I am trying to create two threads resembling TaskA and TaskB. Both TaskA and TaskB do some kind of computation that it is not very interesting for this post. TaskA and TaskB have to be executed 10 times in order to cover the whole array. TaskA has an input AA and an output BB. BB is also the input of TaskB. CC is the output of TaskB. Because BB is written by taskA and read by taskB we need mutexes.
The behavior I would like to achieve is that when TaskA operates on i, TaskB operates on i-1 in parallel, where i is the number of arrays that are processed. I want to avoid TaskB to wait for TaskA to finish for every i.
The problem here is that I have a deadlock. ThreadA and ThreadB represent TaskA and TaskB. To make it easier I removed all the computations and I left only synchronization instructions. The deadlock is caused because ThreadA signals the conditional variable CV[0] before threadB is in the state that waits for CV[0].
Do you know any way to remove the deadlock but without TaskA waiting for TaskB to finish and vice versa. Ideally when TaskA operates on array i TaskB should operate on array i-1.
/* Includes */
#include <unistd.h> /* Symbolic Constants */
#include <sys/types.h> /* Primitive System Data Types */
#include <errno.h> /* Errors */
#include <stdio.h> /* Input/Output */
#include <stdlib.h> /* General Utilities */
#include <pthread.h> /* POSIX Threads */
#include <string.h> /* String handling */
#include <semaphore.h> /* Semaphore */
#include <stdint.h>
#define ARRAY_SIZE 2048*2400
#define DEBUG
//#define CHECK_RESULTS
pthread_mutex_t mutex[10];
pthread_cond_t cv[10];
/* prototype for thread routine */
void threadA ( void *ptr );
void threadB ( void *ptr );
struct thread_arg
{
uint32_t *in;
uint32_t *out;
uint32_t ID;
};
int main()
{
pthread_t pthA;
pthread_t pthB;
//Memory allocation
uint32_t *AA = malloc(10*ARRAY_SIZE*sizeof(uint32_t));
uint32_t *BB = malloc(10*ARRAY_SIZE*sizeof(uint32_t));
uint32_t *CC = malloc(10*ARRAY_SIZE*sizeof(uint32_t));
unsigned int j,i;
// THread Arguments
struct thread_arg arguments[2];
arguments[0].in = AA;
arguments[0].out = BB;
arguments[0].ID = 1;
arguments[1].in = BB;
arguments[1].out = CC;
arguments[1].ID = 2;
//Init arguments data
for (j=0;j<10;j++)
{
for (i=0;i<ARRAY_SIZE;i++)
{
AA[j*ARRAY_SIZE+i] = i;
BB[j*ARRAY_SIZE+i] = 0;
CC[j*ARRAY_SIZE+i] = 99 ;
}
}
//Semaphore and conditional variables init
for (i=0;i<10;i++){
pthread_mutex_init(&mutex[i], NULL);
pthread_cond_init (&cv[i], NULL);
}
pthread_create (&pthA, NULL, (void *) &threadA, (void *) &arguments[0]);
pthread_create (&pthB, NULL, (void *) &threadB, (void *) &arguments[1]);
pthread_join(pthA, NULL);
pthread_join(pthB, NULL);
// Destroy Semaphores and CVs
for (i=0;i<10;i++)
{
pthread_mutex_destroy(&mutex[i]);
pthread_cond_destroy(&cv[i]);
}
// Checking results
exit(0);
} /* main() */
void threadA ( void *ptr )
{
int i;
struct thread_arg *arg = (struct thread_arg *) ptr;
for (i=0;i<10;i++)
{
pthread_mutex_lock(&mutex[i]);
printf("TA: LOCK_M%d \n",i);
pthread_cond_signal(&cv[i]);
printf("TA: SIG_CV%d\n",i);
pthread_mutex_unlock(&mutex[i]);
printf("TA: UNL_M%d\n",i);
}
pthread_exit(0); /* exit thread */
}
void threadB ( void *ptr )
{
int i;
struct thread_arg *arg = (struct thread_arg *) ptr;
for (i=0;i<10;i++)
{
pthread_mutex_lock(&mutex[i]);
printf("TB: WAIT_CV%d\n",i,i);
pthread_cond_wait(&cv[i], &mutex[i]);
printf("TB CV%d_PASSED\n",i);
pthread_mutex_unlock(&mutex[i]);
printf("TB UNL_M%d \n",i);
}
pthread_exit(NULL);
}