rename '--cluster' flag to '--parallel' in ProfileApp

Now, to instruct the profile to include parallel scripts, you would do:

$> ipython profile create foo --parallel
instead of
$> ipython profile create foo --cluster

docs updated accordingly.

IPython/core/profileapp.py

@@ -1,219 +1,219 b''
 # encoding: utf-8
 """
 An application for managing IPython profiles.
 
 To be invoked as the `ipython profile` subcommand.
 
 Authors:
 
 * Min RK
 
 """
 
 #-----------------------------------------------------------------------------
 #  Copyright (C) 2008-2011  The IPython Development Team
 #
 #  Distributed under the terms of the BSD License.  The full license is in
 #  the file COPYING, distributed as part of this software.
 #-----------------------------------------------------------------------------
 
 #-----------------------------------------------------------------------------
 # Imports
 #-----------------------------------------------------------------------------
 
 import logging
 import os
 
 from IPython.config.application import Application, boolean_flag
 from IPython.core.application import (
     BaseIPythonApplication, base_flags, base_aliases
 )
 from IPython.core.profiledir import ProfileDir
 from IPython.utils.path import get_ipython_dir
 from IPython.utils.traitlets import Unicode, Bool, Dict
 
 #-----------------------------------------------------------------------------
 # Constants
 #-----------------------------------------------------------------------------
 
-create_help = """Create an ipcluster profile by name
+create_help = """Create an IPython profile by name
 
 Create an ipython profile directory by its name or
 profile directory path. Profile directories contain
 configuration, log and security related files and are named
 using the convention 'profile_<name>'. By default they are
 located in your ipython directory. Once created, you will
 can edit the configuration files in the profile
 directory to configure IPython. Most users will create a
-cluster directory by profile name,
+profile directory by name,
 `ipython profile create myprofile`, which will put the directory
 in `<ipython_dir>/profile_myprofile`.
 """
 list_help = """List available IPython profiles
 
 List all available profiles, by profile location, that can
 be found in the current working directly or in the ipython
 directory. Profile directories are named using the convention
 'profile_<profile>'.
 """
 profile_help = """Manage IPython profiles
 
 Profile directories contain
 configuration, log and security related files and are named
 using the convention 'profile_<name>'. By default they are
 located in your ipython directory.  You can create profiles
 with `ipython profile create <name>`, or see the profiles you
 already have with `ipython profile list`
 
 To get started configuring IPython, simply do:
 
 $> ipython profile create
 
 and IPython will create the default profile in <ipython_dir>/profile_default,
 where you can edit ipython_config.py to start configuring IPython.
 
 """
 
 #-----------------------------------------------------------------------------
 # Profile Application Class (for `ipython profile` subcommand)
 #-----------------------------------------------------------------------------
 
 
 
 class ProfileList(Application):
     name = u'ipython-profile'
     description = list_help
     
     aliases = Dict(dict(
         ipython_dir = 'ProfileList.ipython_dir',
         log_level = 'Application.log_level',
     ))
     flags = Dict(dict(
         debug = ({'Application' : {'log_level' : 0}},
             "Set log_level to 0, maximizing log output."
         )
     ))
     ipython_dir = Unicode(get_ipython_dir(), config=True, 
         help="""
         The name of the IPython directory. This directory is used for logging
         configuration (through profiles), history storage, etc. The default
         is usually $HOME/.ipython. This options can also be specified through
         the environment variable IPYTHON_DIR.
         """
     )
     
     def list_profile_dirs(self):
         # Find the search paths
         paths = [os.getcwdu(), self.ipython_dir]
 
         self.log.warn('Searching for IPython profiles in paths: %r' % paths)
         for path in paths:
             files = os.listdir(path)
             for f in files:
                 full_path = os.path.join(path, f)
                 if os.path.isdir(full_path) and f.startswith('profile_'):
                     profile = f.split('_',1)[-1]
                     start_cmd = 'ipython profile=%s' % profile
                     print start_cmd + " ==> " + full_path
     
     def start(self):
         self.list_profile_dirs()
 
 
 create_flags = {}
 create_flags.update(base_flags)
 create_flags.update(boolean_flag('reset', 'ProfileCreate.overwrite', 
                 "reset config files to defaults", "leave existing config files"))
-create_flags.update(boolean_flag('cluster', 'ProfileCreate.cluster', 
+create_flags.update(boolean_flag('parallel', 'ProfileCreate.parallel', 
                 "Include parallel computing config files", 
                 "Don't include parallel computing config files"))
 
 class ProfileCreate(BaseIPythonApplication):
     name = u'ipython-profile'
     description = create_help
     auto_create = Bool(True, config=False)
     
