add ssh tunneling to Engine

'enginessh' alias added to ipcontroller to new IPControllerApp.engine_ssh_server

ssh/keyfile added to ipengine/EngineFactory

IPython/parallel/apps/ipcontrollerapp.py

@@ -1,431 +1,441 b''
 #!/usr/bin/env python
 # encoding: utf-8
 """
 The IPython controller 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
 #-----------------------------------------------------------------------------
 
 from __future__ import with_statement
 
 import os
 import socket
 import stat
 import sys
 import uuid
 
 from multiprocessing import Process
 
 import zmq
 from zmq.devices import ProcessMonitoredQueue
 from zmq.log.handlers import PUBHandler
 from zmq.utils import jsonapi as json
 
 from IPython.config.application import boolean_flag
 from IPython.core.profiledir import ProfileDir
 
 from IPython.parallel.apps.baseapp import (
     BaseParallelApplication,
     base_aliases,
     base_flags,
 )
 from IPython.utils.importstring import import_item
 from IPython.utils.traitlets import Instance, Unicode, Bool, List, Dict
 
 # from IPython.parallel.controller.controller import ControllerFactory
 from IPython.zmq.session import Session
 from IPython.parallel.controller.heartmonitor import HeartMonitor
 from IPython.parallel.controller.hub import HubFactory
 from IPython.parallel.controller.scheduler import TaskScheduler,launch_scheduler
 from IPython.parallel.controller.sqlitedb import SQLiteDB
 
 from IPython.parallel.util import signal_children, split_url, asbytes
 
 # conditional import of MongoDB backend class
 
 try:
     from IPython.parallel.controller.mongodb import MongoDB
 except ImportError:
     maybe_mongo = []
 else:
     maybe_mongo = [MongoDB]
 
 
 #-----------------------------------------------------------------------------
 # Module level variables
 #-----------------------------------------------------------------------------
 
 
 #: The default config file name for this application
 default_config_file_name = u'ipcontroller_config.py'
 
 
 _description = """Start the IPython controller for parallel computing.
 
 The IPython controller provides a gateway between the IPython engines and
 clients. The controller needs to be started before the engines and 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 = """
 ipcontroller --ip=192.168.0.1 --port=1000  # listen on ip, port for engines
 ipcontroller --scheme=pure  # use the pure zeromq scheduler
 """
 
 
 #-----------------------------------------------------------------------------
 # The main application
 #-----------------------------------------------------------------------------
 flags = {}
 flags.update(base_flags)
 flags.update({
     'usethreads' : ( {'IPControllerApp' : {'use_threads' : True}},
                     'Use threads instead of processes for the schedulers'),
     'sqlitedb' : ({'HubFactory' : {'db_class' : 'IPython.parallel.controller.sqlitedb.SQLiteDB'}},
                     'use the SQLiteDB backend'),
     'mongodb' : ({'HubFactory' : {'db_class' : 'IPython.parallel.controller.mongodb.MongoDB'}},
                     'use the MongoDB backend'),
     'dictdb' : ({'HubFactory' : {'db_class' : 'IPython.parallel.controller.dictdb.DictDB'}},
                     'use the in-memory DictDB backend'),
     'reuse' : ({'IPControllerApp' : {'reuse_files' : True}},
                     'reuse existing json connection files')
 })
 
 flags.update(boolean_flag('secure', 'IPControllerApp.secure',
     "Use HMAC digests for authentication of messages.",
     "Don't authenticate messages."
 ))
 aliases = dict(
     secure = 'IPControllerApp.secure',
     ssh = 'IPControllerApp.ssh_server',
+    enginessh = 'IPControllerApp.engine_ssh_server',
     location = 'IPControllerApp.location',
 
     ident = 'Session.session',
     user = 'Session.username',
     keyfile = 'Session.keyfile',
 
     url = 'HubFactory.url',
     ip = 'HubFactory.ip',
     transport = 'HubFactory.transport',
     port = 'HubFactory.regport',
 
     ping = 'HeartMonitor.period',
 
     scheme = 'TaskScheduler.scheme_name',
     hwm = 'TaskScheduler.hwm',
 )
 aliases.update(base_aliases)
 
 
 class IPControllerApp(BaseParallelApplication):
 
     name = u'ipcontroller'
     description = _description
     examples = _examples
     config_file_name = Unicode(default_config_file_name)
     classes = [ProfileDir, Session, HubFactory, TaskScheduler, HeartMonitor, SQLiteDB] + maybe_mongo
     
     # change default to True
     auto_create = Bool(True, config=True,
         help="""Whether to create profile dir if it doesn't exist.""")
     
     reuse_files = Bool(False, config=True,
         help='Whether to reuse existing json connection files.'
     )
     secure = Bool(True, config=True,
         help='Whether to use HMAC digests for extra message authentication.'
     )
     ssh_server = Unicode(u'', config=True,
         help="""ssh url for clients to use when connecting to the Controller
         processes. It should be of the form: [user@]server[:port]. The
         Controller's listening addresses must be accessible from the ssh server""",
     )
+    engine_ssh_server = Unicode(u'', config=True,
+        help="""ssh url for engines to use when connecting to the Controller
+        processes. It should be of the form: [user@]server[:port]. The
+        Controller's listening addresses must be accessible from the ssh server""",
+    )
     location = Unicode(u'', config=True,
         help="""The external IP or domain name of the Controller, used for disambiguating
         engine and client connections.""",
     )
     import_statements = List([], config=True,
         help="import statements to be run at startup.  Necessary in some environments"
     )
 
     use_threads = Bool(False, config=True,
         help='Use threads instead of processes for the schedulers',
         )
 
     # internal
     children = List()
     mq_class = Unicode('zmq.devices.ProcessMonitoredQueue')
 
     def _use_threads_changed(self, name, old, new):
         self.mq_class = 'zmq.devices.%sMonitoredQueue'%('Thread' if new else 'Process')
 
     aliases = Dict(aliases)
     flags = Dict(flags)
     
 
     def save_connection_dict(self, fname, cdict):
         """save a connection dict to json file."""
         c = self.config
         url = cdict['url']
         location = cdict['location']
         if not location:
             try:
                 proto,ip,port = split_url(url)
             except AssertionError:
                 pass
             else:
                 try:
                     location = socket.gethostbyname_ex(socket.gethostname())[2][-1]
                 except (socket.gaierror, IndexError):
                     self.log.warn("Could not identify this machine's IP, assuming 127.0.0.1."
                     " You may need to specify '--location=<external_ip_address>' to help"
                     " IPython decide when to connect via loopback.")
                     location = '127.0.0.1'
             cdict['location'] = location
         fname = os.path.join(self.profile_dir.security_dir, fname)
         with open(fname, 'wb') as f:
             f.write(json.dumps(cdict, indent=2))
         os.chmod(fname, stat.S_IRUSR|stat.S_IWUSR)
     
     def load_config_from_json(self):
         """load config from existing json connector files."""
         c = self.config
         # load from engine config
         with open(os.path.join(self.profile_dir.security_dir, 'ipcontroller-engine.json')) as f:
             cfg = json.loads(f.read())
         key = c.Session.key = asbytes(cfg['exec_key'])
         xport,addr = cfg['url'].split('://')
         c.HubFactory.engine_transport = xport
         ip,ports = addr.split(':')
         c.HubFactory.engine_ip = ip
         c.HubFactory.regport = int(ports)
         self.location = cfg['location']
+        if not self.engine_ssh_server:
+            self.engine_ssh_server = cfg['ssh']
         # load client config
         with open(os.path.join(self.profile_dir.security_dir, 'ipcontroller-client.json')) as f:
             cfg = json.loads(f.read())
         assert key == cfg['exec_key'], "exec_key mismatch between engine and client keys"
         xport,addr = cfg['url'].split('://')
         c.HubFactory.client_transport = xport
         ip,ports = addr.split(':')
         c.HubFactory.client_ip = ip
-        self.ssh_server = cfg['ssh']
+        if not self.ssh_server:
+            self.ssh_server = cfg['ssh']
         assert int(ports) == c.HubFactory.regport, "regport mismatch"
     
     def init_hub(self):
         c = self.config
         
         self.do_import_statements()
         reusing = self.reuse_files
         if reusing:
             try:
                 self.load_config_from_json()
             except (AssertionError,IOError):
                 reusing=False
         # check again, because reusing may have failed:
         if reusing:
             pass
         elif self.secure:
             key = str(uuid.uuid4())
             # keyfile = os.path.join(self.profile_dir.security_dir, self.exec_key)
             # with open(keyfile, 'w') as f:
             #     f.write(key)
             # os.chmod(keyfile, stat.S_IRUSR|stat.S_IWUSR)
             c.Session.key = asbytes(key)
         else:
             key = c.Session.key = b''
         
