1
1

3266 Коммитов

Автор SHA1 Сообщение Дата
Nathan Hjelm
b308afa8fd btl/openib: remove derived btl segment type
The derived segment type (btl_openib_segment_t) was intended to store
the registration info needed for put and get. In BTL 3.0 this is no
longer required. I intended to remove this type as part of
open-mpi/ompi@74f1af4548 .

Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
2015-03-10 14:41:15 -06:00
Jeff Squyres
cbd99d5f60 libfabric: update to Github upstream 1b4bb2285b
Get a usnic bug fix.
2015-03-10 12:09:02 -07:00
Jeff Squyres
d97551bdb1 usnic: endpoint type hint moved to a sub-struct
Update to match new libfabric API/structure change.
2015-03-10 09:47:41 -07:00
Jeff Squyres
1a1be2efa0 libfabric: update to Github upstream 7095f3dc 2015-03-10 09:47:40 -07:00
Jeff Squyres
afec1454f5 usnic: only setup the connectivity checker if we have modules
If we ended up with no modules (e.g., all usnic devices were
excluded), there was a race condition in that the connectivity agent
could tear down its local socket before one or more of the local
clients saw it.  Therefore, the local clients would timeout waiting
for the socket to appear.

So move the connectivity checker init later in the bootstrapping
process (it *must* be setup before module_init()), and have it only
invoked if we actually ended up with one or more modules.
2015-03-10 07:43:20 -07:00
Jeff Squyres
06accb721c usnic: ensure to free all resources if no usnic BTLs found
If all usnic devices are excluded, then we need to ensure the error
path includes freeing the filter.

This was Coverity CID 1288085
2015-03-10 07:43:20 -07:00
Jeff Squyres
8fef4e865f dl dlopen: fix use-after-free
Re-structure the loop looking for duplicates a little so that we only
have a single free of the string that happens regardless of whether we
found a duplicate or not.

This was Coverity CID 1288090
2015-03-10 07:43:20 -07:00
Jeff Squyres
3efb5f56ae dl dlopen: ensure dirs is not NULL
opal_argv_split() may have returned NULL.

This was Coverity CID 1288088
2015-03-10 07:43:20 -07:00
Jeff Squyres
86968dcdda dl dlopen: fix resource leak
closedir() was one block higher than it should have been.

This was Coverity CID 1288087.
2015-03-10 07:43:20 -07:00
Jeff Squyres
546ad3f060 dl dlopen: free resources upon error
Ensure to take the right path out upon errors (that will free any
pending resources).

This was Coverity CID 1288086
2015-03-10 07:43:19 -07:00
Rolf vandeVaart
49b5eb6c91 Fix missing initialization of variable 2015-03-10 10:33:27 -04:00
Gilles Gouaillardet
dc0bc756dc iof/base: fix misc memory leak
as reported by Coverity with CID 1196732
2015-03-10 14:37:53 +09:00
Gilles Gouaillardet
f7f7fa73dd opal_cr: fix incorrect NULL assignment
as reported by Coverity with CID 1288084
2015-03-10 12:06:57 +09:00
Jeff Squyres
4b2cba46f4 usnic: fix bootstrap error paths
Fix previously-unfinished error paths during startup/bootstrapping.
Instead of just blindly continuing on when an fi_* function call
fails, opal_show_help and skip that device.

Also, only check the usnic config minimums once.  They're VIC-wide and
won't change on a per-device basis -- we only need to check them once.

Fixes CSCut19179.
2015-03-09 16:57:41 -07:00
Jeff Squyres
914880a368 libtldl: remove libltdl from the tree
The libltdl interface has been completely replaced by the OPAL DL
framework (i.e., the opal_dl interface).

Fixes open-mpi/ompi#311
2015-03-09 08:18:14 -07:00
Jeff Squyres
0a2767a5d3 opal lt_interface: remove in favor of opal_dl interface 2015-03-09 08:18:13 -07:00
Jeff Squyres
1995f6beba cuda: convert to opal_dl interface 2015-03-09 08:18:13 -07:00
Jeff Squyres
a9d86129c6 mca base: convert to opal_dl interface 2015-03-09 08:16:55 -07:00
Jeff Squyres
39364d315c libltdl: dl component based on libltdl
Works on any system that libltdl supports and has ltdl.h and libltdl
available.
2015-03-09 08:16:55 -07:00
Jeff Squyres
7d340c0c26 dlopen: simple dl component based on POSIX dlopen
Works on systems with dlopen (e.g., Linux and OS X).  It requires
dlfcn.h and libdl, which many systems have installed by default.
2015-03-09 08:16:55 -07:00
Jeff Squyres
e81c070ef0 dl framework: new dynamic loader framework
Embedding libltdl without the use of Libtool bootstrapping has
proven... difficult.  Instead, create a new simple "dl" framework.  It
only provides 4 functions:

- open a DSO (very similar to lt_dlopenadvise())
- lookup a symbol in a previously-opened DSO (very similar to lt_dlsym())
- close a previously-opened DSO (very similar to lt_dlclose())
- iterate over all files in a directory (very similar to ld_dlforeachfile())

There will be follow-on commits with a simple dlopen-based component
(nowhere near as complete/functional as libltdl, but good enough for
Linux and OS X), and a libltdl-based component for all other
platforms.

