# python can call pyspark directly

export PYTHONPATH=$SPARK_HOME/python:$SPARK_HOME/python/pyspark:$SPARK_HOME/python/lib/py4j-0.10.4-src.zip:$PYTHONPATH

from __future__ import print_function

from pyspark import *

import os

print(os.environ['SPARK_HOME'])

print(os.environ['HADOOP_HOME'])

if __name__ == '__main__':

    sc = SparkContext("spark://hadoop10:7077")

    rdd = sc.parallelize("hello Pyspark world".split(' '))

    counts = rdd.map(lambda word: (word, 1)) \

        .reduceByKey(lambda a, b: a + b)

    counts.saveAsTextFile('/usr/lib/spark/out')

    counts.foreach(print)

    sc.stop()

bin/spark-submit test1.py

[root@hadoop10 hadoop-2.6.5]# spark-submit --help

Options:

  --master MASTER_URL         spark://host:port, mesos://host:port, yarn,       指定 spark 运行模式，即使在 代码里指定了 spark master，此处也需要重新指定

                              k8s://https://host:port, or local (Default: local[*]).

  --deploy-mode DEPLOY_MODE   Whether to launch the driver program locally ("client") or        client 模式 or cluster 模式

                              on one of the worker machines inside the cluster ("cluster")

                              (Default: client).

  --class CLASS_NAME          Your application's main class (for Java / Scala apps).

  --name NAME                 A name of your application.

  --jars JARS                 Comma-separated list of jars to include on the driver

                              and executor classpaths.

  --packages                  Comma-separated list of maven coordinates of jars to include

                              on the driver and executor classpaths. Will search the local

                              maven repo, then maven central and any additional remote

                              repositories given by --repositories. The format for the

                              coordinates should be groupId:artifactId:version.

  --exclude-packages          Comma-separated list of groupId:artifactId, to exclude while

                              resolving the dependencies provided in --packages to avoid

                              dependency conflicts.

  --repositories              Comma-separated list of additional remote repositories to

                              search for the maven coordinates given with --packages.

  --py-files PY_FILES         Comma-separated list of .zip, .egg, or .py files to place

                              on the PYTHONPATH for Python apps.

  --files FILES               Comma-separated list of files to be placed in the working

                              directory of each executor. File paths of these files

                              in executors can be accessed via SparkFiles.get(fileName).

  --conf PROP=VALUE           Arbitrary Spark configuration property.

  --properties-file FILE      Path to a file from which to load extra properties. If not

                              specified, this will look for conf/spark-defaults.conf.

  --driver-memory MEM         Memory for driver (e.g. 1000M, 2G) (Default: 1024M).      指定 driver 内存，

  --driver-java-options       Extra Java options to pass to the driver.

  --driver-library-path       Extra library path entries to pass to the driver.

  --driver-class-path         Extra class path entries to pass to the driver. Note that

                              jars added with --jars are automatically included in the

                              classpath.

  --executor-memory MEM       Memory per executor (e.g. 1000M, 2G) (Default: 1G).       指定 executor 内存

  --proxy-user NAME           User to impersonate when submitting the application.

                              This argument does not work with --principal / --keytab.

  --help, -h                  Show this help message and exit.      查看所有参数

  --verbose, -v               Print additional debug output.

  --version,                  Print the version of current Spark.

 Cluster deploy mode only:

  --driver-cores NUM          Number of cores used by the driver, only in cluster mode      指定 cpu 个数

                              (Default: 1).

 Spark standalone or Mesos with cluster deploy mode only:

  --supervise                 If given, restarts the driver on failure.

  --kill SUBMISSION_ID        If given, kills the driver specified.

  --status SUBMISSION_ID      If given, requests the status of the driver specified.

 Spark standalone and Mesos only:

  --total-executor-cores NUM  Total cores for all executors.

 Spark standalone and YARN only:

  --executor-cores NUM        Number of cores per executor. (Default: 1 in YARN mode,

                              or all available cores on the worker in standalone mode)

 YARN-only:

  --queue QUEUE_NAME          The YARN queue to submit to (Default: "default").

  --num-executors NUM         Number of executors to launch (Default: 2).

                              If dynamic allocation is enabled, the initial number of

                              executors will be at least NUM.

  --archives ARCHIVES         Comma separated list of archives to be extracted into the

                              working directory of each executor.

  --principal PRINCIPAL       Principal to be used to login to KDC, while running on

                              secure HDFS.

  --keytab KEYTAB             The full path to the file that contains the keytab for the

                              principal specified above. This keytab will be copied to

                              the node running the Application Master via the Secure

                              Distributed Cache, for renewing the login tickets and the

                              delegation tokens periodically.

spark-submit --master yarn-client  --driver-memory 512m  xx.py