Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
/*
|
|
|
|
* Copyright (c) 2004-2005 The Trustees of Indiana University.
|
|
|
|
* All rights reserved.
|
|
|
|
* Copyright (c) 2004-2005 The Trustees of the University of Tennessee.
|
|
|
|
* All rights reserved.
|
|
|
|
* Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
|
|
|
|
* University of Stuttgart. All rights reserved.
|
2005-03-24 15:43:37 +03:00
|
|
|
* Copyright (c) 2004-2005 The Regents of the University of California.
|
|
|
|
* All rights reserved.
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
* $COPYRIGHT$
|
|
|
|
*
|
|
|
|
* Additional copyrights may follow
|
|
|
|
*
|
|
|
|
* $HEADER$
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include "ompi_config.h"
|
|
|
|
|
2005-02-09 06:08:13 +03:00
|
|
|
#include <stdio.h>
|
|
|
|
#ifdef HAVE_UNISTD_H
|
|
|
|
#include <unistd.h>
|
|
|
|
#endif
|
|
|
|
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
#ifdef HAVE_EXECINFO_H
|
|
|
|
#include <execinfo.h>
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifdef HAVE_STRING_H
|
|
|
|
#include <string.h>
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifdef HAVE_SIGNAL_H
|
|
|
|
#include <signal.h>
|
|
|
|
#endif
|
|
|
|
|
2005-07-04 06:38:44 +04:00
|
|
|
#include "opal/util/stacktrace.h"
|
2005-08-13 00:46:25 +04:00
|
|
|
#include "opal/mca/base/mca_base_param.h"
|
|
|
|
#include "ompi/include/constants.h"
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
|
|
|
|
#ifndef _NSIG
|
|
|
|
#define _NSIG 32
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/**
|
|
|
|
* This function is being called as a signal-handler in response
|
|
|
|
* to a user-specified signal (e.g. SIGFPE or SIGSEGV).
|
|
|
|
* For Linux/Glibc, it then uses backtrace and backtrace_symbols
|
|
|
|
* to figure the current stack and then prints that out to stdout.
|
|
|
|
* Yes, printf and malloc are not signal-safe per se, but should be
|
|
|
|
* on Linux?
|
|
|
|
*
|
|
|
|
* @param signo with the signal number raised
|
|
|
|
* @param info with information regarding the reason/send of the signal
|
|
|
|
* @param p
|
|
|
|
*
|
2005-01-28 23:58:38 +03:00
|
|
|
* FIXME: Should distinguish for systems, which don't have siginfo...
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
*/
|
2005-07-13 08:16:03 +04:00
|
|
|
#if OMPI_WANT_PRETTY_PRINT_STACKTRACE && ! defined(WIN32)
|
2005-07-04 06:38:44 +04:00
|
|
|
static void opal_show_stackframe (int signo, siginfo_t * info, void * p)
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
{
|
|
|
|
#ifdef __GLIBC__
|
|
|
|
int i;
|
|
|
|
int trace_size;
|
|
|
|
void * trace[32];
|
|
|
|
char ** messages = (char **)NULL;
|
|
|
|
#endif
|
|
|
|
char print_buffer[1024];
|
|
|
|
char * tmp = print_buffer;
|
|
|
|
int size = sizeof (print_buffer);
|
|
|
|
int ret;
|
2005-03-14 23:57:21 +03:00
|
|
|
char * str = "";
|
2005-02-09 06:08:13 +03:00
|
|
|
char eof_msg[] = "*** End of error message ***\n";
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Yes, we are doing printf inside a signal-handler.
|
|
|
|
* However, backtrace itself calls malloc (which may not be signal-safe,
|
|
|
|
* under linux, printf and malloc are)
|
|
|
|
*
|
|
|
|
* We could use backtrace_symbols_fd and write directly into an
|
|
|
|
* filedescriptor, however, without formatting -- also this fd
|
|
|
|
* should be opened in a sensible way...
