Mailing-List: contact mesos-dev-help@incubator.apache.org; run by ezmlm
Precedence: bulk
Reply-To: mesos-dev@incubator.apache.org
Content-Type: multipart/alternative;
	boundary="===============6210942215106654947=="
MIME-Version: 1.0
Subject: Re: Review Request: Updates and additions to the MPI framework
From: "Harvey Feng" <h.feng@berkeley.edu>
To: "Benjamin Hindman" <benh@berkeley.edu>,
 "Jessica" <jessicaesther@gmail.com>,
	"Charles Reiss" <woggling@gmail.com>
Date: Tue, 08 May 2012 01:29:06 -0000
Message-ID: <20120508012906.1539.35843@reviews.apache.org>
Cc: "mesos" <mesos-dev@incubator.apache.org>,
	"Harvey Feng" <h.feng@berkeley.edu>
In-Reply-To: <20120502132950.13266.79499@reviews.apache.org>
References: <20120502132950.13266.79499@reviews.apache.org>

--===============6210942215106654947==
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: quoted-printable


-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/4768/
-----------------------------------------------------------

(Updated 2012-05-08 01:29:06.075735)


Review request for mesos, Benjamin Hindman, Charles Reiss, and Jessica.


Changes
-------

-Updated some of the logic from the previous diff.
-Better usage of os.path.join()
-References to "nmpiexec*" have been changed to "mpiexec-mesos*", but the f=
ilenames still need to be changed...


Summary
-------

Some updates to point out:

-nmpiexec.py
  -> 'mpdallexit' should terminate all slaves' mpds in the ring. I moved 'd=
river.stop()' to statusUpdate() so that it stops when all tasks have been f=
inished, which occurs when the executor's launched mpd processes have all e=
xited. =

-startmpd.py
  -> Didn't remove cleanup(), and added code in shutdown() that manually ki=
lls mpd processes. They might be useful during abnormal (cleanup) and norma=
l (shutdown) framework/executor termination...I think. cleanup() still term=
inates all mpd's in the slave, but shutdown doesn't. =

  -> killtask() stops the mpd associated with the given tid. =

  -> Task states update nicely now. They correspond to the state of a task'=
s associated mpd process.
-Readme
  -> Included additional info on how to setup and run MPICH2 1.2 and nmpiex=
ec on OS X and Ubuntu/Linux


This addresses bug MESOS-183.
    https://issues.apache.org/jira/browse/MESOS-183


Diffs (updated)
-----

  frameworks/mpi/README.txt cdb4553 =

  frameworks/mpi/nmpiexec 517bdbc =

  frameworks/mpi/nmpiexec.py a5db9c0 =

  frameworks/mpi/startmpd.py 8eeba5e =

  frameworks/mpi/startmpd.sh 44faa05 =


Diff: https://reviews.apache.org/r/4768/diff


Testing
-------


Thanks,

Harvey


--===============6210942215106654947==--