         try:
             self.factory = HubFactory(config=c, log=self.log)
             # self.start_logging()
             self.factory.init_hub()
         except:
             self.log.error("Couldn't construct the Controller", exc_info=True)
             self.exit(1)
         
         if not reusing:
             # save to new json config files
             f = self.factory
             cdict = {'exec_key' : key,
                     'ssh' : self.ssh_server,
                     'url' : "%s://%s:%s"%(f.client_transport, f.client_ip, f.regport),
                     'location' : self.location
                     }
             self.save_connection_dict('ipcontroller-client.json', cdict)
             edict = cdict
             edict['url']="%s://%s:%s"%((f.client_transport, f.client_ip, f.regport))
+            edict['ssh'] = self.engine_ssh_server
             self.save_connection_dict('ipcontroller-engine.json', edict)
 
     #
     def init_schedulers(self):
         children = self.children
         mq = import_item(str(self.mq_class))
         
         hub = self.factory
         # maybe_inproc = 'inproc://monitor' if self.use_threads else self.monitor_url
         # IOPub relay (in a Process)
         q = mq(zmq.PUB, zmq.SUB, zmq.PUB, b'N/A',b'iopub')
         q.bind_in(hub.client_info['iopub'])
         q.bind_out(hub.engine_info['iopub'])
         q.setsockopt_out(zmq.SUBSCRIBE, b'')
         q.connect_mon(hub.monitor_url)
         q.daemon=True
         children.append(q)
 
         # Multiplexer Queue (in a Process)
         q = mq(zmq.XREP, zmq.XREP, zmq.PUB, b'in', b'out')
         q.bind_in(hub.client_info['mux'])
         q.setsockopt_in(zmq.IDENTITY, b'mux')
         q.bind_out(hub.engine_info['mux'])
         q.connect_mon(hub.monitor_url)
         q.daemon=True
         children.append(q)
 
         # Control Queue (in a Process)
         q = mq(zmq.XREP, zmq.XREP, zmq.PUB, b'incontrol', b'outcontrol')
         q.bind_in(hub.client_info['control'])
         q.setsockopt_in(zmq.IDENTITY, b'control')
         q.bind_out(hub.engine_info['control'])
         q.connect_mon(hub.monitor_url)
         q.daemon=True
         children.append(q)
         try:
             scheme = self.config.TaskScheduler.scheme_name
         except AttributeError:
             scheme = TaskScheduler.scheme_name.get_default_value()
         # Task Queue (in a Process)
         if scheme == 'pure':
             self.log.warn("task::using pure XREQ Task scheduler")
             q = mq(zmq.XREP, zmq.XREQ, zmq.PUB, b'intask', b'outtask')
             # q.setsockopt_out(zmq.HWM, hub.hwm)
             q.bind_in(hub.client_info['task'][1])
             q.setsockopt_in(zmq.IDENTITY, b'task')
             q.bind_out(hub.engine_info['task'])
             q.connect_mon(hub.monitor_url)
             q.daemon=True
             children.append(q)
         elif scheme == 'none':
             self.log.warn("task::using no Task scheduler")
 
         else:
             self.log.info("task::using Python %s Task scheduler"%scheme)
             sargs = (hub.client_info['task'][1], hub.engine_info['task'],
                                 hub.monitor_url, hub.client_info['notification'])
             kwargs = dict(logname='scheduler', loglevel=self.log_level,
                             log_url = self.log_url, config=dict(self.config))
             if 'Process' in self.mq_class:
                 # run the Python scheduler in a Process
                 q = Process(target=launch_scheduler, args=sargs, kwargs=kwargs)
                 q.daemon=True
                 children.append(q)
             else:
                 # single-threaded Controller
                 kwargs['in_thread'] = True
                 launch_scheduler(*sargs, **kwargs)
 
     
     def save_urls(self):
         """save the registration urls to files."""
         c = self.config
         
         sec_dir = self.profile_dir.security_dir
         cf = self.factory
         
         with open(os.path.join(sec_dir, 'ipcontroller-engine.url'), 'w') as f:
             f.write("%s://%s:%s"%(cf.engine_transport, cf.engine_ip, cf.regport))
         
