c++ std:thread编译出错记录

本文详细介绍了如何在C++11中正确使用线程库。首先,需要确保编译器支持C++11标准,并通过指定编译选项来启用。其次,为使程序能够成功运行,还需链接到操作系统提供的线程库,如Linux下的libpthread。文章通过一个简单的示例程序,展示了从编译到执行过程中可能遇到的问题及解决方案。

https://coderwall.com/p/rzkw6q


Consider the following code, which uses the C++11 (used to be known as C++0x) thread library:

#include <iostream>
#include <thread>

using namespace std;

void hello_world()
{
  cout << "Hello from thread!\n";
}

int main()
{
  thread t(hello_world);
  t.join();
  return 0;
}

How can we get this to work? If we compile it with:

g++ bare.cpp -o bare

We'll get something like:

/usr/include/c++/4.5/bits/c++0x_warning.h:31:2: error: #error This file requires compiler and library support for the upcoming ISO C++ standard, C++0x. This support is currently experimental, and must be enabled with the -std=c++0x or -std=gnu++0x compiler options.

... and maybe something about the thread type used in the code:

error: ‘thread’ was not declared in this scope

So we add the std=c++0x ...

g++ bare.cpp -std=c++0x -o bare

No errors during compilation, but when we try to execute bare...

$ ./bare
terminate called after throwing an instance of 'std::system_error'
  what():  
Aborted

... oops. We have to link this against the operating system's implementation of threads. In linux, this is the libpthread library. The winning command is:

g++ bare.cpp -std=c++0x -lpthread -o bare

and then:

$ ./bare
Hello from thread!

<think>我们根据用户的问题和提供的参考资料,详细讲解C++std::thread的使用,包括线程创建、管理、同步机制等。 参考资料主要涉及[^1][^2][^3][^4],我们将结合这些内容进行讲解。 内容大纲: 1. 线程创建:使用函数指针、Lambda、函数对象、成员函数等 2. 线程管理:join和detach 3. 线程同步:互斥锁(std::mutex)和条件变量(std::condition_variable)等 4. 参数传递的注意事项 5. 线程局部存储(thread_local) 6. 异常处理 我们将按照上述结构详细展开,并给出代码示例。</think>### C++ `std::thread` 使用详解:线程创建与管理 C++11 引入的 `<thread>` 头文件提供了强大的多线程支持,其中 `std::thread` 是线程管理的核心类。以下是详细使用指南: --- #### 一、线程创建方式 线程可通过多种可调用对象创建: 1. **函数指针** ```cpp void task(int param) { std::cout << "线程执行: " << param << std::endl; } int main() { std::thread t(task, 42); // 创建线程并传递参数 t.join(); } ``` 2. **Lambda 表达式**(推荐) ```cpp std::thread t([](const std::string& msg) { std::cout << "Lambda线程: " << msg << std::endl; }, "Hello Thread"); ``` 3. **函数对象(Functor)** ```cpp struct Task { void operator()(int x) const { std::cout << "函数对象: " << x*x << std::endl; } }; std::thread t(Task{}, 5); // 传递函数对象实例 ``` 4. **类成员函数** ```cpp class Worker { public: void run(const std::string& data) { std::cout << "成员函数线程: " << data << std::endl; } }; Worker w; std::thread t(&Worker::run, &w, "Data"); // 需传递对象指针[^3] ``` --- #### 二、线程生命周期管理 1. **`join()`**:阻塞当前线程直到目标线程完成 ```cpp std::thread t([]{ /* 任务 */ }); t.join(); // 主线程在此等待 ``` 2. **`detach()`**:分离线程(后台运行,无法再控制) ```cpp std::thread t([]{ /* 长时间任务 */ }); t.detach(); // 主线程继续执行 ``` > ⚠️ 警告:未`join()`或`detach()`的线程析构时会调用`std::terminate()`[^2] 3. **`joinable()`**:检查线程是否可管理 ```cpp if (t.joinable()) { t.join(); // 安全操作 } ``` --- #### 三、线程同步机制 避免数据竞争需使用同步原语: 1. **互斥锁 (`std::mutex`)** ```cpp std::mutex mtx; int counter = 0; void safe_increment() { std::lock_guard<std::mutex> lock(mtx); // RAII自动解锁 ++counter; } ``` 2. **条件变量 (`std::condition_variable`)** 实现线程间通信: ```cpp std::condition_variable cv; std::mutex mtx; bool data_ready = false; // 生产者线程 void producer() { std::lock_guard<std::mutex> lock(mtx); data_ready = true; cv.notify_one(); // 通知消费者 } // 消费者线程 void consumer() { std::unique_lock<std::mutex> lock(mtx); cv.wait(lock, []{ return data_ready; }); // 阻塞直到条件满足 } ``` --- #### 四、参数传递注意事项 1. **默认按值传递**:参数被复制到线程独立内存空间 ```cpp int x = 10; std::thread t([](int a){ a *= 2; }, x); // x值不变 ``` 2. **引用传递需用 `std::ref` 包装** ```cpp int y = 20; std::thread t([](int& b){ b *= 2; }, std::ref(y)); // y变为40 ``` 3. **移动语义优化大对象** ```cpp std::vector<int> big_data(1000); std::thread t([](std::vector<int>&& data){ // 使用移动后的数据 }, std::move(big_data)); // 转移所有权 ``` --- #### 五、线程局部存储 (`thread_local`) 创建线程私有变量: ```cpp thread_local int thread_id = 0; // 每个线程独立副本 void print_id() { std::cout << "线程ID: " << thread_id++ << std::endl; } int main() { std::thread t1(print_id); // 输出0 std::thread t2(print_id); // 输出0(非1) t1.join(); t2.join(); } ``` --- #### 六、异常处理 线程内异常需捕获处理,否则导致程序终止: ```cpp void risky_task() { try { throw std::runtime_error("线程内部错误"); } catch (const std::exception& e) { std::cerr << "捕获异常: " << e.what() << std::endl; } } ``` --- ### 最佳实践 1. 优先使用 RAII 包装器(如 `std::lock_guard`) 2. 避免全局变量,使用参数传递数据 3. 用 `std::async` 替代 `std::thread` 实现任务并行(简化资源管理)[^4] 4. C++20 推荐 `std::jthread`(自动管理生命周期) ```cpp // std::async 示例 auto future = std::async(std::launch::async, []{ return std::sqrt(2.0); // 异步计算 }); double result = future.get(); // 获取结果 ``` --- ### 相关问题 1. 如何实现线程池以提高大量小任务的性能? 2. `std::atomic` 在无锁编程中如何应用? 3. 多线程调试有哪些常用工具和技巧? 4. C++20 协程如何简化异步编程模型? > 源码示例在 GCC/Clang 需编译选项:`-std=c++11 -pthread` > MSVC 需启用:`/std:c++latest /EHsc` [^1]: 线程创建方式与参数传递机制 [^2]: 线程生命周期管理关键点 [^3]: 类成员函数线程化实现 [^4]: 高级异步任务处理方案
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值