[mpich-discuss] MPICH-3.2: SIGSEGV in MPID_Request_create () at src/mpid/ch3/src/ch3u_request.c:101
Mark Davis
markdavisinboston at gmail.com
Fri Aug 12 21:37:09 CDT 2016
I've tried both git HEAD (3ea7589) as well as the August 1 master
snapshot and am having trouble building it; I'm getting the same error
in both cases. I've configured with --enable-g=most but otherwise it's
all default. I'm running on OSX (Darwin - 15.6.0) and clang 3.8.1.
It's erroring on compiling src/mpi/attr/lib_libpmpi_la-attr_delete.lo
due to an issue with the macro MPL_free
Has anyone seen this before? I'm including the full error trace below:
Making all in .
CC src/mpi/attr/lib_libpmpi_la-attr_delete.lo
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:217:
./src/include/mpir_request.h:281:13: warning: multi-character
character constant [-Wmultichar]
MPL_free(req->u.ureq.greq_fns);
^
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:110:26:
note: expanded from macro 'MPL_free'
#define MPL_free(a) free((void *)(a))
^
./src/include/mpir_mem.h:92:27: note: expanded from macro 'free'
#define free(a) 'Error use MPL_free' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:217:
./src/include/mpir_request.h:281:13: warning: character constant too
long for its type
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:110:26:
note: expanded from macro 'MPL_free'
#define MPL_free(a) free((void *)(a))
^
./src/include/mpir_mem.h:92:27: note: expanded from macro 'free'
#define free(a) 'Error use MPL_free' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:217:
./src/include/mpir_request.h:281:13: error: expected ';' after expression
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:110:26:
note: expanded from macro 'MPL_free'
#define MPL_free(a) free((void *)(a))
^
./src/include/mpir_mem.h:92:50: note: expanded from macro 'free'
#define free(a) 'Error use MPL_free' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:217:
./src/include/mpir_request.h:281:13: error: expected expression
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:110:26:
note: expanded from macro 'MPL_free'
#define MPL_free(a) free((void *)(a))
^
./src/include/mpir_mem.h:92:51: note: expanded from macro 'free'
#define free(a) 'Error use MPL_free' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:225:
In file included from ./src/include/mpir_cvars.h:17:
In file included from ./src/include/mpitimpl.h:18:
./src/include/mpir_utarray.h:238:43: warning: multi-character
character constant [-Wmultichar]
*_dst = (*_src == NULL) ? NULL : (char*)utarray_strdup_(*_src);
^
./src/include/mpir_utarray.h:56:33: note: expanded from macro 'utarray_strdup_'
#define utarray_strdup_(x_) MPL_strdup(x_)
^
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:17:20:
note: expanded from macro 'MPL_strdup'
#define MPL_strdup strdup
^
./src/include/mpir_mem.h:100:27: note: expanded from macro 'strdup'
#define strdup(a) 'Error use MPL_strdup' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:225:
In file included from ./src/include/mpir_cvars.h:17:
In file included from ./src/include/mpitimpl.h:18:
./src/include/mpir_utarray.h:238:43: warning: character constant too
long for its type
./src/include/mpir_utarray.h:56:33: note: expanded from macro 'utarray_strdup_'
#define utarray_strdup_(x_) MPL_strdup(x_)
^
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:17:20:
note: expanded from macro 'MPL_strdup'
#define MPL_strdup strdup
^
./src/include/mpir_mem.h:100:27: note: expanded from macro 'strdup'
#define strdup(a) 'Error use MPL_strdup' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:225:
In file included from ./src/include/mpir_cvars.h:17:
In file included from ./src/include/mpitimpl.h:18:
./src/include/mpir_utarray.h:238:43: error: expected ';' after expression
./src/include/mpir_utarray.h:56:33: note: expanded from macro 'utarray_strdup_'
#define utarray_strdup_(x_) MPL_strdup(x_)
^
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:17:20:
note: expanded from macro 'MPL_strdup'
#define MPL_strdup strdup
^
./src/include/mpir_mem.h:100:50: note: expanded from macro 'strdup'
#define strdup(a) 'Error use MPL_strdup' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:225:
In file included from ./src/include/mpir_cvars.h:17:
In file included from ./src/include/mpitimpl.h:18:
./src/include/mpir_utarray.h:238:43: error: expected expression
./src/include/mpir_utarray.h:56:33: note: expanded from macro 'utarray_strdup_'
#define utarray_strdup_(x_) MPL_strdup(x_)
^
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:17:20:
note: expanded from macro 'MPL_strdup'
#define MPL_strdup strdup
^
./src/include/mpir_mem.h:100:51: note: expanded from macro 'strdup'
#define strdup(a) 'Error use MPL_strdup' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:225:
In file included from ./src/include/mpir_cvars.h:17:
In file included from ./src/include/mpitimpl.h:18:
./src/include/mpir_utarray.h:242:14: warning: multi-character
character constant [-Wmultichar]
if (*eltc) utarray_free_(*eltc);
^
./src/include/mpir_utarray.h:54:33: note: expanded from macro 'utarray_free_'
#define utarray_free_(x_) MPL_free(x_)
^
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:110:26:
note: expanded from macro 'MPL_free'
#define MPL_free(a) free((void *)(a))
^
./src/include/mpir_mem.h:92:27: note: expanded from macro 'free'
#define free(a) 'Error use MPL_free' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:225:
In file included from ./src/include/mpir_cvars.h:17:
In file included from ./src/include/mpitimpl.h:18:
./src/include/mpir_utarray.h:242:14: warning: character constant too
long for its type
./src/include/mpir_utarray.h:54:33: note: expanded from macro 'utarray_free_'
#define utarray_free_(x_) MPL_free(x_)
^
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:110:26:
note: expanded from macro 'MPL_free'
#define MPL_free(a) free((void *)(a))
^
./src/include/mpir_mem.h:92:27: note: expanded from macro 'free'
#define free(a) 'Error use MPL_free' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:225:
In file included from ./src/include/mpir_cvars.h:17:
In file included from ./src/include/mpitimpl.h:18:
./src/include/mpir_utarray.h:242:14: error: expected ';' after expression
./src/include/mpir_utarray.h:54:33: note: expanded from macro 'utarray_free_'
#define utarray_free_(x_) MPL_free(x_)
^
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:110:26:
note: expanded from macro 'MPL_free'
#define MPL_free(a) free((void *)(a))
^
./src/include/mpir_mem.h:92:50: note: expanded from macro 'free'
#define free(a) 'Error use MPL_free' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:225:
In file included from ./src/include/mpir_cvars.h:17:
In file included from ./src/include/mpitimpl.h:18:
./src/include/mpir_utarray.h:242:14: error: expected expression
./src/include/mpir_utarray.h:54:33: note: expanded from macro 'utarray_free_'
#define utarray_free_(x_) MPL_free(x_)
^
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:110:26:
note: expanded from macro 'MPL_free'
#define MPL_free(a) free((void *)(a))
^
./src/include/mpir_mem.h:92:51: note: expanded from macro 'free'
#define free(a) 'Error use MPL_free' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:61:29: warning: multi-character
character constant [-Wmultichar]
nIndirect = (int *) MPL_calloc(objmem->indirect_size, sizeof(int));
^
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:109:26:
note: expanded from macro 'MPL_calloc'
#define MPL_calloc(a,b) calloc((size_t)(a),(size_t)(b))
^
./src/include/mpir_mem.h:91:27: note: expanded from macro 'calloc'
#define calloc(a,b) 'Error use MPL_calloc' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:61:29: warning: character constant too
long for its type
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:109:26:
note: expanded from macro 'MPL_calloc'
#define MPL_calloc(a,b) calloc((size_t)(a),(size_t)(b))
^
./src/include/mpir_mem.h:91:27: note: expanded from macro 'calloc'
#define calloc(a,b) 'Error use MPL_calloc' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:61:29: error: expected ';' after expression
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:109:26:
note: expanded from macro 'MPL_calloc'
#define MPL_calloc(a,b) calloc((size_t)(a),(size_t)(b))
^
./src/include/mpir_mem.h:91:50: note: expanded from macro 'calloc'
#define calloc(a,b) 'Error use MPL_calloc' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:61:29: error: expected expression
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:109:26:
note: expanded from macro 'MPL_calloc'
#define MPL_calloc(a,b) calloc((size_t)(a),(size_t)(b))
^
./src/include/mpir_mem.h:91:51: note: expanded from macro 'calloc'
#define calloc(a,b) 'Error use MPL_calloc' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:117:9: warning: multi-character
character constant [-Wmultichar]
MPL_free(nIndirect);
^
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:110:26:
note: expanded from macro 'MPL_free'
