Python accumulators._start_update_server函数代码示例

    def __init__(self, master, jobName, sparkHome=None, pyFiles=None,
        environment=None, batchSize=1024):
        """
        Create a new SparkContext.

        @param master: Cluster URL to connect to
               (e.g. mesos://host:port, spark://host:port, local[4]).
        @param jobName: A name for your job, to display on the cluster web UI
        @param sparkHome: Location where Spark is installed on cluster nodes.
        @param pyFiles: Collection of .zip or .py files to send to the cluster
               and add to PYTHONPATH.  These can be paths on the local file
               system or HDFS, HTTP, HTTPS, or FTP URLs.
        @param environment: A dictionary of environment variables to set on
               worker nodes.
        @param batchSize: The number of Python objects represented as a single
               Java object.  Set 1 to disable batching or -1 to use an
               unlimited batch size.
        """
        with SparkContext._lock:
            if SparkContext._active_spark_context:
                raise ValueError("Cannot run multiple SparkContexts at once")
            else:
                SparkContext._active_spark_context = self
        self.master = master
        self.jobName = jobName
        self.sparkHome = sparkHome or None # None becomes null in Py4J
        self.environment = environment or {}
        self.batchSize = batchSize  # -1 represents a unlimited batch size

        # Create the Java SparkContext through Py4J
        empty_string_array = self.gateway.new_array(self.jvm.String, 0)
        self._jsc = self.jvm.JavaSparkContext(master, jobName, sparkHome,
                                              empty_string_array)

        # Create a single Accumulator in Java that we'll send all our updates through;
        # they will be passed back to us through a TCP server
        self._accumulatorServer = accumulators._start_update_server()
        (host, port) = self._accumulatorServer.server_address
        self._javaAccumulator = self._jsc.accumulator(
                self.jvm.java.util.ArrayList(),
                self.jvm.PythonAccumulatorParam(host, port))

        self.pythonExec = os.environ.get("PYSPARK_PYTHON", 'python')
        # Broadcast's __reduce__ method stores Broadcast instances here.
        # This allows other code to determine which Broadcast instances have
        # been pickled, so it can determine which Java broadcast objects to
        # send.
        self._pickled_broadcast_vars = set()

        # Deploy any code dependencies specified in the constructor
        for path in (pyFiles or []):
            self.addPyFile(path)
        SparkFiles._sc = self
        sys.path.append(SparkFiles.getRootDirectory())

    def _do_init(self, master, appName, sparkHome, pyFiles, environment, batchSize, serializer,
                 conf, jsc, profiler_cls):
        self.environment = environment or {}
        # java gateway must have been launched at this point.
        if conf is not None and conf._jconf is not None:
            # conf has been initialized in JVM properly, so use conf directly. This represent the
            # scenario that JVM has been launched before SparkConf is created (e.g. SparkContext is
            # created and then stopped, and we create a new SparkConf and new SparkContext again)
            self._conf = conf
        else:
            self._conf = SparkConf(_jvm=SparkContext._jvm)
            if conf is not None:
                for k, v in conf.getAll():
                    self._conf.set(k, v)

        self._batchSize = batchSize  # -1 represents an unlimited batch size
        self._unbatched_serializer = serializer
        if batchSize == 0:
            self.serializer = AutoBatchedSerializer(self._unbatched_serializer)
        else:
            self.serializer = BatchedSerializer(self._unbatched_serializer,
                                                batchSize)

        # Set any parameters passed directly to us on the conf
        if master:
            self._conf.setMaster(master)
        if appName:
            self._conf.setAppName(appName)
        if sparkHome:
            self._conf.setSparkHome(sparkHome)
        if environment:
            for key, value in environment.items():
                self._conf.setExecutorEnv(key, value)
        for key, value in DEFAULT_CONFIGS.items():
            self._conf.setIfMissing(key, value)

        # Check that we have at least the required parameters
        if not self._conf.contains("spark.master"):
            raise Exception("A master URL must be set in your configuration")
        if not self._conf.contains("spark.app.name"):
            raise Exception("An application name must be set in your configuration")

        # Read back our properties from the conf in case we loaded some of them from
        # the classpath or an external config file
        self.master = self._conf.get("spark.master")
        self.appName = self._conf.get("spark.app.name")
        self.sparkHome = self._conf.get("spark.home", None)

        for (k, v) in self._conf.getAll():
            if k.startswith("spark.executorEnv."):
                varName = k[len("spark.executorEnv."):]
                self.environment[varName] = v

        self.environment["PYTHONHASHSEED"] = os.environ.get("PYTHONHASHSEED", "0")

        # Create the Java SparkContext through Py4J
        self._jsc = jsc or self._initialize_context(self._conf._jconf)
        # Reset the SparkConf to the one actually used by the SparkContext in JVM.
        self._conf = SparkConf(_jconf=self._jsc.sc().conf())

        # Create a single Accumulator in Java that we'll send all our updates through;
        # they will be passed back to us through a TCP server
        self._accumulatorServer = accumulators._start_update_server()
        (host, port) = self._accumulatorServer.server_address
        self._javaAccumulator = self._jvm.PythonAccumulatorV2(host, port)
        self._jsc.sc().register(self._javaAccumulator)

        self.pythonExec = os.environ.get("PYSPARK_PYTHON", 'python')
        self.pythonVer = "%d.%d" % sys.version_info[:2]

        # Broadcast's __reduce__ method stores Broadcast instances here.
        # This allows other code to determine which Broadcast instances have
        # been pickled, so it can determine which Java broadcast objects to
        # send.
        self._pickled_broadcast_vars = BroadcastPickleRegistry()

        SparkFiles._sc = self
        root_dir = SparkFiles.getRootDirectory()
        sys.path.insert(1, root_dir)

        # Deploy any code dependencies specified in the constructor
        self._python_includes = list()
        for path in (pyFiles or []):
            self.addPyFile(path)

        # Deploy code dependencies set by spark-submit; these will already have been added
        # with SparkContext.addFile, so we just need to add them to the PYTHONPATH
        for path in self._conf.get("spark.submit.pyFiles", "").split(","):
            if path != "":
                (dirname, filename) = os.path.split(path)
                if filename[-4:].lower() in self.PACKAGE_EXTENSIONS:
                    self._python_includes.append(filename)
                    sys.path.insert(1, os.path.join(SparkFiles.getRootDirectory(), filename))

        # Create a temporary directory inside spark.local.dir:
        local_dir = self._jvm.org.apache.spark.util.Utils.getLocalDir(self._jsc.sc().conf())
        self._temp_dir = \
            self._jvm.org.apache.spark.util.Utils.createTempDir(local_dir, "pyspark") \
                .getAbsolutePath()

#.........这里部分代码省略.........

    def _do_init(self, master, appName, sparkHome, pyFiles, environment, batchSize, serializer,
                 conf, jsc):
        self.environment = environment or {}
        self._conf = conf or SparkConf(_jvm=self._jvm)
        self._batchSize = batchSize  # -1 represents an unlimited batch size
        self._unbatched_serializer = serializer
        if batchSize == 1:
            self.serializer = self._unbatched_serializer
        elif batchSize == 0:
            self.serializer = AutoBatchedSerializer(self._unbatched_serializer)
        else:
            self.serializer = BatchedSerializer(self._unbatched_serializer,
                                                batchSize)

        # Set any parameters passed directly to us on the conf
        if master:
            self._conf.setMaster(master)
        if appName:
            self._conf.setAppName(appName)
        if sparkHome:
            self._conf.setSparkHome(sparkHome)
        if environment:
            for key, value in environment.iteritems():
                self._conf.setExecutorEnv(key, value)
        for key, value in DEFAULT_CONFIGS.items():
            self._conf.setIfMissing(key, value)

        # Check that we have at least the required parameters
        if not self._conf.contains("spark.master"):
            raise Exception("A master URL must be set in your configuration")
        if not self._conf.contains("spark.app.name"):
            raise Exception("An application name must be set in your configuration")

        # Read back our properties from the conf in case we loaded some of them from
        # the classpath or an external config file
        self.master = self._conf.get("spark.master")
        self.appName = self._conf.get("spark.app.name")
        self.sparkHome = self._conf.get("spark.home", None)
        for (k, v) in self._conf.getAll():
            if k.startswith("spark.executorEnv."):
                varName = k[len("spark.executorEnv."):]
                self.environment[varName] = v

        # Create the Java SparkContext through Py4J
        self._jsc = jsc or self._initialize_context(self._conf._jconf)

        # Create a single Accumulator in Java that we'll send all our updates through;
        # they will be passed back to us through a TCP server
        self._accumulatorServer = accumulators._start_update_server()
        (host, port) = self._accumulatorServer.server_address
        self._javaAccumulator = self._jsc.accumulator(
            self._jvm.java.util.ArrayList(),
            self._jvm.PythonAccumulatorParam(host, port))

        self.pythonExec = os.environ.get("PYSPARK_PYTHON", 'python')