The intent is that the dlopen-based component can be built by default
in almost all cases.  But if libltdl is available, that component will
be built.  End result: we still get DSO-based functionality by default
in (almost?) all cases.  Without embedding libltdl.  Which is what we
want.
2015-03-09 08:16:55 -07:00
Gilles Gouaillardet
1746e23f11 opal/cr: fix misc memory leak and error case
as reported by Coverity with CIDs 71858 and 710640
2015-03-09 19:28:52 +09:00
Gilles Gouaillardet
2789d782ab timer/linux: fix insecure data handling
as reported by Coverity with CID 1269923
2015-03-09 19:14:56 +09:00
Gilles Gouaillardet
307a33991c opal/dss_unpack: correctly handle some bozo cases
as reported by Coverity with CIDs 1269987 and 1269988
2015-03-09 14:24:00 +09:00
Rolf vandeVaart
237c268a09 Add extra check during cleanup to make sure we really should clean up the CUDA resources. 2015-03-06 13:12:19 -05:00
Gilles Gouaillardet
da90ed4483 opal/compress: remove misc dead code
as reported by Coverity with CIDs 71856,
1269714, 1269715, 1269717, 1269718, 1269723, 1269724
2015-03-06 15:34:08 +09:00
Gilles Gouaillardet
5b41de4886 opal/dss: fix memory allocation in opal_dss_copy_null
as reported by Coverity with CID 71915
2015-03-06 15:15:11 +09:00
Gilles Gouaillardet
521317341d btl/openib: fix a double free
as reported by Coverity with CID 1287033
2015-03-06 14:58:11 +09:00
George Bosilca
5905bd2ff9 As the pStack pointer changes during the execution it is not
safe to free it. Instead, keep a copy of the original location
to be able to free the correct memory region.
2015-03-05 13:36:21 -05:00
George Bosilca
75479c0f17 Fix some typos. 2015-03-05 12:59:58 -05:00
George Bosilca
3c489ea5d5 Use malloc instead of alloca as some users could use very large arrays
of datatypes. Thanks Bogdan Sataric for the bug report.
2015-03-05 12:24:28 -05:00
Alina Sklarevich
1560ed9761 initialize opal_common_verbs_want_fork_support to -1.
This way, if the call to ibv_fork_init() fails, the job will still
continue.
2015-03-05 14:29:09 +02:00
Gilles Gouaillardet
e1cc931e1b btl/tcp: silence CID 710616 2015-03-05 14:20:08 +09:00
Gilles Gouaillardet
852dbafd51 mca/base: fix misc memory leaks
as reported by Coverity with CIDs 710628, 1196713 and 1269855
2015-03-05 14:06:18 +09:00
Gilles Gouaillardet
134c866aa9 btl/openib: fix misc memory leaks
as reported by Coverity with CIDs 1269848, 1269852 and 1269862
2015-03-05 14:06:18 +09:00
Gilles Gouaillardet
d1b2f043ff fix misc memory leaks
as already reported by Coverity with CIDs
71818, 71819, 72250, 715767, 1196749 and 1274002
2015-03-05 13:58:05 +09:00
Mike Dubman
171d674ca4 Merge pull request #441 from open-mpi/revert-438-topic/use_opal_common_verbs_want_fork_support
Revert "create the opal_common_verbs_want_fork_support parameter."
2015-03-04 10:13:00 +02:00
Gilles Gouaillardet
f43b5b46ee btl/openib: fix heterogeneous support
Thanks @bosilca for the pointer
2015-03-04 13:53:05 +09:00
Gilles Gouaillardet
81b0444ef2 btl/openib: fix comment syntax, no code change
and silence gcc warning about nested comments
2015-03-04 11:24:14 +09:00
Rolf vandeVaart
edf58eb549 Implement CUDA-aware workaround while fork support worked out 2015-03-03 09:50:01 -05:00
Mike Dubman
98503b56e0 Revert "create the opal_common_verbs_want_fork_support parameter." 2015-03-03 14:28:31 +02:00
Mike Dubman
cc7caf699e Merge pull request #438 from alinask/topic/use_opal_common_verbs_want_fork_support
create the opal_common_verbs_want_fork_support parameter.
2015-03-02 07:43:37 +02:00
Gilles Gouaillardet
04a0438b56 sec/munge: send NULL terminated strings 2015-03-02 12:19:46 +09:00
Alina Sklarevich
8fe42f1bc1 create the opal_common_verbs_want_fork_support parameter.
call the opal_common_verbs_mca_register function to make sure that
opal_common_verbs_want_fork_support mca parameter is created and therefore
can be used to control the fork support.
2015-03-01 17:40:49 +02:00
Jeff Squyres
336626dafe spelling: trivial spelling fix
s/interupted/interrupted/gi
2015-02-27 18:30:43 -08:00
Jeff Squyres
4f1139590f datatypes: trivial spelling fix
s/commited/committed/gi
2015-02-27 18:16:01 -08:00
Ralph Castain
d81c372ea2 Remove the "forwarding" of envars when direct launched - there aren't any envars we can forward under that use-case 2015-02-27 12:19:48 -08:00
Rolf vandeVaart
e48bc77342 Fix the coverity fix 2015-02-27 12:49:44 -05:00
Rolf vandeVaart
cfe91d4d0f Fix compile error for CUDA-aware by using new fork MCA parameter. 2015-02-27 10:00:46 -05:00
Gilles Gouaillardet
e0026224e7 pstat linux: close the files
as reported by Coverity with CID 71983
2015-02-27 19:48:01 +09:00