LuaPlus: How to call Lua function from multithreaded C++?

Question

I have a kind of callback function in my Lua script which I would like to call from different threads on the C++ side (0-100 times per second). So far it basically work, but as soon as I call it multiple times in a very short period of time it crashes the program causing errors like:
-As????ion failed: 0, file ...LuaFunction.h, line 146 or this one (completely random)

I think this happens, when it gets called from the C++ side before it finished another task. The most obvious thing for me to try (mutex lock all threads during the lua-function call) didn't help at all. :/
If I only call the Lua-function like once per 2 seconds, then I don't get any errors at all (Well, until the clean up part, if it gets to that point it will crash without a specific error).

Here is my code (I tried to crop and simplify my code as much as possible, and added a lot of commenting):

#include "stdafx.hpp"
#include <pthread.h> //for multithreading
#include <windows.h>
#include <iostream>
#include <map>
using namespace std;

unsigned int maxThreads = 100;
map<unsigned int, pthread_t> threads;
map<unsigned int, bool> threadsState;

pthread_mutex_t mutex; //to lock the pthreads (to keep printing from overlapping etc)

LuaPlus::LuaState* pState = LuaPlus::LuaState::Create( true ); //initialize LuaPlus
LuaPlus::LuaObject globals = pState->GetGlobals();

struct argumentStruct { //to pass multiple arguments to the function called when starting a pthread
    unsigned int threadId;
    int a;
    int b;
};

map<unsigned int, struct argumentStruct> argumentMap; //we store the arguments of active threads in here

void *ThreadFunction(void *arguments) { //will be called for every pthread we're going to create
    struct argumentStruct*args = (struct argumentStruct*)arguments; //get the arrgument struct
    int threadId = args->threadId; //get variables for each struct field
    int a = args->a;
    int b = args->b;
    Sleep(3000); //since this is a very simplified version of my actual project
    int c = a+b;
    pthread_mutex_lock(&mutex); //lock pthreads for the next lines
      LuaPlus::LuaFunction<int> CPP_OnMyEvent = pState->GetGlobal("LUA_OnMyEvent"); //get the Lua callback function to call on the C++ side
      CPP_OnMyEvent(a,b,c); //call to our lua-callback function
    pthread_mutex_unlock(&mutex); //unlock pthreads
    threadsState[threadId] = false; //mark the thread as finished/ready to get overwritten by a new one
    return NULL;
}
bool AddThread(int a, int b) {
    for (;;) {
        if (threads.size() < maxThreads) { //if our array of threads isn't full yet, create a new thread
            int id = threads.size();
            argumentMap[id].threadId = threads.size();
            argumentMap[id].a = a;
            argumentMap[id].b = b;
            threadsState[id] = true; //mark the thread as existing/running
            pthread_create(&threads[id], NULL, &ThreadFunction, (void *)&argumentMap[id]);
            return true;
        } else {
            unsigned int id;
            for (auto thread=threads.begin(); thread!=threads.end(); ++thread) {
                id = thread->first;
                if(!threadsState[id]) { //if thread with id "id" has finished, create a new thread on it's pthread_t
                    argumentMap[id].threadId = id;
                    argumentMap[id].a = a;
                    argumentMap[id].b = b;
                    threadsState[id] = true; //mark the thread as existing/running
                    pthread_join(threads[id], NULL);
                    pthread_create(&threads[id], NULL, &ThreadFunction, (void *)&argumentMap[id]);
                    return true;
                }
            }
        }
    }
    return false;
}


int main() {
    pthread_mutex_init(&mutex, NULL); //initialize the mutex
    //LuaPlus::LuaState* pState = LuaPlus::LuaState::Create( true ); //we already initialized this globally
    //LuaPlus::LuaObject globals = pState->GetGlobals();
    //pState->DoString("function LUA_OnMyEvent(arg1,arg2) print(arg1..arg2) end"); //it's already in main.lua

    globals.RegisterDirect("AddThread", AddThread);

    char pPath[ MAX_PATH ];
    GetCurrentDirectory(MAX_PATH,pPath);
    strcat_s(pPath,MAX_PATH,"\\main.lua");
    if( pState->DoFile(pPath) ) { //run our main.lua script which contains the callback function that will run a print
        if( pState->GetTop() == 1 )
            std::cout << "An error occured: " << pState->CheckString(1) << std::endl;
    }

    for (auto thread=threads.begin(); thread!=threads.end(); ++thread) { //wait for threads to finish
        unsigned int id = thread->first;
        if(threadsState[id])
            pthread_join(threads[id], NULL);
    }

