Unix Multi-Process Programming Inter-Process Communications (IPC)

Что такое процесс в юниксе .

 #include <unistd.h>	/* defines fork(), and pid_t.      */
 #include <sys/wait.h>	/* defines the wait() system call. */
 /* storage place for the pid of the child process, and its exit status. */
 pid_t child_pid;
 int child_status;
 /* lets fork off a child process... */
 child_pid = fork();
 /* check what the fork() call actually did */
 switch (child_pid) {
     case -1:	/* fork() failed */
 	perror("fork");	/* print a system-defined error message */
 	exit(1);
     case 0:	/* fork() succeeded, we're inside the child process */
 	printf("hello world\n");
 	exit(0);	/* here the CHILD process exits, not the parent. */
     default:	/* fork() succeeded, we're inside the parent process */
 	wait(&child_status);	/* wait till the child process exits */
 }
 /* parent's process code may continue here... */
 
Child Process Termination

 #include <stdio.h>     /* basic I/O routines.   */
 #include <unistd.h>    /* define fork(), etc.   */
 #include <sys/types.h> /* define pid_t, etc.    */
 #include <sys/wait.h>  /* define wait(), etc.   */
 #include <signal.h>    /* define signal(), etc. */
 /* first, here is the code for the signal handler */
 void catch_child(int sig_num)
 {
     /* when we get here, we know there's a zombie child waiting */
     int child_status;
     wait(&child_status);
     printf("child exited.\n");
 }
 /* and somewhere in the main() function ... */
 /* define the signal handler for the CHLD signal */
 signal(SIGCHLD, catch_child);
 /* and the child process forking code... */
 {
     int child_pid;
     int i;
     child_pid = fork();
     switch (child_pid) {
         case -1:         /* fork() failed */
             perror("fork");
             exit(1);
         case 0:          /* inside child process  */
             printf("hello world\n");
             sleep(5);    /* sleep a little, so we'll have */
                          /* time to see what is going on  */
             exit(0);
         default:         /* inside parent process */
             break;
     }
     /* parent process goes on, minding its own business... */
     /* for example, some output...                         */
     for (i=0; i<10; i++) {
         printf("%d\n", i);
         sleep(1);    /* sleep for a second, so we'll have time to see the mix */
     }
 }

 /* first, define an array to store the two file descriptors */
 int pipes[2];
 /* now, create the pipe */
 int rc = pipe(pipes);
 if (rc == -1) { /* pipe() failed */
     perror("pipe");
     exit(1);
 }

 #include <stdio.h>    /* standard I/O routines.                */
 #include <unistd.h>   /* defines pipe(), amongst other things. */
 /* this routine handles the work of the child process. */
 void do_child(int data_pipe[]) {
     int c;	/* data received from the parent. */
     int rc;	/* return status of read().       */
     /* first, close the un-needed write-part of the pipe. */
     close(data_pipe[1]);
     /* now enter a loop of reading data from the pipe, and printing it */
     while ((rc = read(data_pipe[0], &c, 1)) > 0) {
 	putchar(c);
     }
     /* probably pipe was broken, or got EOF via the pipe. */
     exit(0);
 }
 /* this routine handles the work of the parent process. */
 void do_parent(int data_pipe[])
 {
     int c;	/* data received from the user. */
     int rc;	/* return status of getchar().  */
     /* first, close the un-needed read-part of the pipe. */
     close(data_pipe[0]);
     /* now enter a loop of read user input, and writing it to the pipe. */
     while ((c = getchar()) > 0) {
 	/* write the character to the pipe. */
         rc = write(data_pipe[1], &c, 1);
 	if (rc == -1) { /* write failed - notify the user and exit */
 	    perror("Parent: write");
 	    close(data_pipe[1]);
 	    exit(1);
         }
     }
     /* probably got EOF from the user. */
     close(data_pipe[1]); /* close the pipe, to let the child know we're done. */
     exit(0);
 }
 /* and the main function. */
 int main(int argc, char* argv[])
 {
     int data_pipe[2]; /* an array to store the file descriptors of the pipe. */
     int pid;       /* pid of child process, or 0, as returned via fork.    */
     int rc;        /* stores return values of various routines.            */
 
