Skip to content

Conversation

@rhc54
Copy link
Contributor

@rhc54 rhc54 commented Apr 5, 2016

Allow definition of CLI options by environment. Refactor orterun to mesh with the orted_submit code, thus improving code reuse. Eliminate the orte-submit tool as orterun can now meet that need.

@hppritcha
Copy link
Member

bot:retest

@rhc54
Copy link
Contributor Author

rhc54 commented Apr 5, 2016

I was seeing some weirdness from github in general - took me several tries to get the updated branch to appear in my repo. So these failures may just be another symptom of something going on with github today.

@rhc54
Copy link
Contributor Author

rhc54 commented Apr 5, 2016

bot:retest

/* if this job is being launched against a fixed DVM, then there is
* nothing for us to do - the DVM will stand as is */
if (orte_get_attribute(&jdata->attributes, ORTE_JOB_FIXED_DVM, NULL, OPAL_BOOL)) {
opal_output(0, "DVM");
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I bet this line was leftover debugging. Probably needs to be removed.

@rhc54 rhc54 self-assigned this Apr 6, 2016
@hppritcha
Copy link
Member

What does the label stand for?

@rhc54
Copy link
Contributor Author

rhc54 commented Apr 6, 2016

It means this is "Work-In-Progress, Do-Not-Merge". I've asked some folks to check the branch to ensure it provides the basic operations they were asking for, and then it needs some cleanup before it will be ready. This PR just lets us track that the changes aren't breaking anything (at least, per Jenkins) while we work on it, and gives others a "heads up".

@rhc54
Copy link
Contributor Author

rhc54 commented Apr 6, 2016

Let me provide more clarity as to what we are attempting to do so others can perhaps contribute or at least review with context. The objective of this effort is to allow tools to "mimic" a variety of environments. As an example, we might want mpiexec to take the options currently employed by Platform MPI so that users transitioning from Platform to OMPI will not have to modify their scripts.

These changes allow the selected component to define the command line options as they like, and then they will parse the actual command line against that definition.

Prior changes provide the ability to "stack" these definitions, so the framework stubs will cycle across the components in priority order to allow them to:

  • detect if they were specifically identified, or if they detect that we are in an environment where they should be used;
  • add their command line option definitions to the overall definition

So you could create a tool, for example, that has common options regardless of environment, and then have schizo add the environment-specific options.

HTH

…ironment. Refactor orterun to mesh with the orted_submit code, thus improving code reuse. Eliminate the orte-submit tool as orterun can now meet that need.

Cleanups per @jjhursey review
@rhc54
Copy link
Contributor Author

rhc54 commented May 1, 2016

Not sure what this PR has to do with the mindist mapper, so let's try this again

@rhc54
Copy link
Contributor Author

rhc54 commented May 1, 2016

bot:retest

@rhc54
Copy link
Contributor Author

rhc54 commented May 1, 2016

looks like there is a problem on the mellanox jenkins server - getting random errors, this time a memory allocation problem in the tcp btl.

@rhc54
Copy link
Contributor Author

rhc54 commented May 1, 2016

Verified with MTT:

+-------------+-----------------+-------------+----------+------+------+----------+------+--------------------------------------------------------------------------+
| Phase       | Section         | MPI Version | Duration | Pass | Fail | Time out | Skip | Detailed report                                                          |
+-------------+-----------------+-------------+----------+------+------+----------+------+--------------------------------------------------------------------------+
| MPI Install | my installation | 3.0.0a1     | 00:01    | 1    |      |          |      | MPI_Install-my_installation-my_installation-3.0.0a1-my_installation.html |
| Test Build  | trivial         | 3.0.0a1     | 00:00    | 1    |      |          |      | Test_Build-trivial-my_installation-3.0.0a1-my_installation.html          |
| Test Build  | ibm             | 3.0.0a1     | 00:40    | 1    |      |          |      | Test_Build-ibm-my_installation-3.0.0a1-my_installation.html              |
| Test Build  | intel           | 3.0.0a1     | 01:14    | 1    |      |          |      | Test_Build-intel-my_installation-3.0.0a1-my_installation.html            |
| Test Build  | onesided        | 3.0.0a1     | 00:04    | 1    |      |          |      | Test_Build-onesided-my_installation-3.0.0a1-my_installation.html         |
| Test Build  | java            | 3.0.0a1     | 00:02    | 1    |      |          |      | Test_Build-java-my_installation-3.0.0a1-my_installation.html             |
| Test Build  | orte            | 3.0.0a1     | 00:01    | 1    |      |          |      | Test_Build-orte-my_installation-3.0.0a1-my_installation.html             |
| Test Run    | trivial         | 3.0.0a1     | 00:06    | 6    |      |          |      | Test_Run-trivial-my_installation-3.0.0a1-my_installation.html            |
| Test Run    | ibm             | 3.0.0a1     | 09:32    | 380  |      |          |      | Test_Run-ibm-my_installation-3.0.0a1-my_installation.html                |
| Test Run    | spawn           | 3.0.0a1     | 00:09    | 6    | 1    |          |      | Test_Run-spawn-my_installation-3.0.0a1-my_installation.html              |
| Test Run    | loopspawn       | 3.0.0a1     | 10:02    | 1    |      |          |      | Test_Run-loopspawn-my_installation-3.0.0a1-my_installation.html          |
| Test Run    | intel           | 3.0.0a1     | 24:07    | 474  |      |          | 4    | Test_Run-intel-my_installation-3.0.0a1-my_installation.html              |
| Test Run    | intel_skip      | 3.0.0a1     | 12:08    | 431  |      |          | 47   | Test_Run-intel_skip-my_installation-3.0.0a1-my_installation.html         |
| Test Run    | onesided        | 3.0.0a1     | 01:30    | 30   |      | 2        |      | Test_Run-onesided-my_installation-3.0.0a1-my_installation.html           |
| Test Run    | java            | 3.0.0a1     | 00:00    | 1    |      |          |      | Test_Run-java-my_installation-3.0.0a1-my_installation.html               |
| Test Run    | orte            | 3.0.0a1     | 00:45    | 19   |      |          |      | Test_Run-orte-my_installation-3.0.0a1-my_installation.html               |
+-------------+-----------------+-------------+----------+------+------+----------+------+--------------------------------------------------------------------------+


    Total Tests:    1358
    Total Failures: 3
    Total Passed:   1355
    Total Duration: 3621 secs. (01:00:21)

@rhc54 rhc54 merged commit 2fa8b6c into open-mpi:master May 1, 2016
@rhc54 rhc54 deleted the topic/schizo branch May 1, 2016 22:09
@rhc54 rhc54 restored the topic/schizo branch May 6, 2016 03:48
@rhc54 rhc54 deleted the topic/schizo branch May 21, 2016 14:07
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants