Spark广播变量使用示例
实现原理
广播变量用来高效分发较大的对象。向所有工作节点发送一个较大的只读值,以供一个或多个 Spark 操作使用。比如,如果你的应用需要向所有节点发送一个较大的只读查询表,广播变量用起来都很顺手。在多个并行操作中使用同一个变量,但是 Spark 会为每个任务分别发送。
代码
package com.zxl.spark.core
import org.apache.spark.broadcast.Broadcast
import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}
object BroadcastDemo {
def main(args: Array[String]): Unit = {
val conf: SparkConf = new SparkConf().setMaster("local[4]").setAppName("BroadcastDemo")
val sc: SparkContext = new SparkContext(conf)
val rdd: RDD[(String, Int)] = sc.makeRDD(List( ("a",1), ("b", 2), ("c", 3), ("d", 4) ),4)
val list: List[(String, Int)] = List(("a", 4), ("b", 5), ("c", 6), ("d", 7))
val broadcast: Broadcast[List[(String, Int)]] = sc.broadcast(list)
rdd.map{
case (key,num)=>{
var num2=0
for ((k,v) <- broadcast.value) {
if (k==key){
num2=v
}
}
(key,(num,num2))
}
}.collect().foreach(println)
}
}
执行日志
D:\Develop\Java\jdk1.8.0_202\bin\java.exe "-javaagent:D:\Programs\IntelliJ IDEA 2021.1.2\lib\idea_rt.jar=56164:D:\Programs\IntelliJ IDEA 2021.1.2\bin" -Dfile.encoding=UTF-8 -classpath D:\Develop\Java\jdk1.8.0_202\jre\lib\charsets.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\deploy.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\ext\access-bridge-64.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\ext\cldrdata.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\ext\dnsns.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\ext\jaccess.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\ext\jfxrt.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\ext\localedata.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\ext\nashorn.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\ext\sunec.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\ext\sunjce_provider.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\ext\sunmscapi.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\ext\sunpkcs11.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\ext\zipfs.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\javaws.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\jce.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\jfr.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\jfxswt.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\jsse.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\management-agent.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\plugin.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\resources.jar;D:\Develop\Java\jdk1.8.0_202\jre\lib\rt.jar;E:\Workspace\Spark\SparkDemo1\target\classes;D:\Develop\scala-2.12.13\lib\scala-library.jar;D:\Develop\scala-2.12.13\lib\scala-parser-combinators_2.12-1.0.7.jar;D:\Develop\scala-2.12.13\lib\scala-reflect.jar;D:\Develop\scala-2.12.13\lib\scala-swing_2.12-2.0.3.jar;D:\Develop\scala-2.12.13\lib\scala-xml_2.12-1.0.6.jar;E:\Repository\org\apache\spark\spark-core_2.12\3.1.1\spark-core_2.12-3.1.1.jar;E:\Repository\com\thoughtworks\paranamer\paranamer\2.8\paranamer-2.8.jar;E:\Repository\org\apache\avro\avro\1.8.2\avro-1.8.2.jar;E:\Repository\org\codehaus\jackson\jackson-core-asl\1.9.13\jackson-core-asl-1.9.13.jar;E:\Repository\org\codehaus\jackson\jackson-mapper-asl\1.9.13\jackson-mapper-asl-1.9.13.jar;E:\Repository\org\apache\commons\commons-compress\1.8.1\commons-compress-1.8.1.jar;E:\Repository\org\tukaani\xz\1.5\xz-1.5.jar;E:\Repository\org\apache\avro\avro-mapred\1.8.2\avro-mapred-1.8.2-hadoop2.jar;E:\Repository\org\apache\avro\avro-ipc\1.8.2\avro-ipc-1.8.2.jar;E:\Repository\commons-codec\commons-codec\1.9\commons-codec-1.9.jar;E:\Repository\com\twitter\chill_2.12\0.9.5\chill_2.12-0.9.5.jar;E:\Repository\com\esotericsoftware\kryo-shaded\4.0.2\kryo-shaded-4.0.2.jar;E:\Repository\com\esotericsoftware\minlog\1.3.0\minlog-1.3.0.jar;E:\Repository\org\objenesis\objenesis\2.5.1\objenesis-2.5.1.jar;E:\Repository\com\twitter\chill-java\0.9.5\chill-java-0.9.5.jar;E:\Repository\org\apache\xbean\xbean-asm7-shaded\4.15\xbean-asm7-shaded-4.15.jar;E:\Repository\org\apache\hadoop\hadoop-client\3.2.0\hadoop-client-3.2.0.jar;E:\Repository\org\apache\hadoop\hadoop-common\3.2.0\hadoop-common-3.2.0.jar;E:\Repository\org\apache\httpcomponents\httpclient\4.5.2\httpclient-4.5.2.jar;E:\Repository\org\apache\httpcomponents\httpcore\4.4.4\httpcore-4.4.4.jar;E:\Repository\commons-collections\commons-collections\3.2.2\commons-collections-3.2.2.jar;E:\Repository\org\eclipse\jetty\jetty-servlet\9.3.24.v20180605\jetty-servlet-9.3.24.v20180605.jar;E:\Repository\org\eclipse\jetty\jetty-security\9.3.24.v20180605\jetty-security-9.3.24.v20180605.jar;E:\Repository\javax\servlet\jsp\jsp-api\2.1\jsp-api-2.1.jar;E:\Repository\commons-beanutils\commons-beanutils\1.9.3\commons-beanutils-1.9.3.jar;E:\Repository\org\apache\commons\commons-configuration2\2.1.1\commons-configuration2-2.1.1.jar;E:\Repository\com\google\re2j\re2j\1.1\re2j-1.1.jar;E:\Repository\com\google\code\gson\gson\2.2.4\gson-2.2.4.jar;E:\Repository\org\apache\curator\curator-client\2.12.0\curator-client-2.12.0.jar;E:\Repository\org\apache\htrace\htrace-core4\4.1.0-incubating\htrace-core4-4.1.0-incubating.jar;E:\Repository\org\apache\kerby\kerb-simplekdc\1.0.1\kerb-simplekdc-1.0.1.jar;E:\Repository\org\apache\kerby\kerb-client\1.0.1\kerb-client-1.0.1.jar;E:\Repository\org\apache\kerby\kerby-config\1.0.1\kerby-config-1.0.1.jar;E:\Repository\org\apache\kerby\kerb-core\1.0.1\kerb-core-1.0.1.jar;E:\Repository\org\apache\kerby\kerby-pkix\1.0.1\kerby-pkix-1.0.1.jar;E:\Repository\org\apache\kerby\kerby-asn1\1.0.1\kerby-asn1-1.0.1.jar;E:\Repository\org\apache\kerby\kerby-util\1.0.1\kerby-util-1.0.1.jar;E:\Repository\org\apache\kerby\kerb-common\1.0.1\kerb-common-1.0.1.jar;E:\Repository\org\apache\kerby\kerb-crypto\1.0.1\kerb-crypto-1.0.1.jar;E:\Repository\org\apache\kerby\kerb-util\1.0.1\kerb-util-1.0.1.jar;E:\Repository\org\apache\kerby\token-provider\1.0.1\token-provider-1.0.1.jar;E:\Repository\org\apache\kerby\kerb-admin\1.0.1\kerb-admin-1.0.1.jar;E:\Repository\org\apache\kerby\kerb-server\1.0.1\kerb-server-1.0.1.jar;E:\Repository\org\apache\kerby\kerb-identity\1.0.1\kerb-identity-1.0.1.jar;E:\Repository\org\apache\kerby