Below is some info collected from a core generated from running ring_c
without mpirun.
It looks like a bogus btl_module pointer or corrupted object is the culprit
in this crash.
-Paul
Core was generated by `./ring_c '.
Program terminated with signal 11, Segmentation fault.
#0 0x00000080c9b990ac in .strcmp () from /lib64/libc.so.6
Missing separate debuginfos, use: debuginfo-install
glibc-2.12-1.47.el6_2.5.ppc64 libibverbs-1.1.5-3.el6.ppc64
librdmacm-1.0.14.1-3.el6.ppc64 numactl-2.0.3-9.el6.ppc64
sssd-client-1.5.1-66.el6_2.3.ppc64
(gdb) where
#0 0x00000080c9b990ac in .strcmp () from /lib64/libc.so.6
#1 0x00000fffa1490c7c in mca_bml_r2_add_btls ()
at
/home/hargrov1/OMPI/openmpi-1.7-latest-linux-ppc64-gcc/openmpi-1.7.5a1r30639/ompi/mca/bml/r2/bml_r2.c:101
#2 0x00000fffa1490f1c in mca_bml_r2_add_procs (nprocs=1,
procs=0x1002b1ebac0, reachable=0xfffed51b058)
at
/home/hargrov1/OMPI/openmpi-1.7-latest-linux-ppc64-gcc/openmpi-1.7.5a1r30639/ompi/mca/bml/r2/bml_r2.c:156
#3 0x00000fffa169df3c in mca_pml_ob1_add_procs (procs=0x1002b1ebac0,
nprocs=1)
at
/home/hargrov1/OMPI/openmpi-1.7-latest-linux-ppc64-gcc/openmpi-1.7.5a1r30639/ompi/mca/pml/ob1/pml_ob1.c:332
#4 0x00000fffa13b11f0 in ompi_mpi_init (argc=1, argv=0xfffed51b778,
requested=0, provided=0xfffed51b264)
at
/home/hargrov1/OMPI/openmpi-1.7-latest-linux-ppc64-gcc/openmpi-1.7.5a1r30639/ompi/runtime/ompi_mpi_init.c:776
#5 0x00000fffa13ff670 in PMPI_Init (argc=0xfffed51b360,
argv=0xfffed51b368) at pinit.c:84
#6 0x00000000100009ac in main (argc=1, argv=0xfffed51b778) at ring_c.c:19
(gdb) up
#1 0x00000fffa1490c7c in mca_bml_r2_add_btls ()
at
/home/hargrov1/OMPI/openmpi-1.7-latest-linux-ppc64-gcc/openmpi-1.7.5a1r30639/ompi/mca/bml/r2/bml_r2.c:101
101 if (0 ==
(gdb) l
96 selected_btl !=
(mca_btl_base_selected_module_t*)opal_list_get_end(btls);
97 selected_btl =
(mca_btl_base_selected_module_t*)opal_list_get_next(selected_btl)) {
98 mca_btl_base_module_t *btl = selected_btl->btl_module;
99 mca_bml_r2.btl_modules[mca_bml_r2.num_btl_modules++] = btl;
100 for (i = 0; NULL != btl_names_argv && NULL !=
btl_names_argv[i]; ++i) {
101 if (0 ==
102 strcmp(btl_names_argv[i],
103
btl->btl_component->btl_version.mca_component_name)) {
104 break;
105 }
(gdb) print i
$1 = 0
(gdb) print btl_names_argv[i]
$2 = 0x1002b1cfc40 "self"
(gdb) print btl->btl_component->btl_version.mca_component_name
Cannot access memory at address 0x38
(gdb) print btl->btl_component
$3 = (mca_btl_base_component_t *) 0x0
(gdb) print *btl
$4 = {btl_component = 0x0, btl_eager_limit = 33, btl_rndv_eager_limit =
5715139723404663124,
btl_max_send_size = 4998801257537028948, btl_rdma_pipeline_send_length =
32,
btl_rdma_pipeline_frag_size = 113, btl_min_rdma_pipeline_size =
16046253926196952813,
btl_exclusivity = 4095, btl_latency = 2700574648, btl_bandwidth = 1,
btl_flags = 1886351212,
btl_seg_size = 17590591428656, btl_add_procs = 0x1af00000000,
btl_del_procs = 0xfffa0dc5b80,
btl_register = 0xfffa0dc5b80, btl_finalize = 0x100000001, btl_alloc =
0xfffa0dc5b58,
btl_free = 0x1002b1d0760, btl_prepare_src = 0x25, btl_prepare_dst =
0x221, btl_send = 0, btl_sendi = 0x31,
btl_put = 0x62746c5f75736e69, btl_get = 0x635f77616e745f6e, btl_dump =
0x756d615f64657669,
btl_mpool = 0x63655f6173736967, btl_register_error = 0x6e6d656e74000000,
btl_ft_event = 0x31}
[...]
