Question

我有一个问题，要求我多次执行特定的可变长度计算（通常> 10 ^ 8），并且我要运行的处理器数量很少（<= 16）。下面的简化代码可以一次成功地成批创建NTHREADS批处理中的pthread，但是它的缺点是其他所有内容都会暂停直到每个批处理中最慢的线程完成。由于最慢的线程有时可能比最快的线程慢10-100倍，因此，平均而言，这意味着处理器可能大部分时间处于空闲状态。

我想做的是通过在每次终止时创建一个新的pthread来保持所有处理器繁忙。如果有一种方法可以检索当前活动的pthread的数量，那么我可以轻松地做到这一点，但是我还没有找到一种方法来实现这一点。

这可能吗？如果可以，怎么办？

#include <pthread.h>
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>

struct arg_struct {
  double x ;
  double y ;
};

int nloops = 0 ;  // initialize loop counter

void process(struct arg_struct  *args)
{
  int thisloop ;

  float x,y ;
  x = args->x ; y = args->y ;
  free(args) ;  // we're done with passed arguments

  nloops++ ;  // increment global counter 
  thisloop = nloops ;  // capture current loop  number

  sleep(11-nloops) ;  // variable delay
  printf("thisloop = %d   threadID = %d args = %.1f %.1f\n", thisloop,  (int) pthread_self(), x, y) ;

  pthread_exit(NULL); // exit thread
}

int main()
{
  const int MINLOOPS = 10 ;  // total number of loops to execute
  const int MAXTHREADS = 4 ;  // maximum number of threads at any one time

  int N, remaining ;
  pthread_t tid[MAXTHREADS];

  while (1)
    {
      remaining = MINLOOPS - nloops ;
      if (remaining == 0) break ;
      if (remaining < MAXTHREADS)
        N = remaining;
      else
        N = MAXTHREADS;

      for (int i = 0; i < N; i++) {  // create a set of simultaneous threads

        struct arg_struct *args = malloc(sizeof(struct arg_struct));  // initialize arguments
        args->x = i;  args->y = -i ;

        pthread_create(&tid[i], NULL, (void *) process,  (void *) args ) ;  
        printf("Created thread %d\n", (int) tid[i]) ;
      }

      for (int i = 0; i < N; i++) // wait until all threads in current loop have completed 
        pthread_join(tid[i], NULL);
    }
}

输出为：

Created thread 216977408
Created thread 217513984
Created thread 218050560
Created thread 218587136
thisloop = 4   threadID = 218587136 args = 3.0 -3.0
thisloop = 3   threadID = 218050560 args = 2.0 -2.0
thisloop = 2   threadID = 217513984 args = 1.0 -1.0
thisloop = 1   threadID = 216977408 args = 0.0 0.0
Created thread 216977408
Created thread 217513984
Created thread 218050560
Created thread 218587136
thisloop = 8   threadID = 218050560 args = 2.0 -2.0
thisloop = 7   threadID = 218587136 args = 3.0 -3.0
thisloop = 6   threadID = 217513984 args = 1.0 -1.0
thisloop = 5   threadID = 216977408 args = 0.0 0.0
Created thread 216977408
Created thread 217513984
thisloop = 10   threadID = 217513984 args = 1.0 -1.0
thisloop = 9   threadID = 216977408 args = 0.0 0.0

Answer 1

在发布我的问题之后，我想出了一个似乎可以接受的解决方案，如果可能的话，可能是幼稚的（在我知道最好的方法是线程池之前；请参见上面的paddy的评论）。基本上，它需要进行一些记账，包括将其他变量传递给线程处理。这是我想出的：

struct arg_struct {
  double x ;
  double y ;
  int ithread ;
  int loopno ;
};

const int MINLOOPS = 10 ;  // total number of loops to execute
const int MAXTHREADS = 4 ;  // maximum number of threads at any one time
pthread_t tid[MAXTHREADS] ; // table of active threads

int loopno = 0 ;  // initialize loop counter
int nthreads = 0 ; // current number of active threads

void process(struct arg_struct  *args)
{
  int loopno,ithread ;
  float x,y ;
  x = args->x ; y = args->y ; ithread = args->ithread ; loopno = args->loopno ;
  free(args) ;  // we're done with passed arguments

  sleep(MINLOOPS-loopno+1) ;  // variable delay
  printf("thisloop = %d   threadID = %d args = %.1f %.1f ithread = %d\n", loopno,  (int) pthread_self(), x, y, ithread) ;

  nthreads-- ;   // done with current thread
  tid[ithread] = 0 ;
  pthread_exit(NULL); // exit thread
}

int main()
{
  int ithread ;

  for (ithread=0; ithread<MAXTHREADS; ithread++) tid[ithread] = 0 ;  // initialize thread table

  while (loopno < MINLOOPS)
    {
      if (nthreads < MAXTHREADS) {  // check whether new thread needed
        for (int ith=0; ith<MAXTHREADS; ith++)  // find empty table entry
          {
            if (tid[ith] == 0) {
              ithread = ith ;
              break ;
            }
          }

        struct arg_struct *args = malloc(sizeof(struct arg_struct));  // initialize arguments

        loopno++ ;
        args->x = loopno;  args->y = -loopno ; args->ithread = ithread ; args->loopno = loopno ;
        pthread_create(&tid[ithread], NULL, (void *) process,  (void *) args ) ;  
        nthreads++ ;
        printf("Created thread %d\n", (int) tid[ithread]) ;
      }
    }

  for (int i = 0; i < MAXTHREADS; i++) // wait until remaining threads have completed 
    pthread_join(tid[i], NULL) ;

}

则输出为：

Created thread 82550784
Created thread 83087360
Created thread 83623936
Created thread 84160512
thisloop = 4   threadID = 84160512 args = 4.0 -4.0 ithread = 3
Created thread 84697088
thisloop = 3   threadID = 83623936 args = 3.0 -3.0 ithread = 2
Created thread 85233664
thisloop = 2   threadID = 83087360 args = 2.0 -2.0 ithread = 1
Created thread 85770240
thisloop = 1   threadID = 82550784 args = 1.0 -1.0 ithread = 0
Created thread 86306816
thisloop = 7   threadID = 85770240 args = 7.0 -7.0 ithread = 1
Created thread 86843392
thisloop = 6   threadID = 85233664 args = 6.0 -6.0 ithread = 2
Created thread 87379968
thisloop = 8   threadID = 86306816 args = 8.0 -8.0 ithread = 0
thisloop = 5   threadID = 84697088 args = 5.0 -5.0 ithread = 3
thisloop = 10   threadID = 87379968 args = 10.0 -10.0 ithread = 2
thisloop = 9   threadID = 86843392 args = 9.0 -9.0 ithread = 1

C：一次维护N个并发pthread，以进行M >> N个独立的计算

1 个答案: