remove IPython.external.ssh

This code moved to zmq a while ago, let’s just depend on that.

IPython/kernel/connect.py

@@ -1,578 +1,576 b''
 """Utilities for connecting to kernels
 
 The :class:`ConnectionFileMixin` class in this module encapsulates the logic
 related to writing and reading connections files.
 """
 # Copyright (c) IPython Development Team.
 # Distributed under the terms of the Modified BSD License.
 
 #-----------------------------------------------------------------------------
 # Imports
 #-----------------------------------------------------------------------------
 
 from __future__ import absolute_import
 
 import glob
 import json
 import os
 import socket
 import sys
 from getpass import getpass
 from subprocess import Popen, PIPE
 import tempfile
 
 import zmq
-
-# external imports
-from IPython.external.ssh import tunnel
+from zmq.ssh import tunnel
 
 # IPython imports
 from IPython.config import LoggingConfigurable
 from IPython.core.profiledir import ProfileDir
 from IPython.utils.localinterfaces import localhost
 from IPython.utils.path import filefind, get_ipython_dir
 from IPython.utils.py3compat import (str_to_bytes, bytes_to_str, cast_bytes_py2,
                                      string_types)
 from IPython.utils.traitlets import (
     Bool, Integer, Unicode, CaselessStrEnum, Instance,
 )
 
 
 #-----------------------------------------------------------------------------
 # Working with Connection Files
 #-----------------------------------------------------------------------------
 
 def write_connection_file(fname=None, shell_port=0, iopub_port=0, stdin_port=0, hb_port=0,
                          control_port=0, ip='', key=b'', transport='tcp',
                          signature_scheme='hmac-sha256',
                          ):
     """Generates a JSON config file, including the selection of random ports.
     
     Parameters
     ----------
 
     fname : unicode
         The path to the file to write
 
     shell_port : int, optional
         The port to use for ROUTER (shell) channel.
 
     iopub_port : int, optional
         The port to use for the SUB channel.
 
     stdin_port : int, optional
         The port to use for the ROUTER (raw input) channel.
 
     control_port : int, optional
         The port to use for the ROUTER (control) channel.
 
     hb_port : int, optional
         The port to use for the heartbeat REP channel.
 
     ip  : str, optional
         The ip address the kernel will bind to.
 
     key : str, optional
         The Session key used for message authentication.
     
     signature_scheme : str, optional
         The scheme used for message authentication.
         This has the form 'digest-hash', where 'digest'
         is the scheme used for digests, and 'hash' is the name of the hash function
         used by the digest scheme.
         Currently, 'hmac' is the only supported digest scheme,
         and 'sha256' is the default hash function.
 
     """
     if not ip:
         ip = localhost()
     # default to temporary connector file
     if not fname:
         fd, fname = tempfile.mkstemp('.json')
         os.close(fd)
     
     # Find open ports as necessary.
     
     ports = []
     ports_needed = int(shell_port <= 0) + \
                    int(iopub_port <= 0) + \
                    int(stdin_port <= 0) + \
                    int(control_port <= 0) + \
                    int(hb_port <= 0)
     if transport == 'tcp':
         for i in range(ports_needed):
             sock = socket.socket()
             # struct.pack('ii', (0,0)) is 8 null bytes
             sock.setsockopt(socket.SOL_SOCKET, socket.SO_LINGER, b'\0' * 8)
             sock.bind(('', 0))
             ports.append(sock)
         for i, sock in enumerate(ports):
             port = sock.getsockname()[1]
             sock.close()
             ports[i] = port
     else:
         N = 1
         for i in range(ports_needed):
             while os.path.exists("%s-%s" % (ip, str(N))):
                 N += 1
             ports.append(N)
             N += 1
     if shell_port <= 0:
         shell_port = ports.pop(0)
     if iopub_port <= 0:
         iopub_port = ports.pop(0)
     if stdin_port <= 0:
         stdin_port = ports.pop(0)
     if control_port <= 0:
         control_port = ports.pop(0)
     if hb_port <= 0:
         hb_port = ports.pop(0)
     
     cfg = dict( shell_port=shell_port,
                 iopub_port=iopub_port,
                 stdin_port=stdin_port,
                 control_port=control_port,
                 hb_port=hb_port,
               )
     cfg['ip'] = ip
     cfg['key'] = bytes_to_str(key)
     cfg['transport'] = transport
     cfg['signature_scheme'] = signature_scheme
     
     with open(fname, 'w') as f:
         f.write(json.dumps(cfg, indent=2))
     
     return fname, cfg
 
 
 def get_connection_file(app=None):
     """Return the path to the connection file of an app
     
     Parameters
     ----------
     app : IPKernelApp instance [optional]
         If unspecified, the currently running app will be used
     """
     if app is None:
         from IPython.kernel.zmq.kernelapp import IPKernelApp
         if not IPKernelApp.initialized():
             raise RuntimeError("app not specified, and not in a running Kernel")
 
         app = IPKernelApp.instance()
     return filefind(app.connection_file, ['.', app.profile_dir.security_dir])
 
 
 def find_connection_file(filename, profile=None):
     """find a connection file, and return its absolute path.
     
     The current working directory and the profile's security
     directory will be searched for the file if it is not given by
     absolute path.
     
     If profile is unspecified, then the current running application's
     profile will be used, or 'default', if not run from IPython.
     
     If the argument does not match an existing file, it will be interpreted as a
     fileglob, and the matching file in the profile's security dir with
     the latest access time will be used.
     
     Parameters
     ----------
     filename : str
         The connection file or fileglob to search for.
     profile : str [optional]
         The name of the profile to use when searching for the connection file,
         if different from the current IPython session or 'default'.
     
     Returns
     -------
     str : The absolute path of the connection file.
     """
     from IPython.core.application import BaseIPythonApplication as IPApp
     try:
         # quick check for absolute path, before going through logic
         return filefind(filename)
     except IOError:
         pass
     
     if profile is None:
         # profile unspecified, check if running from an IPython app
         if IPApp.initialized():
             app = IPApp.instance()
             profile_dir = app.profile_dir
         else:
             # not running in IPython, use default profile
             profile_dir = ProfileDir.find_profile_dir_by_name(get_ipython_dir(), 'default')
     else:
         # find profiledir by profile name:
         profile_dir = ProfileDir.find_profile_dir_by_name(get_ipython_dir(), profile)
     security_dir = profile_dir.security_dir
     
     try:
         # first, try explicit name
         return filefind(filename, ['.', security_dir])
     except IOError:
         pass
     
     # not found by full name
     
     if '*' in filename:
         # given as a glob already
         pat = filename
     else:
         # accept any substring match
         pat = '*%s*' % filename
     matches = glob.glob( os.path.join(security_dir, pat) )
     if not matches:
         raise IOError("Could not find %r in %r" % (filename, security_dir))
     elif len(matches) == 1:
         return matches[0]
     else:
         # get most recent match, by access time:
         return sorted(matches, key=lambda f: os.stat(f).st_atime)[-1]
 
 
 def get_connection_info(connection_file=None, unpack=False, profile=None):
     """Return the connection information for the current Kernel.
     
     Parameters
     ----------
     connection_file : str [optional]
         The connection file to be used. Can be given by absolute path, or
         IPython will search in the security directory of a given profile.
         If run from IPython, 
         
         If unspecified, the connection file for the currently running
         IPython Kernel will be used, which is only allowed from inside a kernel.
     unpack : bool [default: False]
         if True, return the unpacked dict, otherwise just the string contents
         of the file.
     profile : str [optional]
         The name of the profile to use when searching for the connection file,
         if different from the current IPython session or 'default'.
         
     
     Returns
     -------
     The connection dictionary of the current kernel, as string or dict,
     depending on `unpack`.
     """
     if connection_file is None:
         # get connection file from current kernel
         cf = get_connection_file()
     else:
         # connection file specified, allow shortnames:
         cf = find_connection_file(connection_file, profile=profile)
     
     with open(cf) as f:
         info = f.read()
     
     if unpack:
         info = json.loads(info)
         # ensure key is bytes:
         info['key'] = str_to_bytes(info.get('key', ''))
     return info
 
 
 def connect_qtconsole(connection_file=None, argv=None, profile=None):
     """Connect a qtconsole to the current kernel.
     
     This is useful for connecting a second qtconsole to a kernel, or to a
     local notebook.
     
     Parameters
     ----------
     connection_file : str [optional]
         The connection file to be used. Can be given by absolute path, or
         IPython will search in the security directory of a given profile.
         If run from IPython, 
         
         If unspecified, the connection file for the currently running
         IPython Kernel will be used, which is only allowed from inside a kernel.
     argv : list [optional]
         Any extra args to be passed to the console.
     profile : str [optional]
         The name of the profile to use when searching for the connection file,
         if different from the current IPython session or 'default'.
     
     
     Returns
     -------
     :class:`subprocess.Popen` instance running the qtconsole frontend
     """
     argv = [] if argv is None else argv
     
     if connection_file is None:
         # get connection file from current kernel
         cf = get_connection_file()
     else:
         cf = find_connection_file(connection_file, profile=profile)
     
     cmd = ';'.join([
         "from IPython.qt.console import qtconsoleapp",
         "qtconsoleapp.main()"
     ])
     
     return Popen([sys.executable, '-c', cmd, '--existing', cf] + argv,
         stdout=PIPE, stderr=PIPE, close_fds=(sys.platform != 'win32'),
     )
 
 
 def tunnel_to_kernel(connection_info, sshserver, sshkey=None):
     """tunnel connections to a kernel via ssh
     
     This will open four SSH tunnels from localhost on this machine to the
     ports associated with the kernel.  They can be either direct
     localhost-localhost tunnels, or if an intermediate server is necessary,
     the kernel must be listening on a public IP.
     
     Parameters
     ----------
     connection_info : dict or str (path)
         Either a connection dict, or the path to a JSON connection file
     sshserver : str
         The ssh sever to use to tunnel to the kernel. Can be a full
         `user@server:port` string. ssh config aliases are respected.
     sshkey : str [optional]
         Path to file containing ssh key to use for authentication.
         Only necessary if your ssh config does not already associate
         a keyfile with the host.
     
