Mike Dubman 21be95c9b5 Initialize sm global variables in mca_btl_sm_component_open(), because they are destructed in mca_btl_sm_component_close(), and init() function might not be called or fail. ...

For exammple, mca_btl_sm.knem_fd remained 0, and mca_btl_sm_component_close() ended up doing closing fd 0 which belongs to someone else.

fixed by Yossi, reviewed by miked
cmr=v1.7.4:reviewer=ompi-rm1.7

This commit was SVN r29875.

2013-12-13 06:01:24 +00:00

..

base

Chnage some CUDA configure code and macro names per review request by jsquyres in ticket #3880.

2013-12-06 14:35:10 +00:00

openib

Cleanup udcm structures to avoid issues with nesting structures with

2013-12-12 05:24:37 +00:00

portals4

Remove the proc_pml and proc_bml fields from ompi_proc_t and replace with a

2013-08-30 16:54:55 +00:00

scif

btl/scif: do not return resource busy if we started a connection attempt.

2013-11-11 19:36:34 +00:00

sctp

Silence few warnings.

2013-08-06 09:38:30 +00:00

self

rename ompi_free_list operations to _mt, as per discussions at last face to face meeting

2013-07-08 22:07:52 +00:00

sm

Initialize sm global variables in mca_btl_sm_component_open(), because they are destructed in mca_btl_sm_component_close(), and init() function might not be called or fail.

2013-12-13 06:01:24 +00:00

smcuda

Various minor changes to bring smcuda up to date with sm.

2013-11-07 19:45:56 +00:00

tcp

Revert r29594. That was just plain wrong. Sorry about workday configure change.

2013-11-05 14:45:56 +00:00

template

rename ompi_free_list operations to _mt, as per discussions at last face to face meeting

2013-07-08 22:07:52 +00:00

ugni

Add support for the udreg registration cache and dynamics on XE/XK/XC.

2013-11-18 04:58:37 +00:00

usnic

Technically, the PORT_ACTIVE is not a "bad" event.

2013-12-09 20:45:55 +00:00

vader

Make btl/vader valgrind safe.

2013-10-22 15:33:32 +00:00

btl.h

Chnage some CUDA configure code and macro names per review request by jsquyres in ticket #3880.

2013-12-06 14:35:10 +00:00

Makefile.am

Fix mistake that came in via the ompi-agen tree in r23764. The mistake wasn't part of the core autogen upgrade; it was an additional 'bonus' cleanup. Oops. The mistake will always create a set of directories under installdir, even if you do not --with-devel-headers. The set of directories will be empty, but still -- they should not be there at all. This commit fixes that -- the directories are not created at all if you do not --with-devel-headers

2010-09-24 22:53:28 +00:00