     def _copy_config_files_default(self):
         return True
     
-    cluster = Bool(False, config=True,
+    parallel = Bool(False, config=True,
         help="whether to include parallel computing config files")
-    def _cluster_changed(self, name, old, new):
-        cluster_files = [   'ipcontroller_config.py', 
+    def _parallel_changed(self, name, old, new):
+        parallel_files = [   'ipcontroller_config.py', 
                             'ipengine_config.py', 
                             'ipcluster_config.py'
                         ]
         if new:
-            for cf in cluster_files:
+            for cf in parallel_files:
                 self.config_files.append(cf)
         else:
-            for cf in cluster_files:
+            for cf in parallel_files:
                 if cf in self.config_files:
                     self.config_files.remove(cf)
     
     def parse_command_line(self, argv):
         super(ProfileCreate, self).parse_command_line(argv)
         # accept positional arg as profile name
         if self.extra_args:
             self.profile = self.extra_args[0]
     
     flags = Dict(create_flags)
     
     aliases = Dict(dict(profile='BaseIPythonApplication.profile'))
     
     classes = [ProfileDir]
     
     def init_config_files(self):
         super(ProfileCreate, self).init_config_files()
         # use local imports, since these classes may import from here
         from IPython.frontend.terminal.ipapp import TerminalIPythonApp
         apps = [TerminalIPythonApp]
         try:
             from IPython.frontend.qt.console.qtconsoleapp import IPythonQtConsoleApp
         except ImportError:
             pass
         else:
             apps.append(IPythonQtConsoleApp)
-        if self.cluster:
+        if self.parallel:
             from IPython.parallel.apps.ipcontrollerapp import IPControllerApp
             from IPython.parallel.apps.ipengineapp import IPEngineApp
             from IPython.parallel.apps.ipclusterapp import IPClusterStart
             from IPython.parallel.apps.iploggerapp import IPLoggerApp
             apps.extend([
                 IPControllerApp,
                 IPEngineApp,
                 IPClusterStart,
                 IPLoggerApp,
             ])
         for App in apps:
             app = App()
             app.config.update(self.config)
             app.log = self.log
             app.overwrite = self.overwrite
             app.copy_config_files=True
             app.profile = self.profile
             app.init_profile_dir()
             app.init_config_files()
     
     def stage_default_config_file(self):
         pass
 
 class ProfileApp(Application):
     name = u'ipython-profile'
     description = profile_help
     
     subcommands = Dict(dict(
         create = (ProfileCreate, "Create a new profile dir with default config files"),
         list = (ProfileList, "List existing profiles")
     ))
     
     def start(self):
         if self.subapp is None:
             print "No subcommand specified. Must specify one of: %s"%(self.subcommands.keys())
             print
             self.print_description()
             self.print_subcommands()
             self.exit(1)
         else:
             return self.subapp.start()
 

docs/source/parallel/parallel_process.txt

@@ -1,504 +1,504 b''
 .. _parallel_process:
 
 ===========================================
 Starting the IPython controller and engines
 ===========================================
 
 To use IPython for parallel computing, you need to start one instance of
 the controller and one or more instances of the engine. The controller
 and each engine can run on different machines or on the same machine.
 Because of this, there are many different possibilities.
 
 Broadly speaking, there are two ways of going about starting a controller and engines:
 
 * In an automated manner using the :command:`ipcluster` command.
 * In a more manual way using the :command:`ipcontroller` and 
   :command:`ipengine` commands.
 
 This document describes both of these methods. We recommend that new users
 start with the :command:`ipcluster` command as it simplifies many common usage
 cases.
 
 General considerations
 ======================
 
 Before delving into the details about how you can start a controller and
 engines using the various methods, we outline some of the general issues that
 come up when starting the controller and engines. These things come up no
 matter which method you use to start your IPython cluster.
 
 Let's say that you want to start the controller on ``host0`` and engines on
 hosts ``host1``-``hostn``. The following steps are then required:
 
 1. Start the controller on ``host0`` by running :command:`ipcontroller` on
    ``host0``.
 2. Move the JSON file (:file:`ipcontroller-engine.json`) created by the 
    controller from ``host0`` to hosts ``host1``-``hostn``.
 3. Start the engines on hosts ``host1``-``hostn`` by running 
    :command:`ipengine`.  This command has to be told where the JSON file 
    (:file:`ipcontroller-engine.json`) is located.
 
 At this point, the controller and engines will be connected. By default, the JSON files
 created by the controller are put into the :file:`~/.ipython/cluster_default/security`
 directory. If the engines share a filesystem with the controller, step 2 can be skipped as
 the engines will automatically look at that location.
 
 The final step required to actually use the running controller from a client is to move
 the JSON file :file:`ipcontroller-client.json` from ``host0`` to any host where clients
 will be run. If these file are put into the :file:`~/.ipython/cluster_default/security`
 directory of the client's host, they will be found automatically. Otherwise, the full path
 to them has to be passed to the client's constructor.
 
