Backport PR #2214: use KernelApp.exec_lines/files in IPEngineApp

This change means that all your startup/exec_lines config is inherited by engines.

should be backported for 0.13.1, because engine startup code is impossible to configure in 0.13.

The real long-term fix for this is to make IPEngineApp a subclass of IPKernelApp, but this should be an adequate band-aid until then.

closes  #2213

IPython/parallel/apps/ipengineapp.py

@@ -1,377 +1,384 b''
 #!/usr/bin/env python
 # encoding: utf-8
 """
 The IPython engine application
 
 Authors:
 
 * Brian Granger
 * MinRK
 
 """
 
 #-----------------------------------------------------------------------------
 #  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 json
 import os
 import sys
 import time
 
 import zmq
 from zmq.eventloop import ioloop
 
 from IPython.core.profiledir import ProfileDir
 from IPython.parallel.apps.baseapp import (
     BaseParallelApplication,
     base_aliases,
     base_flags,
     catch_config_error,
 )
 from IPython.zmq.log import EnginePUBHandler
 from IPython.zmq.ipkernel import Kernel, IPKernelApp
 from IPython.zmq.session import (
     Session, session_aliases, session_flags
 )
 
 from IPython.config.configurable import Configurable
 
 from IPython.parallel.engine.engine import EngineFactory
 from IPython.parallel.util import disambiguate_url
 
 from IPython.utils.importstring import import_item
 from IPython.utils.py3compat import cast_bytes
 from IPython.utils.traitlets import Bool, Unicode, Dict, List, Float, Instance
 
 
 #-----------------------------------------------------------------------------
 # Module level variables
 #-----------------------------------------------------------------------------
 
 #: The default config file name for this application
 default_config_file_name = u'ipengine_config.py'
 
 _description = """Start an IPython engine for parallel computing.
 
 IPython engines run in parallel and perform computations on behalf of a client
 and controller. A controller needs to be started before the engines. The
 engine can be configured using command line options or using a cluster
 directory. Cluster directories contain config, log and security files and are
 usually located in your ipython directory and named as "profile_name".
 See the `profile` and `profile-dir` options for details.
 """
 
 _examples = """
 ipengine --ip=192.168.0.1 --port=1000     # connect to hub at ip and port
 ipengine --log-to-file --log-level=DEBUG  # log to a file with DEBUG verbosity
 """
 
 #-----------------------------------------------------------------------------
 # MPI configuration
 #-----------------------------------------------------------------------------
 
 mpi4py_init = """from mpi4py import MPI as mpi
 mpi.size = mpi.COMM_WORLD.Get_size()
 mpi.rank = mpi.COMM_WORLD.Get_rank()
 """
 
 
 pytrilinos_init = """from PyTrilinos import Epetra
 class SimpleStruct:
 pass
 mpi = SimpleStruct()
 mpi.rank = 0
 mpi.size = 0
 """
 
 class MPI(Configurable):
     """Configurable for MPI initialization"""
     use = Unicode('', config=True,
         help='How to enable MPI (mpi4py, pytrilinos, or empty string to disable).'
         )
 
     def _use_changed(self, name, old, new):
         # load default init script if it's not set
         if not self.init_script:
             self.init_script = self.default_inits.get(new, '')
 
     init_script = Unicode('', config=True,
         help="Initialization code for MPI")
 
     default_inits = Dict({'mpi4py' : mpi4py_init, 'pytrilinos':pytrilinos_init},
         config=True)
 
 
 #-----------------------------------------------------------------------------
 # Main application
 #-----------------------------------------------------------------------------
 aliases = dict(
     file = 'IPEngineApp.url_file',
     c = 'IPEngineApp.startup_command',
     s = 'IPEngineApp.startup_script',
 
     url = 'EngineFactory.url',
     ssh = 'EngineFactory.sshserver',
     sshkey = 'EngineFactory.sshkey',
     ip = 'EngineFactory.ip',
     transport = 'EngineFactory.transport',
     port = 'EngineFactory.regport',
     location = 'EngineFactory.location',
 
     timeout = 'EngineFactory.timeout',
 
     mpi = 'MPI.use',
 
 )
 aliases.update(base_aliases)
 aliases.update(session_aliases)
 flags = {}
 flags.update(base_flags)
 flags.update(session_flags)
 
 class IPEngineApp(BaseParallelApplication):
 
