run-example -> bin/run-example
This commit is contained in:
Prashant Sharma
parent
b810a85cdd
commit
94b7a7fe37
|
|
@ -24,9 +24,9 @@ Once you've built Spark, the easiest way to start using it is the shell:
|
|||
Or, for the Python API, the Python shell (`./pyspark`).
|
||||
|
||||
Spark also comes with several sample programs in the `examples` directory.
|
||||
To run one of them, use `./run-example <class> <params>`. For example:
|
||||
To run one of them, use `./bin/run-example <class> <params>`. For example:
|
||||
|
||||
./run-example org.apache.spark.examples.SparkLR local[2]
|
||||
./bin/run-example org.apache.spark.examples.SparkLR local[2]
|
||||
|
||||
will run the Logistic Regression example locally on 2 CPUs.
|
||||
|
||||
|
|
|
|||
|
|
@ -36,7 +36,7 @@ if [ -e "$FWDIR/conf/spark-env.sh" ] ; then
|
|||
fi
|
||||
|
||||
if [ -z "$1" ]; then
|
||||
echo "Usage: run-example <example-class> [<args>]" >&2
|
||||
echo "Usage: bin/run-example <example-class> [<args>]" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
|
|
|
|||
|
|
@ -30,7 +30,7 @@ if exist "%FWDIR%conf\spark-env.cmd" call "%FWDIR%conf\spark-env.cmd"
|
|||
|
||||
rem Test that an argument was given
|
||||
if not "x%1"=="x" goto arg_given
|
||||
echo Usage: run-example ^<example-class^> [^<args^>]
|
||||
echo Usage: bin/run-example ^<example-class^> [^<args^>]
|
||||
goto exit
|
||||
:arg_given
|
||||
|
||||
|
|
|
|||
|
|
@ -157,8 +157,8 @@ trait Message[K] {
|
|||
|
||||
# Where to Go from Here
|
||||
|
||||
Two example jobs, PageRank and shortest path, are included in `examples/src/main/scala/org/apache/spark/examples/bagel`. You can run them by passing the class name to the `run-example` script included in Spark; e.g.:
|
||||
Two example jobs, PageRank and shortest path, are included in `examples/src/main/scala/org/apache/spark/examples/bagel`. You can run them by passing the class name to the `bin/run-example` script included in Spark; e.g.:
|
||||
|
||||
./run-example org.apache.spark.examples.bagel.WikipediaPageRank
|
||||
./bin/run-example org.apache.spark.examples.bagel.WikipediaPageRank
|
||||
|
||||
Each example program prints usage help when run without any arguments.
|
||||
|
|
|
|||
|
|
@ -24,9 +24,9 @@ For its Scala API, Spark {{site.SPARK_VERSION}} depends on Scala {{site.SCALA_VE
|
|||
# Running the Examples and Shell
|
||||
|
||||
Spark comes with several sample programs in the `examples` directory.
|
||||
To run one of the samples, use `./run-example <class> <params>` in the top-level Spark directory
|
||||
(the `run-example` script sets up the appropriate paths and launches that program).
|
||||
For example, try `./run-example org.apache.spark.examples.SparkPi local`.
|
||||
To run one of the samples, use `./bin/run-example <class> <params>` in the top-level Spark directory
|
||||
(the `bin/run-example` script sets up the appropriate paths and launches that program).
|
||||
For example, try `./bin/run-example org.apache.spark.examples.SparkPi local`.
|
||||
Each example prints usage help when run with no parameters.
|
||||
|
||||
Note that all of the sample programs take a `<master>` parameter specifying the cluster URL
|
||||
|
|
|
|||
|
|
@ -190,9 +190,9 @@ We hope to generate documentation with Java-style syntax in the future.
|
|||
|
||||
Spark includes several sample programs using the Java API in
|
||||
[`examples/src/main/java`](https://github.com/apache/incubator-spark/tree/master/examples/src/main/java/org/apache/spark/examples). You can run them by passing the class name to the
|
||||
`run-example` script included in Spark; for example:
|
||||
`bin/run-example` script included in Spark; for example:
|
||||
|
||||
./run-example org.apache.spark.examples.JavaWordCount
|
||||
./bin/run-example org.apache.spark.examples.JavaWordCount
|
||||
|
||||
Each example program prints usage help when run
|
||||
without any arguments.
|
||||
|
|
|
|||
|
|
@ -107,7 +107,7 @@ For example:
|
|||
|
||||
SPARK_JAR=./assembly/target/scala-{{site.SCALA_VERSION}}/spark-assembly-{{site.SPARK_VERSION}}-hadoop2.0.5-alpha.jar \
|
||||
SPARK_YARN_APP_JAR=examples/target/scala-{{site.SCALA_VERSION}}/spark-examples-assembly-{{site.SPARK_VERSION}}.jar \
|
||||
./run-example org.apache.spark.examples.SparkPi yarn-client
|
||||
./bin/run-example org.apache.spark.examples.SparkPi yarn-client
|
||||
|
||||
|
||||
SPARK_JAR=./assembly/target/scala-{{site.SCALA_VERSION}}/spark-assembly-{{site.SPARK_VERSION}}-hadoop2.0.5-alpha.jar \
|
||||
|
|
|
|||
|
|
@ -366,9 +366,9 @@ res2: Int = 10
|
|||
# Where to Go from Here
|
||||
|
||||
You can see some [example Spark programs](http://spark.incubator.apache.org/examples.html) on the Spark website.
|
||||
In addition, Spark includes several samples in `examples/src/main/scala`. Some of them have both Spark versions and local (non-parallel) versions, allowing you to see what had to be changed to make the program run on a cluster. You can run them using by passing the class name to the `run-example` script included in Spark; for example:
|
||||
In addition, Spark includes several samples in `examples/src/main/scala`. Some of them have both Spark versions and local (non-parallel) versions, allowing you to see what had to be changed to make the program run on a cluster. You can run them using by passing the class name to the `bin/run-example` script included in Spark; for example:
|
||||
|
||||
./run-example org.apache.spark.examples.SparkPi
|
||||
./bin/run-example org.apache.spark.examples.SparkPi
|
||||
|
||||
Each example program prints usage help when run without any arguments.
|
||||
|
||||
|
|
|
|||
|
|
@ -245,7 +245,7 @@ $ nc -lk 9999
|
|||
Then, in a different terminal, you can start NetworkWordCount by using
|
||||
|
||||
{% highlight bash %}
|
||||
$ ./run-example org.apache.spark.streaming.examples.NetworkWordCount local[2] localhost 9999
|
||||
$ ./bin/run-example org.apache.spark.streaming.examples.NetworkWordCount local[2] localhost 9999
|
||||
{% endhighlight %}
|
||||
|
||||
This will make NetworkWordCount connect to the netcat server. Any lines typed in the terminal running the netcat server will be counted and printed on screen.
|
||||
|
|
@ -283,7 +283,7 @@ Time: 1357008430000 ms
|
|||
</td>
|
||||
</table>
|
||||
|
||||
You can find more examples in `<Spark repo>/streaming/src/main/scala/org/apache/spark/streaming/examples/`. They can be run in the similar manner using `./run-example org.apache.spark.streaming.examples....` . Executing without any parameter would give the required parameter list. Further explanation to run them can be found in comments in the files.
|
||||
You can find more examples in `<Spark repo>/streaming/src/main/scala/org/apache/spark/streaming/examples/`. They can be run in the similar manner using `./bin/run-example org.apache.spark.streaming.examples....` . Executing without any parameter would give the required parameter list. Further explanation to run them can be found in comments in the files.
|
||||
|
||||
# DStream Persistence
|
||||
Similar to RDDs, DStreams also allow developers to persist the stream's data in memory. That is, using `persist()` method on a DStream would automatically persist every RDD of that DStream in memory. This is useful if the data in the DStream will be computed multiple times (e.g., multiple operations on the same data). For window-based operations like `reduceByWindow` and `reduceByKeyAndWindow` and state-based operations like `updateStateByKey`, this is implicitly true. Hence, DStreams generated by window-based operations are automatically persisted in memory, without the developer calling `persist()`.