 Using :command:`ipcluster`
 ===========================
 
 The :command:`ipcluster` command provides a simple way of starting a
 controller and engines in the following situations:
 
 1. When the controller and engines are all run on localhost. This is useful
    for testing or running on a multicore computer.
 2. When engines are started using the :command:`mpiexec` command that comes 
    with most MPI [MPI]_ implementations
 3. When engines are started using the PBS [PBS]_ batch system 
    (or other `qsub` systems, such as SGE).
 4. When the controller is started on localhost and the engines are started on 
    remote nodes using :command:`ssh`.
 5. When engines are started using the Windows HPC Server batch system.
 
 .. note::
 
     Currently :command:`ipcluster` requires that the
     :file:`~/.ipython/profile_<name>/security` directory live on a shared filesystem that is
     seen by both the controller and engines. If you don't have a shared file
     system you will need to use :command:`ipcontroller` and
     :command:`ipengine` directly.
 
 Under the hood, :command:`ipcluster` just uses :command:`ipcontroller`
 and :command:`ipengine` to perform the steps described above.
 
 The simplest way to use ipcluster requires no configuration, and will
 launch a controller and a number of engines on the local machine. For instance, 
 to start one controller and 4 engines on localhost, just do::
 
     $ ipcluster start n=4
 
 To see other command line options, do::
 
     $ ipcluster -h
 
 
 Configuring an IPython cluster
 ==============================
 
 Cluster configurations are stored as `profiles`.  You can create a new profile with::
 
-    $ ipython profile create --cluster profile=myprofile
+    $ ipython profile create --parallel profile=myprofile
 
 This will create the directory :file:`IPYTHONDIR/cluster_myprofile`, and populate it
 with the default configuration files for the three IPython cluster commands. Once
 you edit those files, you can continue to call ipcluster/ipcontroller/ipengine
 with no arguments beyond ``p=myprofile``, and any configuration will be maintained.
 
 There is no limit to the number of profiles you can have, so you can maintain a profile for each
 of your common use cases. The default profile will be used whenever the
 profile argument is not specified, so edit :file:`IPYTHONDIR/cluster_default/*_config.py` to
 represent your most common use case.
 
 The configuration files are loaded with commented-out settings and explanations,
 which should cover most of the available possibilities.
 
 Using various batch systems with :command:`ipcluster`
 ------------------------------------------------------
 
 :command:`ipcluster` has a notion of Launchers that can start controllers
 and engines with various remote execution schemes.  Currently supported
 models include :command:`ssh`, :command`mpiexec`, PBS-style (Torque, SGE),
 and Windows HPC Server.
 
 .. note::
 
     The Launchers and configuration are designed in such a way that advanced
     users can subclass and configure them to fit their own system that we
     have not yet supported (such as Condor)
 
 Using :command:`ipcluster` in mpiexec/mpirun mode
 --------------------------------------------------
 
 
 The mpiexec/mpirun mode is useful if you:
 
 1. Have MPI installed.
 2. Your systems are configured to use the :command:`mpiexec` or
    :command:`mpirun` commands to start MPI processes.
 
 If these are satisfied, you can create a new profile::
 
-    $ ipython profile create --cluster profile=mpi
+    $ ipython profile create --parallel profile=mpi
 
 and edit the file :file:`IPYTHONDIR/cluster_mpi/ipcluster_config.py`.
 
 There, instruct ipcluster to use the MPIExec launchers by adding the lines:
 
 .. sourcecode:: python
 
     c.IPClusterEnginesApp.engine_launcher = 'IPython.parallel.apps.launcher.MPIExecEngineSetLauncher'
 
 If the default MPI configuration is correct, then you can now start your cluster, with::
 
     $ ipcluster start n=4 profile=mpi
 
 This does the following:
 
 1. Starts the IPython controller on current host.
 2. Uses :command:`mpiexec` to start 4 engines.
 
 If you have a reason to also start the Controller with mpi, you can specify:
 
 .. sourcecode:: python
 
     c.IPClusterStartApp.controller_launcher = 'IPython.parallel.apps.launcher.MPIExecControllerLauncher'
 
 .. note::
 
     The Controller *will not* be in the same MPI universe as the engines, so there is not
     much reason to do this unless sysadmins demand it.
 
 On newer MPI implementations (such as OpenMPI), this will work even if you
 don't make any calls to MPI or call :func:`MPI_Init`. However, older MPI
 implementations actually require each process to call :func:`MPI_Init` upon
 starting. The easiest way of having this done is to install the mpi4py
 [mpi4py]_ package and then specify the ``c.MPI.use`` option in :file:`ipengine_config.py`:
 
 .. sourcecode:: python
 
     c.MPI.use = 'mpi4py'
 
 Unfortunately, even this won't work for some MPI implementations. If you are
 having problems with this, you will likely have to use a custom Python
 executable that itself calls :func:`MPI_Init` at the appropriate time.
 Fortunately, mpi4py comes with such a custom Python executable that is easy to
 install and use. However, this custom Python executable approach will not work
 with :command:`ipcluster` currently.
 