     name = 'ipengine'
     description = _description
     examples = _examples
     config_file_name = Unicode(default_config_file_name)
     classes = List([ProfileDir, Session, EngineFactory, Kernel, MPI])
 
     startup_script = Unicode(u'', config=True,
         help='specify a script to be run at startup')
     startup_command = Unicode('', config=True,
             help='specify a command to be run at startup')
 
     url_file = Unicode(u'', config=True,
         help="""The full location of the file containing the connection information for
         the controller. If this is not given, the file must be in the
         security directory of the cluster directory.  This location is
         resolved using the `profile` or `profile_dir` options.""",
         )
     wait_for_url_file = Float(5, config=True,
         help="""The maximum number of seconds to wait for url_file to exist.
         This is useful for batch-systems and shared-filesystems where the
         controller and engine are started at the same time and it
         may take a moment for the controller to write the connector files.""")
 
     url_file_name = Unicode(u'ipcontroller-engine.json', config=True)
 
     def _cluster_id_changed(self, name, old, new):
         if new:
             base = 'ipcontroller-%s' % new
         else:
             base = 'ipcontroller'
         self.url_file_name = "%s-engine.json" % base
 
     log_url = Unicode('', config=True,
         help="""The URL for the iploggerapp instance, for forwarding
         logging to a central location.""")
     
     # an IPKernelApp instance, used to setup listening for shell frontends
     kernel_app = Instance(IPKernelApp)
 
     aliases = Dict(aliases)
     flags = Dict(flags)
     
     @property
     def kernel(self):
         """allow access to the Kernel object, so I look like IPKernelApp"""
         return self.engine.kernel
 
     def find_url_file(self):
         """Set the url file.
 
         Here we don't try to actually see if it exists for is valid as that
         is hadled by the connection logic.
         """
         config = self.config
         # Find the actual controller key file
         if not self.url_file:
             self.url_file = os.path.join(
                 self.profile_dir.security_dir,
                 self.url_file_name
             )
     
     def load_connector_file(self):
         """load config from a JSON connector file,
         at a *lower* priority than command-line/config files.
         """
         
         self.log.info("Loading url_file %r", self.url_file)
         config = self.config
         
         with open(self.url_file) as f:
             d = json.loads(f.read())
         
         if 'exec_key' in d:
             config.Session.key = cast_bytes(d['exec_key'])
         
         try:
             config.EngineFactory.location
         except AttributeError:
             config.EngineFactory.location = d['location']
         
         d['url'] = disambiguate_url(d['url'], config.EngineFactory.location)
         try:
             config.EngineFactory.url
         except AttributeError:
             config.EngineFactory.url = d['url']
         
         try:
             config.EngineFactory.sshserver
         except AttributeError:
             config.EngineFactory.sshserver = d['ssh']
     
     def bind_kernel(self, **kwargs):
         """Promote engine to listening kernel, accessible to frontends."""
         if self.kernel_app is not None:
             return
         
         self.log.info("Opening ports for direct connections as an IPython kernel")
         
         kernel = self.kernel
         
         kwargs.setdefault('config', self.config)
         kwargs.setdefault('log', self.log)
         kwargs.setdefault('profile_dir', self.profile_dir)
         kwargs.setdefault('session', self.engine.session)
         
         app = self.kernel_app = IPKernelApp(**kwargs)
         
         # allow IPKernelApp.instance():
         IPKernelApp._instance = app
         
         app.init_connection_file()
         # relevant contents of init_sockets:
         
         app.shell_port = app._bind_socket(kernel.shell_streams[0], app.shell_port)
         app.log.debug("shell ROUTER Channel on port: %i", app.shell_port)
         
         app.iopub_port = app._bind_socket(kernel.iopub_socket, app.iopub_port)
         app.log.debug("iopub PUB Channel on port: %i", app.iopub_port)
         
         kernel.stdin_socket = self.engine.context.socket(zmq.ROUTER)
         app.stdin_port = app._bind_socket(kernel.stdin_socket, app.stdin_port)
         app.log.debug("stdin ROUTER Channel on port: %i", app.stdin_port)
         
         # start the heartbeat, and log connection info:
         
         app.init_heartbeat()
         
         app.log_connection_info()
         app.write_connection_file()
         
     
     def init_engine(self):
         # This is the working dir by now.
         sys.path.insert(0, '')
         config = self.config
         # print config
         self.find_url_file()
         
