Embedding a Python interpreter in a multi-threaded C++ program with pybind11

Question

I'm trying to use pybind11 in order to make a 3rd party C++ library call a Python method. The library is multithreaded, and each thread creates a Python object, and then does numerous calls to the object's methods.

My problem is that the call to py::gil_scoped_acquire acquire; deadlocks. A minimal code which reproduces the problem is given below. What am I doing wrong?

// main.cpp
class Wrapper
{
public:
  Wrapper()
  {
    py::gil_scoped_acquire acquire;
    auto obj = py::module::import("main").attr("PythonClass")();
    _get_x = obj.attr("get_x");
    _set_x = obj.attr("set_x");
  }
  
  int get_x() 
  {
    py::gil_scoped_acquire acquire;
    return _get_x().cast<int>();
  }

  void set_x(int x)
  {
    py::gil_scoped_acquire acquire;
    _set_x(x);
  }

private:
  py::object _get_x;
  py::object _set_x;
};


void thread_func()
{
  Wrapper w;

  for (int i = 0; i < 10; i++)
  {
    w.set_x(i);
    std::cout << "thread: " << std::this_thread::get_id() << " w.get_x(): " << w.get_x() << std::endl;
    std::this_thread::sleep_for(100ms);    
  }
}

int main() {
  py::scoped_interpreter python;
  
  std::vector<std::thread> threads;

  for (int i = 0; i < 5; ++i)
    threads.push_back(std::thread(thread_func));

  for (auto& t : threads)
    t.join();

  return 0;
}

and the Python code:

// main.py
class PythonClass:
    def __init__(self):
        self._x = 0

    def get_x(self):
        return self._x

    def set_x(self, x):
        self._x = x

Related questions can be found here and here, but did not help me solve the problem.

Answer 1

I managed to resolve the issue by releasing the GIL in the main thread, before starting the worker threads (added py::gil_scoped_release release;). For anybody who is interested, the following now works (also added cleaning up Python objects):

#include <pybind11/embed.h>  
#include <iostream>
#include <thread>
#include <chrono>
#include <sstream>

namespace py = pybind11;
using namespace std::chrono_literals;

class Wrapper
{
public:
  Wrapper()
  {
    py::gil_scoped_acquire acquire;
    _obj = py::module::import("main").attr("PythonClass")();
    _get_x = _obj.attr("get_x");
    _set_x = _obj.attr("set_x");

  }
  
  ~Wrapper()
  {
    _get_x.release();
    _set_x.release();
  }

  int get_x() 
  {
    py::gil_scoped_acquire acquire;
    return _get_x().cast<int>();
  }

  void set_x(int x)
  {
    py::gil_scoped_acquire acquire;
    _set_x(x);
  }

private:
  py::object _obj;
  py::object _get_x;
  py::object _set_x;
};


void thread_func(int iteration)
{
  Wrapper w;

  for (int i = 0; i < 10; i++)
  {
    w.set_x(i);
    std::stringstream msg;
    msg << "iteration: " << iteration << " thread: " << std::this_thread::get_id() << " w.get_x(): " << w.get_x() << std::endl;
    std::cout << msg.str();
    std::this_thread::sleep_for(100ms);    
  }
}

int main() {
  py::scoped_interpreter python;
  py::gil_scoped_release release; // add this to release the GIL

  std::vector<std::thread> threads;
  
  for (int i = 0; i < 5; ++i)
    threads.push_back(std::thread(thread_func, 1));

  for (auto& t : threads)
    t.join();

  return 0;
}