 More details on using MPI with IPython can be found :ref:`here <parallelmpi>`.
 
 
 Using :command:`ipcluster` in PBS mode
 ---------------------------------------
 
 The PBS mode uses the Portable Batch System [PBS]_ to start the engines. 
 
 As usual, we will start by creating a fresh profile::
 
-    $ ipython profile create --cluster profile=pbs
+    $ ipython profile create --parallel profile=pbs
 
 And in :file:`ipcluster_config.py`, we will select the PBS launchers for the controller
 and engines:
 
 .. sourcecode:: python
 
     c.Global.controller_launcher = 'IPython.parallel.apps.launcher.PBSControllerLauncher'
     c.Global.engine_launcher = 'IPython.parallel.apps.launcher.PBSEngineSetLauncher'
 
 IPython does provide simple default batch templates for PBS and SGE, but you may need
 to specify your own. Here is a sample PBS script template:
 
 .. sourcecode:: bash
 
     #PBS -N ipython
     #PBS -j oe
     #PBS -l walltime=00:10:00
     #PBS -l nodes={n/4}:ppn=4
     #PBS -q {queue}
 
     cd $PBS_O_WORKDIR
     export PATH=$HOME/usr/local/bin
     export PYTHONPATH=$HOME/usr/local/lib/python2.7/site-packages
     /usr/local/bin/mpiexec -n {n} ipengine profile_dir={profile_dir}
 
 There are a few important points about this template:
 
 1. This template will be rendered at runtime using IPython's :class:`EvalFormatter`.
    This is simply a subclass of :class:`string.Formatter` that allows simple expressions
    on keys.
 
 2. Instead of putting in the actual number of engines, use the notation
    ``{n}`` to indicate the number of engines to be started. You can also use
    expressions like ``{n/4}`` in the template to indicate the number of nodes.
    There will always be ``{n}`` and ``{profile_dir}`` variables passed to the formatter.
    These allow the batch system to know how many engines, and where the configuration
    files reside. The same is true for the batch queue, with the template variable
    ``{queue}``.
 
 3. Any options to :command:`ipengine` can be given in the batch script
    template, or in :file:`ipengine_config.py`.
 
 4. Depending on the configuration of you system, you may have to set
    environment variables in the script template.
 
 The controller template should be similar, but simpler:
 
 .. sourcecode:: bash
 
     #PBS -N ipython
     #PBS -j oe
     #PBS -l walltime=00:10:00
     #PBS -l nodes=1:ppn=4
     #PBS -q {queue}
 
     cd $PBS_O_WORKDIR
     export PATH=$HOME/usr/local/bin
     export PYTHONPATH=$HOME/usr/local/lib/python2.7/site-packages
     ipcontroller profile_dir={profile_dir}
 
 
 Once you have created these scripts, save them with names like
 :file:`pbs.engine.template`. Now you can load them into the :file:`ipcluster_config` with:
 
 .. sourcecode:: python
 
     c.PBSEngineSetLauncher.batch_template_file = "pbs.engine.template"
     
     c.PBSControllerLauncher.batch_template_file = "pbs.controller.template"
         
 
 Alternately, you can just define the templates as strings inside :file:`ipcluster_config`.
 
 Whether you are using your own templates or our defaults, the extra configurables available are
 the number of engines to launch (``{n}``, and the batch system queue to which the jobs are to be
 submitted (``{queue}``)). These are configurables, and can be specified in
 :file:`ipcluster_config`:
 
 .. sourcecode:: python
 
     c.PBSLauncher.queue = 'veryshort.q'
     c.IPClusterEnginesApp.n = 64
 
 Note that assuming you are running PBS on a multi-node cluster, the Controller's default behavior
 of listening only on localhost is likely too restrictive.  In this case, also assuming the
 nodes are safely behind a firewall, you can simply instruct the Controller to listen for
 connections on all its interfaces, by adding in :file:`ipcontroller_config`:
 
 .. sourcecode:: python
 
     c.RegistrationFactory.ip = '*'
 
 You can now run the cluster with::
 
     $ ipcluster start profile=pbs n=128
 
 Additional configuration options can be found in the PBS section of :file:`ipcluster_config`.
 
 .. note::
 
     Due to the flexibility of configuration, the PBS launchers work with simple changes
     to the template for other :command:`qsub`-using systems, such as Sun Grid Engine,
     and with further configuration in similar batch systems like Condor.
 
 
 Using :command:`ipcluster` in SSH mode
 ---------------------------------------
 
 
 The SSH mode uses :command:`ssh` to execute :command:`ipengine` on remote
 nodes and :command:`ipcontroller` can be run remotely as well, or on localhost.
 
 .. note::
 
     When using this mode it highly recommended that you have set up SSH keys
     and are using ssh-agent [SSH]_ for password-less logins.
 
