性能测试:sem_t诉s.dispatch_semaphore_t和pthread_once_t诉s.dispatch_once_t
-
30-09-2019 - |
题
我想知道什么会更好/更快地使用POSIX呼吁喜欢 pthread_once()
和 sem_wait()
或dispatch_*功能,所以我创造了一个小测试,我感到惊奇的结果(问题和结果是在结束)。
在测试的代码,我在使用mach_absolute_time()时间的话。我真的不关心,这是不完全匹配的了纳秒;我比较值彼此的确切时间单位不重要,只有差异之间的时间间隔做。该数字在该部分的结果是重复性的和不平均;我可以有平均时间,但我不是在寻找确切的数字。
测试。m(简单的控制台应用程序;简单来编译):
#import <Foundation/Foundation.h>
#import <dispatch/dispatch.h>
#include <semaphore.h>
#include <pthread.h>
#include <time.h>
#include <mach/mach_time.h>
// *sigh* OSX does not have pthread_barrier (you can ignore the pthread_barrier
// code, the interesting stuff is lower)
typedef int pthread_barrierattr_t;
typedef struct
{
pthread_mutex_t mutex;
pthread_cond_t cond;
int count;
int tripCount;
} pthread_barrier_t;
int pthread_barrier_init(pthread_barrier_t *barrier, const pthread_barrierattr_t *attr, unsigned int count)
{
if(count == 0)
{
errno = EINVAL;
return -1;
}
if(pthread_mutex_init(&barrier->mutex, 0) < 0)
{
return -1;
}
if(pthread_cond_init(&barrier->cond, 0) < 0)
{
pthread_mutex_destroy(&barrier->mutex);
return -1;
}
barrier->tripCount = count;
barrier->count = 0;
return 0;
}
int pthread_barrier_destroy(pthread_barrier_t *barrier)
{
pthread_cond_destroy(&barrier->cond);
pthread_mutex_destroy(&barrier->mutex);
return 0;
}
int pthread_barrier_wait(pthread_barrier_t *barrier)
{
pthread_mutex_lock(&barrier->mutex);
++(barrier->count);
if(barrier->count >= barrier->tripCount)
{
barrier->count = 0;
pthread_cond_broadcast(&barrier->cond);
pthread_mutex_unlock(&barrier->mutex);
return 1;
}
else
{
pthread_cond_wait(&barrier->cond, &(barrier->mutex));
pthread_mutex_unlock(&barrier->mutex);
return 0;
}
}
//
// ok you can start paying attention now...
//
void onceFunction(void)
{
}
@interface SemaphoreTester : NSObject
{
sem_t *sem1;
sem_t *sem2;
pthread_barrier_t *startBarrier;
pthread_barrier_t *finishBarrier;
}
@property (nonatomic, assign) sem_t *sem1;
@property (nonatomic, assign) sem_t *sem2;
@property (nonatomic, assign) pthread_barrier_t *startBarrier;
@property (nonatomic, assign) pthread_barrier_t *finishBarrier;
@end
@implementation SemaphoreTester
@synthesize sem1, sem2, startBarrier, finishBarrier;
- (void)thread1
{
pthread_barrier_wait(startBarrier);
for(int i = 0; i < 100000; i++)
{
sem_wait(sem1);
sem_post(sem2);
}
pthread_barrier_wait(finishBarrier);
}
- (void)thread2
{
pthread_barrier_wait(startBarrier);
for(int i = 0; i < 100000; i++)
{
sem_wait(sem2);
sem_post(sem1);
}
pthread_barrier_wait(finishBarrier);
}
@end
int main (int argc, const char * argv[])
{
NSAutoreleasePool * pool = [[NSAutoreleasePool alloc] init];
int64_t start;
int64_t stop;
// semaphore non contention test
{
// grrr, OSX doesn't have sem_init
sem_t *sem1 = sem_open("sem1", O_CREAT, 0777, 0);
start = mach_absolute_time();
for(int i = 0; i < 100000; i++)
{
sem_post(sem1);
sem_wait(sem1);
}
stop = mach_absolute_time();
sem_close(sem1);
NSLog(@"0 Contention time = %d", stop - start);
}
// semaphore contention test
{
__block sem_t *sem1 = sem_open("sem1", O_CREAT, 0777, 0);
__block sem_t *sem2 = sem_open("sem2", O_CREAT, 0777, 0);
__block pthread_barrier_t startBarrier;
pthread_barrier_init(&startBarrier, NULL, 3);
__block pthread_barrier_t finishBarrier;
pthread_barrier_init(&finishBarrier, NULL, 3);
dispatch_queue_t queue = dispatch_get_global_queue(DISPATCH_QUEUE_PRIORITY_LOW, 0);
dispatch_async(queue, ^{
pthread_barrier_wait(&startBarrier);
for(int i = 0; i < 100000; i++)
{
sem_wait(sem1);
sem_post(sem2);
}
pthread_barrier_wait(&finishBarrier);
});