         # was the url manually specified?
         keys = set(self.config.EngineFactory.keys())
         keys = keys.union(set(self.config.RegistrationFactory.keys()))
         
         if keys.intersection(set(['ip', 'url', 'port'])):
             # Connection info was specified, don't wait for the file
             url_specified = True
             self.wait_for_url_file = 0
         else:
             url_specified = False
 
         if self.wait_for_url_file and not os.path.exists(self.url_file):
             self.log.warn("url_file %r not found", self.url_file)
             self.log.warn("Waiting up to %.1f seconds for it to arrive.", self.wait_for_url_file)
             tic = time.time()
             while not os.path.exists(self.url_file) and (time.time()-tic < self.wait_for_url_file):
                 # wait for url_file to exist, or until time limit
                 time.sleep(0.1)
             
         if os.path.exists(self.url_file):
             self.load_connector_file()
         elif not url_specified:
             self.log.fatal("Fatal: url file never arrived: %s", self.url_file)
             self.exit(1)
         
         
         try:
-            exec_lines = config.Kernel.exec_lines
+            exec_lines = config.IPKernelApp.exec_lines
         except AttributeError:
-            config.Kernel.exec_lines = []
-            exec_lines = config.Kernel.exec_lines
+            try:
+                exec_lines = config.InteractiveShellApp.exec_lines
+            except AttributeError:
+                exec_lines = config.IPKernelApp.exec_lines = []
+        try:
+            exec_files = config.IPKernelApp.exec_files
+        except AttributeError:
+            try:
+                exec_files = config.InteractiveShellApp.exec_files
+            except AttributeError:
+                exec_files = config.IPKernelApp.exec_files = []
         
         if self.startup_script:
-            enc = sys.getfilesystemencoding() or 'utf8'
-            cmd="execfile(%r)" % self.startup_script.encode(enc)
-            exec_lines.append(cmd)
+            exec_files.append(self.startup_script)
         if self.startup_command:
             exec_lines.append(self.startup_command)
 
         # Create the underlying shell class and Engine
         # shell_class = import_item(self.master_config.Global.shell_class)
         # print self.config
         try:
             self.engine = EngineFactory(config=config, log=self.log)
         except:
             self.log.error("Couldn't start the Engine", exc_info=True)
             self.exit(1)
     
     def forward_logging(self):
         if self.log_url:
             self.log.info("Forwarding logging to %s", self.log_url)
             context = self.engine.context
             lsock = context.socket(zmq.PUB)
             lsock.connect(self.log_url)
             handler = EnginePUBHandler(self.engine, lsock)
             handler.setLevel(self.log_level)
             self.log.addHandler(handler)
     
     def init_mpi(self):
         global mpi
         self.mpi = MPI(config=self.config)
 
         mpi_import_statement = self.mpi.init_script
         if mpi_import_statement:
             try:
                 self.log.info("Initializing MPI:")
                 self.log.info(mpi_import_statement)
                 exec mpi_import_statement in globals()
             except:
                 mpi = None
         else:
             mpi = None
 
     @catch_config_error
     def initialize(self, argv=None):
         super(IPEngineApp, self).initialize(argv)
         self.init_mpi()
         self.init_engine()
         self.forward_logging()
     
     def start(self):
         self.engine.start()
         try:
             self.engine.loop.start()
         except KeyboardInterrupt:
             self.log.critical("Engine Interrupted, shutting down...\n")
 
 
 def launch_new_instance():
     """Create and run the IPython engine"""
     app = IPEngineApp.instance()
     app.initialize()
     app.start()
 
 
 if __name__ == '__main__':
     launch_new_instance()
 

IPython/parallel/engine/engine.py

@@ -1,237 +1,242 b''
 """A simple engine that talks to a controller over 0MQ.
 it handles registration, etc. and launches a kernel
 connected to the Controller's Schedulers.
 