 As usual, we start by creating a clean profile::
 
-    $ ipython profile create --cluster profile=ssh
+    $ ipython profile create --parallel profile=ssh
 
 To use this mode, select the SSH launchers in :file:`ipcluster_config.py`:
 
 .. sourcecode:: python
 
     c.Global.engine_launcher = 'IPython.parallel.apps.launcher.SSHEngineSetLauncher'
     # and if the Controller is also to be remote:
     c.Global.controller_launcher = 'IPython.parallel.apps.launcher.SSHControllerLauncher'
     
 
 The controller's remote location and configuration can be specified:
 
 .. sourcecode:: python
 
     # Set the user and hostname for the controller
     # c.SSHControllerLauncher.hostname = 'controller.example.com'
     # c.SSHControllerLauncher.user = os.environ.get('USER','username')
 
     # Set the arguments to be passed to ipcontroller
     # note that remotely launched ipcontroller will not get the contents of 
     # the local ipcontroller_config.py unless it resides on the *remote host*
     # in the location specified by the `profile_dir` argument.
     # c.SSHControllerLauncher.program_args = ['--reuse', 'ip=0.0.0.0', 'profile_dir=/path/to/cd']
 
 .. note::
 
     SSH mode does not do any file movement, so you will need to distribute configuration
     files manually.  To aid in this, the `reuse_files` flag defaults to True for ssh-launched
     Controllers, so you will only need to do this once, unless you override this flag back
     to False.
 
 Engines are specified in a dictionary, by hostname and the number of engines to be run
 on that host.
 
 .. sourcecode:: python
 
     c.SSHEngineSetLauncher.engines = { 'host1.example.com' : 2,
                 'host2.example.com' : 5,
                 'host3.example.com' : (1, ['profile_dir=/home/different/location']),
                 'host4.example.com' : 8 }
 
 * The `engines` dict, where the keys are the host we want to run engines on and
   the value is the number of engines to run on that host.
 * on host3, the value is a tuple, where the number of engines is first, and the arguments
   to be passed to :command:`ipengine` are the second element.
 
 For engines without explicitly specified arguments, the default arguments are set in
 a single location:
 
 .. sourcecode:: python
 
     c.SSHEngineSetLauncher.engine_args = ['profile_dir=/path/to/cluster_ssh']
 
 Current limitations of the SSH mode of :command:`ipcluster` are:
 
 * Untested on Windows. Would require a working :command:`ssh` on Windows.
   Also, we are using shell scripts to setup and execute commands on remote
   hosts.
 * No file movement - 
 
 Using the :command:`ipcontroller` and :command:`ipengine` commands
 ====================================================================
 
 It is also possible to use the :command:`ipcontroller` and :command:`ipengine`
 commands to start your controller and engines. This approach gives you full
 control over all aspects of the startup process.
 
 Starting the controller and engine on your local machine
 --------------------------------------------------------
 
 To use :command:`ipcontroller` and :command:`ipengine` to start things on your
 local machine, do the following.
 
 First start the controller::
 
     $ ipcontroller
     
 Next, start however many instances of the engine you want using (repeatedly)
 the command::
 
     $ ipengine
 
 The engines should start and automatically connect to the controller using the
 JSON files in :file:`~/.ipython/cluster_default/security`. You are now ready to use the
 controller and engines from IPython.
 
 .. warning:: 
     
     The order of the above operations may be important.  You *must*
     start the controller before the engines, unless you are reusing connection
     information (via `-r`), in which case ordering is not important.
 
 .. note::
 
     On some platforms (OS X), to put the controller and engine into the
     background you may need to give these commands in the form ``(ipcontroller
     &)`` and ``(ipengine &)`` (with the parentheses) for them to work
     properly.
 
 Starting the controller and engines on different hosts
 ------------------------------------------------------
 
 When the controller and engines are running on different hosts, things are
 slightly more complicated, but the underlying ideas are the same:
 
 1. Start the controller on a host using :command:`ipcontroller`.
 2. Copy :file:`ipcontroller-engine.json` from :file:`~/.ipython/profile_<name>/security` on
    the controller's host to the host where the engines will run.
 3. Use :command:`ipengine` on the engine's hosts to start the engines.
 
 The only thing you have to be careful of is to tell :command:`ipengine` where
 the :file:`ipcontroller-engine.json` file is located. There are two ways you
 can do this:
 
 * Put :file:`ipcontroller-engine.json` in the :file:`~/.ipython/profile_<name>/security`
   directory on the engine's host, where it will be found automatically.
 * Call :command:`ipengine` with the ``--file=full_path_to_the_file``
   flag.
 
 The ``--file`` flag works like this::
 
     $ ipengine --file=/path/to/my/ipcontroller-engine.json
 
 .. note::
     
     If the controller's and engine's hosts all have a shared file system  
     (:file:`~/.ipython/profile_<name>/security` is the same on all of them), then things
     will just work!
 