(gdb) print btl
$10 = (mca_btl_base_module_t *) 0x1002b1d03d0
(gdb) print *selected_btl
$11 = {super = {super = {obj_magic_id = 16046253926196952813, obj_class =
0xfffa17bf290,
obj_reference_count = 1,
cls_init_file_name = 0xfffa173e6e0
"/home/hargrov1/OMPI/openmpi-1.7-latest-linux-ppc64-gcc/openmpi-1.7.5a1r30639/ompi/mca/btl/base/btl_base_select.c",
cls_init_lineno = 139}, opal_list_next = 0xfffa18b59c8,
opal_list_prev = 0x1002b1c1eb0, item_free = 1, opal_list_item_refcount
= 1,
opal_list_item_belong_to = 0xfffa18b59a0}, btl_component =
0xfffa17c2570, btl_module = 0x1002b1d03d0}
On Sun, Feb 9, 2014 at 12:32 AM, Paul Hargrove <phhargr...@lbl.gov> wrote:
> I have tried building the current v1.7 tarball (1.7.5a1r30639) with gcc on
> two ppc64/linux machines and one ppc32/linux. All three die in MPI_Init
> when I try to run ring_c.
>
> I've retested 1.7.4 on both ppc64 machines, and thankfully the problem is
> not present.
>
>
> Each of them at least dies with what looks like a potentially useful
> backtrace:
>
> $ mpirun -mca btl sm,self -np 2 examples/ring_c
> *** glibc detected *** examples/ring_c: double free or corruption
> (fasttop): 0x000001003f1d5ce0 ***
> ======= Backtrace: =========
> /lib64/libc.so.6[0x80c9b8f4f4]
>
> /home/hargrov1/OMPI/openmpi-1.7-latest-linux-ppc64-gcc/INST/lib/libmpi.so.1(mca_btl_sm_add_procs-0x2db2c8)[0xfffa29e59a8]
>
> /home/hargrov1/OMPI/openmpi-1.7-latest-linux-ppc64-gcc/INST/lib/libmpi.so.1(+0x2311bc)[0xfffa29711bc]
>
> /home/hargrov1/OMPI/openmpi-1.7-latest-linux-ppc64-gcc/INST/lib/libmpi.so.1(mca_pml_ob1_add_procs-0x14f514)[0xfffa2b7df3c]
>
> /home/hargrov1/OMPI/openmpi-1.7-latest-linux-ppc64-gcc/INST/lib/libmpi.so.1(ompi_mpi_init-0x421ff0)[0xfffa28911f0]
>
> /home/hargrov1/OMPI/openmpi-1.7-latest-linux-ppc64-gcc/INST/lib/libmpi.so.1(MPI_Init-0x3d7120)[0xfffa28df670]
> examples/ring_c[0x100009ac]
> /lib64/libc.so.6[0x80c9b2bcd8]
> /lib64/libc.so.6(__libc_start_main-0x184e00)[0x80c9b2bed0]
> [bd-login:51140] WARNING: common_sm_module_unlink failed.
> [bd-login:51140] WARNING: common_sm_module_unlink failed.
> [bd-login:51140] WARNING: unlink failed.
> [bd-login:51140] WARNING: unlink failed.
> [bd-login:51141] *** Process received signal ***
> [bd-login:51141] Signal: Aborted (6)
> [bd-login:51141] Signal code: (-6)
> [bd-login:51141] [ 0] [0xfffa2da0418]
> [bd-login:51141] [ 1] /lib64/libc.so.6(abort-0x16b278)[0x80c9b46ed8]
> [bd-login:51141] [ 2] /lib64/libc.so.6[0x80c9b87568]
> [bd-login:51141] [ 3] /lib64/libc.so.6[0x80c9b8f4f4]
> [bd-login:51141] [ 4]
> /home/hargrov1/OMPI/openmpi-1.7-latest-linux-ppc64-gcc/INST/lib/libmpi.so.1(mca_btl_sm_add_procs-0x2db2c8)[0xfffa29e59a8]
> [bd-login:51141] [ 5]
> /home/hargrov1/OMPI/openmpi-1.7-latest-linux-ppc64-gcc/INST/lib/libmpi.so.1(+0x2311bc)[0xfffa29711bc]
> [bd-login:51141] [ 6]
> /home/hargrov1/OMPI/openmpi-1.7-latest-linux-ppc64-gcc/INST/lib/libmpi.so.1(mca_pml_ob1_add_procs-0x14f514)[0xfffa2b7df3c]
> [bd-login:51141] [ 7]