     /* first, create a pipe. */
     rc = pipe(data_pipe);
     if (rc == -1) {
 	perror("pipe");
 	exit(1);
     }
     /* now fork off a child process, and set their handling routines. */
     pid = fork();
     switch (pid) {
 	case -1:	/* fork failed. */
 	    perror("fork");
 	    exit(1);
 	case 0:		/* inside child process.  */
 	    do_child(data_pipe);
 	    /* NOT REACHED */
 	default:	/* inside parent process. */
 	    do_parent(data_pipe);
 	    /* NOT REACHED */
     }
     return 0;	/* NOT REACHED */
 }

 #include <stdio.h>    /* standard I/O routines.                  */
 #include <unistd.h>   /* defines pipe(), amongst other things.   */
 #include <ctype.h>    /* defines isascii(), toupper(), and other */
                       /* character manipulation routines.        */
 /* function executed by the user-interacting process. */
 void user_handler(int input_pipe[], int output_pipe[])
 {
     int c;    /* user input - must be 'int', to recognize EOF (= -1). */
     char ch;  /* the same - as a char. */
     int rc;   /* return values of functions. */
     /* first, close unnecessary file descriptors */
     close(input_pipe[1]); /* we don't need to write to this pipe.  */
     close(output_pipe[0]); /* we don't need to read from this pipe. */
     /* loop: read input, send via one pipe, read via other */
     /* pipe, and write to stdout. exit on EOF from user.   */
     while ((c = getchar()) > 0) {
         /* note - when we 'read' and 'write', we must deal with a char, */
         /* rather then an int, because an int is longer then a char,    */
         /* and writing only one byte from it, will lead to unexpected   */
         /* results, depending on how an int is stored on the system.    */
         ch = (char)c;
 	/* write to translator */
         rc = write(output_pipe[1], &ch, 1);
 	if (rc == -1) { /* write failed - notify the user and exit. */
 	    perror("user_handler: write");
 	    close(input_pipe[0]);
 	    close(output_pipe[1]);
 	    exit(1);
         }
 	/* read back from translator */
 	rc = read(input_pipe[0], &ch, 1);
 	c = (int)ch;
 	if (rc <= 0) { /* read failed - notify user and exit. */
 	    perror("user_handler: read");
 	    close(input_pipe[0]);
 	    close(output_pipe[1]);
 	    exit(1);
         }
 	/* print translated character to stdout. */
 	putchar(c);
     }
     /* close pipes and exit. */
     close(input_pipe[0]);
     close(output_pipe[1]);
     exit(0);
 }
 /* now comes the function executed by the translator process. */
 void translator(int input_pipe[], int output_pipe[])
 {
     int c;    /* user input - must be 'int', to recognize EOF (= -1). */
     char ch;  /* the same - as a char. */
     int rc;   /* return values of functions. */
     /* first, close unnecessary file descriptors */
     close(input_pipe[1]); /* we don't need to write to this pipe.  */
     close(output_pipe[0]); /* we don't need to read from this pipe. */
     /* enter a loop of reading from the user_handler's pipe, translating */
     /* the character, and writing back to the user handler.              */
     while (read(input_pipe[0], &ch, 1) > 0) {
 	/* translate any upper-case letter to lower-case. */
         c = (int)ch;
 	if (isascii(c) && isupper(c))
             c = tolower(c);
         ch = (char)c;
         /* write translated character back to user_handler. */
         rc = write(output_pipe[1], &ch, 1);
         if (rc == -1) { /* write failed - notify user and exit. */
             perror("translator: write");
             close(input_pipe[0]);
             close(output_pipe[1]);
             exit(1);
         }
     }
     /* close pipes and exit. */
     close(input_pipe[0]);
     close(output_pipe[1]);
     exit(0);
 }
 /* and finally, the main function: spawn off two processes, */
 /* and let each of them execute its function.               */
 int main(int argc, char* argv[])
 {
     /* 2 arrays to contain file descriptors, for two pipes. */
     int user_to_translator[2];
     int translator_to_user[2];
     int pid;       /* pid of child process, or 0, as returned via fork.    */
     int rc;        /* stores return values of various routines.            */
     /* first, create one pipe. */
     rc = pipe(user_to_translator);
     if (rc == -1) {
 	perror("main: pipe user_to_translator");
 	exit(1);
     }
     /* then, create another pipe. */
     rc = pipe(translator_to_user);
     if (rc == -1) {
 	perror("main: pipe translator_to_user");
 	exit(1);
     }
     /* now fork off a child process, and set their handling routines. */
     pid = fork();
     switch (pid) {
 	case -1:	/* fork failed. */
 	    perror("main: fork");
 	    exit(1);
 	case 0:		/* inside child process.  */
 	    translator(user_to_translator, translator_to_user); /* line 'A' */
 	    /* NOT REACHED */
 	default:	/* inside parent process. */
 	    user_handler(translator_to_user, user_to_translator); /* line 'B' */
 	    /* NOT REACHED */
     }
     return 0;	/* NOT REACHED */
 }