|
||||
|
|
|
|||
|
|
@ -41,7 +41,7 @@ import scala.Tuple2;
|
|||
* <numThreads> is the number of threads the kafka consumer should use
|
||||
*
|
||||
* Example:
|
||||
* `./run-example org.apache.spark.streaming.examples.JavaKafkaWordCount local[2] zoo01,zoo02,
|
||||
* `./bin/run-example org.apache.spark.streaming.examples.JavaKafkaWordCount local[2] zoo01,zoo02,
|
||||
* zoo03 my-consumer-group topic1,topic2 1`
|
||||
*/
|
||||
|
||||
|
|
|
|||
|
|
@ -134,9 +134,9 @@ object FeederActor {
|
|||
* <hostname> and <port> describe the AkkaSystem that Spark Sample feeder is running on.
|
||||
*
|
||||
* To run this example locally, you may run Feeder Actor as
|
||||
* `$ ./run-example spark.streaming.examples.FeederActor 127.0.1.1 9999`
|
||||
* `$ ./bin/run-example spark.streaming.examples.FeederActor 127.0.1.1 9999`
|
||||
* and then run the example
|
||||
* `$ ./run-example spark.streaming.examples.ActorWordCount local[2] 127.0.1.1 9999`
|
||||
* `$ ./bin/run-example spark.streaming.examples.ActorWordCount local[2] 127.0.1.1 9999`
|
||||
*/
|
||||
object ActorWordCount {
|
||||
def main(args: Array[String]) {
|
||||
|
|
|
|||
|
|
@ -28,7 +28,7 @@ import org.apache.spark.streaming.StreamingContext._
|
|||
* <directory> is the directory that Spark Streaming will use to find and read new text files.
|
||||
*
|
||||
* To run this on your local machine on directory `localdir`, run this example
|
||||
* `$ ./run-example spark.streaming.examples.HdfsWordCount local[2] localdir`
|
||||
* `$ ./bin/run-example spark.streaming.examples.HdfsWordCount local[2] localdir`
|
||||
* Then create a text file in `localdir` and the words in the file will get counted.
|
||||
*/
|
||||
object HdfsWordCount {
|
||||
|
|
|
|||
|
|
@ -35,7 +35,7 @@ import org.apache.spark.streaming.util.RawTextHelper._
|
|||
* <numThreads> is the number of threads the kafka consumer should use
|
||||
*
|
||||
* Example:
|
||||
* `./run-example spark.streaming.examples.KafkaWordCount local[2] zoo01,zoo02,zoo03 my-consumer-group topic1,topic2 1`
|
||||
* `./bin/run-example spark.streaming.examples.KafkaWordCount local[2] zoo01,zoo02,zoo03 my-consumer-group topic1,topic2 1`
|
||||
*/
|
||||
object KafkaWordCount {
|
||||
def main(args: Array[String]) {
|
||||
|
|
|
|||
|
|
@ -79,9 +79,9 @@ object MQTTPublisher {
|
|||
* <MqttbrokerUrl> and <topic> describe where Mqtt publisher is running.