> /home/hargrov1/OMPI/openmpi-1.7-latest-linux-ppc64-gcc/INST/lib/libmpi.so.1(ompi_mpi_init-0x421ff0)[0xfffa28911f0]
> [bd-login:51141] [ 8]
> /home/hargrov1/OMPI/openmpi-1.7-latest-linux-ppc64-gcc/INST/lib/libmpi.so.1(MPI_Init-0x3d7120)[0xfffa28df670]
> [bd-login:51141] [ 9] examples/ring_c[0x100009ac]
> [bd-login:51141] [10] /lib64/libc.so.6[0x80c9b2bcd8]
> [bd-login:51141] [11]
> /lib64/libc.so.6(__libc_start_main-0x184e00)[0x80c9b2bed0]
> [bd-login:51141] *** End of error message ***
>
> $ mpirun -mca btl sm,self -np 2 examples/ring_c
> [fc6:27829] *** Process received signal ***
> [fc6:27829] Signal: Segmentation fault (11)
> [fc6:27829] Signal code: Address not mapped (1)
> [fc6:27829] Failing at address: 0x805aa7c9e0
> [fc6:27829] [ 0] [0x100428]
> [fc6:27829] [ 1] /lib64/ld64.so.1(_rtld_global+0x0)[0x804a7d19b8]
> [fc6:27829] [ 2] /lib64/libc.so.6[0x804a888f34]
> [fc6:27829] [ 3] /lib64/libc.so.6(__libc_malloc-0xf95c4)[0x804a88aab4]
> [fc6:27829] [ 4]
> /home/phargrov/OMPI/openmpi-1.7-latest-linux-ppc64/INST/lib/libmpi.so.1(mca_pml_ob1_comm_init_size-0x124550)[0x40000393078]
> [fc6:27829] [ 5]
> /home/phargrov/OMPI/openmpi-1.7-latest-linux-ppc64/INST/lib/libmpi.so.1(mca_pml_ob1_add_comm-0x1276dc)[0x4000038fc1c]
> [fc6:27829] [ 6]
> /home/phargrov/OMPI/openmpi-1.7-latest-linux-ppc64/INST/lib/libmpi.so.1(ompi_mpi_init-0x36fb38)[0x40000130c30]
> [fc6:27829] [ 7]
> /home/phargrov/OMPI/openmpi-1.7-latest-linux-ppc64/INST/lib/libmpi.so.1(MPI_Init-0x3289fc)[0x4000017b34c]
> [fc6:27829] [ 8] examples/ring_c[0x100009b0]
> [fc6:27829] [ 9] /lib64/libc.so.6[0x804a829734]
> [fc6:27829] [10] /lib64/libc.so.6(__libc_start_main-0x15730c)[0x804a8299b4]
> [fc6:27829] *** End of error message ***
>
> $ mpirun -mca btl sm,self -np 2 examples/ring_c
> *** glibc detected *** examples/ring_c: double free or corruption (!prev):
> 0x101b5560 ***
> ======= Backtrace: =========
> /lib/libc.so.6(+0xfe74dd4)[0x480d0dd4]
>
> /home/phargrov/OMPI/openmpi-1.7-latest-linux-ppc32/INST/lib/libmpi.so.1(mca_btl_sm_add_procs+0x66c)[0xfc720c0]
>
> /home/phargrov/OMPI/openmpi-1.7-latest-linux-ppc32/INST/lib/libmpi.so.1(+0x15f7a0)[0xfc5e7a0]
>
> /home/phargrov/OMPI/openmpi-1.7-latest-linux-ppc32/INST/lib/libmpi.so.1(mca_pml_ob1_add_procs+0x14c)[0xfdecc50]
>
> /home/phargrov/OMPI/openmpi-1.7-latest-linux-ppc32/INST/lib/libmpi.so.1(ompi_mpi_init+0xcec)[0xfb96eb4]
>
> /home/phargrov/OMPI/openmpi-1.7-latest-linux-ppc32/INST/lib/libmpi.so.1(MPI_Init+0x1e4)[0xfbdd878]
> examples/ring_c[0x10000724]
> /lib/libc.so.6(+0xfe0e0fc)[0x4806a0fc]
> /lib/libc.so.6(+0xfe0e2a0)[0x4806a2a0]
> [pcp-k-421:02574] *** Process received signal ***
> [pcp-k-421:02574] Signal: Aborted (6)
> [pcp-k-421:02574] Signal code: (-6)
> [pcp-k-421:02574] [ 0] [0x100370]
> [pcp-k-421:02574] [ 1] [0xbfd3a008]
> [pcp-k-421:02574] [ 2] /lib/libc.so.6(abort+0x25c)[0x48084a2c]
> [pcp-k-421:02574] [ 3] /lib/libc.so.6(+0xfe6cc9c)[0x480c8c9c]
> [pcp-k-421:02574] [ 4] /lib/libc.so.6(+0xfe74dd4)[0x480d0dd4]
> [pcp-k-421:02574] [ 5]