         with open(os.path.join(sec_dir, 'ipcontroller-client.url'), 'w') as f:
             f.write("%s://%s:%s"%(cf.client_transport, cf.client_ip, cf.regport))
         
     
     def do_import_statements(self):
         statements = self.import_statements
         for s in statements:
             try:
                 self.log.msg("Executing statement: '%s'" % s)
                 exec s in globals(), locals()
             except:
                 self.log.msg("Error running statement: %s" % s)
 
     def forward_logging(self):
         if self.log_url:
             self.log.info("Forwarding logging to %s"%self.log_url)
             context = zmq.Context.instance()
             lsock = context.socket(zmq.PUB)
             lsock.connect(self.log_url)
             handler = PUBHandler(lsock)
             self.log.removeHandler(self._log_handler)
             handler.root_topic = 'controller'
             handler.setLevel(self.log_level)
             self.log.addHandler(handler)
             self._log_handler = handler
     # #
     
     def initialize(self, argv=None):
         super(IPControllerApp, self).initialize(argv)
         self.forward_logging()
         self.init_hub()
         self.init_schedulers()
     
     def start(self):
         # Start the subprocesses:
         self.factory.start()
         child_procs = []
         for child in self.children:
             child.start()
             if isinstance(child, ProcessMonitoredQueue):
                 child_procs.append(child.launcher)
             elif isinstance(child, Process):
                 child_procs.append(child)
         if child_procs:
             signal_children(child_procs)
 
         self.write_pid_file(overwrite=True)
 
         try:
             self.factory.loop.start()
         except KeyboardInterrupt:
             self.log.critical("Interrupted, Exiting...\n")
             
 
 
 def launch_new_instance():
     """Create and run the IPython controller"""
     if sys.platform == 'win32':
         # make sure we don't get called from a multiprocessing subprocess
         # this can result in infinite Controllers being started on Windows
         # which doesn't have a proper fork, so multiprocessing is wonky
         
         # this only comes up when IPython has been installed using vanilla
         # setuptools, and *not* distribute.
         import multiprocessing
         p = multiprocessing.current_process()
         # the main process has name 'MainProcess'
         # subprocesses will have names like 'Process-1'
         if p.name != 'MainProcess':
             # we are a subprocess, don't start another Controller!
             return
     app = IPControllerApp.instance()
     app.initialize()
     app.start()
 
 
 if __name__ == '__main__':
     launch_new_instance()

IPython/parallel/apps/ipengineapp.py

@@ -1,307 +1,336 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,
 )
 from IPython.zmq.log import EnginePUBHandler
 
 from IPython.config.configurable import Configurable
 from IPython.zmq.session import Session
 from IPython.parallel.engine.engine import EngineFactory
 from IPython.parallel.engine.streamkernel import Kernel
 from IPython.parallel.util import disambiguate_url, asbytes
 
 from IPython.utils.importstring import import_item
 from IPython.utils.traitlets import Bool, Unicode, Dict, List, Float
 
 
 #-----------------------------------------------------------------------------
 # 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 _on_use_changed(self, 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',
 
     ident = 'Session.session',
     user = 'Session.username',
     keyfile = 'Session.keyfile',
 
     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)
 
 
 class IPEngineApp(BaseParallelApplication):
 
     name = Unicode(u'ipengine')
     description = Unicode(_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')
     log_url = Unicode('', config=True,
         help="""The URL for the iploggerapp instance, for forwarding
         logging to a central location.""")
 
     aliases = Dict(aliases)
 
     # def find_key_file(self):
     #     """Set the key 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.master_config
     #     # Find the actual controller key file
     #     if not config.Global.key_file:
     #         try_this = os.path.join(
     #             config.Global.profile_dir, 
     #             config.Global.security_dir,
     #             config.Global.key_file_name
     #         )
     #         config.Global.key_file = try_this
         
