Fix for ipcluster bug: https://bugs.launchpad.net/bugs/358202

To fix this bug, I have added a new function wait_for_file that waits 
for a file to be created and then fires a Deferred.  This is then used 
in ipcluster to wait for the controller to create the engine FURL file.
The controller is also not creating its FURL files as a temp file and
the moving them to make sure that the IO buffer has been flushed.

IPython/kernel/engineconnector.py

@@ -1,92 +1,92 b''
 # encoding: utf-8
 
 """A class that manages the engines connection to the controller."""
 
 __docformat__ = "restructuredtext en"
 
 #-------------------------------------------------------------------------------
 #  Copyright (C) 2008  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 os
 import cPickle as pickle
 
 from twisted.python import log, failure
 from twisted.internet import defer
 
 from IPython.kernel.fcutil import find_furl
 from IPython.kernel.enginefc import IFCEngine
 
 #-------------------------------------------------------------------------------
 # The ClientConnector class
 #-------------------------------------------------------------------------------
 
 class EngineConnector(object):
     """Manage an engines connection to a controller.
     
     This class takes a foolscap `Tub` and provides a `connect_to_controller` 
     method that will use the `Tub` to connect to a controller and register
     the engine with the controller.
     """
     
     def __init__(self, tub):
         self.tub = tub
         
     def connect_to_controller(self, engine_service, furl_or_file):
         """
         Make a connection to a controller specified by a furl.
         
         This method takes an `IEngineBase` instance and a foolcap URL and uses
         the `tub` attribute to make a connection to the controller.  The 
         foolscap URL contains all the information needed to connect to the 
         controller, including the ip and port as well as any encryption and 
         authentication information needed for the connection.
         
         After getting a reference to the controller, this method calls the 
         `register_engine` method of the controller to actually register the 
         engine.
         
         :Parameters:
             engine_service : IEngineBase
                 An instance of an `IEngineBase` implementer
             furl_or_file : str
                 A furl or a filename containing a furl
         """
         if not self.tub.running:
             self.tub.startService()
         self.engine_service = engine_service
         self.engine_reference = IFCEngine(self.engine_service)
         try:
             self.furl = find_furl(furl_or_file)
         except ValueError:
             return defer.fail(failure.Failure())
-            # return defer.fail(failure.Failure(ValueError('not a valid furl or furl file: %r' % furl_or_file)))
-        d = self.tub.getReference(self.furl)
-        d.addCallbacks(self._register, self._log_failure)
-        return d
+        else:
+            d = self.tub.getReference(self.furl)
+            d.addCallbacks(self._register, self._log_failure)
+            return d
     
     def _log_failure(self, reason):
         log.err('EngineConnector: engine registration failed:')
         log.err(reason)
         return reason
 
     def _register(self, rr):
         self.remote_ref = rr
         # Now register myself with the controller
         desired_id = self.engine_service.id
         d = self.remote_ref.callRemote('register_engine', self.engine_reference, 
             desired_id, os.getpid(), pickle.dumps(self.engine_service.properties,2))
         return d.addCallbacks(self._reference_sent, self._log_failure)
 
     def _reference_sent(self, registration_dict):
         self.engine_service.id = registration_dict['id']
         log.msg("engine registration succeeded, got id: %r" % self.engine_service.id)
         return self.engine_service.id
 

IPython/kernel/error.py

@@ -1,185 +1,188 b''
 # encoding: utf-8
 
 """Classes and functions for kernel related errors and exceptions."""
 
 __docformat__ = "restructuredtext en"
 
 #-------------------------------------------------------------------------------
 #  Copyright (C) 2008  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
 #-------------------------------------------------------------------------------
 
 from IPython.kernel.core import error
 from twisted.python import failure
 
 #-------------------------------------------------------------------------------
 # Error classes
 #-------------------------------------------------------------------------------
 
 class KernelError(error.IPythonError):
     pass
 
 class NotDefined(KernelError):
     def __init__(self, name):
         self.name = name
         self.args = (name,)
 
     def __repr__(self):
         return '<NotDefined: %s>' % self.name
     
     __str__ = __repr__
 
 class QueueCleared(KernelError):
     pass
 
 class IdInUse(KernelError):
     pass
 
 class ProtocolError(KernelError):
     pass
 
 class ConnectionError(KernelError):
     pass
 
 class InvalidEngineID(KernelError):
     pass
     
 class NoEnginesRegistered(KernelError):
     pass
     
 class InvalidClientID(KernelError):
     pass
     
 class InvalidDeferredID(KernelError):
     pass
     
 class SerializationError(KernelError):
     pass
     
 class MessageSizeError(KernelError):
     pass
     
 class PBMessageSizeError(MessageSizeError):
     pass
     
 class ResultNotCompleted(KernelError):
     pass
     
 class ResultAlreadyRetrieved(KernelError):
     pass
     
 class ClientError(KernelError):
     pass
 
 class TaskAborted(KernelError):
     pass
 
 class TaskTimeout(KernelError):
     pass
 
 class NotAPendingResult(KernelError):
     pass
 
 class UnpickleableException(KernelError):
     pass
 
 class AbortedPendingDeferredError(KernelError):
     pass
 
 class InvalidProperty(KernelError):
     pass
 
 class MissingBlockArgument(KernelError):
     pass
 
 class StopLocalExecution(KernelError):
     pass
 
 class SecurityError(KernelError):
     pass
 
+class FileTimeoutError(KernelError):
+    pass
+
 class CompositeError(KernelError):
     def __init__(self, message, elist):
         Exception.__init__(self, *(message, elist))
         self.message = message
         self.elist = elist
   
     def _get_engine_str(self, ev):
         try:
             ei = ev._ipython_engine_info
         except AttributeError:
             return '[Engine Exception]'
         else:
             return '[%i:%s]: ' % (ei['engineid'], ei['method'])
     
     def _get_traceback(self, ev):
         try:
             tb = ev._ipython_traceback_text
         except AttributeError:
             return 'No traceback available'
         else:
             return tb
   
     def __str__(self):
         s = str(self.message)
         for et, ev, etb in self.elist:
             engine_str = self._get_engine_str(ev)
             s = s + '\n' + engine_str + str(et.__name__) + ': ' + str(ev)
         return s
     
     def print_tracebacks(self, excid=None):
         if excid is None:
             for (et,ev,etb) in self.elist:
                 print self._get_engine_str(ev)
                 print self._get_traceback(ev)
                 print
         else:
             try:
                 et,ev,etb = self.elist[excid]
             except:
                 raise IndexError("an exception with index %i does not exist"%excid)
             else:
                 print self._get_engine_str(ev)
                 print self._get_traceback(ev)
     
     def raise_exception(self, excid=0):
         try:
             et,ev,etb = self.elist[excid]
         except:
             raise IndexError("an exception with index %i does not exist"%excid)
         else:
             raise et, ev, etb
 
 def collect_exceptions(rlist, method):
     elist = []
     for r in rlist:
         if isinstance(r, failure.Failure):
             r.cleanFailure()
             et, ev, etb = r.type, r.value, r.tb
             # Sometimes we could have CompositeError in our list.  Just take
             # the errors out of them and put them in our new list.  This 
             # has the effect of flattening lists of CompositeErrors into one
             # CompositeError
             if et==CompositeError:
                 for e in ev.elist:
                     elist.append(e)
             else:
                 elist.append((et, ev, etb))
     if len(elist)==0:
         return rlist
     else:
         msg = "one or more exceptions from call to method: %s" % (method)
         # This silliness is needed so the debugger has access to the exception
         # instance (e in this case)
         try:
             raise CompositeError(msg, elist)
         except CompositeError, e:
             raise e
             
 

IPython/kernel/scripts/ipcluster.py

@@ -1,787 +1,801 b''
  #!/usr/bin/env python
 # encoding: utf-8
 
 """Start an IPython cluster = (controller + engines)."""
 
 #-----------------------------------------------------------------------------
 #  Copyright (C) 2008  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 os
 import re
 import sys
 import signal
 import tempfile
 pjoin = os.path.join
 
 from twisted.internet import reactor, defer
 from twisted.internet.protocol import ProcessProtocol
 from twisted.internet.error import ProcessDone, ProcessTerminated
 from twisted.internet.utils import getProcessOutput
 from twisted.python import failure, log
 
 from IPython.external import argparse
 from IPython.external import Itpl
 from IPython.genutils import get_ipython_dir, num_cpus
 from IPython.kernel.fcutil import have_crypto
-from IPython.kernel.error import SecurityError
+from IPython.kernel.config import config_manager as kernel_config_manager
+from IPython.kernel.error import SecurityError, FileTimeoutError
 from IPython.kernel.fcutil import have_crypto
-from IPython.kernel.twistedutil import gatherBoth
+from IPython.kernel.twistedutil import gatherBoth, wait_for_file
 from IPython.kernel.util import printer
 
 
 #-----------------------------------------------------------------------------
 # General process handling code
 #-----------------------------------------------------------------------------
 
 def find_exe(cmd):
     try:
         import win32api
     except ImportError:
         raise ImportError('you need to have pywin32 installed for this to work')
     else:
         try:
             (path, offest) = win32api.SearchPath(os.environ['PATH'],cmd + '.exe')
         except:
             (path, offset) = win32api.SearchPath(os.environ['PATH'],cmd + '.bat')
     return path
 
 class ProcessStateError(Exception):
     pass
 
 class UnknownStatus(Exception):
     pass
 
 class LauncherProcessProtocol(ProcessProtocol):
     """
     A ProcessProtocol to go with the ProcessLauncher.
     """
     def __init__(self, process_launcher):
         self.process_launcher = process_launcher
     
     def connectionMade(self):
         self.process_launcher.fire_start_deferred(self.transport.pid)
     
     def processEnded(self, status):
         value = status.value
         if isinstance(value, ProcessDone):
             self.process_launcher.fire_stop_deferred(0)
         elif isinstance(value, ProcessTerminated):
             self.process_launcher.fire_stop_deferred(
                 {'exit_code':value.exitCode,
                  'signal':value.signal,
                  'status':value.status
                 }
             )
         else:
             raise UnknownStatus("unknown exit status, this is probably a bug in Twisted")
     
     def outReceived(self, data):
         log.msg(data)
     
     def errReceived(self, data):
         log.err(data)
 
 class ProcessLauncher(object):
     """
     Start and stop an external process in an asynchronous manner.
     
