I have function that returns me a value. I want to use threads for doSth function and set returning value for variables above, here is an example:
#include <string>
#include <iostream>
#include <thread>
using namespace std;
// func for execution
int doSth(int number)
{
return number;
}
int main()
{
// some code ...
int numberOne; // no value now, but in thread I want to set a value from it
int numberTwo; // depending on function input value
thread t1(doSth, 1); // set numberOne = 1;
thread t2(doSth, 2); // set numberTwo = 2;
// wait them to execute
t1.join();
t2.join();
// now I should have numberOne = 1; numberTwo = 2
// some code ...
return 0;
}
How could I do it?
How to return value from std::thread
Besides std::async shown in other answers, you can use std::packaged_task:
std::packaged_task<int(int)> task{doSth};
std::future<int> result = task.get_future();
task(1);
int numberOne = result.get();
This allows separating creation of the task, and executing it in case that is needed.
Method 1: Using std::async (higher-level wrapper for threads and futures):
#include <thread>
#include <future>
#include <iostream>
int func() { return 1; }
int main(){
std::future<int> ret = std::async(&func);
int i = ret.get();
std::cout<<"I: "<<i<<std::endl;
return 0;
}
Method 2: Using threads and futures:
#include <thread>
#include <future>
#include <iostream>
void func(std::promise<int> && p) {
p.set_value(1);
}
int main(){
std::promise<int> p;
auto f = p.get_future();
std::thread t(&func, std::move(p));
t.join();
int i = f.get();
std::cout<<"I: "<<i<<std::endl;
return 0;
}
My prefered method is encapsulate the call in a specific method returning nothing (and managing error in the same way).
void try_doSth(int number, int* return_value, int* status)
{
try
{
*return_value = doSth(number);
*status = 0;
}
catch(const std::exception& e) { *status = 1; }
catch(...) { *status = 2; }
}
int r1,r2,s1,s2;
std::thread t1(try_doSth, 1, &r1, &s1);
std::thread t2(try_doSth, 2, &r2, &s2);
Related
I wonder whether I can use the side effects of a conditional_variable test?
Is it guaranteed that the conditional_variable test is returning to execution if it returns true, or can there be the situation that the test returns
true, but it is called again or times out in between?
In the below example maybeCmd_locked() de-queues a cmd, however I want to
avoid that it is called 2 times for one exit of the conditional_variable wait:
if (cv.wait_until(lk, now + 100ms, [&cmd,this]{ return ((cmd = maybeCmd_locked()) != -1); }))
//g++ test.cpp -o test.exe -lstdc++ -lpthread
#include <stdlib.h>
#include <stdio.h>
#include <thread>
#include <queue>
#include <chrono>
#include <mutex>
#include <condition_variable>
using namespace std::literals::chrono_literals;
class eventLooper {
public:
eventLooper() : threadexit(false) {};
bool threadexit;
std::queue<int> cmds;
std::mutex m;
std::condition_variable cv;;
int maybeCmd_locked()
{
if (cmds.size() > 0) {
int cmd = cmds.front();
cmds.pop();
return cmd;
}
return -1;
}
int getNextCmd(void)
{
int cmd = -1;
std::unique_lock<std::mutex> lk(m);
auto now = std::chrono::system_clock::now();
if (cv.wait_until(lk, now + 100ms, [&cmd,this]{ return ((cmd = maybeCmd_locked()) != -1); }))
{
return cmd;
}
return -1;
}
int sendCmd(int cmd)
{
std::lock_guard<std::mutex> lock(m);
cmds.push(cmd);
cv.notify_one();
return 0;
}
void run(void)
{
int cmd;
printf("run\n");
std::this_thread::sleep_for(std::chrono::milliseconds(10));
while (!threadexit)
{
cmd = getNextCmd();
if (cmd == -1) {
std::this_thread::sleep_for(std::chrono::milliseconds(10));
} else {
printf("cmd received: %d\n", cmd);
}
}
}
};
eventLooper e;
int main(int argc, char **argv)
{
(void) argc;
(void) argv;
std::thread n(&eventLooper::run, &e);
for (int i = 0; i < 10; i++)
{
std::this_thread::sleep_for(1000ms);
e.sendCmd(i);
}
std::this_thread::sleep_for(1000ms);
e.threadexit = true;
n.join();
printf("exit\n");
return 0;
}
The predicate is always checked under the lock, and another wait isn't done if the predicate returns true. In a simplifed version of your code (which doesn't have time outs) is:
if (cv.wait(lk, [&cmd,this]{ return ((cmd = maybeCmd_locked()) != -1); }))
{
return cmd;
}
cv.wait(lock, pred) is defined to be equivalent of:
while(!pred())
{
wait(lock);
}
In this case you can see that your predicate cannot be called twice if it returns true the first time.