     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())
+        
+        try:
+            config.Session.key
+        except AttributeError:
+            if d['exec_key']:
+                config.Session.key = asbytes(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 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, for up to 10 seconds
                 time.sleep(0.1)
             
         if os.path.exists(self.url_file):
-            self.log.info("Loading url_file %r"%self.url_file)
-            with open(self.url_file) as f:
-                d = json.loads(f.read())
-            if d['exec_key']:
-                config.Session.key = asbytes(d['exec_key'])
-            d['url'] = disambiguate_url(d['url'], d['location'])
-            config.EngineFactory.url = d['url']
-            config.EngineFactory.location = d['location']
+            self.load_connector_file()
         elif not url_specified:
             self.log.critical("Fatal: url file never arrived: %s"%self.url_file)
             self.exit(1)
         
         
         try:
             exec_lines = config.Kernel.exec_lines
         except AttributeError:
             config.Kernel.exec_lines = []
             exec_lines = config.Kernel.exec_lines
         
         if self.startup_script:
             enc = sys.getfilesystemencoding() or 'utf8'
             cmd="execfile(%r)"%self.startup_script.encode(enc)
             exec_lines.append(cmd)
         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)
             self.log.removeHandler(self._log_handler)
             handler = EnginePUBHandler(self.engine, lsock)
             handler.setLevel(self.log_level)
             self.log.addHandler(handler)
             self._log_handler = 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
 
     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

@@ -1,173 +1,226 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, Int, Type, CFloat, Unicode, CBytes
+from IPython.utils.traitlets import (
+    Instance, Dict, Int, Type, CFloat, Unicode, CBytes, Bool
+)
 # from IPython.utils.localinterfaces import LOCALHOST 
 
 from IPython.parallel.controller.heartmonitor import Heart
 from IPython.parallel.factory import RegistrationFactory
 from IPython.parallel.util import disambiguate_url, asbytes
 
 from IPython.zmq.session import Message
 
 from .streamkernel import Kernel
 
 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 keyfile 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=Int(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 = asbytes(new)
+    using_ssh=Bool(False)
     
     
     def __init__(self, **kwargs):
         super(EngineFactory, self).__init__(**kwargs)
         self.ident = self.session.session
-        ctx = self.context
+    
+    def init_connector(self):
+        """construct connection function, which handles tunnels."""
+        self.using_ssh = bool(self.sshkey or self.sshserver)
         
-        reg = ctx.socket(zmq.XREQ)
-        reg.setsockopt(zmq.IDENTITY, self.bident)
-        reg.connect(self.url)
-        self.registrar = zmqstream.ZMQStream(reg, self.loop)
+        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.XREQ)
+        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(self.complete_registration)
+        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):
+    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.XREP), 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.XREP), loop)
             stream.setsockopt(zmq.IDENTITY, identity)
             shell_streams = [stream]
             for addr in shell_addrs:
-                stream.connect(disambiguate_url(addr, self.location))
+                connect(stream, addr)
             # end single stream-socket
             
             # control stream:
             control_addr = str(msg.content.control)
             control_stream = zmqstream.ZMQStream(ctx.socket(zmq.XREP), loop)
             control_stream.setsockopt(zmq.IDENTITY, identity)
-            control_stream.connect(disambiguate_url(control_addr, self.location))
+            connect(control_stream, control_addr)
             
             # create iopub stream:
             iopub_addr = msg.content.iopub
             iopub_stream = zmqstream.ZMQStream(ctx.socket(zmq.PUB), loop)
             iopub_stream.setsockopt(zmq.IDENTITY, identity)
-            iopub_stream.connect(disambiguate_url(iopub_addr, self.location))
-            
-            # launch heartbeat
-            hb_addrs = msg.content.heartbeat
-            # print (hb_addrs)
+            connect(iopub_stream, iopub_addr)
             
             # # Redirect input streams and set a display hook.
             if self.out_stream_factory:
                 sys.stdout = self.out_stream_factory(self.session, iopub_stream, u'stdout')
                 sys.stdout.topic = 'engine.%i.stdout'%self.id
                 sys.stderr = self.out_stream_factory(self.session, iopub_stream, u'stderr')
                 sys.stderr.topic = 'engine.%i.stderr'%self.id
             if self.display_hook_factory:
                 sys.displayhook = self.display_hook_factory(self.session, iopub_stream)
                 sys.displayhook.topic = '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_stream=iopub_stream, 
                     loop=loop, user_ns = self.user_ns, log=self.log)
             self.kernel.start()
-            hb_addrs = [ disambiguate_url(addr, self.location) for addr in hb_addrs ]
-            heart = Heart(*map(str, hb_addrs), heart_id=identity)
-            heart.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)
         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()