1
1
openmpi/orte/mca/odls/default/help-orte-odls-default.txt
Ralph Castain 6310361532 At long last, the fabled revision to the affinity system has arrived. A more detailed explanation of how this all works will be presented here:
https://svn.open-mpi.org/trac/ompi/wiki/ProcessPlacement

The wiki page is incomplete at the moment, but I hope to complete it over the next few days. I will provide updates on the devel list. As the wiki page states, the default and most commonly used options remain unchanged (except as noted below). New, esoteric and complex options have been added, but unless you are a true masochist, you are unlikely to use many of them beyond perhaps an initial curiosity-motivated experimentation.

In a nutshell, this commit revamps the map/rank/bind procedure to take into account topology info on the compute nodes. I have, for the most part, preserved the default behaviors, with three notable exceptions:

1. I have at long last bowed my head in submission to the system admin's of managed clusters. For years, they have complained about our default of allowing users to oversubscribe nodes - i.e., to run more processes on a node than allocated slots. Accordingly, I have modified the default behavior: if you are running off of hostfile/dash-host allocated nodes, then the default is to allow oversubscription. If you are running off of RM-allocated nodes, then the default is to NOT allow oversubscription. Flags to override these behaviors are provided, so this only affects the default behavior.

2. both cpus/rank and stride have been removed. The latter was demanded by those who didn't understand the purpose behind it - and I agreed as the users who requested it are no longer using it. The former was removed temporarily pending implementation.

3. vm launch is now the sole method for starting OMPI. It was just too darned hard to maintain multiple launch procedures - maybe someday, provided someone can demonstrate a reason to do so.

As Jeff stated, it is impossible to fully test a change of this size. I have tested it on Linux and Mac, covering all the default and simple options, singletons, and comm_spawn. That said, I'm sure others will find problems, so I'll be watching MTT results until this stabilizes.

This commit was SVN r25476.
2011-11-15 03:40:11 +00:00

118 строки
3.7 KiB
Plaintext

# -*- text -*-
#
# Copyright (c) 2004-2007 The Trustees of Indiana University and Indiana
# University Research and Technology
# Corporation. All rights reserved.
# Copyright (c) 2004-2005 The University of Tennessee and The University
# of Tennessee Research Foundation. All rights
# reserved.
# Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
# University of Stuttgart. All rights reserved.
# Copyright (c) 2004-2005 The Regents of the University of California.
# All rights reserved.
# Copyright (c) 2009 Sun Microsystems, Inc. All rights reserved.
# Copyright (c) 2010-2011 Cisco Systems, Inc. All rights reserved.
# $COPYRIGHT$
#
# Additional copyrights may follow
#
# $HEADER$
#
# This is a US/English help file.
#
[execve error]
Open MPI tried to fork a new process via the "execve" system call but
failed. This is an unusual error because Open MPI checks many things
before attempting to launch a child process. This error may be
indicative of another problem on the target host. Your job will now
abort.
Local host: %s
Application name: %s
#
[binding not supported]
Open MPI tried to bind a new process, but process binding is not
supported on the host where it was launched. The process was killed
without launching the target application. Your job will now abort.
Local host: %s
Application name: %s
#
[binding generic error]
Open MPI tried to bind a new process, but something went wrong. The
process was killed without launching the target application. Your job
will now abort.
Local host: %s
Application name: %s
Error message: %s
Location: %s:%d
#
[bound to everything]
Open MPI tried to bind a new process to a specific set of processors,
but ended up binding it to *all* processors. This means that the new
process is effectively unbound.
This is only a warning -- your job will continue. You can suppress
this warning in the future by setting the odls_warn_if_not_bound MCA
parameter to 0.
Local host: %s
Application name: %s
Location: %s:%d
#
[slot list and paffinity_alone]
Open MPI detected that both a slot list was specified and the MCA
parameter "paffinity_alone" was set to true. Only one of these can be
used at a time. Your job will now abort.
Local host: %s
Application name: %s
#
[iof setup failed]
Open MPI tried to launch a child process but the "IOF child setup"
failed. This should not happen. Your job will now abort.
Local host: %s
Application name: %s
#
[not bound]
WARNING: Open MPI tried to bind a process but failed. This is a
warning only; your job will continue.
Local host: %s
Application name: %s
Error message: %s
Location: %s:%d
#
[syscall fail]
A system call failed that should not have. In this particular case,
a warning or error message was not displayed that should have been.
Your job may behave unpredictably after this, or abort.
Local host: %s
Application name: %s
Function: %s
Location: %s:%d
#
[memory not bound]
WARNING: Open MPI tried to bind a process but failed. This is a
warning only; your job will continue, though performance may
be degraded.
Local host: %s
Application name: %s
Error message: %s
Location: %s:%d
#
[memory binding error]
Open MPI tried to bind memory for a new process but something went
wrong. The process was killed without launching the target
application. Your job will now abort.
Local host: %s
Application name: %s
Error message: %s
Location: %s:%d