Hi,

is the following info helpful?

tyr java 160 /usr/local/gdb-7.6.1_64_gcc/bin/gdb mpiexec
GNU gdb (GDB) 7.6.1
Copyright (C) 2013 Free Software Foundation, Inc.
License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
This is free software: you are free to change and redistribute it.
There is NO WARRANTY, to the extent permitted by law.  Type "show copying"
and "show warranty" for details.
This GDB was configured as "sparc-sun-solaris2.10".
For bug reporting instructions, please see:
<http://www.gnu.org/software/gdb/bugs/>...
Reading symbols from 
/export2/prog/SunOS_sparc/openmpi-1.9_64_cc/bin/orterun...done.
(gdb) run -np 1 java InitFinalizeMain 
Starting program: /usr/local/openmpi-1.9_64_cc/bin/mpiexec -np 1 java 
InitFinalizeMain
[Thread debugging using libthread_db enabled]
[New Thread 1 (LWP 1)]
[New LWP    2        ]
#
# A fatal error has been detected by the Java Runtime Environment:
#
#  SIGSEGV (0xb) at pc=0xffffffff7ea3c7f0, pid=22871, tid=2
#
# JRE version: Java(TM) SE Runtime Environment (8.0-b132) (build 1.8.0-b132)
# Java VM: Java HotSpot(TM) 64-Bit Server VM (25.0-b70 mixed mode solaris-sparc 
compressed oops)
# Problematic frame:
# C  [libc.so.1+0x3c7f0]  strlen+0x50
#
# Failed to write core dump. Core dumps have been disabled. To enable core 
dumping, try "ulimit -c unlimited" before starting Java again
#
# An error report file with more information is saved as:
# /home/fd1026/work/skripte/master/parallel/prog/mpi/java/hs_err_pid22871.log
#
# If you would like to submit a bug report, please visit:
#   http://bugreport.sun.com/bugreport/crash.jsp
# The crash happened outside the Java Virtual Machine in native code.
# See problematic frame for where to report the bug.
#
--------------------------------------------------------------------------
mpiexec noticed that process rank 0 with PID 0 on node tyr exited on signal 6 
(Abort).
--------------------------------------------------------------------------
[LWP    2         exited]
[New Thread 2        ]
[Switching to Thread 1 (LWP 1)]
sol_thread_fetch_registers: td_ta_map_id2thr: no thread can be found to satisfy 
query
(gdb) bt
#0  0xffffffff7f6173d0 in rtld_db_dlactivity () from /usr/lib/sparcv9/ld.so.1
#1  0xffffffff7f6175a8 in rd_event () from /usr/lib/sparcv9/ld.so.1
#2  0xffffffff7f618950 in lm_delete () from /usr/lib/sparcv9/ld.so.1
#3  0xffffffff7f6226bc in remove_so () from /usr/lib/sparcv9/ld.so.1
#4  0xffffffff7f624574 in remove_hdl () from /usr/lib/sparcv9/ld.so.1
#5  0xffffffff7f61d97c in dlclose_core () from /usr/lib/sparcv9/ld.so.1
#6  0xffffffff7f61d9d4 in dlclose_intn () from /usr/lib/sparcv9/ld.so.1
#7  0xffffffff7f61db0c in dlclose () from /usr/lib/sparcv9/ld.so.1
#8  0xffffffff7e4e6f88 in vm_close () from 
/usr/local/openmpi-1.9_64_cc/lib64/libopen-pal.so.0
#9  0xffffffff7e4e4274 in lt_dlclose () from 
/usr/local/openmpi-1.9_64_cc/lib64/libopen-pal.so.0
#10 0xffffffff7e53a574 in ri_destructor (obj=0x0) at 
../../../../openmpi-1.9a1r32716/opal/mca/base/mca_base_component_repository.c:382
#11 0xffffffff7e537d50 in opal_obj_run_destructors (object=0x0) at 
../../../../openmpi-1.9a1r32716/opal/class/opal_object.h:446
#12 0xffffffff7e539de4 in mca_base_component_repository_release 
(component=0xf000)
    at 
../../../../openmpi-1.9a1r32716/opal/mca/base/mca_base_component_repository.c:240
#13 0xffffffff7e540448 in mca_base_component_unload (component=0x0, 
output_id=-2145509376)
    at 
../../../../openmpi-1.9a1r32716/opal/mca/base/mca_base_components_close.c:47
#14 0xffffffff7e5404ec in mca_base_component_close 
(component=0xffffff7b000030ff, output_id=255)
    at 
../../../../openmpi-1.9a1r32716/opal/mca/base/mca_base_components_close.c:60
#15 0xffffffff7e5405fc in mca_base_components_close (output_id=767, 
components=0x0, skip=0xffffff7f73cdf800)
    at 
../../../../openmpi-1.9a1r32716/opal/mca/base/mca_base_components_close.c:86
#16 0xffffffff7e54053c in mca_base_framework_components_close (framework=0xff, 
skip=0xffffff7c801c4000)
    at 
../../../../openmpi-1.9a1r32716/opal/mca/base/mca_base_components_close.c:68
#17 0xffffffff7ee48d68 in orte_oob_base_close () at 
../../../../openmpi-1.9a1r32716/orte/mca/oob/base/oob_base_frame.c:98
#18 0xffffffff7e56c23c in mca_base_framework_close 
(framework=0xffffff7e4e413cff)
    at ../../../../openmpi-1.9a1r32716/opal/mca/base/mca_base_framework.c:187
#19 0xffffffff7bb13f00 in rte_finalize () at 
../../../../../openmpi-1.9a1r32716/orte/mca/ess/hnp/ess_hnp_module.c:857
#20 0xffffffff7ec3adf0 in orte_finalize () at 
../../openmpi-1.9a1r32716/orte/runtime/orte_finalize.c:66
#21 0x000000010000e264 in orterun (argc=4607, argv=0x0) at 
../../../../openmpi-1.9a1r32716/orte/tools/orterun/orterun.c:1099
#22 0x00000001000046d4 in main (argc=255, argv=0xffffff7f0af87800) at 
../../../../openmpi-1.9a1r32716/orte/tools/orterun/main.c:13
(gdb) thread 1
[Switching to thread 1 (LWP    1        )]
#0  0xffffffff7f6173d0 in rtld_db_dlactivity () from /usr/lib/sparcv9/ld.so.1
(gdb) list mca_base_component_repository.c:365,383
365     
366     /*
367      * Close a component 
368      */
369     static void ri_destructor(opal_object_t *obj)
370     {
371       repository_item_t *ri = (repository_item_t *) obj;
372       opal_list_item_t *item;
373       int group_id;
374     
375       group_id = mca_base_var_group_find (NULL, ri->ri_type,
376                                           
ri->ri_component_struct->mca_component_name);
377       if (0 <= group_id) {
378         mca_base_var_group_deregister (group_id);
379       }
380     
381       /* Close the component (and potentially unload it from memory */
382       lt_dlclose(ri->ri_dlhandle);
383     
(gdb) break mca_base_component_repository.c:382
Breakpoint 1 at 0xffffffff7e53a564: file 
../../../../openmpi-1.9a1r32716/opal/mca/base/mca_base_component_repository.c, 
line 382.
(gdb) break mca_base_component_repository.c:375
Breakpoint 2 at 0xffffffff7e53a524: file 
../../../../openmpi-1.9a1r32716/opal/mca/base/mca_base_component_repository.c, 
line 375.
(gdb) run
The program being debugged has been started already.
Start it from the beginning? (y or n) y
Starting program: /usr/local/openmpi-1.9_64_cc/bin/mpiexec -np 1 java 
InitFinalizeMain
[Thread debugging using libthread_db enabled]
[New Thread 1 (LWP 1)]
[Switching to Thread 1 (LWP 1)]