     Returns
     -------
     
     (shell, iopub, stdin, hb) : ints
         The four ports on localhost that have been forwarded to the kernel.
     """
     if isinstance(connection_info, string_types):
         # it's a path, unpack it
         with open(connection_info) as f:
             connection_info = json.loads(f.read())
     
     cf = connection_info
     
     lports = tunnel.select_random_ports(4)
     rports = cf['shell_port'], cf['iopub_port'], cf['stdin_port'], cf['hb_port']
     
     remote_ip = cf['ip']
     
     if tunnel.try_passwordless_ssh(sshserver, sshkey):
         password=False
     else:
         password = getpass("SSH Password for %s: " % cast_bytes_py2(sshserver))
     
     for lp,rp in zip(lports, rports):
         tunnel.ssh_tunnel(lp, rp, sshserver, remote_ip, sshkey, password)
     
     return tuple(lports)
 
 
 #-----------------------------------------------------------------------------
 # Mixin for classes that work with connection files
 #-----------------------------------------------------------------------------
 
 channel_socket_types = {
     'hb' : zmq.REQ,
     'shell' : zmq.DEALER,
     'iopub' : zmq.SUB,
     'stdin' : zmq.DEALER,
     'control': zmq.DEALER,
 }
 
 port_names = [ "%s_port" % channel for channel in ('shell', 'stdin', 'iopub', 'hb', 'control')]
 
 class ConnectionFileMixin(LoggingConfigurable):
     """Mixin for configurable classes that work with connection files"""
 
     # The addresses for the communication channels
     connection_file = Unicode('', config=True, 
     help="""JSON file in which to store connection info [default: kernel-<pid>.json]
     
     This file will contain the IP, ports, and authentication key needed to connect
     clients to this kernel. By default, this file will be created in the security dir
     of the current profile, but can be specified by absolute path.
     """)
     _connection_file_written = Bool(False)
 
     transport = CaselessStrEnum(['tcp', 'ipc'], default_value='tcp', config=True)
 
     ip = Unicode(config=True,
         help="""Set the kernel\'s IP address [default localhost].
         If the IP address is something other than localhost, then
         Consoles on other machines will be able to connect
         to the Kernel, so be careful!"""
     )
 
     def _ip_default(self):
         if self.transport == 'ipc':
             if self.connection_file:
                 return os.path.splitext(self.connection_file)[0] + '-ipc'
             else:
                 return 'kernel-ipc'
         else:
             return localhost()
 
     def _ip_changed(self, name, old, new):
         if new == '*':
             self.ip = '0.0.0.0'
 
     # protected traits
 
     hb_port = Integer(0, config=True,
             help="set the heartbeat port [default: random]")
     shell_port = Integer(0, config=True,
             help="set the shell (ROUTER) port [default: random]")
     iopub_port = Integer(0, config=True,
             help="set the iopub (PUB) port [default: random]")
     stdin_port = Integer(0, config=True,
             help="set the stdin (ROUTER) port [default: random]")
     control_port = Integer(0, config=True,
             help="set the control (ROUTER) port [default: random]")
 
     @property
     def ports(self):
         return [ getattr(self, name) for name in port_names ]
 
     # The Session to use for communication with the kernel.
     session = Instance('IPython.kernel.zmq.session.Session')
     def _session_default(self):
         from IPython.kernel.zmq.session import Session
         return Session(parent=self)
 
     #--------------------------------------------------------------------------
     # Connection and ipc file management
     #--------------------------------------------------------------------------
 
     def get_connection_info(self):
         """return the connection info as a dict"""
         return dict(
             transport=self.transport,
             ip=self.ip,
             shell_port=self.shell_port,
             iopub_port=self.iopub_port,
             stdin_port=self.stdin_port,
             hb_port=self.hb_port,
             control_port=self.control_port,
             signature_scheme=self.session.signature_scheme,
             key=self.session.key,
         )
 
     def cleanup_connection_file(self):
         """Cleanup connection file *if we wrote it*
 
         Will not raise if the connection file was already removed somehow.
         """
         if self._connection_file_written:
             # cleanup connection files on full shutdown of kernel we started
             self._connection_file_written = False
             try:
                 os.remove(self.connection_file)
             except (IOError, OSError, AttributeError):
                 pass
 
     def cleanup_ipc_files(self):
         """Cleanup ipc files if we wrote them."""
         if self.transport != 'ipc':
             return
         for port in self.ports:
             ipcfile = "%s-%i" % (self.ip, port)
             try:
                 os.remove(ipcfile)
             except (IOError, OSError):
                 pass
 
     def write_connection_file(self):
         """Write connection info to JSON dict in self.connection_file."""
         if self._connection_file_written and os.path.exists(self.connection_file):
             return
 
         self.connection_file, cfg = write_connection_file(self.connection_file,
             transport=self.transport, ip=self.ip, key=self.session.key,
             stdin_port=self.stdin_port, iopub_port=self.iopub_port,
             shell_port=self.shell_port, hb_port=self.hb_port,
             control_port=self.control_port,
             signature_scheme=self.session.signature_scheme,
         )
         # write_connection_file also sets default ports:
         for name in port_names:
             setattr(self, name, cfg[name])
 
         self._connection_file_written = True
 
     def load_connection_file(self):
         """Load connection info from JSON dict in self.connection_file."""
         self.log.debug(u"Loading connection file %s", self.connection_file)
         with open(self.connection_file) as f:
             cfg = json.load(f)
         self.transport = cfg.get('transport', self.transport)
         self.ip = cfg.get('ip', self._ip_default())
         
         for name in port_names:
             if getattr(self, name) == 0 and name in cfg:
                 # not overridden by config or cl_args
                 setattr(self, name, cfg[name])
         
         if 'key' in cfg:
             self.session.key = str_to_bytes(cfg['key'])
         if 'signature_scheme' in cfg:
             self.session.signature_scheme = cfg['signature_scheme']
 
     #--------------------------------------------------------------------------
     # Creating connected sockets
     #--------------------------------------------------------------------------
 
     def _make_url(self, channel):
         """Make a ZeroMQ URL for a given channel."""
         transport = self.transport
         ip = self.ip
         port = getattr(self, '%s_port' % channel)
 
         if transport == 'tcp':
             return "tcp://%s:%i" % (ip, port)
         else:
             return "%s://%s-%s" % (transport, ip, port)
 
     def _create_connected_socket(self, channel, identity=None):
         """Create a zmq Socket and connect it to the kernel."""
         url = self._make_url(channel)
         socket_type = channel_socket_types[channel]
         self.log.debug("Connecting to: %s" % url)
         sock = self.context.socket(socket_type)
         # set linger to 1s to prevent hangs at exit
         sock.linger = 1000
         if identity:
             sock.identity = identity
         sock.connect(url)
         return sock
 
     def connect_iopub(self, identity=None):
         """return zmq Socket connected to the IOPub channel"""
         sock = self._create_connected_socket('iopub', identity=identity)
         sock.setsockopt(zmq.SUBSCRIBE, b'')
         return sock
 
     def connect_shell(self, identity=None):
         """return zmq Socket connected to the Shell channel"""
         return self._create_connected_socket('shell', identity=identity)
 
     def connect_stdin(self, identity=None):
         """return zmq Socket connected to the StdIn channel"""
         return self._create_connected_socket('stdin', identity=identity)
 
     def connect_hb(self, identity=None):
         """return zmq Socket connected to the Heartbeat channel"""
         return self._create_connected_socket('hb', identity=identity)
 
     def connect_control(self, identity=None):
         """return zmq Socket connected to the Heartbeat channel"""
         return self._create_connected_socket('control', identity=identity)
 
 
 __all__ = [
     'write_connection_file',
     'get_connection_file',
     'find_connection_file',
     'get_connection_info',
     'connect_qtconsole',
     'tunnel_to_kernel',
 ]

IPython/parallel/client/client.py

@@ -1,1868 +1,1868 b''
 """A semi-synchronous Client for IPython parallel"""
 
 # Copyright (c) IPython Development Team.
 # Distributed under the terms of the Modified BSD License.
 
 from __future__ import print_function
 
 import os
 import json
 import sys
 from threading import Thread, Event
 import time
 import warnings
 from datetime import datetime
 from getpass import getpass
 from pprint import pprint
 
 pjoin = os.path.join
 
 import zmq
+from zmq.ssh import tunnel
 
 from IPython.config.configurable import MultipleInstanceError
 from IPython.core.application import BaseIPythonApplication
 from IPython.core.profiledir import ProfileDir, ProfileDirError
 
 from IPython.utils.capture import RichOutput
 from IPython.utils.coloransi import TermColors
 from IPython.utils.jsonutil import rekey, extract_dates, parse_date
 from IPython.utils.localinterfaces import localhost, is_local_ip
 from IPython.utils.path import get_ipython_dir
 from IPython.utils.py3compat import cast_bytes, string_types, xrange, iteritems
 from IPython.utils.traitlets import (HasTraits, Integer, Instance, Unicode,
                                     Dict, List, Bool, Set, Any)
 from IPython.external.decorator import decorator
-from IPython.external.ssh import tunnel
 
 from IPython.parallel import Reference
 from IPython.parallel import error
 from IPython.parallel import util
 
 from IPython.kernel.zmq.session import Session, Message
 from IPython.kernel.zmq import serialize
 
 from .asyncresult import AsyncResult, AsyncHubResult
 from .view import DirectView, LoadBalancedView
 
 #--------------------------------------------------------------------------
 # Decorators for Client methods
 #--------------------------------------------------------------------------
 
 @decorator
 def spin_first(f, self, *args, **kwargs):
     """Call spin() to sync state prior to calling the method."""
     self.spin()
     return f(self, *args, **kwargs)
 
 
 #--------------------------------------------------------------------------
 # Classes
 #--------------------------------------------------------------------------
 
 
 class ExecuteReply(RichOutput):
     """wrapper for finished Execute results"""
     def __init__(self, msg_id, content, metadata):
         self.msg_id = msg_id
         self._content = content
         self.execution_count = content['execution_count']
         self.metadata = metadata
     
     # RichOutput overrides
     
     @property
     def source(self):
         execute_result = self.metadata['execute_result']
         if execute_result:
             return execute_result.get('source', '')
     
