::execute_native_thread_routine (__p=0x56462e25e6f0) at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/src/gcc/libstdc++-v3/src/c++11/thread.cc:80 | |
#3 0x00007f4c096c26db in start_thread (arg=0x7f4b9df1c700) at pthread_create.c:463 | |
#4 0x00007f4c093eb88f in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95 | |
Thread 2 (Thread 0x7f4b9f971700 (LWP 11657)): | |
#0 0x00007f4c093ed237 in accept4 (fd=12, addr=..., addr_len=0x7f4b9f970df8, flags=524288) at ../sysdeps/unix/sysv/linux/accept4.c:32 | |
#1 0x00007f4ba5dd96fa in ?? () from /usr/lib/x86_64-linux-gnu/libcuda.so.1 | |
#2 0x00007f4ba5dcb99d in ?? () from /usr/lib/x86_64-linux-gnu/libcuda.so.1 | |
#3 0x00007f4ba5ddadc8 in ?? () from /usr/lib/x86_64-linux-gnu/libcuda.so.1 | |
#4 0x00007f4c096c26db in start_thread (arg=0x7f4b9f971700) at pthread_create.c:463 | |
#5 0x00007f4c093eb88f in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95 | |
Thread 1 (Thread 0x7f4c09aca740 (LWP 11650)): | |
---Type <return> to continue, or q <return> to quit--- | |
#0 0x00007f4c096c8f85 in futex_abstimed_wait_cancelable (private=<optimized out>, abstime=0x7ffc2b70eee0, expected=0, futex_word=0x56462ad3c93c <_PyRuntime+1340>) at ../sysdeps/unix/sysv/linux/futex-internal.h:205 | |
#1 __pthread_cond_wait_common (abstime=0x7ffc2b70eee0, mutex=0x56462ad3c940 <_PyRuntime+1344>, cond=0x56462ad3c910 <_PyRuntime+1296>) at pthread_cond_wait.c:539 | |
#2 __pthread_cond_timedwait (cond=0x56462ad3c910 <_PyRuntime+1296>, mutex=0x56462ad3c940 <_PyRuntime+1344>, abstime=0x7ffc2b70eee0) at pthread_cond_wait.c:667 | |
#3 0x000056462abd965e in PyCOND_TIMEDWAIT (cond=0x56462ad3c910 <_PyRuntime+1296>, mut=0x56462ad3c940 <_PyRuntime+1344>, us=5000) at /home/conda/feedstock_root/build_artifacts/python_1591034797817/work/Python/condvar.h:90 | |
#4 take_gil () at /home/conda/feedstock_root/build_artifacts/python_1591034797817/work/Python/ceval_gil.h:208 | |
#5 0x000056462abd9692 in PyEval_AcquireThread () at /home/conda/feedstock_root/build_artifacts/python_1591034797817/work/Python/ceval.c:202 | |
#6 0x00007f4bed9d95ea in pybind11::gil_scoped_acquire::gil_scoped_acquire() () from /private/home/tbirch/.conda/envs/torch16/lib/python3.7/site-packages/torch/lib/libtorch_python.so | |
#7 0x00007f4bedcb37af in torch::autograd::PyNode::release_variables() () from /private/home/tbirch/.conda/envs/torch16/lib/python3.7/site-packages/torch/lib/libtorch_python.so | |
#8 0x00007f4be9294982 in torch::autograd::deleteNode(torch::autograd::Node*) () from /private/home/tbirch/.conda/envs/torch16/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so | |
#9 0x00007f4be9291f31 in std::_Sp_counted_ptr_inplace<torch::autograd::ReadyQueue, std::allocator<torch::autograd::ReadyQueue>, (__gnu_cxx::_Lock_policy)2>::_M_dispose() () | |
from /private/home/tbirch/.conda/envs/torch16/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so | |
#10 0x00007f4bed9d16c6 in std::_Sp_counted_base<(__gnu_cxx::_Lock_policy)2>::_M_release() () from /private/home/tbirch/.conda/envs/torch16/lib/python3.7/site-packages/torch/lib/libtorch_python.so | |
#11 0x00007f4bf07b5a9d in (anonymous namespace)::run (p=<optimized out>) at /home/conda/feedstock_root/build_artifacts/ctng-compilers_1578638331887/work/.build/x86_64-conda_cos6-linux-gnu/src/gcc/libstdc++-v3/libsupc++/atexit_thread.cc:75 | |
#12 0x00007f4c0930d041 in __run_exit_handlers (status=1, listp=0x7f4c096b5718 <__exit_funcs>, run_list_atexit=run_list_atexit@entry=true, run_dtors=run_dtors@entry=true) at exit.c:108 | |
#13 0x00007f4c0930d13a in __GI_exit (status=<optimized out>) at exit.c:139 | |
#14 0x000056462ac18308 in Py_Exit (sts=1) at /home/conda/feedstock_root/build_artifacts/python_1591034797817/work/Python/pylifecycle.c:2292 | |
#15 0x000056462ac183ae in handle_system_exit () at /home/conda/feedstock_root/build_artifacts/python_1591034797817/work/Python/pythonrun.c:636 | |
#16 0x000056462ac1843c in PyErr_PrintEx () at /home/conda/feedstock_root/build_artifacts/python_1591034797817/work/Python/pythonrun.c:646 | |
#17 0x000056462ac29672 in PyRun_SimpleStringFlags () at /home/conda/feedstock_root/build_artifacts/python_1591034797817/work/Python/pythonrun.c:457 | |
#18 0x000056462ac29749 in pymain_run_command (cf=0x7ffc2b70f1d0, command=<optimized out>) at /home/conda/feedstock_root/build_artifacts/python_1591034797817/work/Modules/main.c:386 | |
#19 pymain_run_python (pymain=0x7ffc2b70f2e0) at /home/conda/feedstock_root/build_artifacts/python_1591034797817/work/Modules/main.c:2862 | |
#20 pymain_main () at /home/conda/feedstock_root/build_artifacts/python_1591034797817/work/Modules/main.c:3029 | |
#21 0x000056462ac29aec in _Py_UnixMain () at /home/conda/feedstock_root/build_artifacts/python_1591034797817/work/Modules/main.c:3064 | |
#22 0x00007f4c092ebb97 in __libc_start_main (main=0x56462aae8ab0 <main>, argc=4, argv=0x7ffc2b70f438, init=<optimized out>, fini=<optimized out>, rtld_fini=<optimized out>, stack_end=0x7ffc2b70f428) at ../csu/libc-start.c:310 | |
#23 0x000056462abce73d in _start () at ../sysdeps/x86_64/elf/start.S:103 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment