export SPARK_CLASSPATH=$SPARK_CLASSPATH:/home/hadoop/software/mysql-connector-java-5.1.-bin.jar

cd $SPARK_HOME/bin

spark-sql --help

Usage: ./bin/spark-sql [options] [cli option]

Spark assembly has been built with Hive, including Datanucleus jars on classpath

Options:
--master MASTER_URL         spark://host:port, mesos://host:port, yarn, or local.

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

                              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 local jars to include on the driver

                              and executor classpaths.

  --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.

  --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: 512M).

  --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).

  --help, -h                  Show this help message and exit

  --verbose, -v               Print additional debug output

 Spark standalone with cluster deploy mode only:

  --driver-cores NUM          Cores for driver (Default: ).

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

 Spark standalone and Mesos only:

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

 YARN-only:

  --executor-cores NUM        Number of cores per executor (Default: ).

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

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

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

                              working directory of each executor.

CLI options:

-d,--define <key=value>          Variable subsitution to apply to hive

                                  commands. e.g. -d A=B or --define A=B

    --database <databasename>     Specify the database to use

 -e <quoted-query-string>         SQL from command line

 -f <filename>                    SQL from files

 -h <hostname>                    connecting to Hive Server on remote host

    --hiveconf <property=value>   Use value for given property

    --hivevar <key=value>         Variable subsitution to apply to hive

                                  commands. e.g. --hivevar A=B

 -i <filename>                    Initialization SQL file

 -p <port>                        connecting to Hive Server on port number

 -S,--silent                      Silent mode in interactive shell

 -v,--verbose                     Verbose mode (echo executed SQL to the console)

cd $SPARK_HOME/bin

spark-sql

SELECT track_time, url, session_id, referer, ip, end_user_id, city_id FROM page_views WHERE city_id = - limit ;

SELECT session_id, count(*) c FROM page_views group by session_id order by c desc limit ;

create table page_views(

track_time string,

url string,

session_id string,

referer string,

ip string,

end_user_id string,

city_id string

)

ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t';

load data local inpath '/home/spark/software/data/page_views.dat' overwrite into table page_views;