Because the code is very long, I just show the calling relationship of functions.

main()

{

scheduler();

}

scheduler()

{

ImportIndices();

}

ImportIndices()

{

Index IdxNode ;

IdxNode = ReadFile("fileName");

}

Index ReadFile(const char* fileinput)

{

Index TempIndex;

.........

}

vector<int> Index::GetPosition() const { return Position; }

vector<int> Index::GetColumn() const { return Column; }

vector<int> Index::GetYear() const { return Year; }

vector<string> Index::GetName() const { return Name; }

int Index::GetPosition(const int idx) const { return Position[idx]; }

int Index::GetColumn(const int idx) const { return Column[idx]; }

int Index::GetYear(const int idx) const { return Year[idx]; }

string Index::GetName(const int idx) const { return Name[idx]; }

int Index::GetSize() const { return Position.size(); }

The sequential code works well, and there is no scheduler().

The parallel code output from gdb:

----------------------------------------------

Breakpoint 1, myNeplanTaskScheduler(CNSGA2 *, int, int, int, ._85 *, char, int, message_para_to_workers_VecT &, MPI_Datatype, int &, int &, std::vector<std::vector<double, std::allocator<double> >, std::allocator<std::vector<double, std::allocator<double> > > > &, std::vector<std::vector<double, std::allocator<double> >, std::allocator<std::vector<double, std::allocator<double> > > > &, std::vector<double, std::allocator<double> > &, int, std::vector<std::vector<double, std::allocator<double> >, std::allocator<std::vector<double, std::allocator<double> > > > &, MPI_Datatype, int, MPI_Datatype, int) (nsga2=0x118c490,

popSize=<value optimized out>, nodeSize=<value optimized out>,

myRank=<value optimized out>, myChildpop=0x1208d80, genCandTag=65 'A',

generationNum=1, myPopParaVec=std::vector of length 4, capacity 4 = {...},

message_to_master_type=0x7fffffffd540, myT1Flag=@0x7fffffffd68c,

myT2Flag=@0x7fffffffd688,

resultTaskPackageT1=std::vector of length 4, capacity 4 = {...},

resultTaskPackageT2Pr=std::vector of length 4, capacity 4 = {...},

xdataV=std::vector of length 4, capacity 4 = {...}, objSize=7,

resultTaskPackageT12=std::vector of length 4, capacity 4 = {...},

xdata_to_workers_type=0x121c410, myGenerationNum=1,

Mpara_to_workers_type=0x121b9b0, nconNum=0)

at src/nsga2/myNetplanScheduler.cpp:109

109 ImportIndices();

(gdb) c

Continuing.

Breakpoint 2, ImportIndices () at src/index.cpp:120

120 IdxNode = ReadFile("prepdata/idx_node.csv");

(gdb) c

Continuing.

Breakpoint 4, ReadFile (fileinput=0xd8663d "prepdata/idx_node.csv")

at src/index.cpp:86

86 Index TempIndex;

(gdb) c

Continuing.

Breakpoint 5, Index::Index (this=0x7fffffffcb80) at src/index.cpp:20

20 Name(0) {}

(gdb) c

Continuing.

Program received signal SIGSEGV, Segmentation fault.

0x00002aaaab3b0b81 in opal_memory_ptmalloc2_int_malloc ()

from /opt/openmpi-1.3.4-gnu/lib/libopen-pal.so.0

---------------------------------------

the backtrace output from the above parallel OpenMPI code:

(gdb) bt

#0 0x00002aaaab3b0b81 in opal_memory_ptmalloc2_int_malloc ()

from /opt/openmpi-1.3.4-gnu/lib/libopen-pal.so.0

#1 0x00002aaaab3b2bd3 in opal_memory_ptmalloc2_malloc ()

from /opt/openmpi-1.3.4-gnu/lib/libopen-pal.so.0

#2 0x0000003f7c8bd1dd in operator new(unsigned long) ()

from /usr/lib64/libstdc++.so.6

#3 0x00000000004646a7 in __gnu_cxx::new_allocator<int>::allocate (

this=0x7fffffffcb80, __n=0)

at /usr/lib/gcc/x86_64-redhat-linux/4.1.2/../../../../include/c++/4.1.2/ext/new_allocator.h:88

