Brian Barrett c39ba3e2da * re-enable poll_recalc so that it triggers the recalc of the signals ...

properly.  This fixes the random hangs that we were seeing this morning
  on Linux that were a result of fixing the thread deadlock yesterday.
  (worked great on my OS X box, which uses select() instead of poll()).

This commit was SVN r6730.

2005-08-04 14:05:46 +00:00

..

compat

Initial population of the opal tree

2005-07-02 13:43:20 +00:00

config

Initial population of the opal tree

2005-07-02 13:43:20 +00:00

sample

* rename ompi_event to opal_event

2005-07-03 23:09:55 +00:00

test

* rename ompi_event to opal_event

2005-07-03 23:09:55 +00:00

WIN32-Code

* rename ompi_event to opal_event

2005-07-03 23:09:55 +00:00

WIN32-Prj

Initial population of the opal tree

2005-07-02 13:43:20 +00:00

.compile_files

Initial population of the opal tree

2005-07-02 13:43:20 +00:00

epoll_sub.c

Initial population of the opal tree

2005-07-02 13:43:20 +00:00

epoll.c

* rename ompi_event to opal_event

2005-07-03 23:09:55 +00:00

err.c

Initial population of the opal tree

2005-07-02 13:43:20 +00:00

event.3

Initial population of the opal tree

2005-07-02 13:43:20 +00:00

event.c

Bunch more updates from operation Red Storm:

2005-07-14 18:05:30 +00:00

event.h

* rename ompi_event to opal_event

2005-07-03 23:09:55 +00:00

evsignal.h

* rename ompi_event to opal_event

2005-07-03 23:09:55 +00:00

kqueue.c

* rename ompi_event to opal_event

2005-07-03 23:09:55 +00:00

Makefile.am

First cut at Makefile.am changes

2005-07-02 14:08:19 +00:00

poll.c

* re-enable poll_recalc so that it triggers the recalc of the signals

2005-08-04 14:05:46 +00:00

rtsig.c

* rename ompi_event to opal_event

2005-07-03 23:09:55 +00:00

select.c

* rename ompi_output to opal_output

2005-07-03 23:31:27 +00:00

signal.c

* fix deadlock in signal add code. Should not call the event_loop from

2005-08-03 14:10:55 +00:00