object
RawNetworkGrep extends AnyRef
Value Members
-
final
def
!=(arg0: AnyRef): Boolean
-
final
def
!=(arg0: Any): Boolean
-
final
def
##(): Int
-
final
def
==(arg0: AnyRef): Boolean
-
final
def
==(arg0: Any): Boolean
-
final
def
asInstanceOf[T0]: T0
-
def
clone(): AnyRef
-
final
def
eq(arg0: AnyRef): Boolean
-
def
equals(arg0: Any): Boolean
-
def
finalize(): Unit
-
final
def
getClass(): java.lang.Class[_]
-
def
hashCode(): Int
-
final
def
isInstanceOf[T0]: Boolean
-
def
main(args: Array[String]): Unit
-
final
def
ne(arg0: AnyRef): Boolean
-
final
def
notify(): Unit
-
final
def
notifyAll(): Unit
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
-
def
toString(): String
-
final
def
wait(): Unit
-
final
def
wait(arg0: Long, arg1: Int): Unit
-
final
def
wait(arg0: Long): Unit
Inherited from AnyRef
Inherited from Any
Receives text from multiple rawNetworkStreams and counts how many '\n' delimited lines have the word 'the' in them. This is useful for benchmarking purposes. This will only work with spark.streaming.util.RawTextSender running on all worker nodes and with Spark using Kryo serialization (set Java property "spark.serializer" to "spark.KryoSerializer"). Usage: RawNetworkGrep <master> <numStreams> <host> <port> <batchMillis> <master> is the Spark master URL <numStream> is the number rawNetworkStreams, which should be same as number of work nodes in the cluster <host> is "localhost". <port> is the port on which RawTextSender is running in the worker nodes. <batchMillise> is the Spark Streaming batch duration in milliseconds.