From a65f248f558e2803deecb2c470ea4b662a81770a Mon Sep 17 00:00:00 2001 From: Jeff Squyres Date: Fri, 18 Aug 2023 18:32:51 -0400 Subject: [PATCH] wip -- update to match prrte (proposed) PR Signed-off-by: Jeff Squyres --- config/ompi_setup_prrte.m4 | 62 ++- docs/Makefile.am | 5 + docs/_ext | 1 - docs/conf.py | 2 +- docs/installing-open-mpi/packagers.rst | 17 + docs/man-openmpi/man1/.gitignore | 3 + docs/man-openmpi/man1/mpirun.1.rst | 477 ++++++++++++++---- .../man1/mpirun/help-schizo-cli.rst | 1 - .../man1/mpirun/help-schizo-deprecated.rst | 1 - .../man1/mpirun/help-schizo-ompi.rst | 1 - 10 files changed, 460 insertions(+), 110 deletions(-) delete mode 120000 docs/_ext create mode 100644 docs/man-openmpi/man1/.gitignore delete mode 120000 docs/man-openmpi/man1/mpirun/help-schizo-cli.rst delete mode 120000 docs/man-openmpi/man1/mpirun/help-schizo-deprecated.rst delete mode 120000 docs/man-openmpi/man1/mpirun/help-schizo-ompi.rst diff --git a/config/ompi_setup_prrte.m4 b/config/ompi_setup_prrte.m4 index 4dffa6ceb2a..61e22cb0748 100644 --- a/config/ompi_setup_prrte.m4 +++ b/config/ompi_setup_prrte.m4 @@ -19,6 +19,7 @@ dnl Copyright (c) 2019-2020 Intel, Inc. All rights reserved. dnl Copyright (c) 2020-2022 Amazon.com, Inc. or its affiliates. All Rights reserved. dnl Copyright (c) 2021 Nanook Consulting. All rights reserved. dnl Copyright (c) 2021-2022 IBM Corporation. All rights reserved. +dnl Copyright (c) 2023 Jeffrey M. Squyres. All rights reserved. dnl $COPYRIGHT$ dnl dnl Additional copyrights may follow @@ -26,6 +27,32 @@ dnl dnl $HEADER$ dnl +dnl $1 dir +dnl $2 filename +AC_DEFUN([_OMPI_SETUP_PRRTE_DUMMY_RST_FILE], [ + dir=$1 + file=$2 + + mkdir -p "$dir" + rm -rf "$dir/$file" + cat > "$dir/$file" <`` in your current run-time environment (if running under a supported resource manager, Open MPI's -mpirun will usually automatically use the corresponding resource -manager process starter, as opposed to, for example, ``rsh`` or ``ssh``, which -require the use of a hostfile, or will default to running all ``X`` copies -on the localhost), scheduling (by default) in a round-robin fashion by -CPU slot. See the rest of this page for more details. - -Please note that mpirun automatically binds processes as of the start -of the v1.8 series. Three binding patterns are used in the absence of -any further directives (See :ref:`map/rank/bind defaults ` for more details): +``mpirun`` will usually automatically use the corresponding resource +manager process starter, as opposed to ``ssh`` (for example), which +require the use of a hostfile, or will default to running all ``X`` +copies on the localhost), scheduling (by default) in a round-robin +fashion by CPU slot. See the rest of this documentation for more +details. + +Please note that ``mpirun`` automatically binds processes to hardware +resources. Three binding patterns are used in the absence of any +further directives (See :ref:`map/rank/bind defaults +` for more details): * **Bind to core**: when the number of processes is <= 2 * **Bind to package**: when the number of processes is > 2 @@ -79,134 +81,266 @@ that you are either not bound at all (by specifying ``--bind-to none``), or bound to multiple cores using an appropriate binding level or specific number of processing elements per application process. -.. _man1-mpirun-definition-of-slot: +OPEN MPI'S USE OF PRRTE +----------------------- + +Open MPI uses the PMIx Reference Runtime Environment (PRRTE) as the +main engine for launching, monitoring, and terminating MPI processes. + +Much of the documentation below is directly imported from PRRTE. As +such, it frequently refers to PRRTE concepts and command line options. +Except where noted, these concepts and command line argument are all +applicable to Open MPI as well. Open MPI extends the available PRRTE +command line options, and also slightly modifies the PRRTE's default +behaviors in a few cases. These will be specifically described in the +docuemtnation below. -DEFINITION OF 'SLOT' +COMMAND LINE OPTIONS -------------------- -The term "slot" is used extensively in the rest of this manual page. -A slot is an allocation unit for a process. The number of slots on a -node indicate how many processes can potentially execute on that node. -By default, Open MPI will allow one process per slot. +The core of Open MPI's ``mpirun`` processing is performed via the +PRRTE ``prterun(1)`` command. Specifically: ``mpirun`` is effectively +a wrapper around ``prterun``; various environment variables are set +and specific command line parameters are passed to ``prterun``. -If Open MPI is not explicitly told how many slots are available on a -node (e.g., if a hostfile is used and the number of slots is not -specified for a given node), it will determine a maximum number of -slots for that node in one of two ways: +``mpirun`` therefore exports most of the same command line options as +``prtertun``. The following command line options are supported: -#. Default behavior: By default, Open MPI will attempt to discover the - number of processor cores on the node, and use that as the number - of slots available. +.. JMS Need to make this better -- e.g., include 1 file instead of N + files, so that we can be isolated from changes upstream (additions + and removals of CLI options) in PRRTE. -#. When ``--use-hwthread-cpus`` is used: If ``--use-hwthread-cpus`` is - specified on the ``mpirun`` command line, then Open MPI will attempt to - discover the number of hardware threads on the node, and use that - as the number of slots available. +The ``--add-host`` option +^^^^^^^^^^^^^^^^^^^^^^^^^ -This default behavior also occurs when specifying the ``--host`` -option with a single host. Thus, the command: +.. include:: prrte-rst-content/cli-add-host.rst -.. code:: sh +The ``--add-hostfile`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ - shell$ mpirun --host node1 ./a.out +.. include:: prrte-rst-content/cli-add-hostfile.rst -launches a number of processes equal to the number of cores on node -``node1``, whereas: +The ``--allow-run-as-root`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -.. code:: sh +.. include:: prrte-rst-content/cli-allow-run-as-root.rst + +The ``--bind-to`` option +^^^^^^^^^^^^^^^^^^^^^^^^ - shell$ mpirun --host node1 --use-hwthread-cpus ./a.out +.. include:: prrte-rst-content/cli-bind-to.rst -launches a number of processes equal to the number of hardware -threads on ``node1``. +The ``--debug-daemons`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -When Open MPI applications are invoked in an environment managed by a -resource manager (e.g., inside of a Slurm job), and Open MPI was built -with appropriate support for that resource manager, then Open MPI will -be informed of the number of slots for each node by the resource -manager. For example: +.. include:: prrte-rst-content/cli-debug-daemons.rst -.. code:: sh +The ``--debug-daemons-file`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ - shell$ mpirun ./a.out +.. include:: prrte-rst-content/cli-debug-daemons-file.rst -launches one process for every slot (on every node) as dictated by -the resource manager job specification. +The ``--display`` option +^^^^^^^^^^^^^^^^^^^^^^^^ -Also note that the one-process-per-slot restriction can be overridden -in unmanaged environments (e.g., when using hostfiles without a -resource manager) if oversubscription is enabled (by default, it is -disabled). Most MPI applications and HPC environments do not -oversubscribe; for simplicity, the majority of this documentation -assumes that oversubscription is not enabled. +.. include:: prrte-rst-content/cli-display.rst -Slots are not hardware resources +The ``--dvm`` option +^^^^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/cli-dvm.rst + +The ``--dvm-hostfile`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/cli-dvm-hostfile.rst + +The ``--forward-signals`` option ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -Slots are frequently incorrectly conflated with hardware resources. -It is important to realize that slots are an entirely different metric -than the number (and type) of hardware resources available. +.. include:: prrte-rst-content/cli-forward-signals.rst -Here are some examples that may help illustrate the difference: +The ``--host`` option +^^^^^^^^^^^^^^^^^^^^^ -#. More processor cores than slots: Consider a resource manager job - environment that tells Open MPI that there is a single node with 20 - processor cores and 2 slots available. By default, Open MPI will - only let you run up to 2 processes. +.. include:: prrte-rst-content/cli-dash-host.rst - Meaning: you run out of slots long before you run out of processor - cores. +The ``--launcher-hostfile`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -#. More slots than processor cores: Consider a hostfile with a single - node listed with a ``slots=50`` qualification. The node has 20 - processor cores. By default, Open MPI will let you run up to 50 - processes. +.. include:: prrte-rst-content/cli-launcher-hostfile.rst - Meaning: you can run many more processes than you have processor - cores. +The ``--leave-session-attached`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -.. _man1-mpirun-definition-of-processor-element: +.. include:: prrte-rst-content/cli-leave-session-attached.rst -DEFINITION OF 'PROCESSOR ELEMENT' ---------------------------------- +The ``--map-by`` option +^^^^^^^^^^^^^^^^^^^^^^^ -By default, Open MPI defines that a "processing element" is a -processor core. However, if ``--use-hwthread-cpus`` is specified on the -mpirun command line, then a "processing element" is a hardware thread. +.. include:: prrte-rst-content/cli-map-by.rst -OPTIONS (NEW / DYNAMICALLY IMPORTED FROM PRTE) ----------------------------------------------- +The ``--output`` option +^^^^^^^^^^^^^^^^^^^^^^^ -From prterun(1) -^^^^^^^^^^^^^^^ +.. include:: prrte-rst-content/cli-output.rst + +The ``--personality`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/cli-personality.rst + +The ``--pmixmca`` option +^^^^^^^^^^^^^^^^^^^^^^^^ -These options are directly from ``prterun(1)``: +.. include:: prrte-rst-content/cli-pmixmca.rst -.. include:: mpirun/help-schizo-cli.rst +The ``--prefix`` option +^^^^^^^^^^^^^^^^^^^^^^^ -Open MPI-specific options +.. include:: prrte-rst-content/cli-prefix.rst + +The ``--prtemca`` option +^^^^^^^^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/cli-prtemca.rst + +The ``--noprefix`` option ^^^^^^^^^^^^^^^^^^^^^^^^^ -These options are specific to Open MPI: +.. include:: prrte-rst-content/cli-noprefix.rst -.. include:: mpirun/help-schizo-ompi.rst +The ``--rank-by`` option +^^^^^^^^^^^^^^^^^^^^^^^^ -Deprecated options -^^^^^^^^^^^^^^^^^^ +.. include:: prrte-rst-content/cli-rank-by.rst + +The ``--runtime-options`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/cli-runtime-options.rst + +The ``--stream-buffering`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/cli-stream-buffering.rst + +The ``--tune`` option +^^^^^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/cli-tune.rst + +The ``-x`` option +^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/cli-x.rst + + +OPEN MPI-SPECIFIC COMMAND LINE OPTIONS +-------------------------------------- + +The following command line options are specific to Open MPI: + +.. include:: schizo-ompi-rst-content/schizo-ompi-cli.rst + +DEPRECATED COMMAND LINE OPTIONS +------------------------------- + +The following command line options are deprecated and may disappear in +a future version of Open MPI: + +.. JMS Need to make this better -- e.g., include 1 file instead of N + files, so that we can be isolated from changes upstream (additions + and removals of CLI options) in PRRTE. + +The ``--bind-to-core`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/deprecated-bind-to-core.rst + +The ``--display-allocation`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/deprecated-display-allocation.rst + +The ``--display-devel-allocation`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/deprecated-display-devel-allocation.rst + +The ``--display-devel-map`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/deprecated-display-devel-map.rst + +The ``--display-map`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/deprecated-display-map.rst + +The ``--display-topo`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/deprecated-display-topo.rst + +The ``--gmca`` option +^^^^^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/deprecated-gmca.rst + +The ``--mca`` option +^^^^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/deprecated-mca.rst + +The ``--merge-stderr-to-stdout`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/deprecated-merge-stderr-to-stdout.rst + +The ``--output-directory`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/deprecated-output-directory.rst + +The ``--output-filename`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/deprecated-output-filename.rst + +The ``--report-bindings`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/deprecated-report-bindings.rst + +The ``--tag-output`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/deprecated-tag-output.rst + +The ``--timestamp-output`` option +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. include:: prrte-rst-content/deprecated-timestamp-output.rst -These are deprecated options: +The ``--xml`` option +^^^^^^^^^^^^^^^^^^^^ -.. include:: mpirun/help-schizo-deprecated.rst +.. include:: prrte-rst-content/deprecated-xml.rst -OPTIONS (OLD / HARD-CODED CONTENT -- TO BE DELETED) ---------------------------------------------------- +OPTIONS (OLD / HARD-CODED CONTENT -- TO BE AUDITED +-------------------------------------------------- .. admonition:: This is old content :class: error - This is the old section of manually hard-coded content. It will - likely someday be deleted and replaced with the dynamic content - from prterun. + This is the old section of manually hard-coded content. It should + probably be read / audited and see what we want to keep and what we + want to discard. + + Feel free to refer to https://docs.prrte.org/ rather than + replicating content here (e.g., for the definition of a slot and + other things). mpirun will send the name of the directory where it was invoked on the local node to each of the remote nodes, and attempt to change to that @@ -282,10 +416,11 @@ processes will be bound to the package. context. If no value is provided for the number of copies to execute (i.e., neither the ``-n`` nor its synonyms are provided on the command line), Open MPI will automatically execute a copy of the - program on each process slot (see :ref:`defintion of slot ` for description of a - "process slot"). This feature, however, can only be used in the SPMD - model and will return an error (without beginning execution of the - application) otherwise. + program on each process slot (see PRRTE's `defintion of "slot" + `_ + for description of a "process slot"). This feature, however, can + only be used in the SPMD model and will return an error (without + beginning execution of the application) otherwise. .. note:: The ``-n`` option is the preferred option to be used to specify the number of copies of the program to be executed, but the alternate @@ -592,13 +727,17 @@ There are also other options: Note that if a number of slots is not provided to Open MPI (e.g., via the ``slots`` keyword in a hostfile or from a resource manager such as Slurm), the use of this option changes the default - calculation of number of slots on a node. See the :ref:`DEFINITION - OF 'SLOT' ` section. + calculation of number of slots on a node. See the PRRTE's + `defintion of "slot" + `_ + for more details. Also note that the use of this option changes the Open MPI's definition of a "processor element" from a processor core to a - hardware thread. See the :ref:`DEFINITION OF 'PROCESSOR ELEMENT' - ` section. + hardware thread. See + PRRTE's `defintion of a "processor element" + `_ + for more details. The following options are useful for developers; they are not generally useful to most Open MPI users: @@ -632,11 +771,23 @@ There may be other options listed with ``mpirun --help``. Environment Variables ^^^^^^^^^^^^^^^^^^^^^ +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + * ``MPIEXEC_TIMEOUT``: Synonym for the ``--timeout`` command line option. DESCRIPTION ----------- +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + One invocation of ``mpirun`` starts an MPI application running under Open MPI. If the application is single process multiple data (SPMD), the application can be specified on the ``mpirun`` command line. @@ -661,6 +812,12 @@ while others are specific to a single program (e.g., ``-n``). Specifying Host Nodes ^^^^^^^^^^^^^^^^^^^^^ +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + Host nodes can be identified on the ``mpirun`` command line with the ``--host`` option or in a hostfile. @@ -710,6 +867,12 @@ from the resource manager. Specifying Number of Processes ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + As we have just seen, the number of processes to run can be set using the hostfile. Other mechanisms exist. @@ -764,6 +927,12 @@ the ``-n`` option indicated that only 6 processes should be launched. Mapping Processes to Nodes: Using Policies ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + The examples above illustrate the default mapping of process processes to nodes. This mapping can also be controlled with various ``mpirun`` options that describe mapping policies. @@ -876,6 +1045,12 @@ and 2 each running uptime on nodes ``bb`` and ``cc``, respectively. Mapping, Ranking, and Binding: Oh My! ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + Open MPI employs a three-phase procedure for assigning process locations and ranks: @@ -1102,6 +1277,12 @@ value pair may be specific on the command line by prefixing the key with Defaults for Mapping, Ranking, and Binding ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + If the user does not specify each of ``--map-by``, ``--rank-by``, and ``--bind-to`` option then the default values are as follows: * If no options are specified then @@ -1198,6 +1379,12 @@ The mapping pattern might be better seen if we change the default ``--rank-by`` Rankfiles ^^^^^^^^^ +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + Rankfiles are text files that specify detailed information about how individual processes should be mapped to nodes, and to which processor(s) they should be bound. Each line of a rankfile specifies @@ -1257,6 +1444,12 @@ indexes of package and cores. Application Context or Executable Program? ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + To distinguish the two different forms, mpirun looks on the command line for ``--app`` option. If it is specified, then the file named on the command line is assumed to be an application context. If it is @@ -1265,6 +1458,12 @@ not specified, then the file is assumed to be an executable program. Locating Files ^^^^^^^^^^^^^^ +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + If no relative or absolute path is specified for a file, Open MPI will first look for files by searching the directories specified by the ``--path`` option. If there is no ``--path`` option set or if the @@ -1283,6 +1482,12 @@ current working directory from the invocation of ``mpirun``. Current Working Directory ^^^^^^^^^^^^^^^^^^^^^^^^^ +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + The ``--wdir`` ``mpirun`` option (and its synonym, ``--wd``) allows the user to change to an arbitrary directory before the program is invoked. It can also be used in application context files to specify @@ -1310,6 +1515,12 @@ does not wait until :ref:`MPI_INIT(3) ` is called. Standard I/O ^^^^^^^^^^^^ +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + Open MPI directs UNIX