#define MPL_free(a) free((void *)(a))
^
./src/include/mpir_mem.h:92:27: note: expanded from macro 'free'
#define free(a) 'Error use MPL_free' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:117:9: warning: character constant too
long for its type
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:110:26:
note: expanded from macro 'MPL_free'
#define MPL_free(a) free((void *)(a))
^
./src/include/mpir_mem.h:92:27: note: expanded from macro 'free'
#define free(a) 'Error use MPL_free' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:117:9: error: expected ';' after expression
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:110:26:
note: expanded from macro 'MPL_free'
#define MPL_free(a) free((void *)(a))
^
./src/include/mpir_mem.h:92:50: note: expanded from macro 'free'
#define free(a) 'Error use MPL_free' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:117:9: error: expected expression
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:110:26:
note: expanded from macro 'MPL_free'
#define MPL_free(a) free((void *)(a))
^
./src/include/mpir_mem.h:92:51: note: expanded from macro 'free'
#define free(a) 'Error use MPL_free' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:179:9: warning: multi-character
character constant [-Wmultichar]
MPL_free((*indirect)[i]);
^
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:110:26:
note: expanded from macro 'MPL_free'
#define MPL_free(a) free((void *)(a))
^
./src/include/mpir_mem.h:92:27: note: expanded from macro 'free'
#define free(a) 'Error use MPL_free' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:179:9: warning: character constant too
long for its type
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:110:26:
note: expanded from macro 'MPL_free'
#define MPL_free(a) free((void *)(a))
^
./src/include/mpir_mem.h:92:27: note: expanded from macro 'free'
#define free(a) 'Error use MPL_free' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:179:9: error: expected ';' after expression
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:110:26:
note: expanded from macro 'MPL_free'
#define MPL_free(a) free((void *)(a))
^
./src/include/mpir_mem.h:92:50: note: expanded from macro 'free'
#define free(a) 'Error use MPL_free' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:179:9: error: expected expression
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:110:26:
note: expanded from macro 'MPL_free'
#define MPL_free(a) free((void *)(a))
^
./src/include/mpir_mem.h:92:51: note: expanded from macro 'free'
#define free(a) 'Error use MPL_free' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:182:9: warning: multi-character
character constant [-Wmultichar]
MPL_free(indirect);
^
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:110:26:
note: expanded from macro 'MPL_free'
#define MPL_free(a) free((void *)(a))
^
./src/include/mpir_mem.h:92:27: note: expanded from macro 'free'
#define free(a) 'Error use MPL_free' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:182:9: warning: character constant too
long for its type
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:110:26:
note: expanded from macro 'MPL_free'
#define MPL_free(a) free((void *)(a))
^
./src/include/mpir_mem.h:92:27: note: expanded from macro 'free'
#define free(a) 'Error use MPL_free' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:182:9: error: expected ';' after expression
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:110:26:
note: expanded from macro 'MPL_free'
#define MPL_free(a) free((void *)(a))
^
./src/include/mpir_mem.h:92:50: note: expanded from macro 'free'
#define free(a) 'Error use MPL_free' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:182:9: error: expected expression
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:110:26:
note: expanded from macro 'MPL_free'
#define MPL_free(a) free((void *)(a))
^
./src/include/mpir_mem.h:92:51: note: expanded from macro 'free'
#define free(a) 'Error use MPL_free' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:249:30: warning: multi-character
character constant [-Wmultichar]
*indirect = (void *) MPL_calloc(indirect_num_blocks, sizeof(void *));
^
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:109:26:
note: expanded from macro 'MPL_calloc'
#define MPL_calloc(a,b) calloc((size_t)(a),(size_t)(b))
^
./src/include/mpir_mem.h:91:27: note: expanded from macro 'calloc'
#define calloc(a,b) 'Error use MPL_calloc' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:249:30: warning: character constant too