 Make JSON files persistent
 --------------------------
 
 At fist glance it may seem that that managing the JSON files is a bit
 annoying. Going back to the house and key analogy, copying the JSON around
 each time you start the controller is like having to make a new key every time
 you want to unlock the door and enter your house. As with your house, you want
 to be able to create the key (or JSON file) once, and then simply use it at
 any point in the future.
 
 To do this, the only thing you have to do is specify the `--reuse` flag, so that
 the connection information in the JSON files remains accurate::
 
     $ ipcontroller --reuse
 
 Then, just copy the JSON files over the first time and you are set. You can
 start and stop the controller and engines any many times as you want in the
 future, just make sure to tell the controller to reuse the file.
 
 .. note::
 
     You may ask the question: what ports does the controller listen on if you
     don't tell is to use specific ones? The default is to use high random port
     numbers. We do this for two reasons: i) to increase security through
     obscurity and ii) to multiple controllers on a given host to start and
     automatically use different ports.
 
 Log files
 ---------
 
 All of the components of IPython have log files associated with them.
 These log files can be extremely useful in debugging problems with
 IPython and can be found in the directory :file:`~/.ipython/profile_<name>/log`.
 Sending the log files to us will often help us to debug any problems.
 
 
 Configuring `ipcontroller`
 ---------------------------
 
 Ports and addresses
 *******************
 
 
 Database Backend
 ****************
 
 
 .. seealso::
 
     
 
 Configuring `ipengine`
 -----------------------
 
 .. note::
 
     TODO
 
 
 
 .. [PBS] Portable Batch System.  http://www.openpbs.org/
 .. [SSH] SSH-Agent http://en.wikipedia.org/wiki/ssh-agent

docs/source/parallel/parallel_winhpc.txt

@@ -1,334 +1,334 b''
 ============================================
 Getting started with Windows HPC Server 2008
 ============================================
 
 .. note::
 
     Not adapted to zmq yet
 
 Introduction
 ============
 
 The Python programming language is an increasingly popular language for
 numerical computing. This is due to a unique combination of factors. First,
 Python is a high-level and *interactive* language that is well matched to
 interactive numerical work. Second, it is easy (often times trivial) to
 integrate legacy C/C++/Fortran code into Python. Third, a large number of
 high-quality open source projects provide all the needed building blocks for
 numerical computing: numerical arrays (NumPy), algorithms (SciPy), 2D/3D
 Visualization (Matplotlib, Mayavi, Chaco), Symbolic Mathematics (Sage, Sympy)
 and others.
 
 The IPython project is a core part of this open-source toolchain and is
 focused on creating a comprehensive environment for interactive and
 exploratory computing in the Python programming language. It enables all of
 the above tools to be used interactively and consists of two main components:
 
 * An enhanced interactive Python shell with support for interactive plotting
   and visualization.
 * An architecture for interactive parallel computing.
 
 With these components, it is possible to perform all aspects of a parallel
 computation interactively. This type of workflow is particularly relevant in
 scientific and numerical computing where algorithms, code and data are
 continually evolving as the user/developer explores a problem. The broad
 treads in computing (commodity clusters, multicore, cloud computing, etc.)
 make these capabilities of IPython particularly relevant.
 
 While IPython is a cross platform tool, it has particularly strong support for
 Windows based compute clusters running Windows HPC Server 2008. This document
 describes how to get started with IPython on Windows HPC Server 2008. The
 content and emphasis here is practical: installing IPython, configuring
 IPython to use the Windows job scheduler and running example parallel programs
 interactively. A more complete description of IPython's parallel computing
 capabilities can be found in IPython's online documentation
 (http://ipython.scipy.org/moin/Documentation).
 
 Setting up your Windows cluster
 ===============================
 
 This document assumes that you already have a cluster running Windows
 HPC Server 2008. Here is a broad overview of what is involved with setting up
 such a cluster:
 
 1. Install Windows Server 2008 on the head and compute nodes in the cluster.
 2. Setup the network configuration on each host. Each host should have a 
    static IP address.
 3. On the head node, activate the "Active Directory Domain Services" role 
    and make the head node the domain controller.
 4. Join the compute nodes to the newly created Active Directory (AD) domain.
 5. Setup user accounts in the domain with shared home directories.
 6. Install the HPC Pack 2008 on the head node to create a cluster.
 7. Install the HPC Pack 2008 on the compute nodes.
 
 More details about installing and configuring Windows HPC Server 2008 can be
 found on the Windows HPC Home Page (http://www.microsoft.com/hpc). Regardless
 of what steps you follow to set up your cluster, the remainder of this
 document will assume that:
 
 * There are domain users that can log on to the AD domain and submit jobs
   to the cluster scheduler.
 * These domain users have shared home directories. While shared home
   directories are not required to use IPython, they make it much easier to
   use IPython.
 