 Authors:
 
 * Min RK
 """
 #-----------------------------------------------------------------------------
 #  Copyright (C) 2010-2011  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.
 #-----------------------------------------------------------------------------
 
 from __future__ import print_function
 
 import sys
 import time
 from getpass import getpass
 
 import zmq
 from zmq.eventloop import ioloop, zmqstream
 
 from IPython.external.ssh import tunnel
 # internal
 from IPython.utils.traitlets import (
     Instance, Dict, Integer, Type, CFloat, Unicode, CBytes, Bool
 )
 from IPython.utils.py3compat import cast_bytes
 
 from IPython.parallel.controller.heartmonitor import Heart
 from IPython.parallel.factory import RegistrationFactory
 from IPython.parallel.util import disambiguate_url
 
 from IPython.zmq.session import Message
-from IPython.zmq.ipkernel import Kernel
+from IPython.zmq.ipkernel import Kernel, IPKernelApp
 
 class EngineFactory(RegistrationFactory):
     """IPython engine"""
 
     # configurables:
     out_stream_factory=Type('IPython.zmq.iostream.OutStream', config=True,
         help="""The OutStream for handling stdout/err.
         Typically 'IPython.zmq.iostream.OutStream'""")
     display_hook_factory=Type('IPython.zmq.displayhook.ZMQDisplayHook', config=True,
         help="""The class for handling displayhook.
         Typically 'IPython.zmq.displayhook.ZMQDisplayHook'""")
     location=Unicode(config=True,
         help="""The location (an IP address) of the controller.  This is
         used for disambiguating URLs, to determine whether
         loopback should be used to connect or the public address.""")
     timeout=CFloat(2,config=True,
         help="""The time (in seconds) to wait for the Controller to respond
         to registration requests before giving up.""")
     sshserver=Unicode(config=True,
         help="""The SSH server to use for tunneling connections to the Controller.""")
     sshkey=Unicode(config=True,
         help="""The SSH private key file to use when tunneling connections to the Controller.""")
     paramiko=Bool(sys.platform == 'win32', config=True,
         help="""Whether to use paramiko instead of openssh for tunnels.""")
 
     # not configurable:
     user_ns=Dict()
     id=Integer(allow_none=True)
     registrar=Instance('zmq.eventloop.zmqstream.ZMQStream')
     kernel=Instance(Kernel)
 
     bident = CBytes()
     ident = Unicode()
     def _ident_changed(self, name, old, new):
         self.bident = cast_bytes(new)
     using_ssh=Bool(False)
 
 
     def __init__(self, **kwargs):
         super(EngineFactory, self).__init__(**kwargs)
         self.ident = self.session.session
 
     def init_connector(self):
         """construct connection function, which handles tunnels."""
         self.using_ssh = bool(self.sshkey or self.sshserver)
 
         if self.sshkey and not self.sshserver:
             # We are using ssh directly to the controller, tunneling localhost to localhost
             self.sshserver = self.url.split('://')[1].split(':')[0]
 
         if self.using_ssh:
             if tunnel.try_passwordless_ssh(self.sshserver, self.sshkey, self.paramiko):
                 password=False
             else:
                 password = getpass("SSH Password for %s: "%self.sshserver)
         else:
             password = False
 
         def connect(s, url):
             url = disambiguate_url(url, self.location)
             if self.using_ssh:
                 self.log.debug("Tunneling connection to %s via %s"%(url, self.sshserver))
                 return tunnel.tunnel_connection(s, url, self.sshserver,
                             keyfile=self.sshkey, paramiko=self.paramiko,
                             password=password,
                 )
             else:
                 return s.connect(url)
 
         def maybe_tunnel(url):
             """like connect, but don't complete the connection (for use by heartbeat)"""
             url = disambiguate_url(url, self.location)
             if self.using_ssh:
                 self.log.debug("Tunneling connection to %s via %s"%(url, self.sshserver))
                 url,tunnelobj = tunnel.open_tunnel(url, self.sshserver,
                             keyfile=self.sshkey, paramiko=self.paramiko,
                             password=password,
                 )
             return url
         return connect, maybe_tunnel
 
     def register(self):
         """send the registration_request"""
 
         self.log.info("Registering with controller at %s"%self.url)
         ctx = self.context
         connect,maybe_tunnel = self.init_connector()
         reg = ctx.socket(zmq.DEALER)
         reg.setsockopt(zmq.IDENTITY, self.bident)
         connect(reg, self.url)
         self.registrar = zmqstream.ZMQStream(reg, self.loop)
 
 
         content = dict(queue=self.ident, heartbeat=self.ident, control=self.ident)
         self.registrar.on_recv(lambda msg: self.complete_registration(msg, connect, maybe_tunnel))
         # print (self.session.key)
         self.session.send(self.registrar, "registration_request",content=content)
 
     def complete_registration(self, msg, connect, maybe_tunnel):
         # print msg
         self._abort_dc.stop()
         ctx = self.context
         loop = self.loop
         identity = self.bident
         idents,msg = self.session.feed_identities(msg)
         msg = Message(self.session.unserialize(msg))
 
         if msg.content.status == 'ok':
             self.id = int(msg.content.id)
 