|
|
|
|
*/
|
|
|
|
memset (print_buffer, 0, sizeof (print_buffer));
|
|
|
|
|
|
|
|
switch (signo)
|
|
|
|
{
|
|
|
|
case SIGILL:
|
|
|
|
switch (info->si_code)
|
|
|
|
{
|
|
|
|
case ILL_ILLOPC: str = "ILL_ILLOPC"; break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#ifdef ILL_ILLOPN
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
case ILL_ILLOPN: str = "ILL_ILLOPN"; break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#endif
|
|
|
|
#ifdef ILL_ILLADR
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
case ILL_ILLADR: str = "ILL_ILLADR"; break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#endif
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
case ILL_ILLTRP: str = "ILL_ILLTRP"; break;
|
|
|
|
case ILL_PRVOPC: str = "ILL_PRVOPC"; break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#ifdef ILL_PRVREG
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
case ILL_PRVREG: str = "ILL_PRVREG"; break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#endif
|
|
|
|
#ifdef ILL_COPROC
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
case ILL_COPROC: str = "ILL_COPROC"; break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#endif
|
|
|
|
#ifdef ILL_BADSTK
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
case ILL_BADSTK: str = "ILL_BADSTK"; break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#endif
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
}
|
|
|
|
break;
|
|
|
|
case SIGFPE:
|
|
|
|
switch (info->si_code)
|
|
|
|
{
|
2005-01-26 23:05:44 +03:00
|
|
|
#ifdef FPE_INTDIV
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
case FPE_INTDIV: str = "FPE_INTDIV"; break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#endif
|
|
|
|
#ifdef FPE_INTOVF
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
case FPE_INTOVF: str = "FPE_INTOVF"; break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#endif
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
case FPE_FLTDIV: str = "FPE_FLTDIV"; break;
|
|
|
|
case FPE_FLTOVF: str = "FPE_FLTOVF"; break;
|
|
|
|
case FPE_FLTUND: str = "FPE_FLTUND"; break;
|
|
|
|
case FPE_FLTRES: str = "FPE_FLTRES"; break;
|
|
|
|
case FPE_FLTINV: str = "FPE_FLTINV"; break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#ifdef FPE_FLTSUB
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
case FPE_FLTSUB: str = "FPE_FLTSUB"; break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#endif
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
}
|
|
|
|
break;
|
|
|
|
case SIGSEGV:
|
|
|
|
switch (info->si_code)
|
|
|
|
{
|
|
|
|
case SEGV_MAPERR: str = "SEGV_MAPERR"; break;
|
|
|
|
case SEGV_ACCERR: str = "SEGV_ACCERR"; break;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
case SIGBUS:
|
|
|
|
switch (info->si_code)
|
|
|
|
{
|
|
|
|
case BUS_ADRALN: str = "BUS_ADRALN"; break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#ifdef BUSADRERR
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
case BUS_ADRERR: str = "BUS_ADRERR"; break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#endif
|
|
|
|
#ifdef BUS_OBJERR
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
case BUS_OBJERR: str = "BUS_OBJERR"; break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#endif
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
}
|
|
|
|
break;
|
|
|
|
case SIGTRAP:
|
|
|
|
switch (info->si_code)
|
|
|
|
{
|
2005-01-26 23:05:44 +03:00
|
|
|
#ifdef TRAP_BRKPT
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
case TRAP_BRKPT: str = "TRAP_BRKPT"; break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#endif
|
|
|
|
#ifdef TRAP_TRACE
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
case TRAP_TRACE: str = "TRAP_TRACE"; break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#endif
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
}
|
|
|
|
break;
|
|
|
|
case SIGCHLD:
|
|
|
|
switch (info->si_code)
|
|
|
|
{
|
|
|
|
case CLD_EXITED: str = "CLD_EXITED"; break;
|
|
|
|
case CLD_KILLED: str = "CLD_KILLED"; break;
|
|
|
|
case CLD_DUMPED: str = "CLD_DUMPED"; break;
|
|
|
|
case CLD_TRAPPED: str = "CLD_TRAPPED"; break;
|
|
|
|
case CLD_STOPPED: str = "CLD_STOPPED"; break;
|
|
|
|
case CLD_CONTINUED: str = "CLD_CONTINUED"; break;
|
|
|
|
}
|
|
|
