C, Open MPI: segmentation fault from call to MPI_Finalize(). Segfault does not always happen, especially with low numbers of processes

I am writing a simple code to learn how to define an MPI_Datatype and use it in conjunction with MPI_Gatherv. I wanted to make sure I could combine variable length, dynamically allocated arrays of structured data on a process, which seems to be working fine, up until my call to MPI_Finalize(). I have confirmed that this is where the problem starts to manifest itself by using print statements and the Eclipse PTP debugger (backend is gdb-mi). My main question is, how can I get rid of the segmentation fault? The segfault does not occur every time I run the code. For instance, it hasn't happened for 2 or 3 processes, but tends to happen regularly when I run with about 4 or more processes. Also, when I run this code with valgrind, the segmentation fault does not occur. However, I do get error messages from valgrind, though the output is difficult for me to understand when I use MPI functions, even with a large number of targeted suppressions. I am also concerned that if I use more suppressions, I will silence a useful error message. I compile the normal code using these flags, so I am using the C99 standard in both cases: -ansi -pedantic -Wall -O2 -march=barcelona -fomit-frame-pointer -std=c99 and the debugged code with: -ansi -pedantic -std=c99 -Wall -g Both use the gcc 4.4 mpicc compiler, and are run on a cluster using Red Hat Linux with Open MPI v1.4.5. Please let me know if I have left out other important bits of information. Here is the code, and thanks in advance: ``` //#include <unistd.h> #include <string.h> #include <stdio.h> #include <math.h> #include <stdlib.h> //#include <limits.h> #include "mpi.h" #define FULL_PROGRAM 1 struct CD{ int int_ID; double dbl_ID; }; int main(int argc, char *argv[]) { int numprocs, myid, ERRORCODE; #if FULL_PROGRAM struct CD *myData=NULL; //Each process contributes an array of data, comprised of 'struct CD' elements struct CD *allData=NULL; //root will dynamically allocate this array to store all the data from rest of the processes int *p_lens=NULL, *p_disp=NULL; //p_lens stores the number of elements in each process' array, p_disp stores the displacements in bytes int MPI_CD_size; //stores the size of the MPI_Datatype that is defined to allow communication operations using 'struct CD' elements int mylen, total_len=0; //mylen should be the length of each process' array //MAXlen is the maximum allowable array length //total_len will be the sum of mylen across all processes // ============ variables related to defining new MPI_Datatype at runtime ==================================================== struct CD sampleCD = {.int_ID=0, .dbl_ID=0.0}; int blocklengths[2]; //this describes how many blocks of identical data types will be in the new MPI_Datatype MPI_Aint offsets[2]; //this stores the offsets, in bytes(bits?), of the blocks from the 'start' of the datatype MPI_Datatype block_types[2]; //this stores which built-in data types the blocks are comprised of MPI_Datatype myMPI_CD; //just the name of the new datatype MPI_Aint myStruct_address, int_ID_address, dbl_ID_address, int_offset, dbl_offset; //useful place holders for filling the arrays above // =========================================================================================================================== #endif // =================== Initializing MPI functionality ============================ MPI_Init(&argc, &argv); MPI_Comm_size(MPI_COMM_WORLD, &numprocs); MPI_Comm_rank(MPI_COMM_WORLD, &myid); // =============================================================================== #if FULL_PROGRAM // ================== This part actually formally defines the MPI datatype =============================================== MPI_Get_address(&sampleCD, &myStruct_address); //starting point of struct CD MPI_Get_address(&sampleCD.int_ID, &int_ID_address); //starting point of first entry in CD MPI_Get_address(&sampleCD.dbl_ID, &dbl_ID_address); //starting point of second entry in CD int_offset = int_ID_address - myStruct_address; //offset from start of first to start of CD dbl_offset = dbl_ID_address - myStruct_address; //offset from start of second to start of CD blocklengths[0]=1; blocklengths[1]=1; //array telling it how many blocks of identical data types there are, and the number of entries in each block //This says there are two blocks of identical data-types, and both blocks have only one variable in them offsets[0]=int_offset; offsets[1]=dbl_offset; //the first block starts at int_offset, the second block starts at dbl_offset (from 'myData_address' block_types[0]=MPI_INT; block_types[1]=MPI_DOUBLE; //the first