Adding the timeout to the question doesn't change how this work. cv.wait_until(...) is the equivalent of:
while (!pred()) {
if (wait_until(lock, timeout_time) == std::cv_status::timeout) {
return pred();
}
}
Again, its clear that what you're worried about cannot happen.
I have the program to count all words in all .log files in given directory using N threads.
I wrote something like this.
ThreadPool.h
#ifndef THREAD_POOL_H
#define THREAD_POOL_H
#include <boost/thread/condition_variable.hpp>
#include <boost/thread.hpp>
#include <future> // I don't how to work with boost future
#include <queue>
#include <vector>
#include <functional>
class ThreadPool
{
public:
using Task = std::function<void()>; // Our task
explicit ThreadPool(int num_threads)
{
start(num_threads);
}
~ThreadPool()
{
stop();
}
template<class T>
auto enqueue(T task)->std::future<decltype(task())>
{
// packaged_task wraps any Callable target
auto wrapper = std::make_shared<std::packaged_task<decltype(task()) ()>>(std::move(task));
{
boost::unique_lock<boost::mutex> lock{ mutex_p };
tasks_p.emplace([=] {
(*wrapper)();
});
}
event_p.notify_one();
return wrapper->get_future();
}
/*void enqueue(Task task)
{
{
boost::unique_lock<boost::mutex> lock { mutex_p };
tasks_p.emplace(std::move(task));
event_p.notify_one();
}
}*/
private:
std::vector<boost::thread> threads_p; // num of threads
std::queue<Task> tasks_p; // Tasks to make
boost::condition_variable event_p;
boost::mutex mutex_p;
bool isStop = false;
void start(int num_threads)
{
for (int i = 0; i < num_threads; ++i)
{
// Add to the end our thread
threads_p.emplace_back([=] {
while (true)
{
// Task to do
Task task;
{
boost::unique_lock<boost::mutex> lock(mutex_p);
event_p.wait(lock, [=] { return isStop || !tasks_p.empty(); });
// If we make all tasks
if (isStop && tasks_p.empty())
break;
// Take new task from queue
task = std::move(tasks_p.front());
tasks_p.pop();
}
// Execute our task
task();
}
});
}
}
void stop() noexcept
{
{
boost::unique_lock<boost::mutex> lock(mutex_p);
isStop = true;
}
event_p.notify_all();
for (auto& thread : threads_p)
{
thread.join();
}
}
};
#endif
main.cpp
#include "ThreadPool.h"
#include <iostream>
#include <iomanip>
#include <Windows.h>
#include <chrono>
#include <vector>
#include <map>
#include <boost/filesystem.hpp>
#include <boost/thread.hpp>
#include <locale.h>
namespace bfs = boost::filesystem;
//int count_words(boost::filesystem::ifstream& file)
//{
// int counter = 0;
// std::string buffer;
// while (file >> buffer)
// {
// ++counter;
// }
//
// return counter;
//}
//
int count_words(boost::filesystem::path filename)
{
boost::filesystem::ifstream ifs(filename);
return std::distance(std::istream_iterator<std::string>(ifs), std::istream_iterator<std::string>());
}
int main(int argc, const char* argv[])
{
std::cin.tie(0);
std::ios_base::sync_with_stdio(false);
bfs::path path = argv[1];
// If this path is exist and if this is dir
if (bfs::exists(path) && bfs::is_directory(path))
{
// Number of threads. Default = 4
int n = (argc == 3 ? atoi(argv[2]) : 4);
ThreadPool pool(n);
// Container to store all filenames and number of words inside them
//std::map<bfs::path, std::future<int>> all_files_and_sums;
std::vector<std::future<int>> futures;
auto start = std::chrono::high_resolution_clock::now();
// Iterate all files in dir
for (auto& p : bfs::directory_iterator(path)) {
// Takes only .txt files
if (p.path().extension() == ".log") {
// Future for taking value from here
auto fut = pool.enqueue([p]() {
// In this lambda function I count all words in file and return this value
int result = count_words(p.path());
static int count = 0;
++count;
std::ostringstream oss;
oss << count << ". TID, " << GetCurrentThreadId() << "\n";
std::cout << oss.str();
return result;
});
// "filename = words in this .txt file"
futures.emplace_back(std::move(fut));
}
}