     @property
     def data(self):
         execute_result = self.metadata['execute_result']
         if execute_result:
             return execute_result.get('data', {})
     
     @property
     def _metadata(self):
         execute_result = self.metadata['execute_result']
         if execute_result:
             return execute_result.get('metadata', {})
     
     def display(self):
         from IPython.display import publish_display_data
         publish_display_data(self.data, self.metadata)
     
     def _repr_mime_(self, mime):
         if mime not in self.data:
             return
         data = self.data[mime]
         if mime in self._metadata:
             return data, self._metadata[mime]
         else:
             return data
     
     def __getitem__(self, key):
         return self.metadata[key]
     
     def __getattr__(self, key):
         if key not in self.metadata:
             raise AttributeError(key)
         return self.metadata[key]
     
     def __repr__(self):
         execute_result = self.metadata['execute_result'] or {'data':{}}
         text_out = execute_result['data'].get('text/plain', '')
         if len(text_out) > 32:
             text_out = text_out[:29] + '...'
         
         return "<ExecuteReply[%i]: %s>" % (self.execution_count, text_out)
     
     def _repr_pretty_(self, p, cycle):
         execute_result = self.metadata['execute_result'] or {'data':{}}
         text_out = execute_result['data'].get('text/plain', '')
         
         if not text_out:
             return
         
         try:
             ip = get_ipython()
         except NameError:
             colors = "NoColor"
         else:
             colors = ip.colors
         
         if colors == "NoColor":
             out = normal = ""
         else:
             out = TermColors.Red
             normal = TermColors.Normal
         
         if '\n' in text_out and not text_out.startswith('\n'):
             # add newline for multiline reprs
             text_out = '\n' + text_out
         
         p.text(
             out + u'Out[%i:%i]: ' % (
                 self.metadata['engine_id'], self.execution_count
             ) + normal + text_out
         )
 
 
 class Metadata(dict):
     """Subclass of dict for initializing metadata values.
 
     Attribute access works on keys.
 
     These objects have a strict set of keys - errors will raise if you try
     to add new keys.
     """
     def __init__(self, *args, **kwargs):
         dict.__init__(self)
         md = {'msg_id' : None,
               'submitted' : None,
               'started' : None,
               'completed' : None,
               'received' : None,
               'engine_uuid' : None,
               'engine_id' : None,
               'follow' : None,
               'after' : None,
               'status' : None,
 
               'execute_input' : None,
               'execute_result' : None,
               'error' : None,
               'stdout' : '',
               'stderr' : '',
               'outputs' : [],
               'data': {},
               'outputs_ready' : False,
             }
         self.update(md)
         self.update(dict(*args, **kwargs))
 
     def __getattr__(self, key):
         """getattr aliased to getitem"""
         if key in self:
             return self[key]
         else:
             raise AttributeError(key)
 
     def __setattr__(self, key, value):
         """setattr aliased to setitem, with strict"""
         if key in self:
             self[key] = value
         else:
             raise AttributeError(key)
 
     def __setitem__(self, key, value):
         """strict static key enforcement"""
         if key in self:
             dict.__setitem__(self, key, value)
         else:
             raise KeyError(key)
 
 
 class Client(HasTraits):
     """A semi-synchronous client to the IPython ZMQ cluster
 
     Parameters
     ----------
 
     url_file : str/unicode; path to ipcontroller-client.json
         This JSON file should contain all the information needed to connect to a cluster,
         and is likely the only argument needed.
         Connection information for the Hub's registration.  If a json connector
         file is given, then likely no further configuration is necessary.
         [Default: use profile]
     profile : bytes
         The name of the Cluster profile to be used to find connector information.
         If run from an IPython application, the default profile will be the same
         as the running application, otherwise it will be 'default'.
     cluster_id : str
         String id to added to runtime files, to prevent name collisions when using
         multiple clusters with a single profile simultaneously.
         When set, will look for files named like: 'ipcontroller-<cluster_id>-client.json'
         Since this is text inserted into filenames, typical recommendations apply:
         Simple character strings are ideal, and spaces are not recommended (but
         should generally work)
     context : zmq.Context
         Pass an existing zmq.Context instance, otherwise the client will create its own.
     debug : bool
         flag for lots of message printing for debug purposes
     timeout : int/float
         time (in seconds) to wait for connection replies from the Hub
         [Default: 10]
 
     #-------------- session related args ----------------
 
     config : Config object
         If specified, this will be relayed to the Session for configuration
     username : str
         set username for the session object
 
     #-------------- ssh related args ----------------
     # These are args for configuring the ssh tunnel to be used
     # credentials are used to forward connections over ssh to the Controller
     # Note that the ip given in `addr` needs to be relative to sshserver
     # The most basic case is to leave addr as pointing to localhost (127.0.0.1),
     # and set sshserver as the same machine the Controller is on. However,
     # the only requirement is that sshserver is able to see the Controller
     # (i.e. is within the same trusted network).
 
     sshserver : str
         A string of the form passed to ssh, i.e. 'server.tld' or '[e-mail]:port'
         If keyfile or password is specified, and this is not, it will default to
         the ip given in addr.
     sshkey : str; path to ssh private key file
         This specifies a key to be used in ssh login, default None.
         Regular default ssh keys will be used without specifying this argument.
     password : str
         Your ssh password to sshserver. Note that if this is left None,
         you will be prompted for it if passwordless key based login is unavailable.
     paramiko : bool
         flag for whether to use paramiko instead of shell ssh for tunneling.
         [default: True on win32, False else]
 
 
     Attributes
     ----------
 
     ids : list of int engine IDs
         requesting the ids attribute always synchronizes
         the registration state. To request ids without synchronization,
         use semi-private _ids attributes.
 
     history : list of msg_ids
         a list of msg_ids, keeping track of all the execution
         messages you have submitted in order.
 
     outstanding : set of msg_ids
         a set of msg_ids that have been submitted, but whose
         results have not yet been received.
 
     results : dict
         a dict of all our results, keyed by msg_id
 
     block : bool
         determines default behavior when block not specified
         in execution methods
 
     Methods
     -------
 
     spin
         flushes incoming results and registration state changes
         control methods spin, and requesting `ids` also ensures up to date
 
     wait
         wait on one or more msg_ids
 
     execution methods
         apply
         legacy: execute, run
 
     data movement
         push, pull, scatter, gather
 
     query methods
         queue_status, get_result, purge, result_status
 
     control methods
         abort, shutdown
 
     """
 
 
     block = Bool(False)
     outstanding = Set()
     results = Instance('collections.defaultdict', (dict,))
     metadata = Instance('collections.defaultdict', (Metadata,))
     history = List()
     debug = Bool(False)
     _spin_thread = Any()
     _stop_spinning = Any()
 
     profile=Unicode()
     def _profile_default(self):
         if BaseIPythonApplication.initialized():
             # an IPython app *might* be running, try to get its profile
             try:
                 return BaseIPythonApplication.instance().profile
             except (AttributeError, MultipleInstanceError):
                 # could be a *different* subclass of config.Application,
                 # which would raise one of these two errors.
                 return u'default'
         else:
             return u'default'
 
 
     _outstanding_dict = Instance('collections.defaultdict', (set,))
     _ids = List()
     _connected=Bool(False)
     _ssh=Bool(False)
     _context = Instance('zmq.Context')
     _config = Dict()
     _engines=Instance(util.ReverseDict, (), {})
     # _hub_socket=Instance('zmq.Socket')
     _query_socket=Instance('zmq.Socket')
     _control_socket=Instance('zmq.Socket')
     _iopub_socket=Instance('zmq.Socket')
     _notification_socket=Instance('zmq.Socket')
     _mux_socket=Instance('zmq.Socket')
     _task_socket=Instance('zmq.Socket')
     _task_scheme=Unicode()
     _closed = False
     _ignored_control_replies=Integer(0)
     _ignored_hub_replies=Integer(0)
 
     def __new__(self, *args, **kw):
         # don't raise on positional args
         return HasTraits.__new__(self, **kw)
 
     def __init__(self, url_file=None, profile=None, profile_dir=None, ipython_dir=None,
             context=None, debug=False,
             sshserver=None, sshkey=None, password=None, paramiko=None,
             timeout=10, cluster_id=None, **extra_args
             ):
         if profile:
             super(Client, self).__init__(debug=debug, profile=profile)
         else:
             super(Client, self).__init__(debug=debug)
         if context is None:
             context = zmq.Context.instance()
         self._context = context
         self._stop_spinning = Event()
         
         if 'url_or_file' in extra_args:
             url_file = extra_args['url_or_file']
             warnings.warn("url_or_file arg no longer supported, use url_file", DeprecationWarning)
         
         if url_file and util.is_url(url_file):
             raise ValueError("single urls cannot be specified, url-files must be used.")
 
         self._setup_profile_dir(self.profile, profile_dir, ipython_dir)
         
         if self._cd is not None:
             if url_file is None:
                 if not cluster_id:
                     client_json = 'ipcontroller-client.json'
                 else:
                     client_json = 'ipcontroller-%s-client.json' % cluster_id
                 url_file = pjoin(self._cd.security_dir, client_json)
         if url_file is None:
             raise ValueError(
                 "I can't find enough information to connect to a hub!"
                 " Please specify at least one of url_file or profile."
             )
         
         with open(url_file) as f:
             cfg = json.load(f)
         
         self._task_scheme = cfg['task_scheme']
 
         # sync defaults from args, json:
         if sshserver:
             cfg['ssh'] = sshserver
 
         location = cfg.setdefault('location', None)
         
         proto,addr = cfg['interface'].split('://')
         addr = util.disambiguate_ip_address(addr, location)
         cfg['interface'] = "%s://%s" % (proto, addr)
         
