Sorry about 'idx' vs 'index'.
In case Rolf is not correct about this being fixed, see below for the
topology object.
-Paul
(dbx) print *topology
*topology = {
nb_levels = 3736059629U
next_group_depth = 3736059629U
level_nbobjects = (3800392320U, 4294966655U, 1U, 1702192501U,
3792869728U, 4294966655U, 408U, 16777216U, 4428736U, 0, 5150816U, 0, 0, 0,
65U, 0, 0, 0, 842477617U, 859058744U, 808333362U, 1885566011U, 825175866U,
825111095U, 774909494U, 741356081U, 775042865U, 808335409U, 808595758U,
876164154U, 14390U, 0, 0, 0, 65U, 0, 0, 0, 5065504U, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 65U, 0, 0, 0, 1651664214U, 1953067887U,
1701585017U, 543974774U, 544370534U, 543516788U, 1953853298U, 1713398885U,
1701667186U, 1802661751U, 540026912U, 1869488189U, 1919252000U,
1769172834U, 2718068U, 0, 65U, 0, 4219982788U, 4294967295U, 3736059629U,
3736059629U, 3800400896U, 4294966655U, 1U, 0, 3800248320U, 4294966655U,
81U, 0, 16370U, 1072824320U, 0, 0, 0, 0, 65U, 0, 0, 0, 1852404304U,
1869881460U, 1701344288U, 1684957472U, 1952539497U, 1713398885U,
543517801U, 1025518888U, 1953701950U, 1953853284U, 539697196U, 1931492925U,
1919247476U, 10610U, 1835363691U, 1667326815U, 65U, 0, 0, 0, 1651664214U,
1953067887U, 1701585017U, 543974774U, 544370534U, 543516788U, 1713398372U,
1701667186U, 1802661751U, 540026912U)
levels = (0x726576206f6e203d, 0x29797469736f62,
0xfffffffffb87d42c, 0x41, (nil), 0x2072656874656857, 0x612070616d206f74,
0x206b6e617220646e, 0x65737365636f7270, 0x2d646e756f722073,
0x7962206e69626f72, 0x74690065726f6320, 0x2979, 0x41, 0x61636d5f75706367,
0x7469736f62726556, 0x206c6576656c2079, 0x2065687420726f66,
0x206d6d6f63707267, 0x726f77656d617266, 0x6e203d203028206b,
0x736f62726576206f, 0x29797469, 0x41, 0x180, 0x7469736f62726556,
0x206c6576656c2079, 0x2065687420726f66, 0x6d61726620736172,
0x3028206b726f7765, 0x6576206f6e203d20, 0x29797469736f6272, (nil), 0x41,
0x4d4dc0, 0x7469736f62726556, 0x206c6576656c2079, 0x2065687420726f66,
0x7266207370616d72, 0x206b726f77656d61, 0x206f6e203d203028,
0x7469736f62726576, 0x2979, 0x41, 0x6361635f6d656d6b, 0x2072656874656857,
0x6c70736964206f74, 0x6669642061207961, 0x727020656c626166,
0x616d20737365636f, 0x2072657466612070, 0x6f63207369207469, 0x64657475706d,
0x41, 0xfffffffffb87d42c, 0x2072656874656857, 0x612070616d206f74,
0x206b6e617220646e, 0x65737365636f7270, 0x2d646e756f722073,
0x7962206e69626f72, 0x786900746f6c7320, (nil), 0x41, (nil),
0x2072656874656857, 0x612070616d206f74, 0x206b6e617220646e,
0x65737365636f7270, 0x2d646e756f722073, 0x7962206e69626f72, 0x65646f6e20,
(nil), 0x41, (nil), 0x6f207265626d754e, 0x7420737570632066,
0x6f6620657375206f, 0x7220686361652072, 0x322d315b206b6e61,
0x6564282035312a2a, 0x29313d746c756166, 0x5d, 0x41, (nil),
0x6f207265626d754e, 0x7420737570632066, 0x6f6620657375206f,
0x7220686361652072, 0x322d315b206b6e61, 0x6564282035312a2a,
0x29313d746c756166, 0x6c6974736e72005d, 0x41, (nil), 0x2072656874656857,
0x6c70736964206f74, 0x7020656874207961, 0x6d20737365636f72,
0x7265746661207061, 0x6320736920746920, 0x64657475706d6f, 0x720, 0x41,
0xfffffffffba56f14, 0x70614d20414d414c, 0x7365636f7250203a,
0x74756f79616c2073, 0x6974617265746920, 0x726564726f206e6f,
0x6565532820676e69, 0x6e656d75636f6420, 0x296e6f69746174, 0x41, (nil),
0x17500000174, 0x17700000176, 0x17900000178, 0x17b0000017a, 0x650000017c,
(nil), 0x100000000000000, 0x6361635f6d656d6b, 0x41, (nil), 0x6200000061,
0x6400000063, 0x6600000065)
flags = 446676598887U
type_depth = (105, 1935762796, 1702256485, 1869181810,
-1306853266, -254, -74984404, -1, 65, 0, 0, 0)
ignored_types = (842477617, 859058744, 808333362, 1885566011,
825175866, 825111095, 774909494, 741356081, 775042865, 808335409,
808595758, 876164154)
is_thissystem = 1862285366
is_loaded = 2037672307
pid = 41
bridge_nbobjects = 0
bridge_level = 0x41
first_bridge = 0x6361635f64657263
last_bridge = 0x7469736f62726556
pcidev_nbobjects = 1701585017U
pcidev_level = 0x2065687420726f66
first_pcidev = 0x61726620736c646f
last_pcidev = 0x28206b726f77656d
osdev_nbobjects = 540876848U
osdev_level = 0x797469736f627265
first_osdev = 0x29
last_osdev = 0x41
binding_hooks = {
set_thisproc_cpubind = 0x720
get_thisproc_cpubind = 0x3334323832373031
set_thisthread_cpubind = 0x7063743b302e3032