> /home/phargrov/OMPI/openmpi-1.7-latest-linux-ppc32/INST/lib/libmpi.so.1(mca_btl_sm_add_
> procs+0x66c)[0xfc720c0]
> [pcp-k-421:02574] [ 6]
> /home/phargrov/OMPI/openmpi-1.7-latest-linux-ppc32/INST/lib/libmpi.so.1(+0x15f7a0)[0xfc5e7a0]
> [pcp-k-421:02574] [ 7]
> /home/phargrov/OMPI/openmpi-1.7-latest-linux-ppc32/INST/lib/libmpi.so.1(mca_pml_ob1_add_procs+0x14c)[0xfdecc50]
>
> [pcp-k-421:02574] [ 8]
> /home/phargrov/OMPI/openmpi-1.7-latest-linux-ppc32/INST/lib/libmpi.so.1(ompi_mpi_init+0xcec)[0xfb96eb4]
> [pcp-k-421:02574] [ 9]
> /home/phargrov/OMPI/openmpi-1.7-latest-linux-ppc32/INST/lib/libmpi.so.1(MPI_Init+0x1e4)[0xfbdd878]
> [pcp-k-421:02574] [10] examples/ring_c[0x10000724]
> [pcp-k-421:02574] [11] /lib/libc.so.6(+0xfe0e0fc)[0x4806a0fc]
> [pcp-k-421.n2001:02573] WARNING: common_sm_module_unlink failed.
> [pcp-k-421:02574] [12] /lib/libc.so.6(+0xfe0e2a0)[0x4806a2a0]
> [pcp-k-421:02574] *** End of error message ***
> [pcp-k-421.n2001:02573] WARNING: common_sm_module_unlink failed.
> [pcp-k-421.n2001:02573] WARNING: unlink failed.
> [pcp-k-421.n2001:02573] WARNING: A system call failed during shared memory
> initialization that should unlink failed.
> [pcp-k-421:02573] *** Process received signal ***
> [pcp-k-421:02573] Signal: Segmentation fault (11)
> [pcp-k-421:02573] Signal code: Address not mapped (1)
> [pcp-k-421:02573] Failing at address: 0x3f000008
> [pcp-k-421:02573] [ 0] [0x100370]
> [pcp-k-421:02573] [ 1] [0xffffffff]
> [pcp-k-421:02573] [ 2] /lib/libc.so.6(__libc_malloc+0x8c)[0x480d525c]
> [pcp-k-421:02573] [ 3]
> /home/phargrov/OMPI/openmpi-1.7-latest-linux-ppc32/INST/lib/libmpi.so.1(+0x2eb7f8)[0xfdea7f8]
> [pcp-k-421:02573] [ 4]
> /home/phargrov/OMPI/openmpi-1.7-latest-linux-ppc32/INST/lib/libmpi.so.1(+0x2eb5a0)[0xfdea5a0]
> [pcp-k-421:02573] [ 5]
> /home/phargrov/OMPI/openmpi-1.7-latest-linux-ppc32/INST/lib/libmpi.so.1(mca_pml_ob1_add_comm+0x40)[0xfdec108]
> [pcp-k-421:02573] [ 6]
> /home/phargrov/OMPI/openmpi-1.7-latest-linux-ppc32/INST/lib/libmpi.so.1(ompi_mpi_init+0xd6c)[0xfb96f34]
> [pcp-k-421:02573] [ 7]
> /home/phargrov/OMPI/openmpi-1.7-latest-linux-ppc32/INST/lib/libmpi.so.1(MPI_Init+0x1e4)[0xfbdd878]
> [pcp-k-421:02573] [ 8] examples/ring_c[0x10000724]
> [pcp-k-421:02573] [ 9] /lib/libc.so.6(+0xfe0e0fc)[0x4806a0fc]
> [pcp-k-421:02573] [10] /lib/libc.so.6(+0xfe0e2a0)[0x4806a2a0]
> [pcp-k-421:02573] *** End of error message ***
> --------------------------------------------------------------------------
> mpirun noticed that process rank 1 with PID 2574 on node pcp-k-421 exited
> on signal 6 (Aborted).
> --------------------------------------------------------------------------
>
> -Paul
>
> --
> Paul H. Hargrove phhargr...@lbl.gov
> Future Technologies Group
> Computer and Data Sciences Department Tel: +1-510-495-2352
> Lawrence Berkeley National Laboratory Fax: +1-510-486-6900
>
--
Paul H. Hargrove phhargr...@lbl.gov
Future Technologies Group
Computer and Data Sciences Department Tel: +1-510-495-2352
Lawrence Berkeley National Laboratory Fax: +1-510-486-6900