         # turn interface,port into full urls:
         for key in ('control', 'task', 'mux', 'iopub', 'notification', 'registration'):
             cfg[key] = cfg['interface'] + ':%i' % cfg[key]
         
         url = cfg['registration']
         
         if location is not None and addr == localhost():
             # location specified, and connection is expected to be local
             if not is_local_ip(location) and not sshserver:
                 # load ssh from JSON *only* if the controller is not on
                 # this machine
                 sshserver=cfg['ssh']
             if not is_local_ip(location) and not sshserver:
                 # warn if no ssh specified, but SSH is probably needed
                 # This is only a warning, because the most likely cause
                 # is a local Controller on a laptop whose IP is dynamic
                 warnings.warn("""
             Controller appears to be listening on localhost, but not on this machine.
             If this is true, you should specify Client(...,sshserver='you@%s')
             or instruct your controller to listen on an external IP."""%location,
                 RuntimeWarning)
         elif not sshserver:
             # otherwise sync with cfg
             sshserver = cfg['ssh']
 
         self._config = cfg
 
         self._ssh = bool(sshserver or sshkey or password)
         if self._ssh and sshserver is None:
             # default to ssh via localhost
             sshserver = addr
         if self._ssh and password is None:
             if tunnel.try_passwordless_ssh(sshserver, sshkey, paramiko):
                 password=False
             else:
                 password = getpass("SSH Password for %s: "%sshserver)
         ssh_kwargs = dict(keyfile=sshkey, password=password, paramiko=paramiko)
 
         # configure and construct the session
         try:
             extra_args['packer'] = cfg['pack']
             extra_args['unpacker'] = cfg['unpack']
             extra_args['key'] = cast_bytes(cfg['key'])
             extra_args['signature_scheme'] = cfg['signature_scheme']
         except KeyError as exc:
             msg = '\n'.join([
                 "Connection file is invalid (missing '{}'), possibly from an old version of IPython.",
                 "If you are reusing connection files, remove them and start ipcontroller again."
             ])
             raise ValueError(msg.format(exc.message))
         
         self.session = Session(**extra_args)
 
         self._query_socket = self._context.socket(zmq.DEALER)
 
         if self._ssh:
             tunnel.tunnel_connection(self._query_socket, cfg['registration'], sshserver, **ssh_kwargs)
         else:
             self._query_socket.connect(cfg['registration'])
 
         self.session.debug = self.debug
 
         self._notification_handlers = {'registration_notification' : self._register_engine,
                                     'unregistration_notification' : self._unregister_engine,
                                     'shutdown_notification' : lambda msg: self.close(),
                                     }
         self._queue_handlers = {'execute_reply' : self._handle_execute_reply,
                                 'apply_reply' : self._handle_apply_reply}
         
         try:
             self._connect(sshserver, ssh_kwargs, timeout)
         except:
             self.close(linger=0)
             raise
         
         # last step: setup magics, if we are in IPython:
         
         try:
             ip = get_ipython()
         except NameError:
             return
         else:
             if 'px' not in ip.magics_manager.magics:
                 # in IPython but we are the first Client.
                 # activate a default view for parallel magics.
                 self.activate()
 
     def __del__(self):
         """cleanup sockets, but _not_ context."""
         self.close()
 
     def _setup_profile_dir(self, profile, profile_dir, ipython_dir):
         if ipython_dir is None:
             ipython_dir = get_ipython_dir()
         if profile_dir is not None:
             try:
                 self._cd = ProfileDir.find_profile_dir(profile_dir)
                 return
             except ProfileDirError:
                 pass
         elif profile is not None:
             try:
                 self._cd = ProfileDir.find_profile_dir_by_name(
                     ipython_dir, profile)
                 return
             except ProfileDirError:
                 pass
         self._cd = None
 
     def _update_engines(self, engines):
         """Update our engines dict and _ids from a dict of the form: {id:uuid}."""
         for k,v in iteritems(engines):
             eid = int(k)
             if eid not in self._engines:
                 self._ids.append(eid)
             self._engines[eid] = v
         self._ids = sorted(self._ids)
         if sorted(self._engines.keys()) != list(range(len(self._engines))) and \
                         self._task_scheme == 'pure' and self._task_socket:
             self._stop_scheduling_tasks()
 
     def _stop_scheduling_tasks(self):
         """Stop scheduling tasks because an engine has been unregistered
         from a pure ZMQ scheduler.
         """
         self._task_socket.close()
         self._task_socket = None
         msg = "An engine has been unregistered, and we are using pure " +\
               "ZMQ task scheduling.  Task farming will be disabled."
         if self.outstanding:
             msg += " If you were running tasks when this happened, " +\
                    "some `outstanding` msg_ids may never resolve."
         warnings.warn(msg, RuntimeWarning)
 
     def _build_targets(self, targets):
         """Turn valid target IDs or 'all' into two lists:
         (int_ids, uuids).
         """
         if not self._ids:
             # flush notification socket if no engines yet, just in case
             if not self.ids:
                 raise error.NoEnginesRegistered("Can't build targets without any engines")
 
         if targets is None:
             targets = self._ids
         elif isinstance(targets, string_types):
             if targets.lower() == 'all':
                 targets = self._ids
             else:
                 raise TypeError("%r not valid str target, must be 'all'"%(targets))
         elif isinstance(targets, int):
             if targets < 0:
                 targets = self.ids[targets]
             if targets not in self._ids:
                 raise IndexError("No such engine: %i"%targets)
             targets = [targets]
 
         if isinstance(targets, slice):
             indices = list(range(len(self._ids))[targets])
             ids = self.ids
             targets = [ ids[i] for i in indices ]
 
         if not isinstance(targets, (tuple, list, xrange)):
             raise TypeError("targets by int/slice/collection of ints only, not %s"%(type(targets)))
 
         return [cast_bytes(self._engines[t]) for t in targets], list(targets)
 
     def _connect(self, sshserver, ssh_kwargs, timeout):
         """setup all our socket connections to the cluster. This is called from
         __init__."""
 
         # Maybe allow reconnecting?
         if self._connected:
             return
         self._connected=True
 
         def connect_socket(s, url):
             if self._ssh:
                 return tunnel.tunnel_connection(s, url, sshserver, **ssh_kwargs)
             else:
                 return s.connect(url)
 
         self.session.send(self._query_socket, 'connection_request')
         # use Poller because zmq.select has wrong units in pyzmq 2.1.7
         poller = zmq.Poller()
         poller.register(self._query_socket, zmq.POLLIN)
         # poll expects milliseconds, timeout is seconds
         evts = poller.poll(timeout*1000)
         if not evts:
             raise error.TimeoutError("Hub connection request timed out")
         idents,msg = self.session.recv(self._query_socket,mode=0)
         if self.debug:
             pprint(msg)
         content = msg['content']
         # self._config['registration'] = dict(content)
         cfg = self._config
         if content['status'] == 'ok':
             self._mux_socket = self._context.socket(zmq.DEALER)
             connect_socket(self._mux_socket, cfg['mux'])
 
             self._task_socket = self._context.socket(zmq.DEALER)
             connect_socket(self._task_socket, cfg['task'])
 
             self._notification_socket = self._context.socket(zmq.SUB)
             self._notification_socket.setsockopt(zmq.SUBSCRIBE, b'')
             connect_socket(self._notification_socket, cfg['notification'])
 
             self._control_socket = self._context.socket(zmq.DEALER)
             connect_socket(self._control_socket, cfg['control'])
 
             self._iopub_socket = self._context.socket(zmq.SUB)
             self._iopub_socket.setsockopt(zmq.SUBSCRIBE, b'')
             connect_socket(self._iopub_socket, cfg['iopub'])
 
             self._update_engines(dict(content['engines']))
         else:
             self._connected = False
             raise Exception("Failed to connect!")
 
     #--------------------------------------------------------------------------
     # handlers and callbacks for incoming messages
     #--------------------------------------------------------------------------
 
     def _unwrap_exception(self, content):
         """unwrap exception, and remap engine_id to int."""
         e = error.unwrap_exception(content)
         # print e.traceback
         if e.engine_info:
             e_uuid = e.engine_info['engine_uuid']
             eid = self._engines[e_uuid]
             e.engine_info['engine_id'] = eid
         return e
 
     def _extract_metadata(self, msg):
         header = msg['header']
         parent = msg['parent_header']
         msg_meta = msg['metadata']
         content = msg['content']
         md = {'msg_id' : parent['msg_id'],
               'received' : datetime.now(),
               'engine_uuid' : msg_meta.get('engine', None),
               'follow' : msg_meta.get('follow', []),
               'after' : msg_meta.get('after', []),
               'status' : content['status'],
             }
 
         if md['engine_uuid'] is not None:
             md['engine_id'] = self._engines.get(md['engine_uuid'], None)
 
         if 'date' in parent:
             md['submitted'] = parent['date']
         if 'started' in msg_meta:
             md['started'] = parse_date(msg_meta['started'])
         if 'date' in header:
             md['completed'] = header['date']
         return md
 
     def _register_engine(self, msg):
         """Register a new engine, and update our connection info."""
         content = msg['content']
         eid = content['id']
         d = {eid : content['uuid']}
         self._update_engines(d)
 
     def _unregister_engine(self, msg):
         """Unregister an engine that has died."""
         content = msg['content']
         eid = int(content['id'])
         if eid in self._ids:
             self._ids.remove(eid)
             uuid = self._engines.pop(eid)
 
             self._handle_stranded_msgs(eid, uuid)
 
         if self._task_socket and self._task_scheme == 'pure':
             self._stop_scheduling_tasks()
 
     def _handle_stranded_msgs(self, eid, uuid):
         """Handle messages known to be on an engine when the engine unregisters.
 