get_thisthread_cpubind = 0x312e3237312f2f3a
set_proc_cpubind = 0x2c3032312e302e36
get_proc_cpubind = 0x302e38312e323731
set_thread_cpubind = 0x3439343a3032312e
get_thread_cpubind = 0x3836
get_thisproc_last_cpu_location = (nil)
get_thisthread_last_cpu_location = 0x41
get_proc_last_cpu_location = 0x4d51d0
set_thisproc_membind = 0x3334323832373031
get_thisproc_membind = 0x7063743b302e3032
set_thisthread_membind = 0x312e3237312f2f3a
get_thisthread_membind = 0x2c3032312e302e36
set_proc_membind = 0x302e38312e323731
get_proc_membind = 0x3439343a3032312e
set_area_membind = 0x6568003836
get_area_membind = (nil)
alloc = 0x41
alloc_membind = 0x6361635f6d656d6b
free_membind = 0x65706f2f706d742f
}
support = {
discovery = 0x7365732d69706d6e
cpubind = 0x68702d736e6f6973
membind = 0x7040766f72677261
}
userdata_export_cb = 0x5f30322d6a2d7063
userdata_import_cb = 0x2f30373336312f30
first_osdist = 0x302f30
last_osdist = 0xfffffffffba56f14
backends = 0x41
}
On Wed, Dec 17, 2014 at 12:54 PM, Rolf vandeVaart <rvandeva...@nvidia.com>
wrote:
>
> I think this has already been fixed by Ralph this morning. I had
> observed the same issue but is now gone.
>
>
>
> *From:* devel [mailto:devel-boun...@open-mpi.org] *On Behalf Of *Brice
> Goglin
> *Sent:* Wednesday, December 17, 2014 3:53 PM
> *To:* de...@open-mpi.org
> *Subject:* Re: [OMPI devel] Solaris/x86-64 SEGV with 1.8-latest
>
>
>
> Le 17/12/2014 21:43, Paul Hargrove a écrit :
>
>
>
> Dbx gives me
>
> t@1 (l@1) terminated by signal SEGV (no mapping at the fault address)
>
> Current function is opal_hwloc172_hwloc_get_obj_by_depth
>
> 74 return topology->levels[depth][idx];
>
> (dbx) where
>
> current thread: t@1
>
> =>[1] opal_hwloc172_hwloc_get_obj_by_depth(topology = 0x4d49e0, depth = 0,
> idx = 0), line 74 in "traversal.c"
>
> [2] opal_hwloc172_hwloc_get_root_obj(topology = 0x4d49e0), line 118 in
> "helper.h"
>
> [3] opal_hwloc_base_get_nbobjs_by_type(topo = 0x4d49e0, target =
> OPAL_HWLOC172_hwloc_OBJ_CORE, cache_level = 0, rtype = '\003'), line 833 in
> "hwloc_base_util.c"
>
> [4] orte_rmaps_rr_byobj(jdata = 0x43c940, app = 0x483fe0, node_list =
> 0xfffffd7fffdff4b0, num_slots = 2, num_procs = 2U, target =
> OPAL_HWLOC172_hwloc_OBJ_CORE, cache_level = 0), line 495 in
> "rmaps_rr_mappers.c"
>
> [5] orte_rmaps_rr_map(jdata = 0x43c940), line 165 in "rmaps_rr.c"
>
> [6] orte_rmaps_base_map_job(fd = -1, args = 4, cbdata = 0x4a3300), line
> 277 in "rmaps_base_map_job.c"
>
> [7] event_process_active_single_queue(0x0, 0x0, 0x0, 0x0, 0x0, 0x0), at
> 0xfffffd7fe453afbc
>
> [8] event_process_active(0x0, 0x0, 0x0, 0x0, 0x0, 0x0), at
> 0xfffffd7fe453b361
>
> [9] opal_libevent2021_event_base_loop(0x0, 0x0, 0x0, 0x0, 0x0, 0x0), at
> 0xfffffd7fe453bc79
>
> [10] orterun(argc = 9, argv = 0xfffffd7fffdffa58), line 1081 in
> "orterun.c"
>
> [11] main(argc = 9, argv = 0xfffffd7fffdffa58), line 13 in "main.c"
>
> (dbx) print depth
>
> depth = 0
>
> (dbx) print index
>
> index = 0xfffffd7fff19c174
>
>
>
> Pretty sure that index value is bogus.
>
>
>
>
> I see "idx" instead of "index" in the code above. index may be a pointer
> to the "index()" function in your standard library?
> Anyway, depth=0 and idx=0 is totally valid, especially when called from
> hwloc_get_root_obj(). Something bad happened to the topology object? Can
> you print the contents of topology and topology->nblevels and
> topology->levels ?
>
> Brice
> ------------------------------
> This email message is for the sole use of the intended recipient(s) and
> may contain confidential information. Any unauthorized review, use,
> disclosure or distribution is prohibited. If you are not the intended
> recipient, please contact the sender by reply email and destroy all copies
> of the original message.
> ------------------------------
>
> _______________________________________________
> devel mailing list
> de...@open-mpi.org
> Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/devel
> Link to this post:
> http://www.open-mpi.org/community/lists/devel/2014/12/16652.php
>
--
Paul H. Hargrove phhargr...@lbl.gov
Computer Languages & Systems Software (CLaSS) Group
Computer Science Department Tel: +1-510-495-2352
Lawrence Berkeley National Laboratory Fax: +1-510-486-6900
