我已经使用 Scala 编写了 Kafka 流程序并在 Spark 独立集群中执行。代码在我的本地运行良好。我已经在 Azure VM 中完成了 Kafka、Cassandra 和 Spark 设置。我已打开所有入站和出站端口以避免端口阻塞。
开始大师
sbin>./start-master.sh
启动奴隶
sbin# ./start-slave.sh spark://vm-hostname:7077
我已经在 Master WEB UI 中验证了这个状态。
提交作业
bin#./spark-submit --class xyStreamJob --master spark://vm-hostname:7077 /home/user/appl.jar
我注意到应用程序添加并显示在 Master WEB UI 中。
我已经向主题发布了几条消息,并且没有收到消息并将其保存到 Cassandra DB。
我单击主 Web 控制台上的应用程序名称,并注意到该应用程序控制台页面中没有 Streaming 选项卡。
为什么应用程序不能在 VM 中运行而在本地运行良好?
如何调试 VM 中的问题?
def main(args: Array[String]): Unit = {
val spark = SparkHelper.getOrCreateSparkSession()
val ssc = new StreamingContext(spark.sparkContext, Seconds(1))
spark.sparkContext.setLogLevel("WARN")
val kafkaStream = {
val kafkaParams = Map[String, Object](
"bootstrap.servers" ->
"vmip:9092",
"key.deserializer" -> classOf[StringDeserializer],
"value.deserializer" -> classOf[StringDeserializer],
"group.id" -> "loc",
"auto.offset.reset" -> "latest",
"enable.auto.commit" -> (false: java.lang.Boolean)
)
val topics = Array("hello")
val numPartitionsOfInputTopic = 3
val streams = (1 to numPartitionsOfInputTopic) map {
_ => KafkaUtils.createDirectStream[String, String]( ssc, PreferConsistent, Subscribe[String, String](topics, kafkaParams) )
}
streams
}
kafkaStream.foreach(rdd=> {
rdd.foreachRDD(conRec=> {
val offsetRanges = conRec.asInstanceOf[HasOffsetRanges].offsetRanges
conRec.foreach(str=> {
try {
println(str.value().trim)
CassandraHelper.saveItemEvent(str.value().trim)
}catch {
case ex: Exception => {
println(ex.getMessage)
}
}
})
rdd.asInstanceOf[CanCommitOffsets].commitAsync(offsetRanges)
})
println("Read Msg")
})
println(" Spark parallel reader is ready !!!")
ssc.start()
ssc.awaitTermination()
}
def getSparkConf(): SparkConf = {
val conf = new SparkConf(true)
.setAppName("TestAppl")
.set("spark.cassandra.connection.host", "vmip")
.set("spark.streaming.stopGracefullyOnShutdown","true")
.setMaster("spark://vm-hostname:7077")
conf
}
版本
scalaVersion := "2.11.8"
val sparkVersion = "2.2.0"
val connectorVersion = "2.0.7"
libraryDependencies ++= Seq(
"org.apache.spark" %% "spark-core" % sparkVersion %"provided",
"org.apache.spark" %% "spark-sql" % sparkVersion %"provided",
"org.apache.spark" %% "spark-hive" % sparkVersion %"provided",
"com.datastax.spark" %% "spark-cassandra-connector" % connectorVersion ,
"org.apache.kafka" %% "kafka" % "0.10.1.0",
"org.apache.spark" %% "spark-streaming-kafka-0-10" % sparkVersion,
"org.apache.spark" %% "spark-streaming" % sparkVersion %"provided",
)
mergeStrategy in assembly := {
case PathList("org", "apache", "spark", "unused", "UnusedStubClass.class") => MergeStrategy.first
case x => (mergeStrategy in assembly).value(x)
}