个人简介网站怎么做,网站建设年终总结怎么写,赚钱软件学生,伊滨区网站建设问题
上一节我们针对函数内静态变量初始化在多线程环境中要不要用锁保护提出了疑问#xff0c;代码如下#xff1a; class Singleton {
public:static Singleton getInstance() {std::lock_guardstd::mutex lock(mutex); // Acquire lock for thread safetysta…问题
上一节我们针对函数内静态变量初始化在多线程环境中要不要用锁保护提出了疑问代码如下 class Singleton {
public:static Singleton getInstance() {std::lock_guardstd::mutex lock(mutex); // Acquire lock for thread safetystatic Singleton instance; // Local static variable for thread safetyreturn instance;结论
不必。C11已经自己加锁了。
__cxa_guard_acquire
为了简单我们先简单写个试验程序
class Product {
public:Product(){std::coutProduct constructorstd::endl;}
};void test(){std::coutI am in test()std::endl;static Product pro;std::coutleaving test()std::endl;
}int main() {std::thread first(test);std::thread second(test);first.join();second.join();test();return 0;
}直接用GDB或者objdump看下test函数对应的汇编
(gdb) disass test
Dump of assembler code for function test():0x0000000000400e26 0: push %rbp0x0000000000400e27 1: mov %rsp,%rbp0x0000000000400e2a 4: push %r120x0000000000400e2c 6: push %rbx0x0000000000400e2d 7: mov $0x401808,%esi0x0000000000400e32 12: mov $0x6030c0,%edi0x0000000000400e37 17: callq 0x400ca0 _ZStlsISt11char_traitsIcEERSt13basic_ostreamIcT_ES5_PKcplt0x0000000000400e3c 22: mov $0x400c40,%esi0x0000000000400e41 27: mov %rax,%rdi0x0000000000400e44 30: callq 0x400cd0 _ZNSolsEPFRSoS_Eplt0x0000000000400e49 35: movzbl 0x202390(%rip),%eax # 0x6031e0 _ZGVZ4testvE3pro0x0000000000400e50 42: test %al,%al0x0000000000400e52 44: sete %al0x0000000000400e55 47: test %al,%al0x0000000000400e57 49: je 0x400e86 test()960x0000000000400e59 51: mov $0x6031e0,%edi0x0000000000400e5e 56: callq 0x400d20 __cxa_guard_acquireplt0x0000000000400e63 61: test %eax,%eax0x0000000000400e65 63: setne %al0x0000000000400e68 66: test %al,%al0x0000000000400e6a 68: je 0x400e86 test()960x0000000000400e6c 70: mov $0x0,%r12d0x0000000000400e72 76: mov $0x6031d9,%edi0x0000000000400e77 81: callq 0x40103a Product::Product()0x0000000000400e7c 86: mov $0x6031e0,%edi0x0000000000400e81 91: callq 0x400c70 __cxa_guard_releaseplt0x0000000000400e86 96: mov $0x401817,%esi0x0000000000400e8b 101: mov $0x6030c0,%edi0x0000000000400e90 106: callq 0x400ca0 _ZStlsISt11char_traitsIcEERSt13basic_ostreamIcT_ES5_PKcplt0x0000000000400e95 111: mov $0x400c40,%esi0x0000000000400e9a 116: mov %rax,%rdi0x0000000000400e9d 119: callq 0x400cd0 _ZNSolsEPFRSoS_Eplt0x0000000000400ea2 124: jmp 0x400ec1 test()1550x0000000000400ea4 126: mov %rax,%rbx0x0000000000400ea7 129: test %r12b,%r12b0x0000000000400eaa 132: jne 0x400eb6 test()1440x0000000000400eac 134: mov $0x6031e0,%edi0x0000000000400eb1 139: callq 0x400c60 __cxa_guard_abortplt0x0000000000400eb6 144: mov %rbx,%rax0x0000000000400eb9 147: mov %rax,%rdi0x0000000000400ebc 150: callq 0x400d10 _Unwind_Resumeplt0x0000000000400ec1 155: pop %rbx0x0000000000400ec2 156: pop %r120x0000000000400ec4 158: pop %rbp0x0000000000400ec5 159: retq简单提一下_ZGVZ4testvE3pro demangle一下第一次值是0初始化后是1
[mzhaisingletonFactoryAi]$ cfilt _ZGVZ4testvE3pro
