Thread: MPI Scatter

I'm having difficulties passing the right amount of characters to other processes using scatter. I'm trying to open a file which contains 6 file names and splitting it up and sending a file name to each process. I would look to send two file names to each process and have three processes going at once, but right now I'm just trying to do one. Below is my code, any suggestions you could give I'd greatly appreciate, I've been fiddling with these characters and scattering them for awhile now and am getting pretty frustrated.

Here is what is actually in the txt document I'm reading in right away:
data/file0.txt
data/file1.txt
data/file2.txt
data/file3.txt
data/file4.txt
data/file5.txt

Somewhere it isn't getting that last 't'

Here is the output:
data/file2.tx
data/file3.tx

data/file4.tx
data/file5.tx

Code:

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

int main(int argc, char **argv){
    int p;
    int id;
    
    MPI_Init(&argc, &argv);
    MPI_Comm_size(MPI_COMM_WORLD, &p);
    MPI_Comm_rank(MPI_COMM_WORLD, &id);
    if(id==0) {    // Process 0
        FILE *infile;
        infile = fopen("data/data/filelist.txt", "r");
        if (infile == NULL) {
            printf("I couldn't open file.\n");
        }
        int ch = 0;
        char fileList[84];
        int sizeCount = 0;
        while(ch != EOF){
            //while(ch != '\n'){
                fileList[sizeCount] = ch;
                ch = getc(infile);
                //printf("%c",ch);
                sizeCount++;
            //}
        }
        fclose(infile);
        sizeCount -= 6;
        int lineSize = sizeCount/6;
        printf("sizeCount: %d\n",sizeCount);
        printf("lineSize: %d\n",lineSize);
        char files[5][(sizeCount/6)];
        int counter = 0;
        for(int i = 0; i < 6; i++){
            for(int j = 0; j <= lineSize; j++){
                files[i][j] = fileList[counter];
                //printf("%c", files[i][j]);
                counter++;
            }
        }
        printf("counter:%d", counter);
        printf("\n");

        char receiveArray[lineSize*2];
        MPI_Scatter(files,lineSize*2,MPI_CHAR,receiveArray,lineSize*2,MPI_CHAR,0,MPI_COMM_WORLD);
        
        //do stuff as process 0
        
    }else { // All other processes
        int id;
        MPI_Comm_rank(MPI_COMM_WORLD, &id);
        
        char receiveArray[28];
        MPI_Scatter(NULL,28,MPI_CHAR,receiveArray,28,MPI_CHAR,0,MPI_COMM_WORLD);

        
        //
        //if(id==1) sleep(1);
        //else if(id==2) sleep(2);
        //else if(id==3) sleep(3);
        for(int i = 0; i <= sizeof(receiveArray); i++){
            printf("%c",receiveArray[i]);
        }
        printf("\n");
        //
        //char fileName[23] = "data/data/filelist0.txt";

    //    for(int i = 0; i < sizeof(fileName); i++){
    //        printf("%c", receiveArray[i]);
    //    }
        printf("\n");
        
        /*
        FILE *infile;
        infile = fopen(fileName, "r");
        if (infile == NULL) {
            printf("\nI couldn't open file.\n");
        }
        int ch = 0;
        while(ch != EOF){
                ch = getc(infile);
                printf("%c",ch);
            }
        
        
        */
    }
    MPI_Finalize();
}

Perhaps you should begin with learning how to read a file and use arrays without overflow, before trying any MPI stuff.

Code:

        int ch = 0;
        char fileList[84];
        int sizeCount = 0;
        while(ch != EOF){
            //while(ch != '\n'){
                fileList[sizeCount] = ch;
                ch = getc(infile);
                //printf("%c",ch);
                sizeCount++;
            //}
        }

Now I counted your input data as 90 chars and 6 lines, so you're already off by a large chunk on the fileList array.

> fileList[sizeCount] = ch;
Then you make the first char of your array zero (you haven't read the file yet).

Code:

        sizeCount -= 6;
        int lineSize = sizeCount/6;
        printf("sizeCount: %d\n",sizeCount);
        printf("lineSize: %d\n",lineSize);
        char files[5][(sizeCount/6)];

Why do you subtract 6 from sizeCount?
Why only [5], when you have 6 files?

Code:

        for(int i = 0; i < 6; i++){
            for(int j = 0; j <= lineSize; j++){
                files[i][j] = fileList[counter];
                //printf("%c", files[i][j]);
                counter++;
            }
        }

Both these loops overrun the bounds of their respective array limits.

If you just wanted an array of 6 lines, then why don't you start with

Code:

char files[6][100];
for ( i = 0 ; i < 6 && fgets(files[i], sizeof(files[i]), infile) != NULL ; i++ ) {
  // if you want to remove the \n from the end of the line, then
  // read the FAQ to find out how to do it.
}

Code:

    int p;
    int id;
    
    MPI_Init(&argc, &argv);
    MPI_Comm_size(MPI_COMM_WORLD, &p);
    MPI_Comm_rank(MPI_COMM_WORLD, &id);
    if(id==0) {    // Process 0
        FILE *infile;
        infile = fopen("data/data/filelist.txt", "r");
        if (infile == NULL) {
            printf("I couldn't open file.\n");
        }
        
    int sizeCount = 0;
    char ch;
    char files[6][100];
    for(int i=0; i<6 &&fgets(files[i],sizeof(files[i]),infile)!=NULL;i++){
        for(int j=0; j<14; j++){
            ch = getc(infile);
            files[i][j] = ch;
            sizeCount++;
        }
    }
    fclose(infile);

char receiveArray[28/*lineSize*2*/];
        MPI_Scatter(files,28,MPI_CHAR,receiveArray,28,MPI_CHAR,0,MPI_COMM_WORLD);

    }else { // All other processes
        int id;
        MPI_Comm_rank(MPI_COMM_WORLD, &id);
        
        char receiveArray[28];
        MPI_Scatter(NULL,28,MPI_CHAR,receiveArray,28,MPI_CHAR,0,MPI_COMM_WORLD);

        if(id==1) sleep(1);
        else if(id==2) sleep(2);
        for(int i = 0; i < sizeof(receiveArray); i++){
            printf("%c",receiveArray[i]);
        }

I do this, but now I'm not even getting any characters printed...just garbage from memory

This part shouldn't work

Code:

    char ch = fileList[sizeCount]; // this initializes ch with a random value
    while(ch != EOF){  // EOF is an int (usually -1 ) that doesn't fit into a char 
        //while(ch != '\n'){
            fileList[sizeCount] = ch;
            ch = getc(infile);
            //printf("%c",ch);
            sizeCount++;
        //}
    }

at least define ch to be an int

Kurt

EDIT: salem has already given you a solution for that part that would work

Code:

    char files[6][100];
    for(int i=0; i<6 &&fgets(files[i],sizeof(files[i]),infile)!=NULL;i++){
        for(int j=0; j<14; j++){
            ch = getc(infile);
            files[i][j] = ch;
            sizeCount++;
        }
    }

I suggest you read my post again, and figure out where exactly I said you should call getc() 14 times inside the loop reading each line.

Learn to read the file before posting any more MPI calls.

It prints garbage because you're doing two things.
1. Reading 6 words before you do anything (maybe that's what you want).
2. Using sizeof() rather than strlen() when processing the data.

You read a 5-letter word into a 100 byte buffer.
How many times round the loop printing data do you need?