Hello All,

Continuing my previous mail, I thought attaching this debugger screenshot may help anyone come up with an explanation. The exact location where the segfault happens is also highlighted.

Thanks a lot for any help.



From: devendra rai <dev641@yahoo.co.uk>
To: Open MPI Users <users@open-mpi.org>
Sent: Thursday, 12 January 2012, 17:05
Subject: [OMPI users] SIGSEGV on MPI_Test

Hello Community:

I am running into a strange problem. I get a SIGSEGV when I try to execute MPI_Test:

==21076== Process terminating with default action of signal 11 (SIGSEGV)
==21076==  Bad permissions for mapped region at address 0x43AEE1
==21076==    at 0x509B957: ompi_request_default_test (req_test.c:68)
==21076==    by 0x50EDEBB: PMPI_Test (ptest.c:59)
==21076==    by 0x44210D: InterProcessorTransmit::StartTransmission() (InterProcessorTransmit.cpp:111)

Here is the relevant piece of code:

       for ( this->dbIterator = localdb.begin( ) ; this->dbIterator != localdb.end( ); this->dbIterator++)
            this->TransmissionDetails = (this->dbIterator)->second;
            SendComplete = 0;
            UniqueIDtoSendto = std::get<0>(this->TransmissionDetails);
            RecepientNode = (this->dbIterator)->first;
              Isend_request = MPI::COMM_WORLD.Issend(this->transmitbuffer, this->transmissionsize, MPI_BYTE, (this->dbIterator)->first, std::get<0>(this->TransmissionDetails));
/*This is line 111 */MPI_Test(&(this->Isend_request), &(this->SendComplete), &(this->ISend_status));
                    /* Test whether the transmission was okay*/
                    MPI_Test(&(this->Isend_request), &(this->SendComplete), &(this->ISend_status));

                    /**** see if we need to pause or stop ****/
                               /* The mutex is released after exiting this block */
                               std::unique_lock<std::mutex> pr_dblock(this->mutexforPauseResume);

                                   /* pause till resume signal is received */
                               if(this->stop == 1)
                                   /* stop this transmission */

                               /* mutex is released here */
                    /**** End of pause/ stop check ****/

Am I missing something here? The piece of code shown here runs in a thread.

Thanks a lot for any pointers.



users mailing list