        # Broadcast's __reduce__ method stores Broadcast instances here.
        # This allows other code to determine which Broadcast instances have
        # been pickled, so it can determine which Java broadcast objects to
        # send.
        self._pickled_broadcast_vars = set()

        SparkFiles._sc = self
        root_dir = SparkFiles.getRootDirectory()
        sys.path.insert(1, root_dir)

        # Deploy any code dependencies specified in the constructor
        self._python_includes = list()
        for path in (pyFiles or []):
            self.addPyFile(path)

        # Deploy code dependencies set by spark-submit; these will already have been added
        # with SparkContext.addFile, so we just need to add them to the PYTHONPATH
        for path in self._conf.get("spark.submit.pyFiles", "").split(","):
            if path != "":
                (dirname, filename) = os.path.split(path)
                if filename.lower().endswith("zip") or filename.lower().endswith("egg"):
                    self._python_includes.append(filename)
                    sys.path.insert(1, os.path.join(SparkFiles.getRootDirectory(), filename))

        # Create a temporary directory inside spark.local.dir:
        local_dir = self._jvm.org.apache.spark.util.Utils.getLocalDir(self._jsc.sc().conf())
        self._temp_dir = \
            self._jvm.org.apache.spark.util.Utils.createTempDir(local_dir).getAbsolutePath()

        # profiling stats collected for each PythonRDD
        self._profile_stats = []

    def __init__(self, master, jobName, sparkHome=None, pyFiles=None,
        environment=None, batchSize=1024, serializer=PickleSerializer()):
        """
        Create a new SparkContext.

        @param master: Cluster URL to connect to
               (e.g. mesos://host:port, spark://host:port, local[4]).
        @param jobName: A name for your job, to display on the cluster web UI
        @param sparkHome: Location where Spark is installed on cluster nodes.
        @param pyFiles: Collection of .zip or .py files to send to the cluster
               and add to PYTHONPATH.  These can be paths on the local file
               system or HDFS, HTTP, HTTPS, or FTP URLs.
        @param environment: A dictionary of environment variables to set on
               worker nodes.
        @param batchSize: The number of Python objects represented as a single
               Java object.  Set 1 to disable batching or -1 to use an
               unlimited batch size.
        @param serializer: The serializer for RDDs.


        >>> from pyspark.context import SparkContext
        >>> sc = SparkContext('local', 'test')

        >>> sc2 = SparkContext('local', 'test2') # doctest: +IGNORE_EXCEPTION_DETAIL
        Traceback (most recent call last):
            ...
        ValueError:...
        """
        SparkContext._ensure_initialized(self)

        self.master = master
        self.jobName = jobName
        self.sparkHome = sparkHome or None # None becomes null in Py4J
        self.environment = environment or {}
        self._batchSize = batchSize  # -1 represents an unlimited batch size
        self._unbatched_serializer = serializer
        if batchSize == 1:
            self.serializer = self._unbatched_serializer
        else:
            self.serializer = BatchedSerializer(self._unbatched_serializer,
                                                batchSize)

        # Create the Java SparkContext through Py4J
        empty_string_array = self._gateway.new_array(self._jvm.String, 0)
        self._jsc = self._jvm.JavaSparkContext(master, jobName, sparkHome,
                                              empty_string_array)

        # Create a single Accumulator in Java that we'll send all our updates through;
        # they will be passed back to us through a TCP server
        self._accumulatorServer = accumulators._start_update_server()
        (host, port) = self._accumulatorServer.server_address
        self._javaAccumulator = self._jsc.accumulator(
                self._jvm.java.util.ArrayList(),
                self._jvm.PythonAccumulatorParam(host, port))

        self.pythonExec = os.environ.get("PYSPARK_PYTHON", 'python')
        # Broadcast's __reduce__ method stores Broadcast instances here.
        # This allows other code to determine which Broadcast instances have
        # been pickled, so it can determine which Java broadcast objects to
        # send.
        self._pickled_broadcast_vars = set()

        SparkFiles._sc = self
        root_dir = SparkFiles.getRootDirectory()
        sys.path.append(root_dir)

        # Deploy any code dependencies specified in the constructor
        self._python_includes = list()
        for path in (pyFiles or []):
            self.addPyFile(path)

        # Create a temporary directory inside spark.local.dir:
        local_dir = self._jvm.org.apache.spark.util.Utils.getLocalDir()
        self._temp_dir = \
            self._jvm.org.apache.spark.util.Utils.createTempDir(local_dir).getAbsolutePath()

    def __init__(self, master=None, appName=None, sparkHome=None, pyFiles=None,
        environment=None, batchSize=1024, serializer=PickleSerializer(), conf=None,
        gateway=None):
        """
        Create a new SparkContext. At least the master and app name should be set,
        either through the named parameters here or through C{conf}.