int result = 0;
for (auto& f : futures)
{
result += f.get();
}
auto stop = std::chrono::high_resolution_clock::now();
auto duration = std::chrono::duration_cast<std::chrono::seconds>(stop - start);
std::cout << "Result: " << result << "\n";
std::cout << duration.count() << '\n';
}
else
std::perror("Dir is not exist");
}
Variable N is 4(Number of threads). I've 320 .log files in my directory and I need count words in this files. Everything works fine but when variable "count" is 180 - the program stops for a while and then continues but much slower.
What could be the reason?
CPU - Xeon e5430 (I have tested this program on another CPU - the result is the same).
It depends on how you measure "slow" but basically you are using one of the worst models possible:
one task queue shared between all threads.
The problem with this approach is blocking in each thread on the shared queue.
A much better model is something like
task stealing - you can try creating a task queue pro thread and then use try_lock (which doesnt block) with enabling each thread "stealing" work from some other thread's tasks if it has nothing else to do.
This is very nice explained in excellent Sean Parent Talk about Concurrency.
I've implemented thread pooling following the answer of Kerrek SB in this question.
I've implemented MPMC queue for the functions and vector threads for the threads.
Everything worked perfectly, except that I don't know how to terminate the program, in the end if I just do thread.join since the thread is still waiting for more tasks to do, it will not join and the main thread will not continue.
Any idea how to end the program correctly?
For completeness, this is my code:
function_pool.h
#pragma once
#include <queue>
#include <functional>
#include <mutex>
#include <condition_variable>
class Function_pool
{
private:
std::queue<std::function<void()>> m_function_queue;
std::mutex m_lock;
std::condition_variable m_data_condition;
public:
Function_pool();
~Function_pool();
void push(std::function<void()> func);
std::function<void()> pop();
};
function_pool.cpp
#include "function_pool.h"
Function_pool::Function_pool() : m_function_queue(), m_lock(), m_data_condition()
{
}
Function_pool::~Function_pool()
{
}
void Function_pool::push(std::function<void()> func)
{
std::unique_lock<std::mutex> lock(m_lock);
m_function_queue.push(func);
// when we send the notification immediately, the consumer will try to
get the lock , so unlock asap
lock.unlock();
m_data_condition.notify_one();
}
std::function<void()> Function_pool::pop()
{
std::unique_lock<std::mutex> lock(m_lock);
m_data_condition.wait(lock, [this]() {return !m_function_queue.empty();
});
auto func = m_function_queue.front();
m_function_queue.pop();
return func;
// Lock will be released
}
main.cpp
#include "function_pool.h"
#include <string>
#include <iostream>
#include <mutex>
#include <functional>
#include <thread>
#include <vector>
Function_pool func_pool;
void example_function()
{
std::cout << "bla" << std::endl;
}
void infinite_loop_func()
{
while (true)
{
std::function<void()> func = func_pool.pop();
func();
}
}
int main()
{
std::cout << "stating operation" << std::endl;
int num_threads = std::thread::hardware_concurrency();
std::cout << "number of threads = " << num_threads << std::endl;
std::vector<std::thread> thread_pool;
for (int i = 0; i < num_threads; i++)
{
thread_pool.push_back(std::thread(infinite_loop_func));
}
//here we should send our functions
func_pool.push(example_function);
for (int i = 0; i < thread_pool.size(); i++)
{
thread_pool.at(i).join();
}
int i;
std::cin >> i;
}
Your problem is located in infinite_loop_func, which is an infinite loop and by result doesn't terminate. I've read the previous answer which suggests throwing an exception, however, I don't like it since exceptions should not be used for the regular control flow.