         It is possible that this will fire prematurely - that is, an engine will
         go down after completing a result, and the client will be notified
         of the unregistration and later receive the successful result.
         """
 
         outstanding = self._outstanding_dict[uuid]
 
         for msg_id in list(outstanding):
             if msg_id in self.results:
                 # we already
                 continue
             try:
                 raise error.EngineError("Engine %r died while running task %r"%(eid, msg_id))
             except:
                 content = error.wrap_exception()
             # build a fake message:
             msg = self.session.msg('apply_reply', content=content)
             msg['parent_header']['msg_id'] = msg_id
             msg['metadata']['engine'] = uuid
             self._handle_apply_reply(msg)
 
     def _handle_execute_reply(self, msg):
         """Save the reply to an execute_request into our results.
 
         execute messages are never actually used. apply is used instead.
         """
 
         parent = msg['parent_header']
         msg_id = parent['msg_id']
         if msg_id not in self.outstanding:
             if msg_id in self.history:
                 print("got stale result: %s"%msg_id)
             else:
                 print("got unknown result: %s"%msg_id)
         else:
             self.outstanding.remove(msg_id)
 
         content = msg['content']
         header = msg['header']
 
         # construct metadata:
         md = self.metadata[msg_id]
         md.update(self._extract_metadata(msg))
         # is this redundant?
         self.metadata[msg_id] = md
         
         e_outstanding = self._outstanding_dict[md['engine_uuid']]
         if msg_id in e_outstanding:
             e_outstanding.remove(msg_id)
 
         # construct result:
         if content['status'] == 'ok':
             self.results[msg_id] = ExecuteReply(msg_id, content, md)
         elif content['status'] == 'aborted':
             self.results[msg_id] = error.TaskAborted(msg_id)
         elif content['status'] == 'resubmitted':
             # TODO: handle resubmission
             pass
         else:
             self.results[msg_id] = self._unwrap_exception(content)
 
     def _handle_apply_reply(self, msg):
         """Save the reply to an apply_request into our results."""
         parent = msg['parent_header']
         msg_id = parent['msg_id']
         if msg_id not in self.outstanding:
             if msg_id in self.history:
                 print("got stale result: %s"%msg_id)
                 print(self.results[msg_id])
                 print(msg)
             else:
                 print("got unknown result: %s"%msg_id)
         else:
             self.outstanding.remove(msg_id)
         content = msg['content']
         header = msg['header']
 
         # construct metadata:
         md = self.metadata[msg_id]
         md.update(self._extract_metadata(msg))
         # is this redundant?
         self.metadata[msg_id] = md
 
         e_outstanding = self._outstanding_dict[md['engine_uuid']]
         if msg_id in e_outstanding:
             e_outstanding.remove(msg_id)
 
         # construct result:
         if content['status'] == 'ok':
             self.results[msg_id] = serialize.unserialize_object(msg['buffers'])[0]
         elif content['status'] == 'aborted':
             self.results[msg_id] = error.TaskAborted(msg_id)
         elif content['status'] == 'resubmitted':
             # TODO: handle resubmission
             pass
         else:
             self.results[msg_id] = self._unwrap_exception(content)
 
     def _flush_notifications(self):
         """Flush notifications of engine registrations waiting
         in ZMQ queue."""
         idents,msg = self.session.recv(self._notification_socket, mode=zmq.NOBLOCK)
         while msg is not None:
             if self.debug:
                 pprint(msg)
             msg_type = msg['header']['msg_type']
             handler = self._notification_handlers.get(msg_type, None)
             if handler is None:
                 raise Exception("Unhandled message type: %s" % msg_type)
             else:
                 handler(msg)
             idents,msg = self.session.recv(self._notification_socket, mode=zmq.NOBLOCK)
 
     def _flush_results(self, sock):
         """Flush task or queue results waiting in ZMQ queue."""
         idents,msg = self.session.recv(sock, mode=zmq.NOBLOCK)
         while msg is not None:
             if self.debug:
                 pprint(msg)
             msg_type = msg['header']['msg_type']
             handler = self._queue_handlers.get(msg_type, None)
             if handler is None:
                 raise Exception("Unhandled message type: %s" % msg_type)
             else:
                 handler(msg)
             idents,msg = self.session.recv(sock, mode=zmq.NOBLOCK)
 
     def _flush_control(self, sock):
         """Flush replies from the control channel waiting
         in the ZMQ queue.
 
         Currently: ignore them."""
         if self._ignored_control_replies <= 0:
             return
         idents,msg = self.session.recv(sock, mode=zmq.NOBLOCK)
         while msg is not None:
             self._ignored_control_replies -= 1
             if self.debug:
                 pprint(msg)
             idents,msg = self.session.recv(sock, mode=zmq.NOBLOCK)
 
     def _flush_ignored_control(self):
         """flush ignored control replies"""
         while self._ignored_control_replies > 0:
             self.session.recv(self._control_socket)
             self._ignored_control_replies -= 1
 
     def _flush_ignored_hub_replies(self):
         ident,msg = self.session.recv(self._query_socket, mode=zmq.NOBLOCK)
         while msg is not None:
             ident,msg = self.session.recv(self._query_socket, mode=zmq.NOBLOCK)
 
     def _flush_iopub(self, sock):
         """Flush replies from the iopub channel waiting
         in the ZMQ queue.
         """
         idents,msg = self.session.recv(sock, mode=zmq.NOBLOCK)
         while msg is not None:
             if self.debug:
                 pprint(msg)
             parent = msg['parent_header']
             # ignore IOPub messages with no parent.
             # Caused by print statements or warnings from before the first execution.
             if not parent:
                 idents,msg = self.session.recv(sock, mode=zmq.NOBLOCK)
                 continue
             msg_id = parent['msg_id']
             content = msg['content']
             header = msg['header']
             msg_type = msg['header']['msg_type']
 
             # init metadata:
             md = self.metadata[msg_id]
 
             if msg_type == 'stream':
                 name = content['name']
                 s = md[name] or ''
                 md[name] = s + content['data']
             elif msg_type == 'error':
                 md.update({'error' : self._unwrap_exception(content)})
             elif msg_type == 'execute_input':
                 md.update({'execute_input' : content['code']})
             elif msg_type == 'display_data':
                 md['outputs'].append(content)
             elif msg_type == 'execute_result':
                 md['execute_result'] = content
             elif msg_type == 'data_message':
                 data, remainder = serialize.unserialize_object(msg['buffers'])
                 md['data'].update(data)
             elif msg_type == 'status':
                 # idle message comes after all outputs
                 if content['execution_state'] == 'idle':
                     md['outputs_ready'] = True
             else:
                 # unhandled msg_type (status, etc.)
                 pass
 
             # reduntant?
             self.metadata[msg_id] = md
 
             idents,msg = self.session.recv(sock, mode=zmq.NOBLOCK)
 
     #--------------------------------------------------------------------------
     # len, getitem
     #--------------------------------------------------------------------------
 
     def __len__(self):
         """len(client) returns # of engines."""
         return len(self.ids)
 
     def __getitem__(self, key):
         """index access returns DirectView multiplexer objects
 
         Must be int, slice, or list/tuple/xrange of ints"""
         if not isinstance(key, (int, slice, tuple, list, xrange)):
             raise TypeError("key by int/slice/iterable of ints only, not %s"%(type(key)))
         else:
             return self.direct_view(key)
     
     def __iter__(self):
         """Since we define getitem, Client is iterable
         
         but unless we also define __iter__, it won't work correctly unless engine IDs
         start at zero and are continuous.
         """
         for eid in self.ids:
             yield self.direct_view(eid)
     
     #--------------------------------------------------------------------------
     # Begin public methods
     #--------------------------------------------------------------------------
 
     @property
     def ids(self):
         """Always up-to-date ids property."""
         self._flush_notifications()
         # always copy:
         return list(self._ids)
 
     def activate(self, targets='all', suffix=''):
         """Create a DirectView and register it with IPython magics
         
         Defines the magics `%px, %autopx, %pxresult, %%px`
         
         Parameters
         ----------
         
         targets: int, list of ints, or 'all'
             The engines on which the view's magics will run
         suffix: str [default: '']
             The suffix, if any, for the magics.  This allows you to have
             multiple views associated with parallel magics at the same time.
             
             e.g. ``rc.activate(targets=0, suffix='0')`` will give you
             the magics ``%px0``, ``%pxresult0``, etc. for running magics just
             on engine 0.
         """
         view = self.direct_view(targets)
         view.block = True
         view.activate(suffix)
         return view
 
     def close(self, linger=None):
         """Close my zmq Sockets
         
         If `linger`, set the zmq LINGER socket option,
         which allows discarding of messages.
         """
         if self._closed:
             return
         self.stop_spin_thread()
         snames = [ trait for trait in self.trait_names() if trait.endswith("socket") ]
         for name in snames:
             socket = getattr(self, name)
             if socket is not None and not socket.closed:
                 if linger is not None:
                     socket.close(linger=linger)
                 else:
                     socket.close()
         self._closed = True
 
     def _spin_every(self, interval=1):
         """target func for use in spin_thread"""
         while True:
             if self._stop_spinning.is_set():
                 return
             time.sleep(interval)
             self.spin()
 
     def spin_thread(self, interval=1):
         """call Client.spin() in a background thread on some regular interval
         
         This helps ensure that messages don't pile up too much in the zmq queue
         while you are working on other things, or just leaving an idle terminal.
         
         It also helps limit potential padding of the `received` timestamp
         on AsyncResult objects, used for timings.
         
         Parameters
         ----------
         
         interval : float, optional
             The interval on which to spin the client in the background thread
             (simply passed to time.sleep).
         
         Notes
         -----
         
         For precision timing, you may want to use this method to put a bound
         on the jitter (in seconds) in `received` timestamps used
         in AsyncResult.wall_time.
         
         """
         if self._spin_thread is not None:
             self.stop_spin_thread()
         self._stop_spinning.clear()
         self._spin_thread = Thread(target=self._spin_every, args=(interval,))
         self._spin_thread.daemon = True
         self._spin_thread.start()
     
     def stop_spin_thread(self):
         """stop background spin_thread, if any"""
         if self._spin_thread is not None:
             self._stop_spinning.set()
             self._spin_thread.join()
             self._spin_thread = None
 
     def spin(self):
         """Flush any registration notifications and execution results
         waiting in the ZMQ queue.
         """
         if self._notification_socket:
             self._flush_notifications()
         if self._iopub_socket:
             self._flush_iopub(self._iopub_socket)
         if self._mux_socket:
             self._flush_results(self._mux_socket)
         if self._task_socket:
             self._flush_results(self._task_socket)
         if self._control_socket:
             self._flush_control(self._control_socket)
         if self._query_socket:
             self._flush_ignored_hub_replies()
 
     def wait(self, jobs=None, timeout=-1):
         """waits on one or more `jobs`, for up to `timeout` seconds.
 