     Currently this uses deferreds to notify other parties of process state
     changes.  This is an awkward design and should be moved to using
     a formal NotificationCenter.
     """
     def __init__(self, cmd_and_args):
         self.cmd = cmd_and_args[0]
         self.args = cmd_and_args
         self._reset()
     
     def _reset(self):
         self.process_protocol = None
         self.pid = None
         self.start_deferred = None
         self.stop_deferreds = []
         self.state = 'before' # before, running, or after
     
     @property
     def running(self):
         if self.state == 'running':
             return True
         else:
             return False
     
     def fire_start_deferred(self, pid):
         self.pid = pid
         self.state = 'running'
         log.msg('Process %r has started with pid=%i' % (self.args, pid))
         self.start_deferred.callback(pid)
     
     def start(self):
         if self.state == 'before':
             self.process_protocol = LauncherProcessProtocol(self)
             self.start_deferred = defer.Deferred()
             self.process_transport = reactor.spawnProcess(
                 self.process_protocol,
                 self.cmd,
                 self.args,
                 env=os.environ
             )
             return self.start_deferred
         else:
             s = 'the process has already been started and has state: %r' % \
                 self.state
             return defer.fail(ProcessStateError(s))
     
     def get_stop_deferred(self):
         if self.state == 'running' or self.state == 'before':
             d = defer.Deferred()
             self.stop_deferreds.append(d)
             return d
         else:
             s = 'this process is already complete'
             return defer.fail(ProcessStateError(s))
     
     def fire_stop_deferred(self, exit_code):
         log.msg('Process %r has stopped with %r' % (self.args, exit_code))
         self.state = 'after'
         for d in self.stop_deferreds:
             d.callback(exit_code)
     
     def signal(self, sig):
         """
         Send a signal to the process.
         
         The argument sig can be ('KILL','INT', etc.) or any signal number.
         """
         if self.state == 'running':
             self.process_transport.signalProcess(sig)
     
     # def __del__(self):
     #     self.signal('KILL')
     
     def interrupt_then_kill(self, delay=1.0):
         self.signal('INT')
         reactor.callLater(delay, self.signal, 'KILL')
 
 
 #-----------------------------------------------------------------------------
 # Code for launching controller and engines
 #-----------------------------------------------------------------------------
 
 
 class ControllerLauncher(ProcessLauncher):
     
     def __init__(self, extra_args=None):
         if sys.platform == 'win32':
             # This logic is needed because the ipcontroller script doesn't
             # always get installed in the same way or in the same location.
             from IPython.kernel.scripts import ipcontroller
             script_location = ipcontroller.__file__.replace('.pyc', '.py')
             # The -u option here turns on unbuffered output, which is required
             # on Win32 to prevent wierd conflict and problems with Twisted.
             # Also, use sys.executable to make sure we are picking up the 
             # right python exe.
             args = [sys.executable, '-u', script_location]
         else:
             args = ['ipcontroller']
         self.extra_args = extra_args
         if extra_args is not None:
             args.extend(extra_args)
         
         ProcessLauncher.__init__(self, args)
 
 
 class EngineLauncher(ProcessLauncher):
     
     def __init__(self, extra_args=None):
         if sys.platform == 'win32':
             # This logic is needed because the ipcontroller script doesn't
             # always get installed in the same way or in the same location.
             from IPython.kernel.scripts import ipengine
             script_location = ipengine.__file__.replace('.pyc', '.py')
             # The -u option here turns on unbuffered output, which is required
             # on Win32 to prevent wierd conflict and problems with Twisted.
             # Also, use sys.executable to make sure we are picking up the 
             # right python exe.
             args = [sys.executable, '-u', script_location]
         else:
             args = ['ipengine']
         self.extra_args = extra_args
         if extra_args is not None:
             args.extend(extra_args)
         
         ProcessLauncher.__init__(self, args)
 
 
 class LocalEngineSet(object):
     
     def __init__(self, extra_args=None):
         self.extra_args = extra_args
         self.launchers = []
     
     def start(self, n):
         dlist = []
         for i in range(n):
             el = EngineLauncher(extra_args=self.extra_args)
             d = el.start()
             self.launchers.append(el)
             dlist.append(d)
         dfinal = gatherBoth(dlist, consumeErrors=True)
         dfinal.addCallback(self._handle_start)
         return dfinal
     
     def _handle_start(self, r):
         log.msg('Engines started with pids: %r' % r)
         return r
     
     def _handle_stop(self, r):
         log.msg('Engines received signal: %r' % r)
         return r
     
     def signal(self, sig):
         dlist = []
         for el in self.launchers:
             d = el.get_stop_deferred()
             dlist.append(d)
             el.signal(sig)
         dfinal = gatherBoth(dlist, consumeErrors=True)
         dfinal.addCallback(self._handle_stop)
         return dfinal
     
     def interrupt_then_kill(self, delay=1.0):
         dlist = []
         for el in self.launchers:
             d = el.get_stop_deferred()
             dlist.append(d)
             el.interrupt_then_kill(delay)
         dfinal = gatherBoth(dlist, consumeErrors=True)
         dfinal.addCallback(self._handle_stop)
         return dfinal
 
 
 class BatchEngineSet(object):
     
     # Subclasses must fill these in.  See PBSEngineSet
     submit_command = ''
     delete_command = ''
     job_id_regexp = ''
     
     def __init__(self, template_file, **kwargs):
         self.template_file = template_file
         self.context = {}
         self.context.update(kwargs)
         self.batch_file = self.template_file+'-run'
     
     def parse_job_id(self, output):
         m = re.match(self.job_id_regexp, output)
         if m is not None:
             job_id = m.group()
         else:
             raise Exception("job id couldn't be determined: %s" % output)
         self.job_id = job_id
         log.msg('Job started with job id: %r' % job_id)
         return job_id
     
     def write_batch_script(self, n):
         self.context['n'] = n
         template = open(self.template_file, 'r').read()
         log.msg('Using template for batch script: %s' % self.template_file)
         script_as_string = Itpl.itplns(template, self.context)
         log.msg('Writing instantiated batch script: %s' % self.batch_file)
         f = open(self.batch_file,'w')
         f.write(script_as_string)
         f.close()
     
     def handle_error(self, f):
         f.printTraceback()
         f.raiseException()
     
     def start(self, n):
         self.write_batch_script(n)
         d = getProcessOutput(self.submit_command,
             [self.batch_file],env=os.environ)
         d.addCallback(self.parse_job_id)
         d.addErrback(self.handle_error)
         return d
     
     def kill(self):
         d = getProcessOutput(self.delete_command,
             [self.job_id],env=os.environ)
         return d
 
 class PBSEngineSet(BatchEngineSet):
     
     submit_command = 'qsub'
     delete_command = 'qdel'
     job_id_regexp = '\d+'
     
     def __init__(self, template_file, **kwargs):
         BatchEngineSet.__init__(self, template_file, **kwargs)
 
 
 sshx_template="""#!/bin/sh
 "$@" &> /dev/null &
 echo $!
 """
 
 engine_killer_template="""#!/bin/sh
 ps -fu `whoami` | grep '[i]pengine' | awk '{print $2}' | xargs kill -TERM
 """
 
 class SSHEngineSet(object):
     sshx_template=sshx_template
     engine_killer_template=engine_killer_template
     
     def __init__(self, engine_hosts, sshx=None, ipengine="ipengine"):
         """Start a controller on localhost and engines using ssh.
         
         The engine_hosts argument is a dict with hostnames as keys and
         the number of engine (int) as values.  sshx is the name of a local
         file that will be used to run remote commands.  This file is used
         to setup the environment properly.
         """
         
         self.temp_dir = tempfile.gettempdir()
         if sshx is not None:
             self.sshx = sshx
         else:
             # Write the sshx.sh file locally from our template.
             self.sshx = os.path.join(
                 self.temp_dir,
                 '%s-main-sshx.sh' % os.environ['USER']
             )
             f = open(self.sshx, 'w')
             f.writelines(self.sshx_template)
             f.close()
         self.engine_command = ipengine
         self.engine_hosts = engine_hosts
         # Write the engine killer script file locally from our template.
         self.engine_killer = os.path.join(
             self.temp_dir,  
             '%s-local-engine_killer.sh' % os.environ['USER']
         )
         f = open(self.engine_killer, 'w')
         f.writelines(self.engine_killer_template)
         f.close()
     
     def start(self, send_furl=False):
         dlist = []
         for host in self.engine_hosts.keys():
             count = self.engine_hosts[host]
             d = self._start(host, count, send_furl)
             dlist.append(d)
         return gatherBoth(dlist, consumeErrors=True)
     
     def _start(self, hostname, count=1, send_furl=False):
         if send_furl:
             d = self._scp_furl(hostname)
         else:
             d = defer.succeed(None)
         d.addCallback(lambda r: self._scp_sshx(hostname))
         d.addCallback(lambda r: self._ssh_engine(hostname, count))
         return d
         
     def _scp_furl(self, hostname):
         scp_cmd = "scp ~/.ipython/security/ipcontroller-engine.furl %s:.ipython/security/" % (hostname)
         cmd_list = scp_cmd.split()
         cmd_list[1] = os.path.expanduser(cmd_list[1])
         log.msg('Copying furl file: %s' % scp_cmd)
         d = getProcessOutput(cmd_list[0], cmd_list[1:], env=os.environ) 
         return d
     
     def _scp_sshx(self, hostname):
         scp_cmd = "scp %s %s:%s/%s-sshx.sh" % (
             self.sshx, hostname, 
             self.temp_dir, os.environ['USER']
         )
         print
         log.msg("Copying sshx: %s" % scp_cmd)
         sshx_scp = scp_cmd.split()
         d = getProcessOutput(sshx_scp[0], sshx_scp[1:], env=os.environ)
         return d
     
     def _ssh_engine(self, hostname, count):
         exec_engine = "ssh %s sh %s/%s-sshx.sh %s" % (
             hostname, self.temp_dir, 
             os.environ['USER'], self.engine_command
         )
         cmds = exec_engine.split()
         dlist = []
         log.msg("about to start engines...")
         for i in range(count):
             log.msg('Starting engines: %s' % exec_engine)
             d = getProcessOutput(cmds[0], cmds[1:], env=os.environ)
             dlist.append(d)
         return gatherBoth(dlist, consumeErrors=True)
     
     def kill(self):
         dlist = []
         for host in self.engine_hosts.keys():
             d = self._killall(host)
             dlist.append(d)
         return gatherBoth(dlist, consumeErrors=True)
     
     def _killall(self, hostname):
         d = self._scp_engine_killer(hostname)
         d.addCallback(lambda r: self._ssh_kill(hostname))
         # d.addErrback(self._exec_err)
         return d
 
     def _scp_engine_killer(self, hostname):
         scp_cmd = "scp %s %s:%s/%s-engine_killer.sh" % (
             self.engine_killer, 
             hostname, 
             self.temp_dir, 
             os.environ['USER']
         )
         cmds = scp_cmd.split()
         log.msg('Copying engine_killer: %s' % scp_cmd)
         d = getProcessOutput(cmds[0], cmds[1:], env=os.environ)
         return d
     
     def _ssh_kill(self, hostname):
         kill_cmd = "ssh %s sh %s/%s-engine_killer.sh" % (
             hostname,
             self.temp_dir, 
             os.environ['USER']
         )
         log.msg('Killing engine: %s' % kill_cmd)
         kill_cmd = kill_cmd.split()
         d = getProcessOutput(kill_cmd[0], kill_cmd[1:], env=os.environ)
         return d
 
     def _exec_err(self, r):
         log.msg(r)
 
 #-----------------------------------------------------------------------------
 # Main functions for the different types of clusters
 #-----------------------------------------------------------------------------
 
 # TODO:
 # The logic in these codes should be moved into classes like LocalCluster
 # MpirunCluster, PBSCluster, etc.  This would remove alot of the duplications.
 # The main functions should then just parse the command line arguments, create
 # the appropriate class and call a 'start' method.
 
+
 def check_security(args, cont_args):
     if (not args.x or not args.y) and not have_crypto:
         log.err("""
 OpenSSL/pyOpenSSL is not available, so we can't run in secure mode.
 Try running ipcluster with the -xy flags:  ipcluster local -xy -n 4""")
         reactor.stop()
         return False
     if args.x:
         cont_args.append('-x')
     if args.y:
         cont_args.append('-y')
     return True
 
+
 def check_reuse(args, cont_args):
     if args.r:
         cont_args.append('-r')
         if args.client_port == 0 or args.engine_port == 0:
             log.err("""
 To reuse FURL files, you must also set the client and engine ports using
 the --client-port and --engine-port options.""")
             reactor.stop()
             return False
         cont_args.append('--client-port=%i' % args.client_port)
         cont_args.append('--engine-port=%i' % args.engine_port)
     return True
 
+
+def _err_and_stop(f):
+    log.err(f)
+    reactor.stop()
+
+
+def _delay_start(cont_pid, start_engines, furl_file, reuse):
+    if not reuse:
+        if os.path.isfile(furl_file):
+            os.unlink(furl_file)
+    log.msg('Waiting for controller to finish starting...')
+    d = wait_for_file(furl_file, delay=0.2, max_tries=50)
+    d.addCallback(lambda _: log.msg('Controller started'))
+    d.addCallback(lambda _: start_engines(cont_pid))
+    return d
+
+
 def main_local(args):
     cont_args = []
     cont_args.append('--logfile=%s' % pjoin(args.logdir,'ipcontroller'))
     
     # Check security settings before proceeding
     if not check_security(args, cont_args):
         return
     
     # See if we are reusing FURL files
     if not check_reuse(args, cont_args):
         return
     
     cl = ControllerLauncher(extra_args=cont_args)
     dstart = cl.start()
     def start_engines(cont_pid):
         engine_args = []
         engine_args.append('--logfile=%s' % \
             pjoin(args.logdir,'ipengine%s-' % cont_pid))
         eset = LocalEngineSet(extra_args=engine_args)
         def shutdown(signum, frame):
             log.msg('Stopping local cluster')
             # We are still playing with the times here, but these seem
             # to be reliable in allowing everything to exit cleanly.
             eset.interrupt_then_kill(0.5)
             cl.interrupt_then_kill(0.5)
             reactor.callLater(1.0, reactor.stop)
         signal.signal(signal.SIGINT,shutdown)
         d = eset.start(args.n)
         return d
-    def delay_start(cont_pid):
-        # This is needed because the controller doesn't start listening
-        # right when it starts and the controller needs to write
-        # furl files for the engine to pick up
-        reactor.callLater(1.0, start_engines, cont_pid)
-    dstart.addCallback(delay_start)
-    dstart.addErrback(lambda f: f.raiseException())
+    config = kernel_config_manager.get_config_obj()
+    furl_file = config['controller']['engine_furl_file']
+    dstart.addCallback(_delay_start, start_engines, furl_file, args.r)
+    dstart.addErrback(_err_and_stop)
 
 
 def main_mpi(args):
     cont_args = []
     cont_args.append('--logfile=%s' % pjoin(args.logdir,'ipcontroller'))
     
     # Check security settings before proceeding
     if not check_security(args, cont_args):
         return
     
     # See if we are reusing FURL files
     if not check_reuse(args, cont_args):
         return
     
     cl = ControllerLauncher(extra_args=cont_args)
     dstart = cl.start()
     def start_engines(cont_pid):
         raw_args = [args.cmd]
         raw_args.extend(['-n',str(args.n)])
         raw_args.append('ipengine')
         raw_args.append('-l')
         raw_args.append(pjoin(args.logdir,'ipengine%s-' % cont_pid))
         if args.mpi:
             raw_args.append('--mpi=%s' % args.mpi)
         eset = ProcessLauncher(raw_args)
         def shutdown(signum, frame):
             log.msg('Stopping local cluster')
             # We are still playing with the times here, but these seem
             # to be reliable in allowing everything to exit cleanly.
             eset.interrupt_then_kill(1.0)
             cl.interrupt_then_kill(1.0)
             reactor.callLater(2.0, reactor.stop)
         signal.signal(signal.SIGINT,shutdown)
         d = eset.start()
         return d
-    def delay_start(cont_pid):
-        # This is needed because the controller doesn't start listening
-        # right when it starts and the controller needs to write
-        # furl files for the engine to pick up
-        reactor.callLater(1.0, start_engines, cont_pid)
-    dstart.addCallback(delay_start)
-    dstart.addErrback(lambda f: f.raiseException())
+    config = kernel_config_manager.get_config_obj()
+    furl_file = config['controller']['engine_furl_file']
+    dstart.addCallback(_delay_start, start_engines, furl_file, args.r)
+    dstart.addErrback(_err_and_stop)
 
 
 def main_pbs(args):
     cont_args = []
     cont_args.append('--logfile=%s' % pjoin(args.logdir,'ipcontroller'))
     
     # Check security settings before proceeding
     if not check_security(args, cont_args):
         return
     
     # See if we are reusing FURL files
     if not check_reuse(args, cont_args):
         return
     
     cl = ControllerLauncher(extra_args=cont_args)
     dstart = cl.start()
     def start_engines(r):
         pbs_set =  PBSEngineSet(args.pbsscript)
         def shutdown(signum, frame):
             log.msg('Stopping pbs cluster')
             d = pbs_set.kill()
             d.addBoth(lambda _: cl.interrupt_then_kill(1.0))
             d.addBoth(lambda _: reactor.callLater(2.0, reactor.stop))
         signal.signal(signal.SIGINT,shutdown)
         d = pbs_set.start(args.n)
         return d
-    dstart.addCallback(start_engines)
-    dstart.addErrback(lambda f: f.raiseException())
+    config = kernel_config_manager.get_config_obj()
+    furl_file = config['controller']['engine_furl_file']
+    dstart.addCallback(_delay_start, start_engines, furl_file, args.r)
+    dstart.addErrback(_err_and_stop)
 
 
 def main_ssh(args):
     """Start a controller on localhost and engines using ssh.
     
     Your clusterfile should look like::
     
         send_furl = False # True, if you want 
         engines = {
             'engine_host1' : engine_count, 
             'engine_host2' : engine_count2
         } 
     """
     clusterfile = {}
     execfile(args.clusterfile, clusterfile)
     if not clusterfile.has_key('send_furl'):
         clusterfile['send_furl'] = False
         
     cont_args = []
     cont_args.append('--logfile=%s' % pjoin(args.logdir,'ipcontroller'))
     
     # Check security settings before proceeding
     if not check_security(args, cont_args):
         return
     
     # See if we are reusing FURL files
     if not check_reuse(args, cont_args):
         return
     
     cl = ControllerLauncher(extra_args=cont_args)
     dstart = cl.start()
     def start_engines(cont_pid):
         ssh_set = SSHEngineSet(clusterfile['engines'], sshx=args.sshx)
         def shutdown(signum, frame):
             d = ssh_set.kill()
             cl.interrupt_then_kill(1.0)
             reactor.callLater(2.0, reactor.stop)
         signal.signal(signal.SIGINT,shutdown)
         d = ssh_set.start(clusterfile['send_furl'])
         return d
-    
-    def delay_start(cont_pid):
-        reactor.callLater(1.0, start_engines, cont_pid)
-        
-    dstart.addCallback(delay_start)
-    dstart.addErrback(lambda f: f.raiseException())
+    config = kernel_config_manager.get_config_obj()
+    furl_file = config['controller']['engine_furl_file']
+    dstart.addCallback(_delay_start, start_engines, furl_file, args.r)
+    dstart.addErrback(_err_and_stop)
 
 
 def get_args():
     base_parser = argparse.ArgumentParser(add_help=False)
     base_parser.add_argument(
         '-r',
         action='store_true',
         dest='r',
         help='try to reuse FURL files.  Use with --client-port and --engine-port'
     )
     base_parser.add_argument(
         '--client-port',
         type=int,
         dest='client_port',
         help='the port the controller will listen on for client connections',
         default=0
     )
     base_parser.add_argument(
         '--engine-port',
         type=int,
         dest='engine_port',
         help='the port the controller will listen on for engine connections',
         default=0
     )
     base_parser.add_argument(
         '-x',
         action='store_true',
         dest='x',
         help='turn off client security'
     )
     base_parser.add_argument(
         '-y',
         action='store_true',
         dest='y',
         help='turn off engine security'
     )
     base_parser.add_argument(
         "--logdir", 
         type=str,
         dest="logdir",
         help="directory to put log files (default=$IPYTHONDIR/log)",
         default=pjoin(get_ipython_dir(),'log')
     )
     base_parser.add_argument(
         "-n",
         "--num", 
         type=int,
         dest="n",
         default=2,
         help="the number of engines to start"
     )
     
     parser = argparse.ArgumentParser(
         description='IPython cluster startup.  This starts a controller and\
         engines using various approaches.  THIS IS A TECHNOLOGY PREVIEW AND\
         THE API WILL CHANGE SIGNIFICANTLY BEFORE THE FINAL RELEASE.'
     )
     subparsers = parser.add_subparsers(
         help='available cluster types.  For help, do "ipcluster TYPE --help"')
     
     parser_local = subparsers.add_parser(
         'local',
         help='run a local cluster',
         parents=[base_parser]
     )
     parser_local.set_defaults(func=main_local)
     
     parser_mpirun = subparsers.add_parser(
         'mpirun',
         help='run a cluster using mpirun (mpiexec also works)',
         parents=[base_parser]
     )
     parser_mpirun.add_argument(
         "--mpi",
         type=str,
         dest="mpi", # Don't put a default here to allow no MPI support
         help="how to call MPI_Init (default=mpi4py)"
     )
     parser_mpirun.set_defaults(func=main_mpi, cmd='mpirun')
 
     parser_mpiexec = subparsers.add_parser(
         'mpiexec',
         help='run a cluster using mpiexec (mpirun also works)',
         parents=[base_parser]
     )
     parser_mpiexec.add_argument(
         "--mpi",
         type=str,
         dest="mpi", # Don't put a default here to allow no MPI support
         help="how to call MPI_Init (default=mpi4py)"
     )
     parser_mpiexec.set_defaults(func=main_mpi, cmd='mpiexec')
     
     parser_pbs = subparsers.add_parser(
         'pbs', 
         help='run a pbs cluster',
         parents=[base_parser]
     )
     parser_pbs.add_argument(
         '--pbs-script',
         type=str, 
         dest='pbsscript',
         help='PBS script template',
         default='pbs.template'
     )
     parser_pbs.set_defaults(func=main_pbs)
     
     parser_ssh = subparsers.add_parser(
         'ssh',
         help='run a cluster using ssh, should have ssh-keys setup',
         parents=[base_parser]
     )
     parser_ssh.add_argument(
         '--clusterfile', 
         type=str,
         dest='clusterfile',
         help='python file describing the cluster',
         default='clusterfile.py',
     )
     parser_ssh.add_argument(
         '--sshx', 
         type=str,
         dest='sshx',
         help='sshx launcher helper'
     )
     parser_ssh.set_defaults(func=main_ssh)
     
     args = parser.parse_args()
     return args
 
 def main():
     args = get_args()
     reactor.callWhenRunning(args.func, args)
     log.startLogging(sys.stdout)
     reactor.run()
 
 if __name__ == '__main__':
     main()

IPython/kernel/scripts/ipcontroller.py

@@ -1,388 +1,405 b''
 #!/usr/bin/env python
 # encoding: utf-8
 
 """The IPython controller."""
 
 __docformat__ = "restructuredtext en"
 
 #-------------------------------------------------------------------------------
 #  Copyright (C) 2008  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
 #-------------------------------------------------------------------------------
 
 # Python looks for an empty string at the beginning of sys.path to enable
 # importing from the cwd.
 import sys
 sys.path.insert(0, '')
 
 import sys, time, os
+import tempfile
 from optparse import OptionParser
 
 from twisted.application import internet, service
 from twisted.internet import reactor, error, defer
 from twisted.python import log
 
 from IPython.kernel.fcutil import Tub, UnauthenticatedTub, have_crypto
 
 # from IPython.tools import growl
 # growl.start("IPython1 Controller")
 
 from IPython.kernel.error import SecurityError
 from IPython.kernel import controllerservice
 from IPython.kernel.fcutil import check_furl_file_security
 
 from IPython.kernel.config import config_manager as kernel_config_manager
 from IPython.config.cutils import import_item
 
 
 #-------------------------------------------------------------------------------
 # Code
 #-------------------------------------------------------------------------------
 
+def get_temp_furlfile(filename):
+    return tempfile.mktemp(dir=os.path.dirname(filename),
+                           prefix=os.path.basename(filename))
+
 def make_tub(ip, port, secure, cert_file):
     """
     Create a listening tub given an ip, port, and cert_file location.
     
     :Parameters:
         ip : str
             The ip address that the tub should listen on.  Empty means all
         port : int
             The port that the tub should listen on.  A value of 0 means
             pick a random port
         secure: boolean
             Will the connection be secure (in the foolscap sense)
         cert_file:
             A filename of a file to be used for theSSL certificate
     """
     if secure:
         if have_crypto:
             tub = Tub(certFile=cert_file)
         else:
             raise SecurityError("""
 OpenSSL/pyOpenSSL is not available, so we can't run in secure mode.
 Try running without security using 'ipcontroller -xy'.
 """)
     else:
         tub = UnauthenticatedTub()
     
     # Set the strport based on the ip and port and start listening
     if ip == '':
         strport = "tcp:%i" % port
     else:
         strport = "tcp:%i:interface=%s" % (port, ip)
     listener = tub.listenOn(strport)
     
     return tub, listener
 
 def make_client_service(controller_service, config):
     """
     Create a service that will listen for clients.
     
     This service is simply a `foolscap.Tub` instance that has a set of Referenceables
     registered with it.
     """
 
     # Now create the foolscap tub
     ip = config['controller']['client_tub']['ip']
     port = config['controller']['client_tub'].as_int('port')
     location = config['controller']['client_tub']['location']
     secure = config['controller']['client_tub']['secure']
     cert_file = config['controller']['client_tub']['cert_file']
     client_tub, client_listener = make_tub(ip, port, secure, cert_file)
     
     # Set the location in the trivial case of localhost
     if ip == 'localhost' or ip == '127.0.0.1':
         location = "127.0.0.1"
     
     if not secure:
         log.msg("WARNING: you are running the controller with no client security")
     
     def set_location_and_register():
         """Set the location for the tub and return a deferred."""
 
         def register(empty, ref, furl_file):
-            client_tub.registerReference(ref, furlFile=furl_file)
+            # We create and then move to make sure that when the file
+            # appears to other processes, the buffer has the flushed
+            # and the file has been closed
+            temp_furl_file = get_temp_furlfile(furl_file)
+            log.msg(temp_furl_file)
+            client_tub.registerReference(ref, furlFile=temp_furl_file)
+            os.rename(temp_furl_file, furl_file)
         
         if location == '':
             d = client_tub.setLocationAutomatically()
         else:
             d = defer.maybeDeferred(client_tub.setLocation, "%s:%i" % (location, client_listener.getPortnum()))
-            
+        
         for ciname, ci in config['controller']['controller_interfaces'].iteritems():
             log.msg("Adapting Controller to interface: %s" % ciname)
             furl_file = ci['furl_file']
             log.msg("Saving furl for interface [%s] to file: %s" % (ciname, furl_file))
             check_furl_file_security(furl_file, secure)
             adapted_controller = import_item(ci['controller_interface'])(controller_service)
             d.addCallback(register, import_item(ci['fc_interface'])(adapted_controller), 
                 furl_file=ci['furl_file'])
     
     reactor.callWhenRunning(set_location_and_register)
     return client_tub
 
 
 def make_engine_service(controller_service, config):
     """
     Create a service that will listen for engines.
     
     This service is simply a `foolscap.Tub` instance that has a set of Referenceables
     registered with it.
     """
 
     # Now create the foolscap tub
     ip = config['controller']['engine_tub']['ip']
     port = config['controller']['engine_tub'].as_int('port')
     location = config['controller']['engine_tub']['location']
     secure = config['controller']['engine_tub']['secure']
     cert_file = config['controller']['engine_tub']['cert_file']
     engine_tub, engine_listener = make_tub(ip, port, secure, cert_file)
     
     # Set the location in the trivial case of localhost
     if ip == 'localhost' or ip == '127.0.0.1':
         location = "127.0.0.1"
     
     if not secure:
         log.msg("WARNING: you are running the controller with no engine security")
     
     def set_location_and_register():
         """Set the location for the tub and return a deferred."""
 
         def register(empty, ref, furl_file):
-            engine_tub.registerReference(ref, furlFile=furl_file)
+            # We create and then move to make sure that when the file
+            # appears to other processes, the buffer has the flushed
+            # and the file has been closed
+            temp_furl_file = get_temp_furlfile(furl_file)
+            log.msg(temp_furl_file)
+            engine_tub.registerReference(ref, furlFile=temp_furl_file)
+            os.rename(temp_furl_file, furl_file)
         
         if location == '':
             d = engine_tub.setLocationAutomatically()
         else:
             d = defer.maybeDeferred(engine_tub.setLocation, "%s:%i" % (location, engine_listener.getPortnum()))
     
         furl_file = config['controller']['engine_furl_file']
         engine_fc_interface = import_item(config['controller']['engine_fc_interface'])
         log.msg("Saving furl for the engine to file: %s" % furl_file)
         check_furl_file_security(furl_file, secure)
         fc_controller = engine_fc_interface(controller_service)
         d.addCallback(register, fc_controller, furl_file=furl_file)
     
     reactor.callWhenRunning(set_location_and_register)
     return engine_tub
     
 def start_controller():
     """
     Start the controller by creating the service hierarchy and starting the reactor.
     
     This method does the following:
     
         * It starts the controller logging
         * In execute an import statement for the controller
         * It creates 2 `foolscap.Tub` instances for the client and the engines
           and registers `foolscap.Referenceables` with the tubs to expose the
           controller to engines and clients.
     """
     config = kernel_config_manager.get_config_obj()
     
     # Start logging
     logfile = config['controller']['logfile']
     if logfile:
         logfile = logfile + str(os.getpid()) + '.log'
         try:
             openLogFile = open(logfile, 'w')
         except:
             openLogFile = sys.stdout
     else:
         openLogFile = sys.stdout
     log.startLogging(openLogFile)
     
     # Execute any user defined import statements
     cis = config['controller']['import_statement']
     if cis:
         try:
             exec cis in globals(), locals()
         except:
             log.msg("Error running import_statement: %s" % cis)
     
     # Delete old furl files unless the reuse_furls is set
     reuse = config['controller']['reuse_furls']
     if not reuse:
         paths = (config['controller']['engine_furl_file'],
             config['controller']['controller_interfaces']['task']['furl_file'],
             config['controller']['controller_interfaces']['multiengine']['furl_file']
         )
         for p in paths:
             if os.path.isfile(p):
                 os.remove(p)
     
     # Create the service hierarchy
     main_service = service.MultiService()
     # The controller service
     controller_service = controllerservice.ControllerService()
     controller_service.setServiceParent(main_service)
     # The client tub and all its refereceables
     client_service = make_client_service(controller_service, config)
     client_service.setServiceParent(main_service)
     # The engine tub
     engine_service = make_engine_service(controller_service, config)
     engine_service.setServiceParent(main_service)
     # Start the controller service and set things running
     main_service.startService()
     reactor.run()
 
 def init_config():
     """
     Initialize the configuration using default and command line options.
     """
     
     parser = OptionParser()
     
     # Client related options
     parser.add_option(
         "--client-ip", 
         type="string",
         dest="client_ip",
         help="the IP address or hostname the controller will listen on for client connections"
     )
     parser.add_option(
         "--client-port", 
         type="int", 
         dest="client_port",
         help="the port the controller will listen on for client connections"
     )    
     parser.add_option(
         '--client-location',
         type="string",
         dest="client_location",
         help="hostname or ip for clients to connect to"
     )
     parser.add_option(
         "-x",
         action="store_false",
         dest="client_secure",
         help="turn off all client security"
     )
     parser.add_option(
         '--client-cert-file',
         type="string",
         dest="client_cert_file",
         help="file to store the client SSL certificate"
     )
     parser.add_option(
         '--task-furl-file',
         type="string",
         dest="task_furl_file",
         help="file to store the FURL for task clients to connect with"
     )
     parser.add_option(
         '--multiengine-furl-file',
         type="string",
         dest="multiengine_furl_file",
         help="file to store the FURL for multiengine clients to connect with"
     )
     # Engine related options
     parser.add_option(
         "--engine-ip", 
         type="string",
         dest="engine_ip",
         help="the IP address or hostname the controller will listen on for engine connections"
     )
     parser.add_option(
         "--engine-port", 
         type="int", 
         dest="engine_port",
         help="the port the controller will listen on for engine connections"
     )    
     parser.add_option(
         '--engine-location',
         type="string",
         dest="engine_location",
         help="hostname or ip for engines to connect to"
     )
     parser.add_option(
         "-y",
         action="store_false",
         dest="engine_secure",
         help="turn off all engine security"
     )
     parser.add_option(
         '--engine-cert-file',
         type="string",
         dest="engine_cert_file",
         help="file to store the engine SSL certificate"
     )
     parser.add_option(
         '--engine-furl-file',
         type="string",
         dest="engine_furl_file",
         help="file to store the FURL for engines to connect with"
     )
     parser.add_option(
         "-l", "--logfile",
         type="string",
         dest="logfile",
         help="log file name (default is stdout)"
     )
     parser.add_option(
         "--ipythondir",
         type="string",
         dest="ipythondir",
         help="look for config files and profiles in this directory"
     )
     parser.add_option(
         "-r",
         action="store_true",
         dest="reuse_furls",
         help="try to reuse all furl files"
     )
     
     (options, args) = parser.parse_args()
     
     kernel_config_manager.update_config_obj_from_default_file(options.ipythondir)
     config = kernel_config_manager.get_config_obj()
     
     # Update with command line options
     if options.client_ip is not None:
         config['controller']['client_tub']['ip'] = options.client_ip
     if options.client_port is not None:
         config['controller']['client_tub']['port'] = options.client_port
     if options.client_location is not None:
         config['controller']['client_tub']['location'] = options.client_location
     if options.client_secure is not None:
         config['controller']['client_tub']['secure'] = options.client_secure
     if options.client_cert_file is not None:
         config['controller']['client_tub']['cert_file'] = options.client_cert_file
     if options.task_furl_file is not None:
         config['controller']['controller_interfaces']['task']['furl_file'] = options.task_furl_file
     if options.multiengine_furl_file is not None:
         config['controller']['controller_interfaces']['multiengine']['furl_file'] = options.multiengine_furl_file
     if options.engine_ip is not None:
         config['controller']['engine_tub']['ip'] = options.engine_ip
     if options.engine_port is not None:
         config['controller']['engine_tub']['port'] = options.engine_port
     if options.engine_location is not None:
         config['controller']['engine_tub']['location'] = options.engine_location
     if options.engine_secure is not None:
         config['controller']['engine_tub']['secure'] = options.engine_secure
     if options.engine_cert_file is not None:
         config['controller']['engine_tub']['cert_file'] = options.engine_cert_file
     if options.engine_furl_file is not None:
         config['controller']['engine_furl_file'] = options.engine_furl_file
     if options.reuse_furls is not None:
             config['controller']['reuse_furls'] = options.reuse_furls
 
     if options.logfile is not None:
         config['controller']['logfile'] = options.logfile
     
     kernel_config_manager.update_config_obj(config)
 
 def main():
     """
     After creating the configuration information, start the controller.
     """
     init_config()
     start_controller()
     
 if __name__ == "__main__":
     main()

IPython/kernel/scripts/ipengine.py

@@ -1,176 +1,182 b''
 #!/usr/bin/env python
 # encoding: utf-8
 
 """Start the IPython Engine."""
 
 __docformat__ = "restructuredtext en"
 
 #-------------------------------------------------------------------------------
 #  Copyright (C) 2008  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
 #-------------------------------------------------------------------------------
 
 # Python looks for an empty string at the beginning of sys.path to enable
 # importing from the cwd.
 import sys
 sys.path.insert(0, '')
 
 import sys, os
 from optparse import OptionParser
 
 from twisted.application import service
 from twisted.internet import reactor
 from twisted.python import log
 
 from IPython.kernel.fcutil import Tub, UnauthenticatedTub
 
 from IPython.kernel.core.config import config_manager as core_config_manager
 from IPython.config.cutils import import_item
 from IPython.kernel.engineservice import EngineService
 from IPython.kernel.config import config_manager as kernel_config_manager
 from IPython.kernel.engineconnector import EngineConnector
 
 
 #-------------------------------------------------------------------------------
 # Code
 #-------------------------------------------------------------------------------
 
 def start_engine():
     """
     Start the engine, by creating it and starting the Twisted reactor.
     
     This method does:
     
         * If it exists, runs the `mpi_import_statement` to call `MPI_Init`
         * Starts the engine logging
         * Creates an IPython shell and wraps it in an `EngineService`
         * Creates a `foolscap.Tub` to use in connecting to a controller.
         * Uses the tub and the `EngineService` along with a Foolscap URL
           (or FURL) to connect to the controller and register the engine
           with the controller
     """
     kernel_config = kernel_config_manager.get_config_obj()
     core_config = core_config_manager.get_config_obj()
     
 
     # Execute the mpi import statement that needs to call MPI_Init
     global mpi
     mpikey = kernel_config['mpi']['default']
     mpi_import_statement = kernel_config['mpi'].get(mpikey, None)
     if mpi_import_statement is not None:
         try:
             exec mpi_import_statement in globals()
         except:
             mpi = None
     else:
         mpi = None
     
     # Start logging
     logfile = kernel_config['engine']['logfile']
     if logfile:
         logfile = logfile + str(os.getpid()) + '.log'
         try:
             openLogFile = open(logfile, 'w')
         except:
             openLogFile = sys.stdout
     else:
         openLogFile = sys.stdout
     log.startLogging(openLogFile)
     
     # Create the underlying shell class and EngineService
     shell_class = import_item(core_config['shell']['shell_class'])
     engine_service = EngineService(shell_class, mpi=mpi)
     shell_import_statement = core_config['shell']['import_statement']
     if shell_import_statement:
         try:
             engine_service.execute(shell_import_statement)
         except:
             log.msg("Error running import_statement: %s" % shell_import_statement)
     
     # Create the service hierarchy
     main_service = service.MultiService()
     engine_service.setServiceParent(main_service)
     tub_service = Tub()
     tub_service.setServiceParent(main_service)
     # This needs to be called before the connection is initiated
     main_service.startService()
     
     # This initiates the connection to the controller and calls
     # register_engine to tell the controller we are ready to do work
     engine_connector = EngineConnector(tub_service)
     furl_file = kernel_config['engine']['furl_file']
     log.msg("Using furl file: %s" % furl_file)
-    d = engine_connector.connect_to_controller(engine_service, furl_file)
-    def handle_error(f):
-        log.err(f)
-        if reactor.running:
-            reactor.stop()
-    d.addErrback(handle_error)
     
+    def call_connect(engine_service, furl_file):
+        d = engine_connector.connect_to_controller(engine_service, furl_file)
+        def handle_error(f):
+            # If this print statement is replaced by a log.err(f) I get
+            # an unhandled error, which makes no sense.  I shouldn't have
+            # to use a print statement here.  My only thought is that
+            # at the beginning of the process the logging is still starting up
+            print "error connecting to controller:", f.getErrorMessage()
+            reactor.callLater(0.1, reactor.stop)
+        d.addErrback(handle_error)
+    
+    reactor.callWhenRunning(call_connect, engine_service, furl_file)
     reactor.run()
 
 
 def init_config():
     """
     Initialize the configuration using default and command line options.
     """
     
     parser = OptionParser()
     
     parser.add_option(
         "--furl-file",
         type="string", 
         dest="furl_file",
         help="The filename containing the FURL of the controller"
     )
     parser.add_option(
         "--mpi",
         type="string",
         dest="mpi",
         help="How to enable MPI (mpi4py, pytrilinos, or empty string to disable)"
     )
     parser.add_option(
         "-l",
         "--logfile",
         type="string",
         dest="logfile",
         help="log file name (default is stdout)"
     )
     parser.add_option(
         "--ipythondir",
         type="string",
         dest="ipythondir",
         help="look for config files and profiles in this directory"
     )
     
     (options, args) = parser.parse_args()
     
     kernel_config_manager.update_config_obj_from_default_file(options.ipythondir)
     core_config_manager.update_config_obj_from_default_file(options.ipythondir)
     
     kernel_config = kernel_config_manager.get_config_obj()
     # Now override with command line options
     if options.furl_file is not None:
         kernel_config['engine']['furl_file'] = options.furl_file
     if options.logfile is not None:
         kernel_config['engine']['logfile'] = options.logfile
     if options.mpi is not None:
         kernel_config['mpi']['default'] = options.mpi
 
 
 def main():
     """
     After creating the configuration information, start the engine.
     """
     init_config()
     start_engine()
 
 
 if __name__ == "__main__":
     main()

IPython/kernel/tests/test_multiengine.py

@@ -1,56 +1,56 b''
 # encoding: utf-8
 
 """"""
 
 __docformat__ = "restructuredtext en"
 
-#-------------------------------------------------------------------------------
+#-----------------------------------------------------------------------------
 #  Copyright (C) 2008  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
-#-------------------------------------------------------------------------------
+#-----------------------------------------------------------------------------
 
 try:
     from twisted.internet import defer
     from IPython.testing.util import DeferredTestCase
     from IPython.kernel.controllerservice import ControllerService
     from IPython.kernel import multiengine as me
     from IPython.kernel.tests.multienginetest import (IMultiEngineTestCase,
         ISynchronousMultiEngineTestCase)
 except ImportError:
     import nose
     raise nose.SkipTest("This test requires zope.interface, Twisted and Foolscap")
 
  
 class BasicMultiEngineTestCase(DeferredTestCase, IMultiEngineTestCase):
 
     def setUp(self):
         self.controller = ControllerService()
         self.controller.startService()
         self.multiengine = me.IMultiEngine(self.controller)
         self.engines = []
     
     def tearDown(self):
         self.controller.stopService()
         for e in self.engines:
             e.stopService()
 
 
 class SynchronousMultiEngineTestCase(DeferredTestCase, ISynchronousMultiEngineTestCase):
 
     def setUp(self):
         self.controller = ControllerService()
         self.controller.startService()
         self.multiengine = me.ISynchronousMultiEngine(me.IMultiEngine(self.controller))
         self.engines = []
     
     def tearDown(self):
         self.controller.stopService()
         for e in self.engines:
             e.stopService()
 

IPython/kernel/tests/test_newserialized.py

@@ -1,102 +1,102 b''
 # encoding: utf-8
 
 """This file contains unittests for the shell.py module."""
 