        @param master: Cluster URL to connect to
               (e.g. mesos://host:port, spark://host:port, local[4]).
        @param appName: A name for your job, to display on the cluster web UI.
        @param sparkHome: Location where Spark is installed on cluster nodes.
        @param pyFiles: Collection of .zip or .py files to send to the cluster
               and add to PYTHONPATH.  These can be paths on the local file
               system or HDFS, HTTP, HTTPS, or FTP URLs.
        @param environment: A dictionary of environment variables to set on
               worker nodes.
        @param batchSize: The number of Python objects represented as a single
               Java object.  Set 1 to disable batching or -1 to use an
               unlimited batch size.
        @param serializer: The serializer for RDDs.
        @param conf: A L{SparkConf} object setting Spark properties.
        @param gateway: Use an existing gateway and JVM, otherwise a new JVM
               will be instatiated.


        >>> from pyspark.context import SparkContext
        >>> sc = SparkContext('local', 'test')

        >>> sc2 = SparkContext('local', 'test2') # doctest: +IGNORE_EXCEPTION_DETAIL
        Traceback (most recent call last):
            ...
        ValueError:...
        """
        if rdd._extract_concise_traceback() is not None:
            self._callsite = rdd._extract_concise_traceback()
        else:
            tempNamedTuple = namedtuple("Callsite", "function file linenum")
            self._callsite = tempNamedTuple(function=None, file=None, linenum=None)
        SparkContext._ensure_initialized(self, gateway=gateway)

        self.environment = environment or {}
        self._conf = conf or SparkConf(_jvm=self._jvm)
        self._batchSize = batchSize  # -1 represents an unlimited batch size
        self._unbatched_serializer = serializer
        if batchSize == 1:
            self.serializer = self._unbatched_serializer
        else:
            self.serializer = BatchedSerializer(self._unbatched_serializer,
                                                batchSize)

        # Set any parameters passed directly to us on the conf
        if master:
            self._conf.setMaster(master)
        if appName:
            self._conf.setAppName(appName)
        if sparkHome:
            self._conf.setSparkHome(sparkHome)
        if environment:
            for key, value in environment.iteritems():
                self._conf.setExecutorEnv(key, value)

        # Check that we have at least the required parameters
        if not self._conf.contains("spark.master"):
            raise Exception("A master URL must be set in your configuration")
        if not self._conf.contains("spark.app.name"):
            raise Exception("An application name must be set in your configuration")

        # Read back our properties from the conf in case we loaded some of them from
        # the classpath or an external config file
        self.master = self._conf.get("spark.master")
        self.appName = self._conf.get("spark.app.name")
        self.sparkHome = self._conf.get("spark.home", None)
        for (k, v) in self._conf.getAll():
            if k.startswith("spark.executorEnv."):
                varName = k[len("spark.executorEnv."):]
                self.environment[varName] = v

        # Create the Java SparkContext through Py4J
        self._jsc = self._initialize_context(self._conf._jconf)

        # Create a single Accumulator in Java that we'll send all our updates through;
        # they will be passed back to us through a TCP server
        self._accumulatorServer = accumulators._start_update_server()
        (host, port) = self._accumulatorServer.server_address
        self._javaAccumulator = self._jsc.accumulator(
                self._jvm.java.util.ArrayList(),
                self._jvm.PythonAccumulatorParam(host, port))

        self.pythonExec = os.environ.get("PYSPARK_PYTHON", 'python')

        # Broadcast's __reduce__ method stores Broadcast instances here.
        # This allows other code to determine which Broadcast instances have
        # been pickled, so it can determine which Java broadcast objects to
        # send.
        self._pickled_broadcast_vars = set()

        SparkFiles._sc = self
        root_dir = SparkFiles.getRootDirectory()
        sys.path.append(root_dir)