The best way to solve this is to explicitly deal with the stop condition. For example:
std::atomic<bool> acceptsFunctions;
Adding this to the function pool allows you to clearly have state and to assert that no new functions being added when you destruct.
std::optional<std::function<void()>> Function_pool::pop()
Returning an empty optional (or function in C++14 and before), allows you to deal with an empty queue. You have to, as condition_variable can do spurious wakeups.
With this, m_data_condition.notify_all() can be used to wake all threads.
Finally we have to fix the infinite loop as it doesn't cover overcommitment and at the same time allows you to execute all functions still in the queue:
while (func_pool.acceptsFunctions || func_pool.containsFunctions())
{
auto f = func_pool.pop();
If (!f)
{
func_pool.m_data_condition.wait_for(1s);
continue;
}
auto &function = *f;
function ();
}
I'll leave it up to you to implement containsFunctions() and clean up the code (infinite_loop_func as member function?) Note that with a counter, you could even deal with background task being spawned.
You can always use a specific exception type to signal to infinite_loop_func that it should return...
class quit_worker_exception: public std::exception {};
Then change infinite_loop_func to...
void infinite_loop_func ()
{
while (true) {
std::function<void()> func = func_pool.pop();
try {
func();
}
catch (quit_worker_exception &ex) {
return;
}
}
}
With the above changes you could then use (in main)...
/*
* Enqueue `thread_pool.size()' function objects whose sole job is
* to throw an instance of `quit_worker_exception' when invoked.
*/
for (int i = 0; i < thread_pool.size(); i++)
func_pool.push([](){ throw quit_worker_exception(); });
/*
* Now just wait for each worker to terminate having received its
* quit_worker_exception.
*/
for (int i = 0; i < thread_pool.size(); i++)
thread_pool.at(i).join();
Each instance of infinite_loop_func will dequeue one function object which, when called, throws a quit_worker_exception causing it to return.
Follwoing [JVApen](https://stackoverflow.com/posts/51382714/revisions) suggestion, I copy my code in case anyone will want a working code:
function_pool.h
#pragma once
#include <queue>
#include <functional>
#include <mutex>
#include <condition_variable>
#include <atomic>
#include <cassert>
class Function_pool
{
private:
std::queue<std::function<void()>> m_function_queue;
std::mutex m_lock;
std::condition_variable m_data_condition;
std::atomic<bool> m_accept_functions;
public:
Function_pool();
~Function_pool();
void push(std::function<void()> func);
void done();
void infinite_loop_func();
};
function_pool.cpp
#include "function_pool.h"
Function_pool::Function_pool() : m_function_queue(), m_lock(), m_data_condition(), m_accept_functions(true)
{
}
Function_pool::~Function_pool()
{
}
void Function_pool::push(std::function<void()> func)
{
std::unique_lock<std::mutex> lock(m_lock);
m_function_queue.push(func);
// when we send the notification immediately, the consumer will try to get the lock , so unlock asap
lock.unlock();
m_data_condition.notify_one();
}
void Function_pool::done()
{
std::unique_lock<std::mutex> lock(m_lock);
m_accept_functions = false;
lock.unlock();
// when we send the notification immediately, the consumer will try to get the lock , so unlock asap
m_data_condition.notify_all();
//notify all waiting threads.