 __docformat__ = "restructuredtext en"
 
-#-------------------------------------------------------------------------------
+#-----------------------------------------------------------------------------
 #  Copyright (C) 2008  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
-#-------------------------------------------------------------------------------
+#-----------------------------------------------------------------------------
 
 try:
     import zope.interface as zi
     from twisted.trial import unittest
     from IPython.testing.util import DeferredTestCase
 
     from IPython.kernel.newserialized import \
         ISerialized, \
         IUnSerialized, \
         Serialized, \
         UnSerialized, \
         SerializeIt, \
         UnSerializeIt
 except ImportError:
     import nose
     raise nose.SkipTest("This test requires zope.interface, Twisted and Foolscap")
 
-#-------------------------------------------------------------------------------
+#-----------------------------------------------------------------------------
 # Tests
-#-------------------------------------------------------------------------------
+#-----------------------------------------------------------------------------
 
 class SerializedTestCase(unittest.TestCase):
 
     def setUp(self):
         pass
     
     def tearDown(self):
         pass
     
     def testSerializedInterfaces(self):
 
         us = UnSerialized({'a':10, 'b':range(10)})
         s = ISerialized(us)
         uss = IUnSerialized(s)
         self.assert_(ISerialized.providedBy(s))
         self.assert_(IUnSerialized.providedBy(us))
         self.assert_(IUnSerialized.providedBy(uss))
         for m in list(ISerialized):
             self.assert_(hasattr(s, m))
         for m in list(IUnSerialized):
             self.assert_(hasattr(us, m))
         for m in list(IUnSerialized):
             self.assert_(hasattr(uss, m))
 
     def testPickleSerialized(self):
         obj = {'a':1.45345, 'b':'asdfsdf', 'c':10000L}
         original = UnSerialized(obj)
         originalSer = ISerialized(original)
         firstData = originalSer.getData()
         firstTD = originalSer.getTypeDescriptor()
         firstMD = originalSer.getMetadata()
         self.assert_(firstTD == 'pickle')
         self.assert_(firstMD == {})
         unSerialized = IUnSerialized(originalSer)
         secondObj = unSerialized.getObject()
         for k, v in secondObj.iteritems():
             self.assert_(obj[k] == v)
         secondSer = ISerialized(UnSerialized(secondObj))
         self.assert_(firstData == secondSer.getData())
         self.assert_(firstTD == secondSer.getTypeDescriptor() )
         self.assert_(firstMD == secondSer.getMetadata())
     
     def testNDArraySerialized(self):
         try:
             import numpy
         except ImportError:
             pass
         else:
             a = numpy.linspace(0.0, 1.0, 1000)
             unSer1 = UnSerialized(a)
             ser1 = ISerialized(unSer1)
             td = ser1.getTypeDescriptor()
             self.assert_(td == 'ndarray')
             md = ser1.getMetadata()
             self.assert_(md['shape'] == a.shape)
             self.assert_(md['dtype'] == a.dtype.str)
             buff = ser1.getData()
             self.assert_(buff == numpy.getbuffer(a))
             s = Serialized(buff, td, md)
             us = IUnSerialized(s)
             final = us.getObject()
             self.assert_(numpy.getbuffer(a) == numpy.getbuffer(final))
             self.assert_(a.dtype.str == final.dtype.str)
             self.assert_(a.shape == final.shape)
         
         

IPython/kernel/twistedutil.py

@@ -1,206 +1,249 b''
 #!/usr/bin/env python
 # encoding: utf-8
 
 """Things directly related to all of twisted."""
 
 __docformat__ = "restructuredtext en"
 
 #-------------------------------------------------------------------------------
 #  Copyright (C) 2008  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 os, sys
 import threading, Queue, atexit
-import twisted
 
+import twisted
 from twisted.internet import defer, reactor
 from twisted.python import log, failure
 
+from IPython.kernel.error import FileTimeoutError
+
 #-------------------------------------------------------------------------------
 # Classes related to twisted and threads
 #-------------------------------------------------------------------------------
 
 
 class ReactorInThread(threading.Thread):
     """Run the twisted reactor in a different thread.
     
     For the process to be able to exit cleanly, do the following:
     
     rit = ReactorInThread()
     rit.setDaemon(True)
     rit.start()
     
     """
     
     def run(self):
         reactor.run(installSignalHandlers=0)
         # self.join()
         
     def stop(self):
         # I don't think this does anything useful.
         blockingCallFromThread(reactor.stop)
         self.join()
 
 if(twisted.version.major >= 8):
     import twisted.internet.threads
     def blockingCallFromThread(f, *a, **kw):
         """
         Run a function in the reactor from a thread, and wait for the result
         synchronously, i.e. until the callback chain returned by the function get a
         result.
         
         Delegates to twisted.internet.threads.blockingCallFromThread(reactor, f, *a, **kw),
         passing twisted.internet.reactor for the first argument.
         
         @param f: the callable to run in the reactor thread
         @type f: any callable.
         @param a: the arguments to pass to C{f}.
         @param kw: the keyword arguments to pass to C{f}.
 
         @return: the result of the callback chain.
         @raise: any error raised during the callback chain.
         """
         return twisted.internet.threads.blockingCallFromThread(reactor, f, *a, **kw)
     
 else:   
     def blockingCallFromThread(f, *a, **kw):
         """
         Run a function in the reactor from a thread, and wait for the result
         synchronously, i.e. until the callback chain returned by the function get a
         result.
 
         @param f: the callable to run in the reactor thread
         @type f: any callable.
         @param a: the arguments to pass to C{f}.
         @param kw: the keyword arguments to pass to C{f}.
 
         @return: the result of the callback chain.
         @raise: any error raised during the callback chain.
         """
         from twisted.internet import reactor
         queue = Queue.Queue()
         def _callFromThread():
             result = defer.maybeDeferred(f, *a, **kw)
             result.addBoth(queue.put)
         
         reactor.callFromThread(_callFromThread)
         result = queue.get()
         if isinstance(result, failure.Failure):
             # This makes it easier for the debugger to get access to the instance
             try:
                 result.raiseException()
             except Exception, e:
                 raise e
         return result
     
 
 
 #-------------------------------------------------------------------------------
 # Things for managing deferreds
 #-------------------------------------------------------------------------------
 
 
 def parseResults(results):
     """Pull out results/Failures from a DeferredList."""
     return [x[1] for x in results]
 
 def gatherBoth(dlist, fireOnOneCallback=0, 
                       fireOnOneErrback=0,
                       consumeErrors=0,
                       logErrors=0):
     """This is like gatherBoth, but sets consumeErrors=1."""
     d = DeferredList(dlist, fireOnOneCallback, fireOnOneErrback,
                      consumeErrors, logErrors)
     if not fireOnOneCallback:
         d.addCallback(parseResults)
     return d
 
 SUCCESS = True
 FAILURE = False
 
 class DeferredList(defer.Deferred):
     """I combine a group of deferreds into one callback.
 
     I track a list of L{Deferred}s for their callbacks, and make a single
     callback when they have all completed, a list of (success, result)
     tuples, 'success' being a boolean.
 
     Note that you can still use a L{Deferred} after putting it in a
     DeferredList.  For example, you can suppress 'Unhandled error in Deferred'
     messages by adding errbacks to the Deferreds *after* putting them in the
     DeferredList, as a DeferredList won't swallow the errors.  (Although a more
     convenient way to do this is simply to set the consumeErrors flag)
     
     Note: This is a modified version of the twisted.internet.defer.DeferredList
     """
 
     fireOnOneCallback = 0
     fireOnOneErrback = 0
 
     def __init__(self, deferredList, fireOnOneCallback=0, fireOnOneErrback=0,
                  consumeErrors=0, logErrors=0):
         """Initialize a DeferredList.
 
         @type deferredList:  C{list} of L{Deferred}s
         @param deferredList: The list of deferreds to track.
         @param fireOnOneCallback: (keyword param) a flag indicating that
                              only one callback needs to be fired for me to call
                              my callback
         @param fireOnOneErrback: (keyword param) a flag indicating that
                             only one errback needs to be fired for me to call
                             my errback
         @param consumeErrors: (keyword param) a flag indicating that any errors
                             raised in the original deferreds should be
                             consumed by this DeferredList.  This is useful to
                             prevent spurious warnings being logged.
         """
         self.resultList = [None] * len(deferredList)
         defer.Deferred.__init__(self)
         if len(deferredList) == 0 and not fireOnOneCallback:
             self.callback(self.resultList)
 
         # These flags need to be set *before* attaching callbacks to the
         # deferreds, because the callbacks use these flags, and will run
         # synchronously if any of the deferreds are already fired.
         self.fireOnOneCallback = fireOnOneCallback
         self.fireOnOneErrback = fireOnOneErrback
         self.consumeErrors = consumeErrors
         self.logErrors = logErrors
         self.finishedCount = 0
 
         index = 0
         for deferred in deferredList:
             deferred.addCallbacks(self._cbDeferred, self._cbDeferred,
                                   callbackArgs=(index,SUCCESS),
                                   errbackArgs=(index,FAILURE))
             index = index + 1
 
     def _cbDeferred(self, result, index, succeeded):
         """(internal) Callback for when one of my deferreds fires.
         """
         self.resultList[index] = (succeeded, result)
 
         self.finishedCount += 1
         if not self.called:
             if succeeded == SUCCESS and self.fireOnOneCallback:
                 self.callback((result, index))
             elif succeeded == FAILURE and self.fireOnOneErrback:
                 # We have modified this to fire the errback chain with the actual
                 # Failure instance the originally occured rather than twisted's
                 # FirstError which wraps the failure
                 self.errback(result)
             elif self.finishedCount == len(self.resultList):
                 self.callback(self.resultList)
 
         if succeeded == FAILURE and self.logErrors:
             log.err(result)
         if succeeded == FAILURE and self.consumeErrors:
             result = None
 
         return result
+
+
+def wait_for_file(filename, delay=0.1, max_tries=10):
+    """Wait (poll) for a file to be created.
+    
+    This method returns a Deferred that will fire when a file exists. It
+    works by polling os.path.isfile in time intervals specified by the
+    delay argument.  If `max_tries` is reached, it will errback with a 
+    `FileTimeoutError`.
+    
+    Parameters
+    ----------
+    filename : str
+        The name of the file to wait for.
+    delay : float
+        The time to wait between polls.
+    max_tries : int
+        The max number of attempts before raising `FileTimeoutError`
+    
+    Returns
+    -------
+    d : Deferred
+        A Deferred instance that will fire when the file exists.
+    """
+    
+    d = defer.Deferred()
+    
+    def _test_for_file(filename, attempt=0):
+        if attempt >= max_tries:
+            d.errback(FileTimeoutError(
+                'timeout waiting for file to be created: %s' % filename
+            ))
+        else:
+            if os.path.isfile(filename):
+                d.callback(True)
+            else:
+                reactor.callLater(delay, _test_for_file, filename, attempt+1)
+    
+    _test_for_file(filename)
+    return d

docs/source/parallel/parallel_process.txt

@@ -1,336 +1,351 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 FURL file (:file:`ipcontroller-engine.furl`) 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 FURL file 
    (:file:`ipcontroller-engine.furl`) is located.
 
