1
1

8 Коммитов

Автор SHA1 Сообщение Дата
Brian Barrett
566a050c23 Next step in the project split, mainly source code re-arranging
- move files out of toplevel include/ and etc/, moving it into the
    sub-projects
  - rather than including config headers with <project>/include, 
    have them as <project>
  - require all headers to be included with a project prefix, with
    the exception of the config headers ({opal,orte,ompi}_config.h
    mpi.h, and mpif.h)

This commit was SVN r8985.
2006-02-12 01:33:29 +00:00
Brian Barrett
03f6a8529c * Fix situation where we were unlocking a mutex we didn't own in an error
cleanup code in the signal part of the event library
* Only attempt to forward standard input if we have a controlling terminal
  (isatty() returns 1) and we are the foreground process OR we do not have
  a controlling terminal (isatty() returns 0).  If we have a controlling
  terminal, check at each SIGCONT if we should change our forwarding,
  since our foreground / background status may have changed.

  Unfortunately, there isn't a great way in the iof framework to know if
  we are capturing a starter's stdin.  Use the logic that if it's a source
  AND tagged as standard input, it's a starter's stdin.  This seems to
  work for all the common usages.

Both these need to go to the v1.0 branch.

This commit was SVN r8894.
2006-02-04 23:26:58 +00:00
Brian Barrett
11932e89d5 Fix nasty bug Josh was seeing where cntl-c wasn't working when orterun hangs up
in finalize after the first cntl-c is sent.

If the signal delete function was called while the signal set was blocked (which
is really most of the time in OMPI), the signal handler would be set to default
and the event library sigset modified, but the signal would never be unblocked.
Now we unblock the signal after reseting the handler...

This commit was SVN r7623.
2005-10-04 19:01:13 +00:00
Brian Barrett
124850d1c5 * fix deadlock in signal add code. Should not call the event_loop from
a function that has the lock.  Instead, recalculate the pending
  events directly.  Same effect, but less deadlock.

This commit was SVN r6720.
2005-08-03 14:10:55 +00:00
Brian Barrett
a13166b500 * rename ompi_output to opal_output
This commit was SVN r6329.
2005-07-03 23:31:27 +00:00
Brian Barrett
23b687b0f4 * rename ompi_event to opal_event
This commit was SVN r6328.
2005-07-03 23:09:55 +00:00
Brian Barrett
39dbeeedfb * rename locking code from ompi to opal
This commit was SVN r6327.
2005-07-03 22:45:48 +00:00
Jeff Squyres
3a9179a0d7 Initial population of the opal tree
This commit was SVN r6267.
2005-07-02 13:43:20 +00:00