    //clean up
    LuaPlus::LuaState::Destroy( pState );
    pState = nullptr;
    pthread_mutex_destroy(&mutex);
    getchar(); //keep console from closing
    return 0;
}

main.lua

function LUA_OnMyEvent(a,b,c)
    print(a.."+"..b.."="..c)
end

for i=1, 999, 1 do
    AddThread(i,i*2)
end

Answer 1

I don't know Lua enough to give you a solution at Lua side, but this view of the problem may help you reaching that out.

When you call AddThread() from Lua, something like this will happen:

1. LuaState allocations
2. AddThread() execution
3. LuaState unwinding

While on ThreadFunction()...

A. Mutex lock
B. LuaState allocations
C. LUA_OnMyEvent() execution
D. LuaState unwinding 
E. Mutex Unlock

There is no mutex control at AddThread, so a race condition can happen between 1/3 and B/D. However, adding the mutex to AddThread would not solve the problem, because it would still run between 1 and 3.

If AddThread() is called only at the program initialization, then you could block all threads till initialization is done. If it is called frequently during program execution, then I would make those calls from a separate LuaState.

[EDIT] 2nd idea: Use a producer/consumer approach. Then C++ threads won't need to run Lua code.

C++ suggestion:

//-- start Task.h --

struct Task{
  static list<Task*> runningTasks;
  static list<Task*> doneTasks;
  static pthread_mutex_t mutex;
  list<Task*>::iterator iterator;

  virtual ~Task(){}

  bool start(){
    pthread_mutex_lock(&mutex);
    bool hasSpace = runningTasks.size() < 100;
    if(hasSpace){
      runningTasks.push_front(this);
      iterator = runningTasks.begin();
      pthread_t unusedID;
      pthread_create(&unusedID, NULL, Task::threadBody, this);
    }
    pthread_mutex_unlock(&mutex);
    return hasSpace;
  }

  virtual void run() = 0;
  virtual void processResults() = 0;

protected:
  void finish(){
    pthread_mutex_lock(&mutex);
    runningTasks.erase(iterator);
    doneTasks.push_front(this);
    pthread_mutex_unlock(&mutex);
  }

  static void* threadBody(void* instance){
    Task* task = static_cast<Task*>(instance);
    task->run();
    task->finish();
    return NULL;
  }
};
//-- end Task.h --

//-- start Task.cpp --

//Instantiate Task's static attributes
pthread_mutex_t Task::mutex;
list<Task*> Task::runningTasks;
list<Task*> Task::doneTasks;

//-- end Task.cpp --

struct SumTask: public Task{
  int a, b, c;
  void run(){
    Sleep(3000);
    c = a+b;
  }
  void processResults(){
    LuaPlus::LuaFunction<int> CPP_OnMyEvent = pState->GetGlobal("LUA_OnMyEvent");
    CPP_OnMyEvent(a,b,c);
  }
}

//functions called by Lua
bool runSumTask(int a, int b){
  SumTask task* = new SumTask();
  task->a = a; task->b = b;
  bool ok = task->start();
  if(!ok)
    delete task;
  return ok;
}

int gatherResults(){
  pthread_mutex_lock(&Task::mutex);
  int totalResults = Task::doneTasks.size();
  while(Task::doneTasks.size() > 0){
    Task* t = Task::doneTasks.front();
    Task::doneTasks.pop_front();
    t->processResults();
    delete t;
  }
  pthread_mutex_unlock(&Task::mutex);
  return totalResults;
}

int main() {
    //Must initialize/destroy Task::mutex
    pthread_mutex_init(&Task::mutex, NULL);
    //...
    pthread_mutex_destroy(&Task::mutex);
}

Lua code:

function LUA_OnMyEvent(a,b,c)
  print(a.."+"..b.."="..c)
end

local totalRunning = 0;
for i=1, 999, 1 do
  if (runSumTask(i,i*2))
    totalRunning = totalRunning + 1;

  totalRunning -= gatherResults();
end

while(totalRunning > 0) do
  totalRunning -= gatherResults();
  mySleepFunction(...);
end