guard variable for test()::pro 着重看下面的__cxa_guard_acquire
看到__cxa_guard_acquire、__cxa_guard_release没中间夹着Product::Product() 即使没见过这两个函数也能猜到和static变量初始化有关防止多个线程同时初始化一个静态变量. 这是我把__cxa_guard_acquire输入搜索引擎搜到的
C constructor guards for static instances Introduction The libstd ABI requires implementations of the following functions: int __cxa_guard_acquire(__guard *g); void __cxa_guard_release(__guard *g); void __cxa_guard_abort(__guard *g); These functions are not intended to be ever used by the programmer, instead the C compiler will emit code calling them if statically allocated class instances are used. In a multi-threaded environment special care needs to be taken to prevent race conditions while initializing and using such instances. This modules provides them. Usage This module is intended to be used by platforms that want to provide C support, but the used standard C library does not provide these guards. In this case, adding this module will do the trick. The programmer / user should never interact with any of the functions. Note that on some platforms the type __guard is defined differently from the generic definition, most notably ARM. For those platforms a header named cxx_ctor_guards_arch.h needs to be created containing the correct typedef and the preprocessor macro CXX_CTOR_GUARDS_CUSTOM_TYPE needs to be defined. https://opensource.apple.com/source/libcppabi/libcppabi-14/src/cxa_guard.cxx int __cxxabiv1::__cxa_guard_acquire(uint64_t* guard_object)
{// Double check that the initializer has not already been runif ( initializerHasRun(guard_object) )return 0;// We now need to acquire a lock that allows only one thread// to run the initializer. If a different thread calls// __cxa_guard_acquire() with the same guard object, we want // that thread to block until this thread is done running the // initializer and calls __cxa_guard_release(). But if the same// thread calls __cxa_guard_acquire() with the same guard object,// we want to abort. // To implement this we have one global pthread recursive mutex // shared by all guard objects, but only one at a time. 用GDB 模拟race condition
如果读者感兴趣可以调试一下我们给出的程序
(gdb) b __cxa_guard_acquire 使得两个线程都停在__cxa_guard_acquire
Breakpoint 2 at 0x7ffff7acf980
(gdb) r
Continuing.
Thread 2 a.out hit Breakpoint 2, 0x00007ffff7acf980 in __cxa_guard_acquire () from /lib64/libstdc.so.6Thread 3 a.out hit Breakpoint 2, 0x00007ffff7acf980 in __cxa_guard_acquire () from /lib64/libstdc.so.6
Quit(gdb) where
Selected thread is running.(gdb) info thread 2、3线程都停在了__cxa_guard_acquireId Target Id Frame
* 1 Thread 0x7ffff7fe1740 (LWP 2468153) a.out (running)2 Thread 0x7ffff6eb9700 (LWP 2468165) a.out 0x00007ffff7acf980 in __cxa_guard_acquire () from /lib64/libstdc.so.63 Thread 0x7ffff66b8700 (LWP 2468166) a.out 0x00007ffff7acf980 in __cxa_guard_acquire () from /lib64/libstdc.so.6(gdb) b Product::Product thread 2
Breakpoint 3 at 0x401046: file static_var_in_func.cpp, line 36.
(gdb) thread apply 2 c 让第二个线程获得锁先停在静态变量初始化中
Thread 2 (Thread 0x7ffff6eb9700 (LWP 2468165)):
Continuing.