         Parameters
         ----------
 
         jobs : int, str, or list of ints and/or strs, or one or more AsyncResult objects
                 ints are indices to self.history
                 strs are msg_ids
                 default: wait on all outstanding messages
         timeout : float
                 a time in seconds, after which to give up.
                 default is -1, which means no timeout
 
         Returns
         -------
 
         True : when all msg_ids are done
         False : timeout reached, some msg_ids still outstanding
         """
         tic = time.time()
         if jobs is None:
             theids = self.outstanding
         else:
             if isinstance(jobs, string_types + (int, AsyncResult)):
                 jobs = [jobs]
             theids = set()
             for job in jobs:
                 if isinstance(job, int):
                     # index access
                     job = self.history[job]
                 elif isinstance(job, AsyncResult):
                     theids.update(job.msg_ids)
                     continue
                 theids.add(job)
         if not theids.intersection(self.outstanding):
             return True
         self.spin()
         while theids.intersection(self.outstanding):
             if timeout >= 0 and ( time.time()-tic ) > timeout:
                 break
             time.sleep(1e-3)
             self.spin()
         return len(theids.intersection(self.outstanding)) == 0
 
     #--------------------------------------------------------------------------
     # Control methods
     #--------------------------------------------------------------------------
 
     @spin_first
     def clear(self, targets=None, block=None):
         """Clear the namespace in target(s)."""
         block = self.block if block is None else block
         targets = self._build_targets(targets)[0]
         for t in targets:
             self.session.send(self._control_socket, 'clear_request', content={}, ident=t)
         error = False
         if block:
             self._flush_ignored_control()
             for i in range(len(targets)):
                 idents,msg = self.session.recv(self._control_socket,0)
                 if self.debug:
                     pprint(msg)
                 if msg['content']['status'] != 'ok':
                     error = self._unwrap_exception(msg['content'])
         else:
             self._ignored_control_replies += len(targets)
         if error:
             raise error
 
 
     @spin_first
     def abort(self, jobs=None, targets=None, block=None):
         """Abort specific jobs from the execution queues of target(s).
 
         This is a mechanism to prevent jobs that have already been submitted
         from executing.
 
         Parameters
         ----------
 
         jobs : msg_id, list of msg_ids, or AsyncResult
             The jobs to be aborted
             
             If unspecified/None: abort all outstanding jobs.
 
         """
         block = self.block if block is None else block
         jobs = jobs if jobs is not None else list(self.outstanding)
         targets = self._build_targets(targets)[0]
         
         msg_ids = []
         if isinstance(jobs, string_types + (AsyncResult,)):
             jobs = [jobs]
         bad_ids = [obj for obj in jobs if not isinstance(obj, string_types + (AsyncResult,))]
         if bad_ids:
             raise TypeError("Invalid msg_id type %r, expected str or AsyncResult"%bad_ids[0])
         for j in jobs:
             if isinstance(j, AsyncResult):
                 msg_ids.extend(j.msg_ids)
             else:
                 msg_ids.append(j)
         content = dict(msg_ids=msg_ids)
         for t in targets:
             self.session.send(self._control_socket, 'abort_request',
                     content=content, ident=t)
         error = False
         if block:
             self._flush_ignored_control()
             for i in range(len(targets)):
                 idents,msg = self.session.recv(self._control_socket,0)
                 if self.debug:
                     pprint(msg)
                 if msg['content']['status'] != 'ok':
                     error = self._unwrap_exception(msg['content'])
         else:
             self._ignored_control_replies += len(targets)
         if error:
             raise error
 
     @spin_first
     def shutdown(self, targets='all', restart=False, hub=False, block=None):
         """Terminates one or more engine processes, optionally including the hub.
         
         Parameters
         ----------
         
         targets: list of ints or 'all' [default: all]
             Which engines to shutdown.
         hub: bool [default: False]
             Whether to include the Hub.  hub=True implies targets='all'.
         block: bool [default: self.block]
             Whether to wait for clean shutdown replies or not.
         restart: bool [default: False]
             NOT IMPLEMENTED
             whether to restart engines after shutting them down.
         """
         from IPython.parallel.error import NoEnginesRegistered
         if restart:
             raise NotImplementedError("Engine restart is not yet implemented")
         
         block = self.block if block is None else block
         if hub:
             targets = 'all'
         try:
             targets = self._build_targets(targets)[0]
         except NoEnginesRegistered:
             targets = []
         for t in targets:
             self.session.send(self._control_socket, 'shutdown_request',
                         content={'restart':restart},ident=t)
         error = False
         if block or hub:
             self._flush_ignored_control()
             for i in range(len(targets)):
                 idents,msg = self.session.recv(self._control_socket, 0)
                 if self.debug:
                     pprint(msg)
                 if msg['content']['status'] != 'ok':
                     error = self._unwrap_exception(msg['content'])
         else:
             self._ignored_control_replies += len(targets)
 
         if hub:
             time.sleep(0.25)
             self.session.send(self._query_socket, 'shutdown_request')
             idents,msg = self.session.recv(self._query_socket, 0)
             if self.debug:
                 pprint(msg)
             if msg['content']['status'] != 'ok':
                 error = self._unwrap_exception(msg['content'])
 
         if error:
             raise error
 
     #--------------------------------------------------------------------------
     # Execution related methods
     #--------------------------------------------------------------------------
 
     def _maybe_raise(self, result):
         """wrapper for maybe raising an exception if apply failed."""
         if isinstance(result, error.RemoteError):
             raise result
 
         return result
 
     def send_apply_request(self, socket, f, args=None, kwargs=None, metadata=None, track=False,
                             ident=None):
         """construct and send an apply message via a socket.
 
         This is the principal method with which all engine execution is performed by views.
         """
 
         if self._closed:
             raise RuntimeError("Client cannot be used after its sockets have been closed")
         
         # defaults:
         args = args if args is not None else []
         kwargs = kwargs if kwargs is not None else {}
         metadata = metadata if metadata is not None else {}
 
         # validate arguments
         if not callable(f) and not isinstance(f, Reference):
             raise TypeError("f must be callable, not %s"%type(f))
         if not isinstance(args, (tuple, list)):
             raise TypeError("args must be tuple or list, not %s"%type(args))
         if not isinstance(kwargs, dict):
             raise TypeError("kwargs must be dict, not %s"%type(kwargs))
         if not isinstance(metadata, dict):
             raise TypeError("metadata must be dict, not %s"%type(metadata))
 
         bufs = serialize.pack_apply_message(f, args, kwargs,
             buffer_threshold=self.session.buffer_threshold,
             item_threshold=self.session.item_threshold,
         )
 
         msg = self.session.send(socket, "apply_request", buffers=bufs, ident=ident,
                             metadata=metadata, track=track)
 
         msg_id = msg['header']['msg_id']
         self.outstanding.add(msg_id)
         if ident:
             # possibly routed to a specific engine
             if isinstance(ident, list):
                 ident = ident[-1]
             if ident in self._engines.values():
                 # save for later, in case of engine death
                 self._outstanding_dict[ident].add(msg_id)
         self.history.append(msg_id)
         self.metadata[msg_id]['submitted'] = datetime.now()
 
         return msg
 
     def send_execute_request(self, socket, code, silent=True, metadata=None, ident=None):
         """construct and send an execute request via a socket.
 
         """
 
         if self._closed:
             raise RuntimeError("Client cannot be used after its sockets have been closed")
         
         # defaults:
         metadata = metadata if metadata is not None else {}
 
         # validate arguments
         if not isinstance(code, string_types):
             raise TypeError("code must be text, not %s" % type(code))
         if not isinstance(metadata, dict):
             raise TypeError("metadata must be dict, not %s" % type(metadata))
         
         content = dict(code=code, silent=bool(silent), user_expressions={})
 
 
         msg = self.session.send(socket, "execute_request", content=content, ident=ident,
                             metadata=metadata)
 
         msg_id = msg['header']['msg_id']
         self.outstanding.add(msg_id)
         if ident:
             # possibly routed to a specific engine
             if isinstance(ident, list):
                 ident = ident[-1]
             if ident in self._engines.values():
                 # save for later, in case of engine death
                 self._outstanding_dict[ident].add(msg_id)
         self.history.append(msg_id)
         self.metadata[msg_id]['submitted'] = datetime.now()
 
         return msg
 
     #--------------------------------------------------------------------------
     # construct a View object
     #--------------------------------------------------------------------------
 
     def load_balanced_view(self, targets=None):
         """construct a DirectView object.
 
         If no arguments are specified, create a LoadBalancedView
         using all engines.
 
         Parameters
         ----------
 
         targets: list,slice,int,etc. [default: use all engines]
             The subset of engines across which to load-balance
         """
         if targets == 'all':
             targets = None
         if targets is not None:
             targets = self._build_targets(targets)[1]
         return LoadBalancedView(client=self, socket=self._task_socket, targets=targets)
 
     def direct_view(self, targets='all'):
         """construct a DirectView object.
 
         If no targets are specified, create a DirectView using all engines.
         
         rc.direct_view('all') is distinguished from rc[:] in that 'all' will
         evaluate the target engines at each execution, whereas rc[:] will connect to
         all *current* engines, and that list will not change.
         
         That is, 'all' will always use all engines, whereas rc[:] will not use
         engines added after the DirectView is constructed.
 
         Parameters
         ----------
 
         targets: list,slice,int,etc. [default: use all engines]
             The engines to use for the View
         """
         single = isinstance(targets, int)
         # allow 'all' to be lazily evaluated at each execution
         if targets != 'all':
             targets = self._build_targets(targets)[1]
         if single:
             targets = targets[0]
         return DirectView(client=self, socket=self._mux_socket, targets=targets)
 
     #--------------------------------------------------------------------------
     # Query methods
     #--------------------------------------------------------------------------
 
     @spin_first
     def get_result(self, indices_or_msg_ids=None, block=None, owner=True):
         """Retrieve a result by msg_id or history index, wrapped in an AsyncResult object.
 
         If the client already has the results, no request to the Hub will be made.
 
         This is a convenient way to construct AsyncResult objects, which are wrappers
         that include metadata about execution, and allow for awaiting results that
         were not submitted by this Client.
 
         It can also be a convenient way to retrieve the metadata associated with
         blocking execution, since it always retrieves
 
         Examples
         --------
         ::
 
             In [10]: r = client.apply()
 
         Parameters
         ----------
 
         indices_or_msg_ids : integer history index, str msg_id, or list of either
             The indices or msg_ids of indices to be retrieved
 
         block : bool
             Whether to wait for the result to be done
         owner : bool [default: True]
             Whether this AsyncResult should own the result.
             If so, calling `ar.get()` will remove data from the
             client's result and metadata cache.
             There should only be one owner of any given msg_id.
 