Breakpoint 2, ri_destructor (obj=0x3000000000ff) at 
../../../../openmpi-1.9a1r32716/opal/mca/base/mca_base_component_repository.c:376
376                                           
ri->ri_component_struct->mca_component_name);
(gdb) ptype opal_object_t
type = struct opal_object_t {
    uint64_t obj_magic_id;
    opal_class_t *obj_class;
    volatile int32_t obj_reference_count;
    const char *cls_init_file_name;
    int cls_init_lineno;
}
(gdb) ptype repository_item_t
type = struct repository_item_t {
    opal_list_item_t super;
    char ri_type[32];
    lt_dlhandle ri_dlhandle;
    const mca_base_component_t *ri_component_struct;
    opal_list_t ri_dependencies;
}
(gdb) ptype opal_list_item_t
type = struct opal_list_item_t {
    opal_object_t super;
    volatile struct opal_list_item_t *opal_list_next;
    volatile struct opal_list_item_t *opal_list_prev;
    int32_t item_free;
    volatile int32_t opal_list_item_refcount;
    volatile struct opal_list_t *opal_list_item_belong_to;
}
(gdb) print obj
$1 = (opal_object_t *) 0x3000000000ff
(gdb) print ri
$2 = (repository_item_t *) 0xffffff7f635b9500
(gdb) print item
$3 = (opal_list_item_t *) 0xffffff7f6342e8ff
(gdb) print *ri
Cannot access memory at address 0xffffff7f635b9500
(gdb) print ri->ri_type
Cannot access memory at address 0xffffff7f635b9548
(gdb) break 377
Breakpoint 3 at 0xffffffff7e53a548: file 
../../../../openmpi-1.9a1r32716/opal/mca/base/mca_base_component_repository.c, 
line 377.
(gdb) next

Breakpoint 3, ri_destructor (obj=0x3000000000ff) at 
../../../../openmpi-1.9a1r32716/opal/mca/base/mca_base_component_repository.c:377
377       if (0 <= group_id) {
(gdb) print group_id
$4 = 1666945535
(gdb) print ri->ri_dlhandle
Cannot access memory at address 0xffffff7f635b9568
(gdb) 


Can I provide anything else?


Kind regards

Siegmar

Reply via email to