             # launch heartbeat
             hb_addrs = msg.content.heartbeat
 
             # possibly forward hb ports with tunnels
             hb_addrs = [ maybe_tunnel(addr) for addr in hb_addrs ]
             heart = Heart(*map(str, hb_addrs), heart_id=identity)
             heart.start()
 
             # create Shell Streams (MUX, Task, etc.):
             queue_addr = msg.content.mux
             shell_addrs = [ str(queue_addr) ]
             task_addr = msg.content.task
             if task_addr:
                 shell_addrs.append(str(task_addr))
 
             # Uncomment this to go back to two-socket model
             # shell_streams = []
             # for addr in shell_addrs:
             #     stream = zmqstream.ZMQStream(ctx.socket(zmq.ROUTER), loop)
             #     stream.setsockopt(zmq.IDENTITY, identity)
             #     stream.connect(disambiguate_url(addr, self.location))
             #     shell_streams.append(stream)
 
             # Now use only one shell stream for mux and tasks
             stream = zmqstream.ZMQStream(ctx.socket(zmq.ROUTER), loop)
             stream.setsockopt(zmq.IDENTITY, identity)
             shell_streams = [stream]
             for addr in shell_addrs:
                 connect(stream, addr)
             # end single stream-socket
 
             # control stream:
             control_addr = str(msg.content.control)
             control_stream = zmqstream.ZMQStream(ctx.socket(zmq.ROUTER), loop)
             control_stream.setsockopt(zmq.IDENTITY, identity)
             connect(control_stream, control_addr)
 
             # create iopub stream:
             iopub_addr = msg.content.iopub
             iopub_socket = ctx.socket(zmq.PUB)
             iopub_socket.setsockopt(zmq.IDENTITY, identity)
             connect(iopub_socket, iopub_addr)
 
             # disable history:
             self.config.HistoryManager.hist_file = ':memory:'
             
             # Redirect input streams and set a display hook.
             if self.out_stream_factory:
                 sys.stdout = self.out_stream_factory(self.session, iopub_socket, u'stdout')
                 sys.stdout.topic = cast_bytes('engine.%i.stdout' % self.id)
                 sys.stderr = self.out_stream_factory(self.session, iopub_socket, u'stderr')
                 sys.stderr.topic = cast_bytes('engine.%i.stderr' % self.id)
             if self.display_hook_factory:
                 sys.displayhook = self.display_hook_factory(self.session, iopub_socket)
                 sys.displayhook.topic = cast_bytes('engine.%i.pyout' % self.id)
 
             self.kernel = Kernel(config=self.config, int_id=self.id, ident=self.ident, session=self.session,
                     control_stream=control_stream, shell_streams=shell_streams, iopub_socket=iopub_socket,
                     loop=loop, user_ns=self.user_ns, log=self.log)
+
             self.kernel.shell.display_pub.topic = cast_bytes('engine.%i.displaypub' % self.id)
-            self.kernel.start()
 
+            # FIXME: This is a hack until IPKernelApp and IPEngineApp can be fully merged
+            app = IPKernelApp(config=self.config, shell=self.kernel.shell, kernel=self.kernel, log=self.log)
+            app.init_profile_dir()
+            app.init_code()
 
+            self.kernel.start()
         else:
             self.log.fatal("Registration Failed: %s"%msg)
             raise Exception("Registration Failed: %s"%msg)
 
         self.log.info("Completed registration with id %i"%self.id)
 
 
     def abort(self):
         self.log.fatal("Registration timed out after %.1f seconds"%self.timeout)
         if self.url.startswith('127.'):
             self.log.fatal("""
             If the controller and engines are not on the same machine,
             you will have to instruct the controller to listen on an external IP (in ipcontroller_config.py):
                 c.HubFactory.ip='*' # for all interfaces, internal and external
                 c.HubFactory.ip='192.168.1.101' # or any interface that the engines can see
             or tunnel connections via ssh.
             """)
         self.session.send(self.registrar, "unregistration_request", content=dict(id=self.id))
         time.sleep(1)
         sys.exit(255)
 
     def start(self):
         dc = ioloop.DelayedCallback(self.register, 0, self.loop)
         dc.start()
         self._abort_dc = ioloop.DelayedCallback(self.abort, self.timeout*1000, self.loop)
         self._abort_dc.start()