standard input to ``/dev/null`` on all processes except the MPI_COMM_WORLD rank 0 process. The MPI_COMM_WORLD rank 0 process inherits standard input from ``mpirun``. @@ -1340,6 +1551,12 @@ will be collected into the ``my_output`` file. Signal Propagation ^^^^^^^^^^^^^^^^^^ +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + When ``mpirun`` receives a SIGTERM and SIGINT, it will attempt to kill the entire job by sending all processes in the job a SIGTERM, waiting a small number of seconds, then sending all processes in the job a @@ -1357,6 +1574,12 @@ Other signals are not currently propagated by ``mpirun``. Process Termination / Signal Handling ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + During the run of an MPI application, if any process dies abnormally (either exiting before invoking :ref:`MPI_FINALIZE(3) `, or dying as the result of a signal), ``mpirun`` will print out an @@ -1377,6 +1600,12 @@ safest) for the user to only clean up non-MPI state. Process Environment ^^^^^^^^^^^^^^^^^^^ +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + Processes in the MPI application inherit their environment from the PRRTE daemon upon the node on which they are running. The environment is typically inherited from the user's shell. On remote @@ -1396,6 +1625,12 @@ for more details. Remote Execution ^^^^^^^^^^^^^^^^ +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + Open MPI requires that the ``PATH`` environment variable be set to find executables on remote nodes (this is typically only necessary in rsh- or ssh-based environments |mdash| batch/scheduled environments @@ -1462,6 +1697,12 @@ is equivalent to Exported Environment Variables ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + All environment variables that are named in the form ``OMPI_*`` will automatically be exported to new processes on the local and remote nodes. Environmental parameters can also be set/forwarded to the new @@ -1479,6 +1720,12 @@ them. Setting MCA Parameters ^^^^^^^^^^^^^^^^^^^^^^ +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + The ``--mca`` switch allows the passing of parameters to various MCA (Modular Component Architecture) modules. MCA modules have direct impact on MPI programs because they allow tunable parameters to be set @@ -1539,6 +1786,12 @@ page for detailed information on this command. Setting MCA parameters and environment variables from file ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + The ``--tune`` command line option and its synonym ``--mca`` ``mca_base_envar_file_prefix`` allows a user to set MCA parameters and environment variables with the syntax described below. This option @@ -1563,6 +1816,12 @@ have higher precedence than variables specified in the file. Running as root ^^^^^^^^^^^^^^^ +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + .. warning:: The Open MPI team **strongly** advises against executing ``mpirun`` as the root user. MPI applications should be run as regular (non-root) users. @@ -1589,6 +1848,12 @@ against this behavior. Exit status ^^^^^^^^^^^ +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + There is no standard definition for what ``mpirun`` should return as an exit status. After considerable discussion, we settled on the following method for assigning the ``mpirun`` exit status (note: in @@ -1630,6 +1895,12 @@ bullet points above). EXAMPLES -------- +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + Be sure also to see the examples throughout the sections above. .. code:: sh @@ -1644,6 +1915,12 @@ messages. RETURN VALUE ------------ +.. admonition:: This is old, hard-coded content + :class: error + + Is this content still current / accurate? Should it be updated and + retained, or removed? + ``mpirun`` returns 0 if all processes started by mpirun exit after calling :ref:`MPI_FINALIZE(3) `. A non-zero value is returned if an internal error occurred in mpirun, or one or more diff --git a/docs/man-openmpi/man1/mpirun/help-schizo-cli.rst b/docs/man-openmpi/man1/mpirun/help-schizo-cli.rst deleted file mode 120000 index 35a6de0d12f..00000000000 --- a/docs/man-openmpi/man1/mpirun/help-schizo-cli.rst +++ /dev/null @@ -1 +0,0 @@ -../../../../3rd-party/prrte/src/docs/help-schizo-cli.rst \ No newline at end of file diff --git a/docs/man-openmpi/man1/mpirun/help-schizo-deprecated.rst b/docs/man-openmpi/man1/mpirun/help-schizo-deprecated.rst deleted file mode 120000 index 61fa713bfeb..00000000000 --- a/docs/man-openmpi/man1/mpirun/help-schizo-deprecated.rst +++ /dev/null @@ -1 +0,0 @@ -../../../../3rd-party/prrte/src/docs/help-schizo-deprecated.rst \ No newline at end of file diff --git a/docs/man-openmpi/man1/mpirun/help-schizo-ompi.rst b/docs/man-openmpi/man1/mpirun/help-schizo-ompi.rst deleted file mode 120000 index da83f06c224..00000000000 --- a/docs/man-openmpi/man1/mpirun/help-schizo-ompi.rst +++ /dev/null @@ -1 +0,0 @@ -../../../../3rd-party/prrte/src/docs/mca/help-schizo-ompi.rst \ No newline at end of file