 #include <stdio.h>     /* standard I/O routines.            */
 #include <sys/types.h> /* standard system data types.       */
 #include <sys/ipc.h>   /* common system V IPC structures.   */
 #include <sys/msg.h>   /* message-queue specific functions. */
 /* create a private message queue, with access only to the owner. */
 int queue_id = msgget(IPC_PRIVATE, 0600); /* <-- this is an octal number. */
 if (queue_id == -1) {
     perror("msgget");
     exit(1);
 }

 struct msgbuf {
     long mtype;     /* message type, a positive number (cannot be zero). */
     char mtext[1];  /* message body array. usually larger than one byte. */
 };
 Пример создания "hello world" message:
 	/* first, define the message string */
 	char* msg_text = "hello world";
 	/* allocate a message with enough space for length of string and */
 	/* one extra byte for the terminating null character.            */
 	struct msgbuf* msg =
 			(struct msgbuf*)malloc(sizeof(struct msgbuf) + strlen(msg_text));
 	/* set the message type. for example - set it to '1'. */
 	msg->mtype = 1;
 	/* finally, place the "hello world" string inside the message. */
 	strcpy(msg->mtext, msg_text);

 	/* prepare a message structure large enough to read our "hello world". */
 	struct msgbuf* recv_msg =
 		(struct msgbuf*)malloc(sizeof(struct msgbuf)+strlen("hello world"));
 	/* use msgrcv() to read the message. We agree to get any type, and thus */
 	/* use '0' in the message type parameter, and use no flags (0).         */
 	int rc = msgrcv(queue_id, recv_msg, strlen("hello world")+1, 0, 0);
 	if (rc == -1) {
 		perror("msgrcv");
 		exit(1);
 	}

 		/* ID of the semaphore set.     */
 		int sem_set_id_1;
 		int sem_set_id_2;
 		/* create a private semaphore set with one semaphore in it, */
 		/* with access only to the owner.                           */
 		sem_set_id_1 = semget(IPC_PRIVATE, 1, IPC_CREAT | 0600);
 		if (sem_set_id_1 == -1) {
 			perror("main: semget");
 			exit(1);
 		}
 		/* create a semaphore set with ID 250, three semaphores */
 		/* in the set, with access only to the owner.           */
 		sem_set_id_2 = semget(250, 3, IPC_CREAT | 0600);
 		if (sem_set_id_2 == -1) {
 			perror("main: semget");
 			exit(1);
 		}