Thread 2 a.out hit Breakpoint 3, Product::Product (this0x6031d9 test()::pro) at static_var_in_func.cpp:36
36 std::coutProduct constructorstd::endl;(gdb) thread apply 3 c 让第三个线程还没获得锁继续运行应该卡在__cxa_guard_acquire
Thread 3 (Thread 0x7ffff66b8700 (LWP 2468166)):
Continuing.
^C
Thread 1 a.out received signal SIGINT, Interrupt.
0x00007ffff78226cd in __pthread_timedjoin_ex () from /lib64/libpthread.so.0
(gdb) thread 3
[Switching to thread 3 (Thread 0x7ffff66b8700 (LWP 2468166))](running)
(gdb) where
Selected thread is running.
(gdb) interrupt
(gdb)
Thread 3 a.out stopped.
0x00007ffff72759bd in syscall () from /lib64/libc.so.6
Quit
(gdb) where 正如预期第三个线程卡在获得锁上
#0 0x00007ffff72759bd in syscall () from /lib64/libc.so.6
#1 0x00007ffff7acfa3f in __cxa_guard_acquire () from /lib64/libstdc.so.6
#2 0x0000000000400e63 in test () at static_var_in_func.cpp:42
#3 0x0000000000401205 in std::__invoke_implvoid, void (*)() (__f0x616008: 0x400e26 test()) at /usr/include/c/8/bits/invoke.h:60
#4 0x0000000000401085 in std::__invokevoid (*)() (__fn0x616008: 0x400e26 test()) at /usr/include/c/8/bits/invoke.h:95
#5 0x00000000004016d4 in std::thread::_Invokerstd::tuplevoid (*)() ::_M_invoke0ul (this0x616008) at /usr/include/c/8/thread:244
#6 0x00000000004016aa in std::thread::_Invokerstd::tuplevoid (*)() ::operator() (this0x616008) at /usr/include/c/8/thread:253
#7 0x000000000040168e in std::thread::_State_implstd::thread::_Invokerstd::tuplevoid (*)() ::_M_run (this0x616000) at /usr/include/c/8/thread:196
#8 0x00007ffff7afbb23 in execute_native_thread_routine () from /lib64/libstdc.so.6
#9 0x00007ffff78211ca in start_thread () from /lib64/libpthread.so.0
#10 0x00007ffff7275e73 in clone () from /lib64/libc.so.6 AI的回答 mzhai: Assume there is a static variable A which is an object of a class, this static variable is defined in a function named funA. When is A initialized? and is there a race condition if two threads call funA concurrently? ChatGPT: In C, static variables inside functions (local static variables) are initialized the first time the program execution encounters their declaration within that function. Theyre initialized in a thread-safe manner in compliance with the C11 standard. For instance, if you have a function funA with a static variable A inside it, like this: void funA() { static MyClass A; // ... } When funA is called for the first time, the static MyClass A; line will be executed. This initialization occurs once, and subsequent calls to funA wont reinitialize A. This initialization is thread-safe in C11 and later, meaning the standard guarantees that it will be properly handled in a multi-threaded context. There wont be a race condition during this initialization. Bard: Heres a breakdown of the initialization and potential race condition: 1. Initialization of static variable A: When: The static variable A will be initialized the first time control flow reaches its declaration within funA, even if its not explicitly used in that particular call.How: The constructor of the class will be invoked to initialize As members.Subsequent calls: In subsequent calls to funA, the already initialized instance of A will be used, and the constructor wont be called again. 2. Race condition in multi-threaded environment: Yes, a race condition can occur if two threads call funA concurrently before A has been initialized.Scenario: Both threads enter funA for the first time.Both threads see that A hasnt been initialized yet.Both threads attempt to create an instance of A, leading to multiple initializations and potential data corruption or crashes. 可见在这方面Bard不如Chat GPT正确。 他山之石
后来搜到一篇外文博客读者可以作为参考。Adventures in Systems Programming: C Local Statics - In Pursuit of Laziness
