Hi all
I am trying to make a manager/worker program that monitors processes
running on different nodes of a clusters. I am writing the program in c++
and I am having problem using the spawn features in MPI. I have tried to use
MPI_Comm_spawn(worker_program, MPI_ARGV_NULL, universe_size-1,
MPI_INFO_NULL, 0, MPI_COMM_SELF, &everyone, MPI_ERRCODEES_IGNORE);
but, I recieve an error at the last parameter indicating that I am
substituting a void* for int*
I then tried to use
MPI::Intracomm::Spawn(worker_program, MPI::ARGV_NULL, universe_size-1,
MPI::INFO_NULL, 3, MPI::COMM_SELF, &everyone);
but this returned three errors, MPI::ARGV_NULL, MPI::INFO_NULL,
Intracomm::Spawn undefined.
I then declared an int* and replaced MPI_ERRCODEES_IGNORE in
MPI_Comm_spawn(worker_program, MPI_ARGV_NULL, universe_size-1,
MPI_INFO_NULL, 0, MPI_COMM_SELF, &everyone, MPI_ERRCODEES_IGNORE);
this led to the successful calling of the worker program, but then I
recieved errors in the worker_program, which when compiled by itself has no
errors. I am now running out of ideas, so you have any idea of what is
going on, or if you know any example of how MPI_Comm_spawn works, it will
be greatly appreciated. The programs I wrote are as the following:
#include <stdio.h>
#include <stdlib.h>
#include <mpi.h>
#include <string>
#include <iostream>
#include <sys/types.h>
#include <unistd.h>
#include <fstream>
#include <sys/times.h>
#include <time.h>
#include <sys/resource.h>
#include <mpi++.h>
#include <intracomm.h>
#include <intercomm.h>
using namespace std;
int main(int argc, char *argv[])
{
int universe_size, *universe_sizep, flag;
MPI_Comm everyone;
char worker_program[100] = "pmm_worker.cpp";
char name [MPI_MAX_PROCESSOR_NAME];
int namelen;
MPI::Init(argc,argv);
int rank = MPI::COMM_WORLD.Get_rank();
int world_size = MPI::COMM_WORLD.Get_size();
MPI_Get_processor_name(name, &namelen);
cout<<"size is "<<world_size<<" "<<name<<endl;
//MPI::Init(argc, argv);
//int world_size = MPI::COMM_WORLD.Get_size();
if(world_size != 1)
cout<<"Top heavy with management"<<endl;
MPI_Comm_get_attr(MPI_COMM_WORLD, MPI_UNIVERSE_SIZE,
&universe_sizep, &flag);
if(!flag)
{
cout<<"This MPI does not support Universe_size."<<endl;
cout<<"How many processes total?"<<endl;
scanf("%d", &universe_size);
}
else
universe_size = *universe_sizep;
if (universe_size == 1)
cout << "no room to start workers"<<endl;
//spawn workers
int *whatever;
// MPI_Comm_spawn(worker_program, MPI_ARGV_NULL, universe_size-1,
MPI_INFO_NULL, 0, MPI_COMM_SELF, &everyone, whatever);
Intracomm::Spawn(worker_program, MPI::ARGV_NULL, universe_size-1,
MPI::INFO_NULL, 3, MPI::COMM_SELF, &everyone);
MPI::Finalize();
return 0;
}
#include <stdio.h>
#include <stdlib.h>
#include <mpi.h>
#include <string>
#include <iostream>
#include <sys/types.h>
#include <unistd.h>
#include <fstream>
#include <sys/times.h>
#include <time.h>
#include <sys/resource.h>
#include <mpi++.h>
using namespace std;
void InfoOutput(string infoContent, int space_count1, int space_count2, int
cpu_or_mem)
{
string info1, info2;
string infoShown;
int space_count = 0;
char check_for_space = ' ';
if(cpu_or_mem == 0)
infoShown = "The total amount of time (in jiffies) this process