         Returns
         -------
 
         AsyncResult
             A single AsyncResult object will always be returned.
 
         AsyncHubResult
             A subclass of AsyncResult that retrieves results from the Hub
 
         """
         block = self.block if block is None else block
         if indices_or_msg_ids is None:
             indices_or_msg_ids = -1
         
         single_result = False
         if not isinstance(indices_or_msg_ids, (list,tuple)):
             indices_or_msg_ids = [indices_or_msg_ids]
             single_result = True
 
         theids = []
         for id in indices_or_msg_ids:
             if isinstance(id, int):
                 id = self.history[id]
             if not isinstance(id, string_types):
                 raise TypeError("indices must be str or int, not %r"%id)
             theids.append(id)
 
         local_ids = [msg_id for msg_id in theids if (msg_id in self.outstanding or msg_id in self.results)]
         remote_ids = [msg_id for msg_id in theids if msg_id not in local_ids]
         
         # given single msg_id initially, get_result shot get the result itself,
         # not a length-one list
         if single_result:
             theids = theids[0]
 
         if remote_ids:
             ar = AsyncHubResult(self, msg_ids=theids, owner=owner)
         else:
             ar = AsyncResult(self, msg_ids=theids, owner=owner)
 
         if block:
             ar.wait()
 
         return ar
 
     @spin_first
     def resubmit(self, indices_or_msg_ids=None, metadata=None, block=None):
         """Resubmit one or more tasks.
 
         in-flight tasks may not be resubmitted.
 
         Parameters
         ----------
 
         indices_or_msg_ids : integer history index, str msg_id, or list of either
             The indices or msg_ids of indices to be retrieved
 
         block : bool
             Whether to wait for the result to be done
 
         Returns
         -------
 
         AsyncHubResult
             A subclass of AsyncResult that retrieves results from the Hub
 
         """
         block = self.block if block is None else block
         if indices_or_msg_ids is None:
             indices_or_msg_ids = -1
 
         if not isinstance(indices_or_msg_ids, (list,tuple)):
             indices_or_msg_ids = [indices_or_msg_ids]
 
         theids = []
         for id in indices_or_msg_ids:
             if isinstance(id, int):
                 id = self.history[id]
             if not isinstance(id, string_types):
                 raise TypeError("indices must be str or int, not %r"%id)
             theids.append(id)
 
         content = dict(msg_ids = theids)
 
         self.session.send(self._query_socket, 'resubmit_request', content)
 
         zmq.select([self._query_socket], [], [])
         idents,msg = self.session.recv(self._query_socket, zmq.NOBLOCK)
         if self.debug:
             pprint(msg)
         content = msg['content']
         if content['status'] != 'ok':
             raise self._unwrap_exception(content)
         mapping = content['resubmitted']
         new_ids = [ mapping[msg_id] for msg_id in theids ]
 
         ar = AsyncHubResult(self, msg_ids=new_ids)
 
         if block:
             ar.wait()
 
         return ar
 
     @spin_first
     def result_status(self, msg_ids, status_only=True):
         """Check on the status of the result(s) of the apply request with `msg_ids`.
 
         If status_only is False, then the actual results will be retrieved, else
         only the status of the results will be checked.
 
         Parameters
         ----------
 
         msg_ids : list of msg_ids
             if int:
                 Passed as index to self.history for convenience.
         status_only : bool (default: True)
             if False:
                 Retrieve the actual results of completed tasks.
 
         Returns
         -------
 
         results : dict
             There will always be the keys 'pending' and 'completed', which will
             be lists of msg_ids that are incomplete or complete. If `status_only`
             is False, then completed results will be keyed by their `msg_id`.
         """
         if not isinstance(msg_ids, (list,tuple)):
             msg_ids = [msg_ids]
 
         theids = []
         for msg_id in msg_ids:
             if isinstance(msg_id, int):
                 msg_id = self.history[msg_id]
             if not isinstance(msg_id, string_types):
                 raise TypeError("msg_ids must be str, not %r"%msg_id)
             theids.append(msg_id)
 
         completed = []
         local_results = {}
 
         # comment this block out to temporarily disable local shortcut:
         for msg_id in theids:
             if msg_id in self.results:
                 completed.append(msg_id)
                 local_results[msg_id] = self.results[msg_id]
                 theids.remove(msg_id)
 
         if theids: # some not locally cached
             content = dict(msg_ids=theids, status_only=status_only)
             msg = self.session.send(self._query_socket, "result_request", content=content)
             zmq.select([self._query_socket], [], [])
             idents,msg = self.session.recv(self._query_socket, zmq.NOBLOCK)
             if self.debug:
                 pprint(msg)
             content = msg['content']
             if content['status'] != 'ok':
                 raise self._unwrap_exception(content)
             buffers = msg['buffers']
         else:
             content = dict(completed=[],pending=[])
 
         content['completed'].extend(completed)
 
         if status_only:
             return content
 
         failures = []
         # load cached results into result:
         content.update(local_results)
 
         # update cache with results:
         for msg_id in sorted(theids):
             if msg_id in content['completed']:
                 rec = content[msg_id]
                 parent = extract_dates(rec['header'])
                 header = extract_dates(rec['result_header'])
                 rcontent = rec['result_content']
                 iodict = rec['io']
                 if isinstance(rcontent, str):
                     rcontent = self.session.unpack(rcontent)
 
                 md = self.metadata[msg_id]
                 md_msg = dict(
                     content=rcontent,
                     parent_header=parent,
                     header=header,
                     metadata=rec['result_metadata'],
                 )
                 md.update(self._extract_metadata(md_msg))
                 if rec.get('received'):
                     md['received'] = parse_date(rec['received'])
                 md.update(iodict)
                 
                 if rcontent['status'] == 'ok':
                     if header['msg_type'] == 'apply_reply':
                         res,buffers = serialize.unserialize_object(buffers)
                     elif header['msg_type'] == 'execute_reply':
                         res = ExecuteReply(msg_id, rcontent, md)
                     else:
                         raise KeyError("unhandled msg type: %r" % header['msg_type'])
                 else:
                     res = self._unwrap_exception(rcontent)
                     failures.append(res)
 
                 self.results[msg_id] = res
                 content[msg_id] = res
 
         if len(theids) == 1 and failures:
             raise failures[0]
 
         error.collect_exceptions(failures, "result_status")
         return content
 
     @spin_first
     def queue_status(self, targets='all', verbose=False):
         """Fetch the status of engine queues.
 
         Parameters
         ----------
 
         targets : int/str/list of ints/strs
                 the engines whose states are to be queried.
                 default : all
         verbose : bool
                 Whether to return lengths only, or lists of ids for each element
         """
         if targets == 'all':
             # allow 'all' to be evaluated on the engine
             engine_ids = None
         else:
             engine_ids = self._build_targets(targets)[1]
         content = dict(targets=engine_ids, verbose=verbose)
         self.session.send(self._query_socket, "queue_request", content=content)
         idents,msg = self.session.recv(self._query_socket, 0)
         if self.debug:
             pprint(msg)
         content = msg['content']
         status = content.pop('status')
         if status != 'ok':
             raise self._unwrap_exception(content)
         content = rekey(content)
         if isinstance(targets, int):
             return content[targets]
         else:
             return content
 
     def _build_msgids_from_target(self, targets=None):
         """Build a list of msg_ids from the list of engine targets"""
         if not targets: # needed as _build_targets otherwise uses all engines
             return []
         target_ids = self._build_targets(targets)[0] 
         return [md_id for md_id in self.metadata if self.metadata[md_id]["engine_uuid"] in target_ids]
     
     def _build_msgids_from_jobs(self, jobs=None):
         """Build a list of msg_ids from "jobs" """
         if not jobs:
             return []
         msg_ids = []
         if isinstance(jobs, string_types + (AsyncResult,)):
             jobs = [jobs]
         bad_ids = [obj for obj in jobs if not isinstance(obj, string_types + (AsyncResult,))]
         if bad_ids:
             raise TypeError("Invalid msg_id type %r, expected str or AsyncResult"%bad_ids[0])
         for j in jobs:
             if isinstance(j, AsyncResult):
                 msg_ids.extend(j.msg_ids)
             else:
                 msg_ids.append(j)
         return msg_ids        
         
     def purge_local_results(self, jobs=[], targets=[]):
         """Clears the client caches of results and their metadata.
 
         Individual results can be purged by msg_id, or the entire
         history of specific targets can be purged.
 
         Use `purge_local_results('all')` to scrub everything from the Clients's
         results and metadata caches.
 
         After this call all `AsyncResults` are invalid and should be discarded.
 
         If you must "reget" the results, you can still do so by using
         `client.get_result(msg_id)` or `client.get_result(asyncresult)`. This will
         redownload the results from the hub if they are still available
         (i.e `client.purge_hub_results(...)` has not been called.        
 
         Parameters
         ----------
 
         jobs : str or list of str or AsyncResult objects
                 the msg_ids whose results should be purged.
         targets : int/list of ints
                 The engines, by integer ID, whose entire result histories are to be purged.
 
         Raises
         ------
 
         RuntimeError : if any of the tasks to be purged are still outstanding.
 
         """
         if not targets and not jobs:
             raise ValueError("Must specify at least one of `targets` and `jobs`")
         
         if jobs == 'all':
             if self.outstanding:
                 raise RuntimeError("Can't purge outstanding tasks: %s" % self.outstanding)
             self.results.clear()
             self.metadata.clear()
         else:
             msg_ids = set()
             msg_ids.update(self._build_msgids_from_target(targets))
             msg_ids.update(self._build_msgids_from_jobs(jobs))
             still_outstanding = self.outstanding.intersection(msg_ids)
             if still_outstanding:
                 raise RuntimeError("Can't purge outstanding tasks: %s" % still_outstanding)
             for mid in msg_ids:
                 self.results.pop(mid, None)
                 self.metadata.pop(mid, None)
 
 
     @spin_first
     def purge_hub_results(self, jobs=[], targets=[]):
         """Tell the Hub to forget results.
 