|
break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#ifdef SIGPOLL
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
case SIGPOLL:
|
|
|
|
switch (info->si_code)
|
|
|
|
{
|
|
|
|
case POLL_IN: str = "POLL_IN"; break;
|
|
|
|
case POLL_OUT: str = "POLL_OUT"; break;
|
|
|
|
case POLL_MSG: str = "POLL_MSG"; break;
|
|
|
|
case POLL_ERR: str = "POLL_ERR"; break;
|
|
|
|
case POLL_PRI: str = "POLL_PRI"; break;
|
|
|
|
case POLL_HUP: str = "POLL_HUP"; break;
|
|
|
|
}
|
|
|
|
break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#endif /* SIGPOLL */
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
default:
|
|
|
|
switch (info->si_code)
|
|
|
|
{
|
2005-01-26 23:05:44 +03:00
|
|
|
#ifdef SI_ASYNCNL
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
case SI_ASYNCNL: str = "SI_ASYNCNL"; break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#endif
|
|
|
|
#ifdef SI_SIGIO
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
case SI_SIGIO: str = "SI_SIGIO"; break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#endif
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
case SI_ASYNCIO: str = "SI_ASYNCIO"; break;
|
|
|
|
case SI_MESGQ: str = "SI_MESGQ"; break;
|
|
|
|
case SI_TIMER: str = "SI_TIMER"; break;
|
|
|
|
case SI_QUEUE: str = "SI_QUEUE"; break;
|
|
|
|
case SI_USER: str = "SI_USER"; break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#ifdef SI_KERNEL
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
case SI_KERNEL: str = "SI_KERNEL"; break;
|
2005-01-26 23:05:44 +03:00
|
|
|
#endif
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
ret = snprintf (tmp, size, "Signal:%d info.si_errno:%d(%s) si_code:%d(%s)\n",
|
|
|
|
signo, info->si_errno, strerror (info->si_errno),
|
|
|
|
info->si_code, str);
|
|
|
|
size -= ret;
|
|
|
|
tmp += ret;
|
|
|
|
|
|
|
|
switch (signo)
|
|
|
|
{
|
|
|
|
case SIGILL:
|
|
|
|
case SIGFPE:
|
|
|
|
case SIGSEGV:
|
|
|
|
case SIGBUS:
|
2005-02-09 06:08:13 +03:00
|
|
|
{
|
|
|
|
ret = snprintf (tmp, size, "Failing at addr:%p\n",
|
|
|
|
info->si_addr);
|
|
|
|
size -= ret;
|
|
|
|
tmp += ret;
|
|
|
|
break;
|
|
|
|
}
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
case SIGCHLD: {
|
2005-02-09 06:08:13 +03:00
|
|
|
ret = snprintf (tmp, size, "si_pid:%d si_uid:%d si_status:%d\n",
|
|
|
|
info->si_pid, info->si_uid, info->si_status);
|
|
|
|
size -= ret;
|
|
|
|
tmp += ret;
|
|
|
|
break;
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
}
|
2005-01-26 23:05:44 +03:00
|
|
|
#ifdef SIGPOLL
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
case SIGPOLL: {
|
2005-04-06 09:32:11 +04:00
|
|
|
#ifdef HAVE_SIGINFO_T_SI_FD
|
2005-02-09 06:08:13 +03:00
|
|
|
ret = snprintf (tmp, size, "si_band:%ld si_fd:%d\n",
|
|
|
|
info->si_band, info->si_fd);
|
2005-04-06 09:32:11 +04:00
|
|
|
#else
|
|
|
|
ret = snprintf (tmp, size, "si_band:%ld\n",
|
|
|
|
info->si_band);
|
|
|
|
#endif
|
2005-02-09 06:08:13 +03:00
|
|
|
size -= ret;
|
|
|
|
tmp += ret;
|
|
|
|
break;
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
}
|
2005-01-26 23:05:44 +03:00
|
|
|
#endif
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
}
|
2005-02-09 06:08:13 +03:00
|
|
|
|
|
|
|
write(1, print_buffer, size);
|
|
|
|
fflush(stderr);
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
|
|
|
|
#ifdef __GLIBC__
|
|
|
|
trace_size = backtrace (trace, 32);
|
|
|
|
messages = backtrace_symbols (trace, trace_size);
|
|
|
|
|
2005-02-09 06:08:13 +03:00
|
|
|
for (i = 0; i < trace_size; i++) {
|
|
|
|
fprintf(stderr, "[%d] func:%s\n", i, messages[i]);
|
|
|
|
fflush(stderr);
|
|
|
|
}
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
#endif
|
2005-02-09 06:08:13 +03:00
|
|
|
|
|
|
|
write(1, eof_msg, sizeof(eof_msg));
|
|
|
|
fflush(stderr);
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
}
|
|
|
|
|
2005-07-13 08:16:03 +04:00
|
|
|
#endif /* OMPI_WANT_PRETTY_PRINT_STACKTRACE && ! defined(WIN32) */
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
|
|
|
|
|
|
|
|
/**
|
2005-07-04 06:38:44 +04:00
|
|
|
* Here we register the opal_show_stackframe function for signals
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
* passed to OpenMPI by the mpi_signal-parameter passed to mpirun
|
|
|
|
* by the user.