block contains MPI_INT, the second contains MPI_DOUBLE MPI_Type_create_struct(2, blocklengths, offsets, block_types, &myMPI_CD); //this uses the above arrays to define the MPI_Datatype...an MPI-2 function MPI_Type_commit(&myMPI_CD); //this is the final step to defining/reserving the data type // ======================================================================================================================== mylen = myid*2; //each process is told how long its array should be...I used to define that randomly but that just makes things messier p_lens = (int*) calloc((size_t)numprocs, sizeof(int)); //allocate memory for the number of elements (p_lens) and offsets from the start of the recv buffer(d_disp) p_disp = (int*) calloc((size_t)numprocs, sizeof(int)); myData = (struct CD*) calloc((size_t)mylen, sizeof(struct CD)); //allocate memory for each process' array //if mylen==0, 'a unique pointer to the heap is returned' if(!p_lens) { MPI_Abort(MPI_COMM_WORLD, 1); exit(EXIT_FAILURE); } if(!p_disp) { MPI_Abort(MPI_COMM_WORLD, 1); exit(EXIT_FAILURE); } if(!myData) { MPI_Abort(MPI_COMM_WORLD, 1); exit(EXIT_FAILURE); } for(double temp=0.0;temp<1e6;++temp) temp += exp(-10.0); MPI_Barrier(MPI_COMM_WORLD); //purely for keeping the output organized by give a delay in time for (int k=0; k<numprocs; ++k) { if(myid==k) { //printf("\t ID %d has %d entries: { ", myid, mylen); for(int i=0; i<mylen; ++i) { myData[i]= (struct CD) {.int_ID=myid*(i+1), .dbl_ID=myid*(i+1)}; //fills data elements with simple pattern //printf("%d: (%d,%lg) ", i, myData[i].int_ID, myData[i].dbl_ID); } //printf("}\n"); } } for(double temp=0.0;temp<1e6;++temp) temp += exp(-10.0); MPI_Barrier(MPI_COMM_WORLD); //purely for keeping the output organized by give a delay in time MPI_Gather(&mylen, 1, MPI_INT, p_lens, 1, MPI_INT, 0, MPI_COMM_WORLD); //Each process sends root the length of the vector they'll be sending #if 1 MPI_Type_size(myMPI_CD, &MPI_CD_size); //gets the size of the MPI_Datatype for p_disp #else MPI_CD_size = sizeof(struct CD); //using this doesn't change things too much... #endif for(int j=0;j<numprocs;++j) { total_len += p_lens[j]; if (j==0) { p_disp[j] = 0; } else { p_disp[j] = p_disp[j-1] + p_lens[j]*MPI_CD_size; } } if (myid==0) { allData = (struct CD*) calloc((size_t)total_len, sizeof(struct CD)); //allocate array if(!allData) { MPI_Abort(MPI_COMM_WORLD, 1); exit(EXIT_FAILURE); } } MPI_Gatherv(myData, mylen, myMPI_CD, allData, p_lens, p_disp, myMPI_CD, 0, MPI_COMM_WORLD); //each array sends root process their array, which is stored in 'allData' // ============================== OUTPUT CONFIRMING THAT COMMUNICATIONS WERE SUCCESSFUL========================================= if(myid==0) { for(int i=0;i<numprocs;++i) { printf("\n\tElements from %d on MASTER are: { ",i); for(int k=0;k<p_lens[i];++k) { printf("%d: (%d,%lg) ", k, (allData+p_disp[i]+k)->int_ID, (allData+p_disp[i]+k)->dbl_ID); } if(p_lens[i]==0) printf("NOTHING "); printf("}\n"); } printf("\n"); //each data element should appear as two identical numbers, counting upward by the process ID } // ========================================================================================================== if (p_lens) { free(p_lens); p_lens=NULL; } //adding this in didn't get rid of the MPI_Finalize seg-fault if (p_disp) { free(p_disp); p_disp=NULL; } if (myData) { free(myData); myData=NULL; } if (allData){ free(allData); allData=NULL; } //the if statement ensures that processes not allocating memory for this pointer don't free anything for(double temp=0.0;temp<1e6;++temp) temp += exp(-10.0); MPI_Barrier(MPI_COMM_WORLD); //purely for keeping the output organized by give a delay in time printf("ID %d: I have reached the end...before MPI_Type_free!\n", myid); // ====================== CLEAN UP ================================================================================ ERRORCODE = MPI_Type_free(&myMPI_CD); //this frees the data type...not always necessary, but a good practice for(double temp=0.0;temp<1e6;++temp) temp += exp(-10.0); MPI_Barrier(MPI_COMM_WORLD); //purely for keeping the output organized by give a delay in time if(ERRORCODE!=MPI_SUCCESS) { printf("ID %d...MPI_Type_free was not successful\n", myid); MPI_Abort(MPI_COMM_WORLD, 911); exit(EXIT_FAILURE); } else { printf("ID %d...MPI_Type_free was successful, entering MPI_Finalize...\n", myid); } #endif ERRORCODE=MPI_Finalize(); for(double temp=0.0;temp<1e7;++temp) temp += exp(-10.0); //NO MPI_Barrier AFTER MPI_Finalize! if(ERRORCODE!=MPI_SUCCESS) { printf("ID %d...MPI_Finalize was not successful\n", myid); MPI_Abort(MPI_COMM_WORLD, 911); exit(EXIT_FAILURE); } else { printf("ID %d...MPI_Finalize was successful\n", myid); } return EXIT_SUCCESS; } ```