         Individual results can be purged by msg_id, or the entire
         history of specific targets can be purged.
 
         Use `purge_results('all')` to scrub everything from the Hub's db.
 
         Parameters
         ----------
 
         jobs : str or list of str or AsyncResult objects
                 the msg_ids whose results should be forgotten.
         targets : int/str/list of ints/strs
                 The targets, by int_id, whose entire history is to be purged.
 
                 default : None
         """
         if not targets and not jobs:
             raise ValueError("Must specify at least one of `targets` and `jobs`")
         if targets:
             targets = self._build_targets(targets)[1]
 
         # construct msg_ids from jobs
         if jobs == 'all':
             msg_ids = jobs
         else:
             msg_ids = self._build_msgids_from_jobs(jobs)
 
         content = dict(engine_ids=targets, msg_ids=msg_ids)
         self.session.send(self._query_socket, "purge_request", content=content)
         idents, msg = self.session.recv(self._query_socket, 0)
         if self.debug:
             pprint(msg)
         content = msg['content']
         if content['status'] != 'ok':
             raise self._unwrap_exception(content)
 
     def purge_results(self,  jobs=[], targets=[]):
         """Clears the cached results from both the hub and the local client
                 
         Individual results can be purged by msg_id, or the entire
         history of specific targets can be purged.
 
         Use `purge_results('all')` to scrub every cached result from both the Hub's and 
         the Client's db.
         
         Equivalent to calling both `purge_hub_results()` and `purge_client_results()` with 
         the same arguments.
 
         Parameters
         ----------
 
         jobs : str or list of str or AsyncResult objects
                 the msg_ids whose results should be forgotten.
         targets : int/str/list of ints/strs
                 The targets, by int_id, whose entire history is to be purged.
 
                 default : None
         """
         self.purge_local_results(jobs=jobs, targets=targets)
         self.purge_hub_results(jobs=jobs, targets=targets)
 
     def purge_everything(self):
         """Clears all content from previous Tasks from both the hub and the local client
         
         In addition to calling `purge_results("all")` it also deletes the history and 
         other bookkeeping lists.        
         """
         self.purge_results("all")
         self.history = []
         self.session.digest_history.clear()
 
     @spin_first
     def hub_history(self):
         """Get the Hub's history
 
         Just like the Client, the Hub has a history, which is a list of msg_ids.
         This will contain the history of all clients, and, depending on configuration,
         may contain history across multiple cluster sessions.
 
         Any msg_id returned here is a valid argument to `get_result`.
 
         Returns
         -------
 
         msg_ids : list of strs
                 list of all msg_ids, ordered by task submission time.
         """
 
         self.session.send(self._query_socket, "history_request", content={})
         idents, msg = self.session.recv(self._query_socket, 0)
 
         if self.debug:
             pprint(msg)
         content = msg['content']
         if content['status'] != 'ok':
             raise self._unwrap_exception(content)
         else:
             return content['history']
 
     @spin_first
     def db_query(self, query, keys=None):
         """Query the Hub's TaskRecord database
 
         This will return a list of task record dicts that match `query`
 
         Parameters
         ----------
 
         query : mongodb query dict
             The search dict. See mongodb query docs for details.
         keys : list of strs [optional]
             The subset of keys to be returned.  The default is to fetch everything but buffers.
             'msg_id' will *always* be included.
         """
         if isinstance(keys, string_types):
             keys = [keys]
         content = dict(query=query, keys=keys)
         self.session.send(self._query_socket, "db_request", content=content)
         idents, msg = self.session.recv(self._query_socket, 0)
         if self.debug:
             pprint(msg)
         content = msg['content']
         if content['status'] != 'ok':
             raise self._unwrap_exception(content)
 
         records = content['records']
 
         buffer_lens = content['buffer_lens']
         result_buffer_lens = content['result_buffer_lens']
         buffers = msg['buffers']
         has_bufs = buffer_lens is not None
         has_rbufs = result_buffer_lens is not None
         for i,rec in enumerate(records):
             # unpack datetime objects
             for hkey in ('header', 'result_header'):
                 if hkey in rec:
                     rec[hkey] = extract_dates(rec[hkey])
             for dtkey in ('submitted', 'started', 'completed', 'received'):
                 if dtkey in rec:
                     rec[dtkey] = parse_date(rec[dtkey])
             # relink buffers
             if has_bufs:
                 blen = buffer_lens[i]
                 rec['buffers'], buffers = buffers[:blen],buffers[blen:]
             if has_rbufs:
                 blen = result_buffer_lens[i]
                 rec['result_buffers'], buffers = buffers[:blen],buffers[blen:]
 
         return records
 
 __all__ = [ 'Client' ]

IPython/parallel/engine/engine.py

@@ -1,298 +1,297 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.
 """
 
 # Copyright (c) IPython Development Team.
 # Distributed under the terms of the Modified BSD License.
 
 from __future__ import print_function
 
 import sys
 import time
 from getpass import getpass
 
 import zmq
 from zmq.eventloop import ioloop, zmqstream
+from zmq.ssh import tunnel
 
-from IPython.external.ssh import tunnel
-# internal
 from IPython.utils.localinterfaces import localhost
 from IPython.utils.traitlets import (
     Instance, Dict, Integer, Type, Float, Integer, 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.kernel.zmq.session import Message
 from IPython.kernel.zmq.ipkernel import Kernel
 from IPython.kernel.zmq.kernelapp import IPKernelApp
 
 class EngineFactory(RegistrationFactory):
     """IPython engine"""
 
     # configurables:
     out_stream_factory=Type('IPython.kernel.zmq.iostream.OutStream', config=True,
         help="""The OutStream for handling stdout/err.
         Typically 'IPython.kernel.zmq.iostream.OutStream'""")
     display_hook_factory=Type('IPython.kernel.zmq.displayhook.ZMQDisplayHook', config=True,
         help="""The class for handling displayhook.
         Typically 'IPython.kernel.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=Float(5.0, config=True,
         help="""The time (in seconds) to wait for the Controller to respond
         to registration requests before giving up.""")
     max_heartbeat_misses=Integer(50, config=True,
         help="""The maximum number of times a check for the heartbeat ping of a 
         controller can be missed before shutting down the engine.
         
         If set to 0, the check is disabled.""")
     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:
     connection_info = Dict()
     user_ns = Dict()
     id = Integer(allow_none=True)
     registrar = Instance('zmq.eventloop.zmqstream.ZMQStream')
     kernel = Instance(Kernel)
     hb_check_period=Integer()
     
     # States for the heartbeat monitoring
     # Initial values for monitored and pinged must satisfy "monitored > pinged == False" so that 
     # during the first check no "missed" ping is reported. Must be floats for Python 3 compatibility.
     _hb_last_pinged = 0.0
     _hb_last_monitored = 0.0
     _hb_missed_beats = 0
     # The zmq Stream which receives the pings from the Heart
     _hb_listener = None
 
     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 str(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(uuid=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 _report_ping(self, msg):
         """Callback for when the heartmonitor.Heart receives a ping"""
         #self.log.debug("Received a ping: %s", msg)
         self._hb_last_pinged = time.time()
 
     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 = self.session.unserialize(msg)
         content = msg['content']
         info = self.connection_info
         
         def url(key):
             """get zmq url for given channel"""
             return str(info["interface"] + ":%i" % info[key])
         
         if content['status'] == 'ok':
             self.id = int(content['id'])
 
             # launch heartbeat
             # possibly forward hb ports with tunnels
             hb_ping = maybe_tunnel(url('hb_ping'))
             hb_pong = maybe_tunnel(url('hb_pong'))
             
             hb_monitor = None
             if self.max_heartbeat_misses > 0:
                 # Add a monitor socket which will record the last time a ping was seen
                 mon = self.context.socket(zmq.SUB)
                 mport = mon.bind_to_random_port('tcp://%s' % localhost())
                 mon.setsockopt(zmq.SUBSCRIBE, b"")
                 self._hb_listener = zmqstream.ZMQStream(mon, self.loop)
                 self._hb_listener.on_recv(self._report_ping)
             
             
                 hb_monitor = "tcp://%s:%i" % (localhost(), mport)
 
             heart = Heart(hb_ping, hb_pong, hb_monitor , heart_id=identity)
             heart.start()
 
             # create Shell Connections (MUX, Task, etc.):
             shell_addrs = url('mux'), url('task')
 
             # 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)
 
             # control stream:
             control_addr = url('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 = url('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.execute_result' % self.id)
 
             self.kernel = Kernel(parent=self, 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)
             
                 
             # periodically check the heartbeat pings of the controller
             # Should be started here and not in "start()" so that the right period can be taken 
             # from the hubs HeartBeatMonitor.period
             if self.max_heartbeat_misses > 0:
                 # Use a slightly bigger check period than the hub signal period to not warn unnecessary 
                 self.hb_check_period = int(content['hb_period'])+10
                 self.log.info("Starting to monitor the heartbeat signal from the hub every %i ms." , self.hb_check_period)
                 self._hb_reporter = ioloop.PeriodicCallback(self._hb_monitor, self.hb_check_period, self.loop)
                 self._hb_reporter.start()
             else:
                 self.log.info("Monitoring of the heartbeat signal from the hub is not enabled.")
 
             
             # FIXME: This is a hack until IPKernelApp and IPEngineApp can be fully merged
             app = IPKernelApp(parent=self, 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 _hb_monitor(self):
         """Callback to monitor the heartbeat from the controller"""
         self._hb_listener.flush()
         if self._hb_last_monitored > self._hb_last_pinged:
             self._hb_missed_beats += 1
             self.log.warn("No heartbeat in the last %s ms (%s time(s) in a row).", self.hb_check_period, self._hb_missed_beats)
         else:
             #self.log.debug("Heartbeat received (after missing %s beats).", self._hb_missed_beats)
             self._hb_missed_beats = 0
 
         if self._hb_missed_beats >= self.max_heartbeat_misses:
             self.log.fatal("Maximum number of heartbeats misses reached (%s times %s ms), shutting down.",
                            self.max_heartbeat_misses, self.hb_check_period)
             self.session.send(self.registrar, "unregistration_request", content=dict(id=self.id))
             self.loop.stop()
 
         self._hb_last_monitored = time.time()
             
         
     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()