#.........这里部分代码省略.........

    def _do_init(self, master, appName, sparkHome, pyFiles, environment, batchSize, serializer,
                 conf, jsc, profiler_cls):
        self.environment = environment or {}
        self._conf = conf or SparkConf(_jvm=self._jvm)
        self._batchSize = batchSize  # -1 represents an unlimited batch size
        self._unbatched_serializer = serializer
        if batchSize == 0:
            self.serializer = AutoBatchedSerializer(self._unbatched_serializer)
        else:
            self.serializer = BatchedSerializer(self._unbatched_serializer,
                                                batchSize)

        # Set any parameters passed directly to us on the conf
        if master:
            self._conf.setMaster(master)
        if appName:
            self._conf.setAppName(appName)
        if sparkHome:
            self._conf.setSparkHome(sparkHome)
        if environment:
            for key, value in environment.items():
                self._conf.setExecutorEnv(key, value)
        for key, value in DEFAULT_CONFIGS.items():
            self._conf.setIfMissing(key, value)

        # Check that we have at least the required parameters
        if not self._conf.contains("spark.master"):
            raise Exception("A master URL must be set in your configuration")
        if not self._conf.contains("spark.app.name"):
            raise Exception("An application name must be set in your configuration")

        # Read back our properties from the conf in case we loaded some of them from
        # the classpath or an external config file
        self.master = self._conf.get("spark.master")
        self.appName = self._conf.get("spark.app.name")
        self.sparkHome = self._conf.get("spark.home", None)

        # Let YARN know it's a pyspark app, so it distributes needed libraries.
        if self.master == "yarn-client":
            self._conf.set("spark.yarn.isPython", "true")

        for (k, v) in self._conf.getAll():
            if k.startswith("spark.executorEnv."):
                varName = k[len("spark.executorEnv."):]
                self.environment[varName] = v
        if sys.version >= '3.3' and 'PYTHONHASHSEED' not in os.environ:
            # disable randomness of hash of string in worker, if this is not
            # launched by spark-submit
            self.environment["PYTHONHASHSEED"] = "0"

        # Create the Java SparkContext through Py4J
        self._jsc = jsc or self._initialize_context(self._conf._jconf)

        # Create a single Accumulator in Java that we'll send all our updates through;
        # they will be passed back to us through a TCP server
        self._accumulatorServer = accumulators._start_update_server()
        (host, port) = self._accumulatorServer.server_address
        self._javaAccumulator = self._jsc.accumulator(
            self._jvm.java.util.ArrayList(),
            self._jvm.PythonAccumulatorParam(host, port))

        self.pythonExec = os.environ.get("PYSPARK_PYTHON", 'python')
        self.pythonVer = "%d.%d" % sys.version_info[:2]

        # Broadcast's __reduce__ method stores Broadcast instances here.
        # This allows other code to determine which Broadcast instances have
        # been pickled, so it can determine which Java broadcast objects to
        # send.
        self._pickled_broadcast_vars = set()

        SparkFiles._sc = self
        root_dir = SparkFiles.getRootDirectory()
        sys.path.insert(1, root_dir)

        # Deploy any code dependencies specified in the constructor
        self._python_includes = list()
        for path in (pyFiles or []):
            self.addPyFile(path)

        # Deploy code dependencies set by spark-submit; these will already have been added
        # with SparkContext.addFile, so we just need to add them to the PYTHONPATH
        for path in self._conf.get("spark.submit.pyFiles", "").split(","):
            if path != "":
                (dirname, filename) = os.path.split(path)
                if filename[-4:].lower() in self.PACKAGE_EXTENSIONS:
                    self._python_includes.append(filename)
                    sys.path.insert(1, os.path.join(SparkFiles.getRootDirectory(), filename))

        # Create a temporary directory inside spark.local.dir:
        local_dir = self._jvm.org.apache.spark.util.Utils.getLocalDir(self._jsc.sc().conf())
        self._temp_dir = \
            self._jvm.org.apache.spark.util.Utils.createTempDir(local_dir, "pyspark") \
                .getAbsolutePath()

        # profiling stats collected for each PythonRDD
        if self._conf.get("spark.python.profile", "false") == "true":
            dump_path = self._conf.get("spark.python.profile.dump", None)
            self.profiler_collector = ProfilerCollector(profiler_cls, dump_path)
        else:
            self.profiler_collector = None
#.........这里部分代码省略.........