 Installation of IPython and its dependencies
 ============================================
 
 IPython and all of its dependencies are freely available and open source.
 These packages provide a powerful and cost-effective approach to numerical and
 scientific computing on Windows. The following dependencies are needed to run
 IPython on Windows:
 
 * Python 2.6 or 2.7 (http://www.python.org)
 * pywin32 (http://sourceforge.net/projects/pywin32/)
 * PyReadline (https://launchpad.net/pyreadline)
 * pyzmq (http://github.com/zeromq/pyzmq/downloads)
 * IPython (http://ipython.scipy.org)
 
 In addition, the following dependencies are needed to run the demos described
 in this document.
 
 * NumPy and SciPy (http://www.scipy.org)
 * Matplotlib (http://matplotlib.sourceforge.net/)
 
 The easiest way of obtaining these dependencies is through the Enthought
 Python Distribution (EPD) (http://www.enthought.com/products/epd.php). EPD is
 produced by Enthought, Inc. and contains all of these packages and others in a
 single installer and is available free for academic users. While it is also
 possible to download and install each package individually, this is a tedious
 process. Thus, we highly recommend using EPD to install these packages on
 Windows.
 
 Regardless of how you install the dependencies, here are the steps you will
 need to follow:
 
 1. Install all of the packages listed above, either individually or using EPD
    on the head node, compute nodes and user workstations.
 
 2. Make sure that :file:`C:\\Python27` and :file:`C:\\Python27\\Scripts` are
    in the system :envvar:`%PATH%` variable on each node.
 
 3. Install the latest development version of IPython. This can be done by
    downloading the the development version from the IPython website
    (http://ipython.scipy.org) and following the installation instructions.
 
 Further details about installing IPython or its dependencies can be found in
 the online IPython documentation (http://ipython.scipy.org/moin/Documentation)
 Once you are finished with the installation, you can try IPython out by
 opening a Windows Command Prompt and typing ``ipython``. This will
 start IPython's interactive shell and you should see something like the
 following screenshot:
 
 .. image:: ipython_shell.*
 
 Starting an IPython cluster
 ===========================
 
 To use IPython's parallel computing capabilities, you will need to start an
 IPython cluster. An IPython cluster consists of one controller and multiple
 engines:
 
 IPython controller
     The IPython controller manages the engines and acts as a gateway between 
     the engines and the client, which runs in the user's interactive IPython
     session. The controller is started using the :command:`ipcontroller`
     command.
 
 IPython engine
     IPython engines run a user's Python code in parallel on the compute nodes. 
     Engines are starting using the :command:`ipengine` command.
 
 Once these processes are started, a user can run Python code interactively and
 in parallel on the engines from within the IPython shell using an appropriate
 client. This includes the ability to interact with, plot and visualize data
 from the engines.
 
 IPython has a command line program called :command:`ipcluster` that automates
 all aspects of starting the controller and engines on the compute nodes.
 :command:`ipcluster` has full support for the Windows HPC job scheduler,
 meaning that :command:`ipcluster` can use this job scheduler to start the
 controller and engines. In our experience, the Windows HPC job scheduler is
 particularly well suited for interactive applications, such as IPython. Once
 :command:`ipcluster` is configured properly, a user can start an IPython
 cluster from their local workstation almost instantly, without having to log
 on to the head node (as is typically required by Unix based job schedulers).
 This enables a user to move seamlessly between serial and parallel
 computations.
 
 In this section we show how to use :command:`ipcluster` to start an IPython
 cluster using the Windows HPC Server 2008 job scheduler. To make sure that
 :command:`ipcluster` is installed and working properly, you should first try
 to start an IPython cluster on your local host. To do this, open a Windows
 Command Prompt and type the following command::
 
     ipcluster start n=2
 
 You should see a number of messages printed to the screen, ending with 
 "IPython cluster: started". The result should look something like the following
 screenshot:
 
 .. image:: ipcluster_start.*
 
 At this point, the controller and two engines are running on your local host.
 This configuration is useful for testing and for situations where you want to
 take advantage of multiple cores on your local computer. 
 
 Now that we have confirmed that :command:`ipcluster` is working properly, we
 describe how to configure and run an IPython cluster on an actual compute
 cluster running Windows HPC Server 2008. Here is an outline of the needed
 steps:
 
-1. Create a cluster profile using: ``ipython profile create --cluster profile=mycluster``
+1. Create a cluster profile using: ``ipython profile create --parallel profile=mycluster``
 
 2. Edit configuration files in the directory :file:`.ipython\\cluster_mycluster`
 
 3. Start the cluster using: ``ipcluser start profile=mycluster n=32``
 
 Creating a cluster profile
 --------------------------
 
 In most cases, you will have to create a cluster profile to use IPython on a
 cluster. A cluster profile is a name (like "mycluster") that is associated
 with a particular cluster configuration. The profile name is used by
 :command:`ipcluster` when working with the cluster.
 