}
void Function_pool::infinite_loop_func()
{
std::function<void()> func;
while (true)
{
{
std::unique_lock<std::mutex> lock(m_lock);
m_data_condition.wait(lock, [this]() {return !m_function_queue.empty() || !m_accept_functions; });
if (!m_accept_functions && m_function_queue.empty())
{
//lock will be release automatically.
//finish the thread loop and let it join in the main thread.
return;
}
func = m_function_queue.front();
m_function_queue.pop();
//release the lock
}
func();
}
}
main.cpp
#include "function_pool.h"
#include <string>
#include <iostream>
#include <mutex>
#include <functional>
#include <thread>
#include <vector>
Function_pool func_pool;
class quit_worker_exception : public std::exception {};
void example_function()
{
std::cout << "bla" << std::endl;
}
int main()
{
std::cout << "stating operation" << std::endl;
int num_threads = std::thread::hardware_concurrency();
std::cout << "number of threads = " << num_threads << std::endl;
std::vector<std::thread> thread_pool;
for (int i = 0; i < num_threads; i++)
{
thread_pool.push_back(std::thread(&Function_pool::infinite_loop_func, &func_pool));
}
//here we should send our functions
for (int i = 0; i < 50; i++)
{
func_pool.push(example_function);
}
func_pool.done();
for (unsigned int i = 0; i < thread_pool.size(); i++)
{
thread_pool.at(i).join();
}
}
I`ve made a test code between std::thread and std::async.
#include <iostream>
#include <mutex>
#include <fstream>
#include <string>
#include <memory>
#include <thread>
#include <future>
#include <functional>
#include <boost/noncopyable.hpp>
#include <boost/lexical_cast.hpp>
#include <boost/filesystem.hpp>
#include <boost/date_time/posix_time/posix_time.hpp>
#include <boost/asio.hpp>
namespace fs = boost::filesystem;
namespace pt = boost::posix_time;
namespace as = boost::asio;
class Log : private boost::noncopyable
{
public:
void LogPath(const fs::path& filePath) {
boost::system::error_code ec;
if(fs::exists(filePath, ec)) {
fs::remove(filePath);
}
this->ofStreamPtr_.reset(new fs::ofstream(filePath));
};
void WriteLog(std::size_t i) {
assert(*this->ofStreamPtr_);
std::lock_guard<std::mutex> lock(this->logMutex_);
*this->ofStreamPtr_ << "Hello, World! " << i << "\n";
};
private:
std::mutex logMutex_;
std::unique_ptr<fs::ofstream> ofStreamPtr_;
};
int main(int argc, char *argv[]) {
if(argc != 2) {
std::cout << "Wrong argument" << std::endl;
exit(1);
}
std::size_t iter_count = boost::lexical_cast<std::size_t>(argv[1]);
Log log;
log.LogPath("log.txt");
std::function<void(std::size_t)> func = std::bind(&Log::WriteLog, &log, std::placeholders::_1);
auto start_time = pt::microsec_clock::local_time();
////// Version 1: use std::thread //////
// {
// std::vector<std::shared_ptr<std::thread> > threadList;
// threadList.reserve(iter_count);
// for(std::size_t i = 0; i < iter_count; i++) {
// threadList.push_back(
// std::make_shared<std::thread>(func, i));
// }
//
// for(auto it: threadList) {
// it->join();
// }
// }
// pt::time_duration duration = pt::microsec_clock::local_time() - start_time;
// std::cout << "Version 1: " << duration << std::endl;
////// Version 2: use std::async //////
start_time = pt::microsec_clock::local_time();
{
for(std::size_t i = 0; i < iter_count; i++) {
auto result = std::async(func, i);
}
}
duration = pt::microsec_clock::local_time() - start_time;
std::cout << "Version 2: " << duration << std::endl;
////// Version 3: use boost::asio::io_service //////
// start_time = pt::microsec_clock::local_time();
// {
// as::io_service ioService;
// as::io_service::strand strand{ioService};
// {
// for(std::size_t i = 0; i < iter_count; i++) {
// strand.post(std::bind(func, i));
// }
// }
// ioService.run();
// }
// duration = pt::microsec_clock::local_time() - start_time;
// std::cout << "Version 3: " << duration << std::endl;
}
With 4-core CentOS 7 box(gcc 4.8.5), Version 1(using std::thread) is about 100x slower compared to other implementations.