dispatch_async(queue, ^{
pthread_barrier_wait(&startBarrier);
for(int i = 0; i < 100000; i++)
{
sem_wait(sem2);
sem_post(sem1);
}
pthread_barrier_wait(&finishBarrier);
});
pthread_barrier_wait(&startBarrier);
// start timing, everyone hit this point
start = mach_absolute_time();
// kick it off
sem_post(sem2);
pthread_barrier_wait(&finishBarrier);
// stop timing, everyone hit the finish point
stop = mach_absolute_time();
sem_close(sem1);
sem_close(sem2);
NSLog(@"2 Threads always contenting time = %d", stop - start);
pthread_barrier_destroy(&startBarrier);
pthread_barrier_destroy(&finishBarrier);
}
// NSTask semaphore contention test
{
sem_t *sem1 = sem_open("sem1", O_CREAT, 0777, 0);
sem_t *sem2 = sem_open("sem2", O_CREAT, 0777, 0);
pthread_barrier_t startBarrier;
pthread_barrier_init(&startBarrier, NULL, 3);
pthread_barrier_t finishBarrier;
pthread_barrier_init(&finishBarrier, NULL, 3);
SemaphoreTester *tester = [[[SemaphoreTester alloc] init] autorelease];
tester.sem1 = sem1;
tester.sem2 = sem2;
tester.startBarrier = &startBarrier;
tester.finishBarrier = &finishBarrier;
[NSThread detachNewThreadSelector:@selector(thread1) toTarget:tester withObject:nil];
[NSThread detachNewThreadSelector:@selector(thread2) toTarget:tester withObject:nil];
pthread_barrier_wait(&startBarrier);
// start timing, everyone hit this point
start = mach_absolute_time();
// kick it off
sem_post(sem2);
pthread_barrier_wait(&finishBarrier);
// stop timing, everyone hit the finish point
stop = mach_absolute_time();
sem_close(sem1);
sem_close(sem2);
NSLog(@"2 NSTasks always contenting time = %d", stop - start);
pthread_barrier_destroy(&startBarrier);
pthread_barrier_destroy(&finishBarrier);
}
// dispatch_semaphore non contention test
{
dispatch_semaphore_t sem1 = dispatch_semaphore_create(0);
start = mach_absolute_time();
for(int i = 0; i < 100000; i++)
{
dispatch_semaphore_signal(sem1);
dispatch_semaphore_wait(sem1, DISPATCH_TIME_FOREVER);
}
stop = mach_absolute_time();
NSLog(@"Dispatch 0 Contention time = %d", stop - start);
}
// dispatch_semaphore non contention test
{
__block dispatch_semaphore_t sem1 = dispatch_semaphore_create(0);
__block dispatch_semaphore_t sem2 = dispatch_semaphore_create(0);
__block pthread_barrier_t startBarrier;
pthread_barrier_init(&startBarrier, NULL, 3);
__block pthread_barrier_t finishBarrier;
pthread_barrier_init(&finishBarrier, NULL, 3);
dispatch_queue_t queue = dispatch_get_global_queue(DISPATCH_QUEUE_PRIORITY_LOW, 0);
dispatch_async(queue, ^{
pthread_barrier_wait(&startBarrier);
for(int i = 0; i < 100000; i++)
{
dispatch_semaphore_wait(sem1, DISPATCH_TIME_FOREVER);
dispatch_semaphore_signal(sem2);
}
pthread_barrier_wait(&finishBarrier);
});
dispatch_async(queue, ^{
pthread_barrier_wait(&startBarrier);
for(int i = 0; i < 100000; i++)
{
dispatch_semaphore_wait(sem2, DISPATCH_TIME_FOREVER);
dispatch_semaphore_signal(sem1);
}
pthread_barrier_wait(&finishBarrier);
});
pthread_barrier_wait(&startBarrier);
// start timing, everyone hit this point
start = mach_absolute_time();
// kick it off
dispatch_semaphore_signal(sem2);
pthread_barrier_wait(&finishBarrier);
// stop timing, everyone hit the finish point
stop = mach_absolute_time();
NSLog(@"Dispatch 2 Threads always contenting time = %d", stop - start);
pthread_barrier_destroy(&startBarrier);
pthread_barrier_destroy(&finishBarrier);
}
// pthread_once time
{
pthread_once_t once = PTHREAD_ONCE_INIT;
start = mach_absolute_time();
for(int i = 0; i <100000; i++)
{
pthread_once(&once, onceFunction);
}
stop = mach_absolute_time();
