文章目录
参考博文: https://blog.csdn.net/klordy_123/article/details/84109501
1. Spark Streaming的checkpoint机制
1.1 Spark Streaming 的checkpoint示例
import org.apache.log4j.{
Level, Logger}
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.types._
import org.apache.spark.sql._
import org.apache.spark.streaming.dstream.DStream
import org.apache.spark.{
SparkConf, SparkContext}
import org.apache.spark.streaming.{
Seconds, StreamingContext}
import org.apache.spark.streaming.kafka.KafkaUtils
object SaveDataToMysql {
def main(args: Array[String]): Unit = {
// 屏蔽不必要的日志 ,在终端上显示需要的日志
Logger.getLogger("org.apache.spark").setLevel(Level.OFF)
Logger.getLogger("org.eclipse.jetty.server").setLevel(Level.OFF)
Logger.getLogger("org.apache.kafka.clients.consumer").setLevel(Level.OFF)
//初始化sparkStreaming
val conf = new SparkConf().setAppName("SaveDataToMysql").setMaster("local[*]")
val sc = new SparkContext(conf)
val ssc = new StreamingContext(sc, Seconds(10))
//连接s3需要的key和密码
ssc.sparkContext.hadoopConfiguration.set("fs.s3a.access.key","aws的key")
ssc.sparkContext.hadoopConfiguration.set("fs.s3a.secret.key","aws的密码")
ssc.sparkContext.hadoopConfiguration.set("fs.s3a.endpoint", "s3.cn-north-1.amazonaws.com.cn")
//设置连接Kafka的配置信息
val zkQuorum = "192.168.1.112:2181" //zookeeper集群的IP:port,IP:port,IP:port
val group = "testgroup" //在consumer.properties配置group.id
val topics = "myTopic1 myTopic2" //选择要连接的producer,它是以topic来区分每个producer的。例如:我这里的创建的topic是huiliyang
val numThreads = 2 //线程
val topicpMap = topics.split("\n").map((_,numThreads.toInt)).toMap //这个是有可能有好几个topic同时提供数据,那么我们要把它用空格分割开,然后映射成(topic,2),再转换成map集合
ssc.checkpoint("hdfs://10.47.85.158:9000/checkpointDir/")
val lines: DStream[String] = KafkaUtils.createStream(ssc,zkQuorum