Iteration Version1 Version2 Version3
100 0.0034s 0.000051s 0.000066s
1000 0.038s 0.00029s 0.00058s
10000 0.41s 0.0042s 0.0059s
100000 throw 0.026s 0.061s
Why threaded version is so slow? I thought each thread won't take long time to complete Log::WriteLog function.
The function may never be called. You are not passing an std::launch policy in Version 2, so you are relying on the default behavior of std::async (emphasis mine):
Behaves the same as async(std::launch::async | std::launch::deferred, f, args...). In other words, f may be executed in another thread or it may be run synchronously when the resulting std::future is queried for a value.
Try re-running your benchmark with this minor change:
auto result = std::async(std::launch::async, func, i);
Alternatively, you could call result.wait() on each std::future in a second loop, similar to how you call join() on all of the threads in Version 1. This forces evaluation of the std::future.
Note that there is a major, unrelated, problem with this benchmark. func immediately acquires a lock for the full duration of the function call, which makes parallelism impossible. There is no advantage to using threads here - I suspect that it will be significantly slower (due to thread creation and locking overhead) than a serial implementation.
In the code below, main() function is calling request() function which inter call th_request_async() function which mm_th_done_cb().
What will be the best and efficient way to proceed in main only after the mm_th_done_cb() is executed.
DUMMY CODE
int mm_th_done_cb(int error_code, th_result_s* th_result, void* user_data)
{
return 0;
}
void request()
{
th_request_s MyItemInfo;
strncpy(MyItemInfo.origin_path, szUrl, 1024+1);
MyItemInfo.orientation = 0;
MyItemInfo.func = mm_th_done_cb;
MyItemInfo.used_cache = 1;
th_request_async(MyItemInfo);
}
int main()
{
request();
// Here I need to do something only after mm_th_done_cb() has been excuted.
}
You can use std::promise:
std::promise<int> promise;
int mm_th_done_cb(int error_code, th_result_s* th_result, void* user_data)
{
promise.set_value(error_code /*this value will be returned by the future.get()*/);
return 0;
}
int main()
{
std::future<int> future = promise.get_future();
request();
int value = future.get();
return 0;
}
If you don't need to return any value from the callback, then you can use a std::promise<void> and std::future<void> pair.
Both examples in wuqiang's answer are wrong.
1.
#include <future>
int main()
{
request();
// WRONG: Here we don't want to call 'mm_th_done_cb' ourselves.
std::future<int> myFuture = std::async(mm_th_done_cb);
//wait until mm_th_done_cb has been excuted;
int result = myFuture.get();
}
2.
#include <condition_variable>
std::mutex mtx;
std::condition_variable cv;
int mm_th_done_cb(int error_code, th_result_s* th_result, void* user_data)
{
cv.notify_one();
return 0;
}
int main()
{
request();
// WRONG: If the 'request' finishes quickly, then the 'mm_th_done_cb'
// callback will be called and will notify the condition variable before
// the following lines execute, i.e. before the main thread starts
// waiting on the condition variable. Thus the 'cv.wait(lck)' will
// never return.
unique_lock<std::mutex> lck(mtx);
cv.wait(lck);
return 0;
}
If C++11 is available,you can std::future
#include <future>
int main()
{
request();
std::future<int> myFuture = std::async(mm_th_done_cb);
//wait until mm_th_done_cb has been excuted;
int result = myFuture.get();
}
or you can use synchronization mechanism.such as condition_variable,which is cross-platform.
#include <condition_variable>
std::mutex mtx;
std::condition_variable cv;
int mm_th_done_cb(int error_code, th_result_s* th_result, void* user_data)
{
cv.notify_one();
return 0;
}
int main()
{
request();
unique_lock<std::mutex> lck(mtx);
cv.wait(lck);
return 0;
}
You can use RegisterWaitForSingleObject