NSLog(@"pthread_once time = %d", stop - start);
}
// dispatch_once time
{
dispatch_once_t once = 0;
start = mach_absolute_time();
for(int i = 0; i <100000; i++)
{
dispatch_once(&once, ^{});
}
stop = mach_absolute_time();
NSLog(@"dispatch_once time = %d", stop - start);
}
[pool drain];
return 0;
}
在我iMac(雪豹服务器10.6.4):
Model Identifier: iMac7,1 Processor Name: Intel Core 2 Duo Processor Speed: 2.4 GHz Number Of Processors: 1 Total Number Of Cores: 2 L2 Cache: 4 MB Memory: 4 GB Bus Speed: 800 MHz
我得到:
0 Contention time = 101410439 2 Threads always contenting time = 109748686 2 NSTasks always contenting time = 113225207 0 Contention named semaphore time = 166061832 2 Threads named semaphore contention time = 203913476 2 NSTasks named semaphore contention time = 204988744 Dispatch 0 Contention time = 3411439 Dispatch 2 Threads always contenting time = 708073977 pthread_once time = 2707770 dispatch_once time = 87433
在我MacbookPro(雪豹10.6.4):
Model Identifier: MacBookPro6,2 Processor Name: Intel Core i5 Processor Speed: 2.4 GHz Number Of Processors: 1 Total Number Of Cores: 2 (though HT is enabled) L2 Cache (per core): 256 KB L3 Cache: 3 MB Memory: 8 GB Processor Interconnect Speed: 4.8 GT/s
我得到了:
0 Contention time = 74172042 2 Threads always contenting time = 82975742 2 NSTasks always contenting time = 82996716 0 Contention named semaphore time = 106772641 2 Threads named semaphore contention time = 162761973 2 NSTasks named semaphore contention time = 162919844 Dispatch 0 Contention time = 1634941 Dispatch 2 Threads always contenting time = 759753865 pthread_once time = 1516787 dispatch_once time = 120778
在iPhone上3GS4.0.2我得到了:
0 Contention time = 5971929 2 Threads always contenting time = 11989710 2 NSTasks always contenting time = 11950564 0 Contention named semaphore time = 16721876 2 Threads named semaphore contention time = 35333045 2 NSTasks named semaphore contention time = 35296579 Dispatch 0 Contention time = 151909 Dispatch 2 Threads always contenting time = 46946548 pthread_once time = 193592 dispatch_once time = 25071
问题和发言:
sem_wait()
和sem_post()
是缓慢的时候不是在竞争- 为什么会这样呢?
- 不OS x不关心的兼容Api?是有一些遗留系统的代码,部队,这是缓慢?
- 为什么不是这些数字相同dispatch_semaphore职能?
sem_wait()
和sem_post()
只是因为缓慢当在争作为当他们不(存在差异,但我认为,这将是一个巨大的差异之间的争议和不;我预期的数字喜欢的是什么dispatch_semaphore代码)sem_wait()
和sem_post()
慢当使用的命名的信号灯。- 为什么?这是因为信必须同步进程之间?也许还有更多的行李的时候这样做。
dispatch_semaphore_wait()
和dispatch_semaphore_signal()
都快疯了时不受竞争(不令人惊讶在这里,因为苹果是鼓吹这个很多)。dispatch_semaphore_wait()
和dispatch_semaphore_signal()
3倍的速度低于sem_wait()
和sem_post()
当下的竞争- 这是为什么如此缓慢?这没有意义我。我希望这是在与sem_t下的竞争。
dispatch_once()
是的速度比pthread_once()
, ,周围的10倍,为什么?唯一我可以从头是,没有功能呼负担dispatch_once()
比pthread_once()
.
动机: 我提出的2套工具来完成工作,为信号量或一次的电话(其实我发现了其他的信号量变异体在此期间,但我会忽略这些,除非作为一个更好的选择)。我只是想知道什么是最好的工具的工作(如果有的选择拧螺丝与飞利浦或平头,我会选择飞利浦如果我没有扭螺丝和平头如果我们要扭螺丝).看来,如果我开始编写实用工具与libdispatch我可能无法口到其他操作系统没有libdispatch工作但...但它是很诱人的利用;)
因为它代表:我将使用libdispatch当我没有担心的便携性和POSIX电话当我这样做。
谢谢!
解决方案
sem_wait()和sem_post()重量同步设计,可以用之间的进程。他们总是涉及往返行程的核心,并可能总是需要你的线要重新安排。他们一般都是不正确的选择进程同步。我不知道为什么命名的变会慢于匿名的人...
Mac OS X实际上是非常良好的关Posix兼容性...但Posix规格有很多可选择的职能,并Mac没有他们所有。你的员额实际上是我第一次听说过pthread_barriers,所以我猜他们要么是相对较新,或不是所有的共同点。(我没有太注意到这演变过去十年左右。)
因派遣的东西落除了在强制极端的争论可能是因为在所涵盖的行为是类似于旋锁。你的调度工作人员的线很可能浪费的一块好的他们的量子在乐观的假设,资源下的竞争将会提供任何周期现在...一点时间有鲨鱼会告诉你的肯定。带回家的时候,应该是"优化"的颠簸在争是穷人的投资程序的时间。而不是花费的时间,在优化的代码 避免 重争放在第一位。
如果你真的有资源,是联合国可以避免的瓶颈,在你的过程,把一个信号灯周围的大规模子最佳的。把它放在它自己的序列遣队列,并尽可能dispatch_async块上执行,队列中。
最后,dispatch_once()快于pthread_once()因为它是规范会和实现可快速在当前处理器。可能以加速的pthread_once()实现,因为我怀疑参考实现使用pthread同步元,但是...嗯...他们已经提供了所有的libdispatch善,而不是。:-)