|
|
|
|
*
|
|
|
|
* @returnvalue OMPI_SUCCESS
|
|
|
|
* @returnvalue OMPI_ERR_BAD_PARAM if the value in the signal-list
|
|
|
|
* is not a valid signal-number
|
|
|
|
*
|
|
|
|
*/
|
2005-07-04 06:38:44 +04:00
|
|
|
int opal_util_register_stackhandlers (void)
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
{
|
2005-07-13 08:16:03 +04:00
|
|
|
#if OMPI_WANT_PRETTY_PRINT_STACKTRACE && ! defined(WIN32)
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
struct sigaction act;
|
|
|
|
char * string_value;
|
|
|
|
char * tmp;
|
|
|
|
char * next;
|
|
|
|
int param;
|
|
|
|
|
|
|
|
param = mca_base_param_find ("mpi", NULL, "signal");
|
|
|
|
mca_base_param_lookup_string (param, &string_value);
|
|
|
|
|
|
|
|
memset(&act, 0, sizeof(act));
|
2005-07-04 06:38:44 +04:00
|
|
|
act.sa_sigaction = opal_show_stackframe;
|
2005-01-26 23:05:44 +03:00
|
|
|
act.sa_flags = SA_SIGINFO;
|
|
|
|
#ifdef SA_ONESHOT
|
|
|
|
act.sa_flags |= SA_ONESHOT;
|
|
|
|
#else
|
|
|
|
act.sa_flags |= SA_RESETHAND;
|
|
|
|
#endif
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
|
|
|
|
for (tmp = next = string_value ;
|
|
|
|
next != NULL && *next != '\0';
|
|
|
|
tmp = next + 1)
|
|
|
|
{
|
|
|
|
int sig;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
sig = strtol (tmp, &next, 10);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If there is no sensible number in the string, exit.
|
|
|
|
* Similarly for any number which is not in the signal-number range
|
|
|
|
*/
|
2005-02-09 06:08:13 +03:00
|
|
|
if (((0 == sig) && (tmp == next)) || (0 > sig) || (_NSIG <= sig)) {
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
return OMPI_ERR_BAD_PARAM;
|
2005-02-09 06:08:13 +03:00
|
|
|
}
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
|
2005-02-09 06:08:13 +03:00
|
|
|
if ((next == NULL) || ((*next != ',') && (*next != '\0'))) {
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
return OMPI_ERR_BAD_PARAM;
|
2005-02-09 06:08:13 +03:00
|
|
|
}
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
|
|
|
|
ret = sigaction (sig, &act, NULL);
|
2005-02-09 06:08:13 +03:00
|
|
|
if (ret != 0) {
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
return OMPI_ERR_IN_ERRNO;
|
2005-02-09 06:08:13 +03:00
|
|
|
}
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
}
|
2005-07-13 08:16:03 +04:00
|
|
|
#endif /* OMPI_WANT_PRETTY_PRINT_STACKTRACE && ! defined(WIN32) */
|
|
|
|
|
Add a Stacktrace feature, which figures where/what signal has happened
after MPI-startup.
For this a new mpirun-parameter "mpi_signal" is added, one may specify a
comma-separated list of signals to grab, e.g. mpirun --mca mpi_signal 8,11
will check for SIGFPE and SIGSEGV.
It only finds the first fault (SA_ONESHOT), as after the return the same
fault will occur again.
As printout, the data provided by siginfo_t is printed to STDOUT (yes,
it calls printf ,-]).
Additionally, with glibc, it uses backtrace and backtrace_symbols to
print the calling stack up to the function in which the signal was raised:
(Rank:0) Going to write to RD_ONLY mmaped shared mem
Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x4020c000
[0] func:/home/rusraink/ompi-gcc/lib/libmpi.so.0 [0x40121afe]
[1] func:./t0 [0x42029180]
[2] func:./t0(__libc_start_main+0x95) [0x42017589]
[3] func:./t0(__libc_start_main+0x49) [0x8048691]
This commit was SVN r4170.
2005-01-26 22:11:46 +03:00
|
|
|
return OMPI_SUCCESS;
|
|
|
|
}
|
|
|
|
|