 At this point, the controller and engines will be connected. By default, the
 FURL files created by the controller are put into the
 :file:`~/.ipython/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 required to actually use the running controller from a
 client is to move the FURL files :file:`ipcontroller-mec.furl` and
 :file:`ipcontroller-tc.furl` from ``host0`` to the host where the clients will
 be run.  If these file are put into the :file:`~/.ipython/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:`mpirun` command that comes 
    with most MPI [MPI]_ implementations
 3. When engines are started using the PBS [PBS]_ batch system.
 4. When the controller is started on localhost and the engines are started on 
    remote nodes using :command:`ssh`.
 
 .. note::
 
     It is also possible for advanced users to add support to
     :command:`ipcluster` for starting controllers and engines using other
     methods (like Sun's Grid Engine for example).
 
 .. note::
 
     Currently :command:`ipcluster` requires that the
     :file:`~/.ipython/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.  This constraint can be relaxed if you are 
     using the :command:`ssh` method to start the cluster.
 
 Underneath the hood, :command:`ipcluster` just uses :command:`ipcontroller`
 and :command:`ipengine` to perform the steps described above.
 
 Using :command:`ipcluster` in local mode
 ----------------------------------------
 
 To start one controller and 4 engines on localhost, just do::
 
     $ ipcluster local -n 4
 
 To see other command line options for the local mode, do::
 
     $ ipcluster local -h
 
 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.
 
 .. note::
 
     The preferred command to use is :command:`mpiexec`.  However, we also 
     support :command:`mpirun` for backwards compatibility.  The underlying
     logic used is exactly the same, the only difference being the name of the 
     command line program that is called.
 
 If these are satisfied, you can start an IPython cluster using::
 
     $ ipcluster mpiexec -n 4
 
 This does the following:
 
 1. Starts the IPython controller on current host.
 2. Uses :command:`mpiexec` to start 4 engines.
 
 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 call ipcluster with the ``--mpi`` option::
 
     $ ipcluster mpiexec -n 4 --mpi=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.
 
 Additional command line options for this mode can be found by doing::
 
     $ ipcluster mpiexec -h
 
 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.  To use this mode, you first need to create a PBS script template that will be used to start the engines.  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 parallel
 
     cd $$PBS_O_WORKDIR
     export PATH=$$HOME/usr/local/bin
     export PYTHONPATH=$$HOME/usr/local/lib/python2.4/site-packages
     /usr/local/bin/mpiexec -n ${n} ipengine --logfile=$$PBS_O_WORKDIR/ipengine
 
 There are a few important points about this template:
 
 1. This template will be rendered at runtime using IPython's :mod:`Itpl` 
    template engine.
 
 2. Instead of putting in the actual number of engines, use the notation
    ``${n}`` to indicate the number of engines to be started. You can also uses
    expressions like ``${n/4}`` in the template to indicate the number of 
    nodes.
 
 3. Because ``$`` is a special character used by the template engine, you must  
    escape any ``$`` by using ``$$``.  This is important when referring to 
    environment variables in the template.
 
 4. Any options to :command:`ipengine` should be given in the batch script 
    template.
 
 5. Depending on the configuration of you system, you may have to set 
    environment variables in the script template.
 
 Once you have created such a script, save it with a name like :file:`pbs.template`.  Now you are ready to start your job::
 
     $ ipcluster pbs -n 128 --pbs-script=pbs.template
 
 Additional command line options for this mode can be found by doing::
 
     $ ipcluster pbs -h
 
 Using :command:`ipcluster` in SSH mode
 --------------------------------------
 
 The SSH mode uses :command:`ssh` to execute :command:`ipengine` on remote
 nodes and the :command:`ipcontroller` on localhost.
 
 When using using this mode it highly recommended that you have set up SSH keys and are using ssh-agent [SSH]_ for password-less logins.
 
 To use this mode you need a python file describing the cluster, here is an example of such a "clusterfile":
 
 .. sourcecode:: python
     
     send_furl = True
     engines = { 'host1.example.com' : 2,
                 'host2.example.com' : 5,
                 'host3.example.com' : 1,
                 'host4.example.com' : 8 }
 
 Since this is a regular python file usual python syntax applies. Things to note:
 
 * The `engines` dict, where the keys is the host we want to run engines on and
   the value is the number of engines to run on that host.
 * send_furl can either be `True` or `False`, if `True` it will copy over the
   furl needed for :command:`ipengine` to each host.
 
 The ``--clusterfile`` command line option lets you specify the file to use for
 the cluster definition. Once you have your cluster file and you can
 :command:`ssh` into the remote hosts with out an password you are ready to
 start your cluster like so:
 
 .. sourcecode:: bash 
 
    $ ipcluster ssh --clusterfile /path/to/my/clusterfile.py
 
 
 Two helper shell scripts are used to start and stop :command:`ipengine` on remote hosts:
 
 * sshx.sh 
 * engine_killer.sh
 
 Defaults for both of these are contained in the source code for :command:`ipcluster`. The default scripts are written to a local file in a tmep directory and then copied to a temp directory on the remote host and executed from there.  On most Unix, Linux and OS X systems this is /tmp.
 
 The default sshx.sh is the following:
 
 .. sourcecode:: bash
 
    #!/bin/sh
    "$@" &> /dev/null &
    echo $!
 
 If you want to use a custom sshx.sh script you need to use the ``--sshx``
 option and specify the file to use. Using a custom sshx.sh file could be
 helpful when you need to setup the environment on the remote host before
 executing :command:`ipengine`.
 
 For a detailed options list:
 
 .. sourcecode:: bash
 
    $ ipcluster ssh -h
 
 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.
 * :command:`ipcontroller` is started on localhost, with no option to start it
   on a remote node.
 
 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 FURL files in :file:`~./ipython/security`. You are now ready to use the controller and engines from IPython.
 
 .. warning:: 
 	
 	The order of the above operations is very important.  You *must*
  	start the controller before the engines, since the engines connect 
 	to the controller as they get started.
 
 .. 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.furl` from :file:`~./ipython/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.furl` file is located.  There are two ways you can do this:
 
 * Put :file:`ipcontroller-engine.furl` in the :file:`~./ipython/security`
   directory on the engine's host, where it will be found automatically.
 * Call :command:`ipengine` with the ``--furl-file=full_path_to_the_file``
   flag.
 
 The ``--furl-file`` flag works like this::
 
     $ ipengine --furl-file=/path/to/my/ipcontroller-engine.furl
 
 .. note::
     
     If the controller's and engine's hosts all have a shared file system  
     (:file:`~./ipython/security` is the same on all of them), then things
     will just work!
 
 Make FURL files persistent
 ---------------------------
 
-At fist glance it may seem that that managing the FURL files is a bit annoying.  Going back to the house and key analogy, copying the FURL 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 FURL file) once, and then simply use it at any point in the future.
+At fist glance it may seem that that managing the FURL files is a bit
+annoying. Going back to the house and key analogy, copying the FURL 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 FURL file) once, and then simply use it at
+any point in the future.
 
-This is possible.  The only thing you have to do is decide what ports the controller will listen on for the engines and clients.  This is done as follows::
+This is possible. but before you do this, you **must** remove any old FURL
+files in the :file:`~/.ipython/security` directory.
+
+.. warning::
+
+    You **must** remove old FURL files before using persistent FURL files.
+
+Then, The only thing you have to do is decide what ports the controller will
+listen on for the engines and clients. This is done as follows::
 
     $ ipcontroller -r --client-port=10101 --engine-port=10102
 
-These options also work with all of the various modes of 
+These options also work with all of the various modes of
 :command:`ipcluster`::
 
     $ ipcluster local -n 2 -r --client-port=10101 --engine-port=10102
 
-Then, just copy the furl 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 use the *same* ports.
+Then, just copy the furl 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 use the *same* ports.
 
 .. 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/log`.  Sending
 the log files to us will often help us to debug any problems.
 
 
 .. [PBS] Portable Batch System.  http://www.openpbs.org/
 .. [SSH] SSH-Agent http://en.wikipedia.org/wiki/Ssh-agent