long for its type
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:109:26:
note: expanded from macro 'MPL_calloc'
#define MPL_calloc(a,b) calloc((size_t)(a),(size_t)(b))
^
./src/include/mpir_mem.h:91:27: note: expanded from macro 'calloc'
#define calloc(a,b) 'Error use MPL_calloc' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:249:30: error: expected ';' after expression
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:109:26:
note: expanded from macro 'MPL_calloc'
#define MPL_calloc(a,b) calloc((size_t)(a),(size_t)(b))
^
./src/include/mpir_mem.h:91:50: note: expanded from macro 'calloc'
#define calloc(a,b) 'Error use MPL_calloc' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:249:30: error: expected expression
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:109:26:
note: expanded from macro 'MPL_calloc'
#define MPL_calloc(a,b) calloc((size_t)(a),(size_t)(b))
^
./src/include/mpir_mem.h:91:51: note: expanded from macro 'calloc'
#define calloc(a,b) 'Error use MPL_calloc' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:264:26: warning: multi-character
character constant [-Wmultichar]
block_ptr = (void *) MPL_calloc(indirect_num_indices, obj_size);
^
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:109:26:
note: expanded from macro 'MPL_calloc'
#define MPL_calloc(a,b) calloc((size_t)(a),(size_t)(b))
^
./src/include/mpir_mem.h:91:27: note: expanded from macro 'calloc'
#define calloc(a,b) 'Error use MPL_calloc' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:264:26: warning: character constant too
long for its type
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:109:26:
note: expanded from macro 'MPL_calloc'
#define MPL_calloc(a,b) calloc((size_t)(a),(size_t)(b))
^
./src/include/mpir_mem.h:91:27: note: expanded from macro 'calloc'
#define calloc(a,b) 'Error use MPL_calloc' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:264:26: error: expected ';' after expression
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:109:26:
note: expanded from macro 'MPL_calloc'
#define MPL_calloc(a,b) calloc((size_t)(a),(size_t)(b))
^
./src/include/mpir_mem.h:91:50: note: expanded from macro 'calloc'
#define calloc(a,b) 'Error use MPL_calloc' :::
^
In file included from src/mpi/attr/attr_delete.c:8:
In file included from ./src/include/mpiimpl.h:228:
./src/include/mpir_handlemem.h:264:26: error: expected expression
/Users/m/local/src/mpich-master-v3.2-370-g0d6412303488/src/mpl/include/mpl_trmem.h:109:26:
note: expanded from macro 'MPL_calloc'
#define MPL_calloc(a,b) calloc((size_t)(a),(size_t)(b))
^
./src/include/mpir_mem.h:91:51: note: expanded from macro 'calloc'
#define calloc(a,b) 'Error use MPL_calloc' :::
^
18 warnings and 18 errors generated.
make[2]: *** [src/mpi/attr/lib_libpmpi_la-attr_delete.lo] Error 1
make[1]: *** [all-recursive] Error 1
Makefile:10270: recipe for target 'all' failed
gmake: *** [all] Error 2
On Thu, Aug 11, 2016 at 5:21 PM, Halim Amer <aamer at anl.gov> wrote:
> This should be related to the alignment problem reported before
> (http://lists.mpich.org/pipermail/discuss/2016-May/004764.html).
>
> We plan to include a fix in the 3.2.x bug fix release series. Meanwhile,
> please try the repo version (git.mpich.org/mpich.git), which should not
> suffer from this problem.
>
> --Halim
> www.mcs.anl.gov/~aamer
>
>
> On 8/11/16 8:48 AM, Mark Davis wrote:
>>
>> Hello, I'm running into a segfault when I run some relatively simple
>> MPI programs. In this particular case, I'm running a small program in
>> a loop that does MPI_Bcast, once per loop, within MPI_COMM_WORLD. The
>> buffer consists of just 7 doubles. I'm running with 6 procs on a
>> machine with 8 cores on OSX (Darwin - 15.6.0 Darwin Kernel Version
>> 15.6.0: Thu Jun 23 18:25:34 PDT 2016;
>> root:xnu-3248.60.10~1/RELEASE_X86_64 x86_64). When I run the same
>> program with a smaller number of procs, the error usually doesn't show
>> up. My compiler (both for compiling the MPICH source as well as my
>> application) is clang 3.8.1.
>>
>> When I run the same program on linux, also with MPICH-3.2 (I believe
>> the same exact source), compiled with gcc 5.3, I do not get this
>> error. This seems to be something I get only with
>>
>> gdb shows the following stack trace. I have a feeling that this has
>> something to do with my toolchain and/or libraries on my system given
>> that I never get this error on my other system (linux). However, it's
>> possible that there's an application bug as well.