#4 0x00000000004646cf in std::_Vector_base<int, std::allocator<int> >::_M_allocate (this=0x7fffffffcb80, __n=0)

at /usr/lib/gcc/x86_64-redhat-linux/4.1.2/../../../../include/c++/4.1.2/bits/stl_vector.h:127

#5 0x0000000000464701 in std::_Vector_base<int, std::allocator<int> >::_Vector_base (this=0x7fffffffcb80, __n=0, __a=...)

at /usr/lib/gcc/x86_64-redhat-linux/4.1.2/../../../../include/c++/4.1.2/bits/stl_vector.h:113

#6 0x0000000000464d0b in std::vector<int, std::allocator<int> >::vector (

this=0x7fffffffcb80, __n=0, __value=@0x7fffffffc968, __a=...)

at /usr/lib/gcc/x86_64-redhat-linux/4.1.2/../../../../include/c++/4.1.2/bits/stl_vector.h:216

#7 0x00000000004890d7 in Index::Index (this=0x7fffffffcb80)

---Type <return> to continue, or q <return> to quit---

at src/index.cpp:20

#8 0x000000000048927a in ReadFile (fileinput=0xd8663d "prepdata/idx_node.csv")

at src/index.cpp:86

#9 0x0000000000489533 in ImportIndices () at src/index.cpp:120

#10 0x0000000000445e0e in myNeplanTaskScheduler(CNSGA2 *, int, int, int, ._85 *, char, int, message_para_to_workers_VecT &, MPI_Datatype, int &, int &, std::vector<std::vector<double, std::allocator<double> >, std::allocator<std::vector<double, std::allocator<double> > > > &, std::vector<std::vector<double, std::allocator<double> >, std::allocator<std::vector<double, std::allocator<double> > > > &, std::vector<double, std::allocator<double> > &, int, std::vector<std::vector<double, std::allocator<double> >, std::allocator<std::vector<double, std::allocator<double> > > > &, MPI_Datatype, int, MPI_Datatype, int) (nsga2=0x118c490,

popSize=<value optimized out>, nodeSize=<value optimized out>,

myRank=<value optimized out>, myChildpop=0x1208d80, genCandTag=65 'A',

generationNum=1, myPopParaVec=std::vector of length 4, capacity 4 = {...},

message_to_master_type=0x7fffffffd540, myT1Flag=@0x7fffffffd68c,

myT2Flag=@0x7fffffffd688,

resultTaskPackageT1=std::vector of length 4, capacity 4 = {...},

resultTaskPackageT2Pr=std::vector of length 4, capacity 4 = {...},

xdataV=std::vector of length 4, capacity 4 = {...}, objSize=7,

resultTaskPackageT12=std::vector of length 4, capacity 4 = {...},

xdata_to_workers_type=0x121c410, myGenerationNum=1,

Mpara_to_workers_type=0x121b9b0, nconNum=0)

---Type <return> to continue, or q <return> to quit---

at src/nsga2/myNetplanScheduler.cpp:109

#11 0x000000000044f44b in main (argc=1, argv=0x7fffffffd998)

at src/nsga2/main-parallel2.cpp:216

----------------------------------------------------

What is "opal_memory_ptmalloc2_int_malloc ()" ?

The gdb output from sequential code:

-------------------------------------

Breakpoint 1, main (argc=<value optimized out>, argv=<value optimized out>)

at src/nsga2/main-seq.cpp:32

32 ImportIndices();

(gdb) c

Continuing.

Breakpoint 2, ImportIndices () at src/index.cpp:115

115 IdxNode = ReadFile("prepdata/idx_node.csv");

(gdb) c

Continuing.