 	/* use this to store return values of system calls.   */
 	int rc;
 	/* initialize the first semaphore in our set to '3'.  */
 	rc = semctl(sem_set_id_2, 0, SETVAL, 3);
 	if (rc == -1) {
 		perror("main: semctl");
 		exit(1);
 	}
 	/* initialize the second semaphore in our set to '6'. */
 	rc = semctl(sem_set_id_2, 1, SETVAL, 6);
 	if (rc == -1) {
 		perror("main: semctl");
 		exit(1);
 	}
 	/* initialize the third semaphore in our set to '0'.  */
 	rc = semctl(sem_set_id_2, 2, SETVAL, 0);
 	if (rc == -1) {
 		perror("main: semctl");
 		exit(1);
 	}

 	/* this function updates the contents of the file with the given path name. */
 	void update_file(char* file_path, int number)
 	{
 		/* structure for semaphore operations.   */
 		struct sembuf sem_op;
 		FILE* file;
 		/* wait on the semaphore, unless it's value is non-negative. */
 		sem_op.sem_num = 0;
 		sem_op.sem_op = -1;   /* <-- Comment 1 */
 		sem_op.sem_flg = 0;
 		semop(sem_set_id, &sem_op, 1);
 		/* Comment 2 */
 		/* we "locked" the semaphore, and are assured exclusive access to file.  */
 		/* manipulate the file in some way. for example, write a number into it. */
 		file = fopen(file_path, "w");
 		if (file) {
 			fprintf(file, "%d\n", number);
 			fclose(file);
 		}
 		/* finally, signal the semaphore - increase its value by one. */
 		sem_op.sem_num = 0;
 		sem_op.sem_op = 1;   /* <-- Comment 3 */
 		sem_op.sem_flg = 0;
 		semop(sem_set_id, &sem_op, 1);
 	}

 	/* this variable will contain the semaphore set. */
 	int sem_set_id;
 	/* semaphore value, for semctl().                */
 	union semun sem_val;
 	/* structure for semaphore operations.           */
 	struct sembuf sem_op;
 	/* first we create a semaphore set with a single semaphore, */
 	/* whose counter is initialized to '0'.                     */
 	sem_set_id = semget(IPC_PRIVATE, 1, 0600);
 	if (sem_set_id == -1) {
 		perror("semget");
 		exit(1);
 	}
 	sem_val.val = 0;
 	semctl(sem_set_id, 0, SETVAL, sem_val);
 	/* we now do some producing function, and then signal the   */
 	/* semaphore, increasing its counter by one.                */
 	.
 	.
 	sem_op.sem_num = 0;
 	sem_op.sem_op = 1;
 	sem_op.sem_flg = 0;
 	semop(sem_set_id, &sem_op, 1);
 	.
 	.
 	.
 	/* meanwhile, in a different process, we try to consume the      */
 	/* resource protected (and counter) by the semaphore.            */
 	/* we block on the semaphore, unless it's value is non-negative. */
 	sem_op.sem_num = 0;
 	sem_op.sem_op = -1;
 	sem_op.sem_flg = 0;
 	semop(sem_set_id, &sem_op, 1);
 
 	/* when we get here, it means that the semaphore's value is '0'  */
 	/* or more, so there's something to consume.                     */
 	.
 	.

 
 
Semaphores - A Complete Example
 Смотрите архив :
 	tiny-lpr.c
 	tiny-lpd.c

With shared memory, we declare a given section in the memory as one that will be used simultaneously by several processes. This means that the data found in this memory section (or memory segment) will be seen by several processes. This also means that several processes might try to alter this memory area at the same time, and thus some method should be used to synchronize their access to this memory area (did anyone say "apply mutual exclusion using a semaphore" ?).

In order to understand the concept of shared memory, we should first check how virtual memory is managed on the system.

In order to achieve virtual memory, the system divides memory into small pages each of the same size. For each process, a table mapping virtual memory pages into physical memory pages is kept. When the process is scheduled for running, its memory table is loaded by the operating system, and each memory access causes a mapping (by the CPU) to a physical memory page. If the virtual memory page is not found in memory, it is looked up in swap space, and loaded from there (this operation is also called 'page in').