>>
>> I'm running the MPICH-3.2 stable release; I haven't tried anything
>> from the repository yet.
>>
>> Does anyone have any ideas about what's going on here? I'm happy to
>> provide more details.
>>
>> Thank you,
>> Mark
>>
>>
>> Program received signal SIGSEGV, Segmentation fault.
>> MPID_Request_create () at src/mpid/ch3/src/ch3u_request.c:101
>> 101 req->dev.ext_hdr_ptr = NULL;
>> (gdb) bt full
>> #0 MPID_Request_create () at src/mpid/ch3/src/ch3u_request.c:101
>> No locals.
>> #1 0x00000001003ac4c9 in MPIDI_CH3U_Recvq_FDP_or_AEU
>> (match=<optimized out>, foundp=0x7fff5fbfe2bc) at
>> src/mpid/ch3/src/ch3u_recvq.c:830
>> proc_failure_bit_masked = <error reading variable
>> proc_failure_bit_masked (Cannot access memory at address 0x1)>
>> error_bit_masked = <error reading variable error_bit_masked
>> (Cannot access memory at address 0x1)>
>> prev_rreq = <optimized out>
>> channel_matched = <optimized out>
>> rreq = <optimized out>
>> #2 0x00000001003d1ffe in MPIDI_CH3_PktHandler_EagerSend
>> (vc=<optimized out>, pkt=0x1004b3fd8 <MPIU_DBG_MaxLevel>,
>> buflen=0x7fff5fbfe440, rreqp=0x7fff5fbfe438) at
>> src/mpid/ch3/src/ch3u_eager.c:629
>> mpi_errno = <error reading variable mpi_errno (Cannot access
>> memory at address 0x0)>
>> found = <error reading variable found (Cannot access memory at
>> address 0xefefefefefefefef)>
>> rreq = <optimized out>
>> data_len = <optimized out>
>> complete = <optimized out>
>> #3 0x00000001003f6045 in MPID_nem_handle_pkt (vc=<optimized out>,
>> buf=0x102ad07e0 "", buflen=<optimized out>) at
>> src/mpid/ch3/channels/nemesis/src/ch3_progress.c:760
>> len = 140734799800192
>> mpi_errno = <optimized out>
>> complete = <error reading variable complete (Cannot access
>> memory at address 0x1)>
>> rreq = <optimized out>
>> #4 0x00000001003f4e41 in MPIDI_CH3I_Progress
>> (progress_state=0x7fff5fbfe750, is_blocking=1) at
>> src/mpid/ch3/channels/nemesis/src/ch3_progress.c:570
>> payload_len = 4299898840
>> cell_buf = <optimized out>
>> rreq = <optimized out>
>> vc = 0x102ad07e8
>> made_progress = <error reading variable made_progress (Cannot
>> access memory at address 0x0)>
>> mpi_errno = <optimized out>
>> #5 0x000000010035386d in MPIC_Wait (request_ptr=<optimized out>,
>> errflag=<optimized out>) at src/mpi/coll/helper_fns.c:225
>> progress_state = {ch = {completion_count = -1409286143}}
>> mpi_errno = <error reading variable mpi_errno (Cannot access
>> memory at address 0x0)>
>> #6 0x0000000100353b10 in MPIC_Send (buf=0x100917c30,
>> count=4299945096, datatype=-1581855963, dest=<optimized out>,
>> tag=4975608, comm_ptr=0x1004b3fd8 <MPIU_DBG_MaxLevel>,
>> errflag=<optimized out>) at src/mpi/coll/helper_fns.c:302
>> mpi_errno = <optimized out>
>> request_ptr = 0x1004bf7e0 <MPID_Request_direct+1760>
>> #7 0x0000000100246031 in MPIR_Bcast_binomial (buffer=<optimized out>,
>> count=<optimized out>, datatype=<optimized out>, root=<optimized out>,
>> comm_ptr=<optimized out>, errflag=<optimized out>) at
>> src/mpi/coll/bcast.c:280
>> nbytes = <optimized out>
>> mpi_errno_ret = <optimized out>
>> mpi_errno = 0
>> comm_size = <optimized out>
>> rank = 2
>> type_size = <optimized out>
>> tmp_buf = 0x0
>> position = <optimized out>
>> relative_rank = <optimized out>
>> mask = <optimized out>
>> src = <optimized out>
>> status = <optimized out>