|
||||
*
|
||||
* To run this example locally, you may run publisher as
|
||||
* `$ ./run-example org.apache.spark.streaming.examples.MQTTPublisher tcp://localhost:1883 foo`
|
||||
* `$ ./bin/run-example org.apache.spark.streaming.examples.MQTTPublisher tcp://localhost:1883 foo`
|
||||
* and run the example as
|
||||
* `$ ./run-example org.apache.spark.streaming.examples.MQTTWordCount local[2] tcp://localhost:1883 foo`
|
||||
* `$ ./bin/run-example org.apache.spark.streaming.examples.MQTTWordCount local[2] tcp://localhost:1883 foo`
|
||||
*/
|
||||
object MQTTWordCount {
|
||||
|
||||
|
|
|
|||
|
|
@ -29,7 +29,7 @@ import org.apache.spark.streaming.StreamingContext._
|
|||
* To run this on your local machine, you need to first run a Netcat server
|
||||
* `$ nc -lk 9999`
|
||||
* and then run the example
|
||||
* `$ ./run-example spark.streaming.examples.NetworkWordCount local[2] localhost 9999`
|
||||
* `$ ./bin/run-example spark.streaming.examples.NetworkWordCount local[2] localhost 9999`
|
||||
*/
|
||||
object NetworkWordCount {
|
||||
def main(args: Array[String]) {
|
||||
|
|
|
|||
|
|
@ -29,7 +29,7 @@ import org.apache.spark.streaming.StreamingContext._
|
|||
* To run this on your local machine, you need to first run a Netcat server
|
||||
* `$ nc -lk 9999`
|
||||
* and then run the example
|
||||
* `$ ./run-example spark.streaming.examples.StatefulNetworkWordCount local[2] localhost 9999`
|
||||
* `$ ./bin/run-example spark.streaming.examples.StatefulNetworkWordCount local[2] localhost 9999`
|
||||
*/
|
||||
object StatefulNetworkWordCount {
|
||||
def main(args: Array[String]) {
|
||||
|
|
|
|||
|
|
@ -62,9 +62,9 @@ object SimpleZeroMQPublisher {
|
|||
* <zeroMQurl> and <topic> describe where zeroMq publisher is running.
|
||||
*
|
||||
* To run this example locally, you may run publisher as
|
||||
* `$ ./run-example spark.streaming.examples.SimpleZeroMQPublisher tcp://127.0.1.1:1234 foo.bar`
|
||||
* `$ ./bin/run-example spark.streaming.examples.SimpleZeroMQPublisher tcp://127.0.1.1:1234 foo.bar`
|
||||
* and run the example as
|
||||
* `$ ./run-example spark.streaming.examples.ZeroMQWordCount local[2] tcp://127.0.1.1:1234 foo`
|
||||
* `$ ./bin/run-example spark.streaming.examples.ZeroMQWordCount local[2] tcp://127.0.1.1:1234 foo`
|
||||
*/
|
||||
object ZeroMQWordCount {
|
||||
def main(args: Array[String]) {
|
||||
|
|
|
|||
|
|
@ -39,8 +39,8 @@ object PageView extends Serializable {
|
|||
/** Generates streaming events to simulate page views on a website.
|
||||
*
|
||||
* This should be used in tandem with PageViewStream.scala. Example:
|
||||
* $ ./run-example spark.streaming.examples.clickstream.PageViewGenerator 44444 10
|
||||
* $ ./run-example spark.streaming.examples.clickstream.PageViewStream errorRatePerZipCode localhost 44444
|
||||
* $ ./bin/run-example spark.streaming.examples.clickstream.PageViewGenerator 44444 10
|
||||
* $ ./bin/run-example spark.streaming.examples.clickstream.PageViewStream errorRatePerZipCode localhost 44444
|
||||
*
|
||||
* When running this, you may want to set the root logging level to ERROR in
|
||||
* conf/log4j.properties to reduce the verbosity of the output.
|
||||
|
|
|
|||
|
|
@ -25,8 +25,8 @@ import org.apache.spark.SparkContext._
|
|||
* operators available in Spark streaming.
|
||||
*
|
||||
* This should be used in tandem with PageViewStream.scala. Example:
|
||||
* $ ./run-example spark.streaming.examples.clickstream.PageViewGenerator 44444 10
|
||||
* $ ./run-example spark.streaming.examples.clickstream.PageViewStream errorRatePerZipCode localhost 44444
|
||||
* $ ./bin/run-example spark.streaming.examples.clickstream.PageViewGenerator 44444 10
|
||||
* $ ./bin/run-example spark.streaming.examples.clickstream.PageViewStream errorRatePerZipCode localhost 44444
|
||||
*/
|
||||
object PageViewStream {
|
||||
def main(args: Array[String]) {
|
||||
|
|
|
|||
Loading…
Reference in a new issue