When the process is started, it is being allocated a memory segment to hold the runtime stack, a memory segment to hold the programs code (the code segment), and a memory area for data (the data segment). Each such segment might be composed of many memory pages. When ever the process needs to allocate more memory, new pages are being allocated for it, to enlarge its data segment.

When a process is being forked off from another process, the memory page table of the parent process is being copied to the child process, but not the pages themselves. If the child process will try to update any of these pages, then this page specifically will be copied, and then only the copy of the child process will be modified. This behavior is very efficient for processes that call fork() and immediately use the exec() system call to replace the program it runs.

What we see from all of this is that all we need in order to support shared memory, is to some memory pages as shared, and to allow a way to identify them. This way, one process will create a shared memory segment, other processes will attach to them (by placing their physical address in the process's memory pages table). From now all these processes will access the same physical memory when accessing these pages, thus sharing this memory area.

Allocating A Shared Memory Segment

A shared memory segment first needs to be allocated (created), using the shmget() system call. This call gets a key for the segment (like the keys used in msgget() and semget()), the desired segment size, and flags to denote access permissions and whether to create this page if it does not exist yet. shmget() returns an identifier that can be later used to access the memory segment. Here is how to use this call:

 /* this variable is used to hold the returned segment identifier. */
 int shm_id;
 
 /* allocate a shared memory segment with size of 2048 bytes,      */
 /* accessible only to the current user.                             */
 shm_id = shmget(100, 2048, IPC_CREAT | IPC_EXCL | 0600);
 if (shm_id == -1) {
     perror("shmget: ");
     exit(1);
 }
 

After we allocated a memory page, we need to add it to the memory page table of the process. This is done using the shmat() (shared-memory attach) system call. Assuming 'shm_id' contains an identifier returned by a call to shmget(), here is how to do this:

 /* these variables are used to specify where the page is attached.  */
 char* shm_addr;
 char* shm_addr_ro;
 
 /* attach the given shared memory segment, at some free position */
 /* that will be allocated by the system.                         */
 shm_addr = shmat(shm_id, NULL, 0);
 if (!shm_addr) { /* operation failed. */
     perror("shmat: ");
     exit(1);
 }
 
 /* attach the same shared memory segment again, this time in     */
 /* read-only mode. Any write operation to this page using this   */
 /* address will cause a segmentation violation (SIGSEGV) signal. */
 shm_addr_ro = shmat(shm_id, NULL, SHM_RDONLY);
 if (!shm_addr_ro) { /* operation failed. */
     perror("shmat: ");
     exit(1);
 }
 

Placing data in a shared memory segment is done by using the pointer returned by the shmat() system call. Any kind of data may be placed in a shared segment, except for pointers. The reason for this is simple: pointers contain virtual addresses. Since the same segment might be attached in a different virtual address in each process, a pointer referring to one memory area in one process might refer to a different memory area in another process. We can try to work around this problem by attaching the shared segment in the same virtual address in all processes (by supplying an address as the second parameter to shmat(), and adding the SHM_RND flag to its third parameter), but this might fail if the given virtual address is already in use by the process.

Here is an example of placing data in a shared memory segment, and later on reading this data. We assume that 'shm_addr' is a character pointer, containing an address returned by a call to shmat().

 /* define a structure to be used in the given shared memory segment. */
 struct country {
     char name[30];
     char capital_city[30];
     char currency[30];
     int population;
 };
 
 /* define a countries array variable. */
 int* countries_num;
 struct country* countries;
 
 /* create a countries index on the shared memory segment. */
 countries_num = (int*) shm_addr;
 *countries_num = 0;
 countries = (struct country*) ((void*)shm_addr+sizeof(int));
 
 strcpy(countries[0].name, "U.S.A");
 strcpy(countries[0].capital_city, "Washington");
 strcpy(countries[0].currency, "U.S. Dollar");
 countries[0].population = 250000000;
 (*countries_num)++;
 
 strcpy(countries[1].name, "Israel");
 strcpy(countries[1].capital_city, "Jerusalem");
 strcpy(countries[1].currency, "New Israeli Shekel");
 countries[1].population = 6000000;
 (*countries_num)++;
 
 strcpy(countries[1].name, "France");
 strcpy(countries[1].capital_city, "Paris");
 strcpy(countries[1].currency, "Frank");
 countries[1].population = 60000000;
 (*countries_num)++;
 