>> recvd_size = <optimized out>
>> dst = <optimized out>
>> #8 0x00000001002455a3 in MPIR_SMP_Bcast (buffer=<optimized out>,
>> count=<optimized out>, datatype=<optimized out>, root=<optimized out>,
>> comm_ptr=<optimized out>, errflag=<optimized out>) at
>> src/mpi/coll/bcast.c:1087
>> mpi_errno_ = <error reading variable mpi_errno_ (Cannot access
>> memory at address 0x0)>
>> mpi_errno = <optimized out>
>> mpi_errno_ret = <optimized out>
>> nbytes = <optimized out>
>> type_size = <optimized out>
>> status = <optimized out>
>> recvd_size = <optimized out>
>> #9 MPIR_Bcast_intra (buffer=0x100917c30, count=<optimized out>,
>> datatype=<optimized out>, root=1, comm_ptr=<optimized out>,
>> errflag=<optimized out>) at src/mpi/coll/bcast.c:1245
>> nbytes = <optimized out>
>> mpi_errno_ret = <error reading variable mpi_errno_ret (Cannot
>> access memory at address 0x0)>
>> mpi_errno = <optimized out>
>> type_size = <optimized out>
>> comm_size = <optimized out>
>> #10 0x000000010024751e in MPIR_Bcast (buffer=<optimized out>,
>> count=<optimized out>, datatype=<optimized out>, root=<optimized out>,
>> comm_ptr=0x0, errflag=<optimized out>) at src/mpi/coll/bcast.c:1475
>> mpi_errno = <optimized out>
>> #11 MPIR_Bcast_impl (buffer=0x1004bf7e0 <MPID_Request_direct+1760>,
>> count=-269488145, datatype=-16, root=0, comm_ptr=0x0,
>> errflag=0x1004bf100 <MPID_Request_direct>) at
>> src/mpi/coll/bcast.c:1451
>> mpi_errno = <optimized out>
>> #12 0x00000001000f3c24 in MPI_Bcast (buffer=<optimized out>, count=7,
>> datatype=1275069445, root=1, comm=<optimized out>) at
>> src/mpi/coll/bcast.c:1585
>> errflag = 2885681152
>> mpi_errno = <optimized out>
>> comm_ptr = <optimized out>
>> #13 0x0000000100001df7 in run_test<int> (my_rank=2,
>> num_ranks=<optimized out>, count=<optimized out>, root_rank=1,
>> datatype=@0x7fff5fbfeaec: 1275069445, iterations=<optimized out>) at
>> bcast_test.cpp:83
>> No locals.
>> #14 0x00000001000019cd in main (argc=<optimized out>, argv=<optimized
>> out>) at bcast_test.cpp:137
>> root_rank = <optimized out>
>> count = <optimized out>
>> iterations = <optimized out>
>> my_rank = 4978656
>> num_errors = <optimized out>
>> runtime_ns = <optimized out>
>> stats = {<std::__1::__basic_string_common<true>> = {<No data
>> fields>}, __r_ =
>> {<std::__1::__libcpp_compressed_pair_imp<std::__1::basic_string<char,
>> std::__1::char_traits<char>, std::__1::allocator<char> >::__rep,
>> std::__1::allocator<char>, 2>> = {<std::__1::allocator<char>> = {<No
>> data fields>}, __first_ = {{__l = {__cap_ = 17289301308300324847,
>> __size_ = 17289301308300324847, __data_ = 0xefefefefefefefef <error:
>> Cannot access memory at address 0xefefefefefefefef>}
>> _______________________________________________
>> discuss mailing list discuss at mpich.org
>> To manage subscription options or unsubscribe:
>> https://lists.mpich.org/mailman/listinfo/discuss
>>
> _______________________________________________
> discuss mailing list discuss at mpich.org
> To manage subscription options or unsubscribe:
> https://lists.mpich.org/mailman/listinfo/discuss
_______________________________________________
discuss mailing list discuss at mpich.org
To manage subscription options or unsubscribe:
https://lists.mpich.org/mailman/listinfo/discuss
More information about the discuss
mailing list