 Associated with each cluster profile is a cluster directory. This cluster
 directory is a specially named directory (typically located in the
 :file:`.ipython` subdirectory of your home directory) that contains the
 configuration files for a particular cluster profile, as well as log files and
 security keys. The naming convention for cluster directories is:
 :file:`profile_<profile name>`. Thus, the cluster directory for a profile named
 "foo" would be :file:`.ipython\\cluster_foo`.
 
 To create a new cluster profile (named "mycluster") and the associated cluster
 directory, type the following command at the Windows Command Prompt::
 
-    ipython profile create --cluster profile=mycluster
+    ipython profile create --parallel profile=mycluster
 
 The output of this command is shown in the screenshot below. Notice how
 :command:`ipcluster` prints out the location of the newly created cluster
 directory.
 
 .. image:: ipcluster_create.*
 
 Configuring a cluster profile
 -----------------------------
 
 Next, you will need to configure the newly created cluster profile by editing
 the following configuration files in the cluster directory:
 
 * :file:`ipcluster_config.py`
 * :file:`ipcontroller_config.py`
 * :file:`ipengine_config.py`
 
 When :command:`ipcluster` is run, these configuration files are used to 
 determine how the engines and controller will be started. In most cases,
 you will only have to set a few of the attributes in these files.
 
 To configure :command:`ipcluster` to use the Windows HPC job scheduler, you
 will need to edit the following attributes in the file
 :file:`ipcluster_config.py`::
 
     # Set these at the top of the file to tell ipcluster to use the
     # Windows HPC job scheduler.
     c.Global.controller_launcher = \
         'IPython.parallel.apps.launcher.WindowsHPCControllerLauncher'
     c.Global.engine_launcher = \
         'IPython.parallel.apps.launcher.WindowsHPCEngineSetLauncher'
 
     # Set these to the host name of the scheduler (head node) of your cluster.
     c.WindowsHPCControllerLauncher.scheduler = 'HEADNODE'
     c.WindowsHPCEngineSetLauncher.scheduler = 'HEADNODE'
 
 There are a number of other configuration attributes that can be set, but
 in most cases these will be sufficient to get you started.
 
 .. warning::
     If any of your configuration attributes involve specifying the location
     of shared directories or files, you must make sure that you use UNC paths
     like :file:`\\\\host\\share`. It is also important that you specify
     these paths using raw Python strings: ``r'\\host\share'`` to make sure
     that the backslashes are properly escaped.
 
 Starting the cluster profile
 ----------------------------
 
 Once a cluster profile has been configured, starting an IPython cluster using
 the profile is simple::
 
     ipcluster start profile=mycluster n=32
 
 The ``-n`` option tells :command:`ipcluster` how many engines to start (in
 this case 32). Stopping the cluster is as simple as typing Control-C.
 
 Using the HPC Job Manager
 -------------------------
 
 When ``ipcluster start`` is run the first time, :command:`ipcluster` creates
 two XML job description files in the cluster directory:
 
 * :file:`ipcontroller_job.xml`
 * :file:`ipengineset_job.xml`
 
 Once these files have been created, they can be imported into the HPC Job
 Manager application. Then, the controller and engines for that profile can be
 started using the HPC Job Manager directly, without using :command:`ipcluster`.
 However, anytime the cluster profile is re-configured, ``ipcluster start``
 must be run again to regenerate the XML job description files. The
 following screenshot shows what the HPC Job Manager interface looks like
 with a running IPython cluster.
 
 .. image:: hpc_job_manager.*
 
 Performing a simple interactive parallel computation
 ====================================================
 
 Once you have started your IPython cluster, you can start to use it. To do
 this, open up a new Windows Command Prompt and start up IPython's interactive
 shell by typing::
 
     ipython
 
 Then you can create a :class:`MultiEngineClient` instance for your profile and
 use the resulting instance to do a simple interactive parallel computation. In
 the code and screenshot that follows, we take a simple Python function and
 apply it to each element of an array of integers in parallel using the
 :meth:`MultiEngineClient.map` method:
 
 .. sourcecode:: ipython
 
     In [1]: from IPython.parallel import *
 
     In [2]: c = MultiEngineClient(profile='mycluster')
 
     In [3]: mec.get_ids()
     Out[3]: [0, 1, 2, 3, 4, 5, 67, 8, 9, 10, 11, 12, 13, 14]
 
     In [4]: def f(x):
        ...:     return x**10
 
     In [5]: mec.map(f, range(15))  # f is applied in parallel
     Out[5]:
     [0,
      1,
      1024,
      59049,
      1048576,
      9765625,
      60466176,
      282475249,
      1073741824,
      3486784401L,
      10000000000L,
      25937424601L,
      61917364224L,
      137858491849L,
      289254654976L]
 
 The :meth:`map` method has the same signature as Python's builtin :func:`map`
 function, but runs the calculation in parallel. More involved examples of using
 :class:`MultiEngineClient` are provided in the examples that follow.
 
 .. image:: mec_simple.*