 /* now, print out the countries data. */
 for (i=0; i < (*countries_num); i++) {
     printf("Country %d:\n", i+1);
     printf("  name: %s:\n", countries[i].name);
     printf("  capital city: %s:\n", countries[i].capital_city);
     printf("  currency: %s:\n", countries[i].currency);
     printf("  population: %d:\n", countries[i].population);
 }
 

1. No usage of malloc().
   
   Since the memory page was already allocated when we called shmget(), there is no need to use malloc() when placing data in that segment. Instead, we do all memory management ourselves, by simple pointer arithmetic operations. We also need to make sure the shared segment was allocated enough memory to accommodate future growth of our data - there are no means for enlarging the size of the segment once allocated (unlike when using normal memory management - we can always move data to a new memory location using the realloc() function).
   
   
2. Memory alignment.
   
   In the example above, we assumed that the page's address is aligned properly for an integer to be placed in it. If it was not, any attempt to try to alter the contents of 'countries_num' would trigger a bus error (SIGBUS) signal. further, we assumed the alignment of our structure is the same as that needed for an integer (when we placed the structures array right after the integer variable).
   
   
3. Completeness of the data model.
   
   By placing all the data relating to our data model in the shared memory segment, we make sure all processes attaching to this segment can use the full data kept in it. A naive mistake would be to place the countries counter in a local variable, while placing the countries array in the shared memory segment. If we did that, other processes trying to access this segment would have no means of knowing how many countries are in there.
   
   

After we finished using a shared memory segment, we should destroy it. It is safe to destroy it even if it is still in use (i.e. attached by some process). In such a case, the segment will be destroyed only after all processes detach it. Here is how to destroy a segment:

 /* this structure is used by the shmctl() system call. */
 struct shmid_ds shm_desc;
 
 /* destroy the shared memory segment. */
 if (shmctl(shm_id, IPC_RMID, &shm_desc) == -1) {
     perror("main: shmctl: ");
 }
 

A Complete Example

As a naive example of using shared memory, we collected the source code from the above sections into a file named shared-mem.c. It shows how a single process uses shared memory. Naturally, when two processes (or more) use a single shared memory segment, there may be race conditions, if one process tries to update this segment, while another is reading from it. To avoid this, we need to use some locking mechanism - SysV semaphores (used as mutexes) come to mind here. An example of two processes that access the same shared memory segment using a semaphore to synchronize their access, is found in the file shared-mem-with-semaphore.c.

One of the problems with SysV IPC methods is the need to choose a unique identifier for our processes. How can we make sure that the identifier of a semaphore in our project won't collide with the identifier of a semaphore in some other program installed on the system?

To help with that, the ftok() system call was introduced. This system call accepts two parameters, a path to a file and a character, and generates a more-or-less unique identifier. It does that by finding the "i-node" number of the file (more or less the number of the disk sector containing this file's information), combines it with the second parameter, and thus generates an identifier, that can be later fed to semget, shmget() or msgget(). Here is how to use ftok():

 /* identifier returned by ftok() */
 key_t set_key;
 
 /* generate a "unique" key for our set, using the */
 /* directory "/usr/local/lib/ourprojectdir".      */
 set_key = ftok("/usr/local/lib/ourprojectdir", 'a');
 if (set_key == -1) {
     perror("ftok: ");
     exit(1);
 }
 
 /* now we can use 'set_key' to generate a set id, for example. */
 sem_set_id = semget(set_key, 1, IPC_CREAT | 0600);
 .
 .
 

Оставьте свой комментарий !
Ваше имя: Комментарий: Оба поля являются обязательными  Автор   Комментарий к данной статье