is schdule in the user and the kernel mode is ";
else
infoShown = "The total amount of memory of this process and its
data (in pages) are ";
for (int i = 0; i < infoContent.length(); i++)
{
if(infoContent[i] == ' ')
space_count++;
//cout << i << " " << infoContent[i] <<endl;
if(space_count == space_count1)
{
for (int j = i+1; j < infoContent.length(); j++)
{
if(infoContent[j] != check_for_space)
{
info1 += infoContent[j];
// cout << mem1;
}
else
break;
}
}
if(space_count == space_count2)
{
for (int j = i+1; j < infoContent.length(); j++)
{
if(infoContent[j] != check_for_space)
{
info2 += infoContent[j];
// cout << mem1;
}
else
break;
}
}
}
cout<<infoShown<<info1<<", "<<info2<<endl;
}
//***********************************************************************************************************
int main(int argc, char* argv[])
{
// Get Command from parent
int size;
MPI_Comm parent;
MPI::Init(argc, argv);
MPI_Comm_get_parent(&parent);
if(parent == MPI_COMM_NULL)
cout<<"No Parent!";
//MPI_Comm_remote_size(parent, &size);
//if(size != 1)
//cout<<"Something is wrong with the parent";
int pid = getpid();
cout << pid << " is the pid "<<endl;
string cpid;
char i;
tms cpuTime;
times(&cpuTime);
double jiffy = sysconf(_SC_CLK_TCK);
double page_size = sysconf(_SC_PAGE_SIZE);
rusage cpuTimeFromG;
int who = RUSAGE_SELF;
getrusage(who , &cpuTimeFromG);
cout<<"On this system, a jiffy is 1/"<<jiffy<<" second"<<endl;
cout<<"the page size is "<<page_size<<" bytes"<<endl;
cout<<"the user time is " << cpuTime.tms_utime <<endl;
cout<<"the system time is " << cpuTime.tms_stime<<endl;
cout<<"the approximation of processor time used by the program is "<<
clock()<<endl;
cout<<"the user time from getrusage is " << cpuTimeFromG.ru_utime.tv_sec
<<endl;
cout<<"the system time from getrusage is " <<
cpuTimeFromG.ru_stime.tv_sec<<endl;
cout<<"the number of messages sent is " << cpuTimeFromG.ru_msgsnd <<endl;
cout<<"the number of messages recieve is " << cpuTimeFromG.ru_msgrcv<<endl;
while(pid > 0)
{
i = (char)(pid % 10) + 48;
pid = pid / 10;
cpid = i + cpid;
}
string cpuInfo = "//proc//" + cpid +"//stat";
string memInfo = "//proc//" + cpid +"//statm";
ifstream OpenCpuInfoFile(cpuInfo.c_str());
ifstream OpenMemInfoFile(memInfo.c_str());
// ifstream object is used for getting input
//char filename[50]; // string to hold file name
char n1, n2;
string cpuContent;
string memContent;
// open the file
// fin.open(filename);
// check for successful file open
if( !OpenCpuInfoFile || !OpenMemInfoFile)
{
cout << "can't open file\n";
exit(1);
}
// loop, reading two integers at a time
while( !OpenCpuInfoFile.eof())
{
OpenCpuInfoFile.get(n1);
cpuContent+=n1;
}
while( !OpenMemInfoFile.eof())
{
OpenMemInfoFile.get(n2);
memContent+=n2;
}
// cout<<"mem string s length is " << memContent.length() <<endl;
//cout<<"cpu string s length is " << cpuContent.length() <<endl;
InfoOutput(memContent, 3, 4, 1); //send memContent and specify the
position of the space to obtain desired info
InfoOutput(cpuContent, 13, 14, 0); //send cpuContent and specify the
position of the space to obtain desired info
// fin.close();
OpenMemInfoFile.close();
OpenCpuInfoFile.close();
MPI::Finalize();
return 0;
}
|
