Re: [O-MPI devel] Modification to triggers

2006-02-09 Thread Ralph H. Castain
Hmmmyuck! I'll take a look - will set it back to what it was 
before in the interim.


Thanks
Ralph

At 07:05 AM 2/9/2006, you wrote:

On Feb 8, 2006, at 12:46 PM, Ralph H. Castain wrote:

> In addition, I took advantage of the change to fix something Brian
> had flagged in the orte/mca/rmgr/urm/rmgr_urm.c file where he noted
> that the wireup of stdin for io forwarding should occur at the LAUNCH
> stage (as opposed to the STG1 stage gate where it was occurring).
> Given the availability of the new triggers, I changed that to conform
> to his noted request.
>
> Brian: please check that code to ensure I did this correctly.

I can't figure out exactly what is going on, but it looks like this
change broke standard input forwarding.  I currently have it traced
back (via printf debugging) to the fact that the
orte_rmgr_urm_wireup_callback() callback never gets triggered in
mpirun, so the wireup_stdin() function is never called and we never
start pushing mpirun's standard input into the iof system.

At that point, we fall into parts of the code with which I'm not too
familiar, so I have to hand this one back to you ;).

Brian


--
   Brian Barrett
   Open MPI developer
   http://www.open-mpi.org/


___
devel mailing list
de...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/devel





Re: [O-MPI devel] Modification to triggers

2006-02-09 Thread Brian Barrett

On Feb 8, 2006, at 12:46 PM, Ralph H. Castain wrote:


In addition, I took advantage of the change to fix something Brian
had flagged in the orte/mca/rmgr/urm/rmgr_urm.c file where he noted
that the wireup of stdin for io forwarding should occur at the LAUNCH
stage (as opposed to the STG1 stage gate where it was occurring).
Given the availability of the new triggers, I changed that to conform
to his noted request.

Brian: please check that code to ensure I did this correctly.


I can't figure out exactly what is going on, but it looks like this  
change broke standard input forwarding.  I currently have it traced  
back (via printf debugging) to the fact that the  
orte_rmgr_urm_wireup_callback() callback never gets triggered in  
mpirun, so the wireup_stdin() function is never called and we never  
start pushing mpirun's standard input into the iof system.


At that point, we fall into parts of the code with which I'm not too  
familiar, so I have to hand this one back to you ;).


Brian


--
  Brian Barrett
  Open MPI developer
  http://www.open-mpi.org/




[O-MPI devel] Modification to triggers

2006-02-08 Thread Ralph H. Castain

Hi all

As you'll see in my latest commit, I have made a slight modification 
to the standard triggers that ensures we define them for ALL of the 
process and job states. This will now allow users to subscribe to 
triggers (for example) on all processes achieving INIT, LAUNCH, and 
RUNNING states, if they want to do something when that happens.


I modified the way we were defining the subscriptions (in 
orte/mca/rmgr/base/rmgr_base_stage_gate.c) to allow a caller to 
define which standard triggers they wanted to know about. This 
avoided overburdening the launch system and orterun with callbacks in 
which they have no interest.


In addition, I took advantage of the change to fix something Brian 
had flagged in the orte/mca/rmgr/urm/rmgr_urm.c file where he noted 
that the wireup of stdin for io forwarding should occur at the LAUNCH 
stage (as opposed to the STG1 stage gate where it was occurring). 
Given the availability of the new triggers, I changed that to conform 
to his noted request.


Brian: please check that code to ensure I did this correctly.

As always, please let me know if you encounter any problems. I will 
continue to test it myself as best I can.

Ralph