Breakpoint 4, ReadFile (fileinput=0xd6bb9d "prepdata/idx_node.csv")

at src/index.cpp:86

86 Index TempIndex;

(gdb) c

Continuing.

Breakpoint 5, Index::Index (this=0x7fffffffd6d0) at src/index.cpp:20

20 Name(0) {}

(gdb) c

Continuing.

Breakpoint 4, ReadFile (fileinput=0xd6bbb3 "prepdata/idx_ud.csv")

at src/index.cpp:86

86 Index TempIndex;

(gdb) bt

#0 ReadFile (fileinput=0xd6bbb3 "prepdata/idx_ud.csv") at src/index.cpp:86

#1 0x0000000000471cc9 in ImportIndices () at src/index.cpp:116

#2 0x000000000043bba6 in main (argc=<value optimized out>,

argv=<value optimized out>) at src/nsga2/main-seq.cpp:32

--------------------------------------

thanks

From: belaid_moa@hotmail.com
To: users@open-mpi.org; dtustudy68@hotmail.com
Subject: RE: [OMPI users] OMPI seg fault by a class with weird address.
Date: Tue, 15 Mar 2011 06:16:35 +0000

Hi Jack,
1- Where is your main function to see how you called your class?
2- I do not see the implementation of GetPosition, GetName, etc.?

With best regards,
-Belaid.

From: dtustudy68@hotmail.com
To: users@open-mpi.org
Date: Mon, 14 Mar 2011 19:04:12 -0600
Subject: [OMPI users] OMPI seg fault by a class with weird address.

Hi,

I got a run-time error of a Open MPI C++ program.

The following output is from gdb:

--------------------------------------------------------------------------

Program received signal SIGSEGV, Segmentation fault.

0x00002aaaab3b0b81 in opal_memory_ptmalloc2_int_malloc ()

from /opt/openmpi-1.3.4-gnu/lib/libopen-pal.so.0

At the point

Breakpoint 9, Index::Index (this=0x7fffffffcb80) at src/index.cpp:20

20 Name(0) {}

The Index has been called before this point and no problem:

-------------------------------------------------------

Breakpoint 9, Index::Index (this=0x117d800) at src/index.cpp:20

20 Name(0) {}

(gdb) c

Continuing.

Breakpoint 9, Index::Index (this=0x117d860) at src/index.cpp:20

20 Name(0) {}

(gdb) c

Continuing.

----------------------------------------------------------------------------

It seems that the 0x7fffffffcb80 address is a problem.

But, I donot know the reason and how to remove the bug.

Any help is really appreciated.

thanks

the following is the index definition.

---------------------------------------------------------

class Index {

public:

Index();

Index(const Index& rhs);

~Index();

Index& operator=(const Index& rhs);

vector<int> GetPosition() const;

vector<int> GetColumn() const;

vector<int> GetYear() const;

vector<string> GetName() const;

int GetPosition(const int idx) const;

int GetColumn(const int idx) const;

int GetYear(const int idx) const;

string GetName(const int idx) const;

int GetSize() const;

void Add(const int idx, const int col, const string& name);

void Add(const int idx, const int col, const int year, const string& name);

void Add(const int idx, const Step& col, const string& name);

void WriteFile(const char* fileinput) const;

private:

vector<int> Position;

vector<int> Column;

vector<int> Year;

vector<string> Name;

};

// Contructors and destructor for the Index class

Index::Index() :

Position(0),

Column(0),

Year(0),

Name(0) {}

Index::Index(const Index& rhs) :

Position(rhs.GetPosition()),

Column(rhs.GetColumn()),

Year(rhs.GetYear()),

Name(rhs.GetName()) {}

Index::~Index() {}

Index& Index::operator=(const Index& rhs) {

Position = rhs.GetPosition();

Column = rhs.GetColumn(),

Year = rhs.GetYear(),

Name = rhs.GetName();

return *this;

}

----------------------------------------------------------

_______________________________________________ users mailing list users@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users