\kerby-xdr\1.0.1\kerby-xdr-1.0.1.jar;E:\Repository\org\codehaus\woodstox\stax2-api\3.1.4\stax2-api-3.1.4.jar;E:\Repository\com\fasterxml\woodstox\woodstox-core\5.0.3\woodstox-core-5.0.3.jar;E:\Repository\dnsjava\dnsjava\2.1.7\dnsjava-2.1.7.jar;E:\Repository\org\apache\hadoop\hadoop-hdfs-client\3.2.0\hadoop-hdfs-client-3.2.0.jar;E:\Repository\com\squareup\okhttp\okhttp\2.7.5\okhttp-2.7.5.jar;E:\Repository\com\squareup\okio\okio\1.6.0\okio-1.6.0.jar;E:\Repository\org\apache\hadoop\hadoop-mapreduce-client-core\3.2.0\hadoop-mapreduce-client-core-3.2.0.jar;E:\Repository\org\apache\hadoop\hadoop-mapreduce-client-jobclient\3.2.0\hadoop-mapreduce-client-jobclient-3.2.0.jar;E:\Repository\org\apache\hadoop\hadoop-mapreduce-client-common\3.2.0\hadoop-mapreduce-client-common-3.2.0.jar;E:\Repository\org\apache\hadoop\hadoop-annotations\3.2.0\hadoop-annotations-3.2.0.jar;E:\Repository\org\apache\spark\spark-launcher_2.12\3.1.1\spark-launcher_2.12-3.1.1.jar;E:\Repository\org\apache\spark\spark-kvstore_2.12\3.1.1\spark-kvstore_2.12-3.1.1.jar;E:\Repository\org\fusesource\leveldbjni\leveldbjni-all\1.8\leveldbjni-all-1.8.jar;E:\Repository\com\fasterxml\jackson\core\jackson-core\2.10.0\jackson-core-2.10.0.jar;E:\Repository\com\fasterxml\jackson\core\jackson-annotations\2.10.0\jackson-annotations-2.10.0.jar;E:\Repository\org\apache\spark\spark-network-common_2.12\3.1.1\spark-network-common_2.12-3.1.1.jar;E:\Repository\org\apache\spark\spark-network-shuffle_2.12\3.1.1\spark-network-shuffle_2.12-3.1.1.jar;E:\Repository\org\apache\spark\spark-unsafe_2.12\3.1.1\spark-unsafe_2.12-3.1.1.jar;E:\Repository\javax\activation\activation\1.1.1\activation-1.1.1.jar;E:\Repository\org\apache\curator\curator-recipes\2.13.0\curator-recipes-2.13.0.jar;E:\Repository\org\apache\curator\curator-framework\2.13.0\curator-framework-2.13.0.jar;E:\Repository\org\apache\zookeeper\zookeeper\3.4.14\zookeeper-3.4.14.jar;E:\Repository\org\apache\yetus\audience-annotations\0.5.0\audience-annotations-0.5.0.jar;E:\Repository\jakarta\servlet\jakarta.servlet-api\4.0.3\jakarta.servlet-api-4.0.3.jar;E:\Repository\org\apache\commons\commons-lang3\3.10\commons-lang3-3.10.jar;E:\Repository\org\apache\commons\commons-math3\3.4.1\commons-math3-3.4.1.jar;E:\Repository\org\apache\commons\commons-text\1.6\commons-text-1.6.jar;E:\Repository\com\google\code\findbugs\jsr305\3.0.0\jsr305-3.0.0.jar;E:\Repository\org\slf4j\slf4j-api\1.7.30\slf4j-api-1.7.30.jar;E:\Repository\org\slf4j\jul-to-slf4j\1.7.30\jul-to-slf4j-1.7.30.jar;E:\Repository\org\slf4j\jcl-over-slf4j\1.7.30\jcl-over-slf4j-1.7.30.jar;E:\Repository\log4j\log4j\1.2.17\log4j-1.2.17.jar;E:\Repository\org\slf4j\slf4j-log4j12\1.7.30\slf4j-log4j12-1.7.30.jar;E:\Repository\com\ning\compress-lzf\1.0.3\compress-lzf-1.0.3.jar;E:\Repository\org\xerial\snappy\snappy-java\1.1.8.2\snappy-java-1.1.8.2.jar;E:\Repository\org\lz4\lz4-java\1.7.1\lz4-java-1.7.1.jar;E:\Repository\com\github\luben\zstd-jni\1.4.8-1\zstd-jni-1.4.8-1.jar;E:\Repository\org\roaringbitmap\RoaringBitmap\0.9.0\RoaringBitmap-0.9.0.jar;E:\Repository\org\roaringbitmap\shims\0.9.0\shims-0.9.0.jar;E:\Repository\commons-net\commons-net\3.1\commons-net-3.1.jar;E:\Repository\org\scala-lang\modules\scala-xml_2.12\1.2.0\scala-xml_2.12-1.2.0.jar;E:\Repository\org\scala-lang\scala-library\2.12.10\scala-library-2.12.10.jar;E:\Repository\org\scala-lang\scala-reflect\2.12.10\scala-reflect-2.12.10.jar;E:\Repository\org\json4s\json4s-jackson_2.12\3.7.0-M5\json4s-jackson_2.12-3.7.0-M5.jar;E:\Repository\org\json4s\json4s-core_2.12\3.7.0-M5\json4s-core_2.12-3.7.0-M5.jar;E:\Repository\org\json4s\json4s-ast_2.12\3.7.0-M5\json4s-ast_2.12-3.7.0-M5.jar;E:\Repository\org\json4s\json4s-scalap_2.12\3.7.0-M5\json4s-scalap_2.12-3.7.0-M5.jar;E:\Repository\org\glassfish\jersey\core\jersey-client\2.30\jersey-client-2.30.jar;E:\Repository\jakarta\ws\rs\jakarta.ws.rs-api\2.1.6\jakarta.ws.rs-api-2.1.6.jar;E:\Repository\org\glassfish\hk2\external\jakarta.inject\2.6.1\jakarta.inject-2.6.1.jar;E:\Repository\org\glassfish\jersey\core\jersey-common\2.30\jersey-common-2.30.jar;E:\Repository\jakarta\annotation\jakarta.annotation-api\1.3.5\jakarta.annotation-api-1.3.5.jar;E:\Repository\org\glassfish\hk2\osgi-resource-locator\1.0.3\osgi-resource-locator-1.0.3.jar;E:\Repository\org\glassfish\jersey\core\jersey-server\2.30\jersey-server-2.30.jar;E:\Repository\org\glassfish\jersey\media\jersey-media-jaxb\2.30\jersey-media-jaxb-2.30.jar;E:\Repository\jakarta\validation\jakarta.validation-api\2.0.2\jakarta.validation-api-2.0.2.jar;E:\Repository\org\glassfish\jersey\containers\jersey-container-servlet\2.30\jersey-container-servlet-2.30.jar;E:\Repository\org\glassfish\jersey\containers\jersey-container-servlet-core\2.30\jersey-container-servlet-core-2.30.jar;E:\Repository\org\glassfish\jersey\inject\jersey-hk2\2.30\jersey-hk2-2.30.jar;E:\Repository\org\glassfish\hk2\hk2-locator\2.6.1\hk2-locator-2.6.1.jar;E:\Repository\org\glassfish\hk2\external\aopalliance-repackaged\2.6.1\aopalliance-repackaged-2.6.1.jar;E:\Repository\org\glassfish\hk2\hk2-api\2.6.1\hk2-api-2.6.1.jar;E:\Repository\org\glassfish\hk2\hk2-utils\2.6.1\hk2-utils-2.6.1.jar;E:\Repository\org\javassist\javassist\3.25.0-GA\javassist-3.25.0-GA.jar;E:\Repository\io\netty\netty-all\4.1.51.Final\netty-all-4.1.51.Final.jar;E:\Repository\com\clearspring\analytics\stream\2.9.6\stream-2.9.6.jar;E:\Repository\io\dropwizard\metrics\metrics-core\4.1.1\metrics-core-4.1.1.jar;E:\Repository\io\dropwizard\metrics\metrics-jvm\4.1.1\metrics-jvm-4.1.1.jar;E:\Repository\io\dropwizard\metrics\metrics-json\4.1.1\metrics-json-4.1.1.jar;E:\Repository\io\dropwizard\metrics\metrics-graphite\4.1.1\metrics-graphite-4.1.1.jar;E:\Repository\io\dropwizard\metrics\metrics-jmx\4.1.1\metrics-jmx-4.1.1.jar;E:\Repository\com\fasterxml\jackson\core\jackson-databind\2.10.0\jackson-databind-2.10.0.jar;E:\Repository\com\fasterxml\jackson\module\jackson-module-scala_2.12\2.10.0\jackson-module-scala_2.12-2.10.0.jar;E:\Repository\com\fasterxml\jackson\module\jackson-module-paranamer\2.10.0\jackson-module-paranamer-2.10.0.jar;E:\Repository\org\apache\ivy\ivy\2.4.0\ivy-2.4.0.jar;E:\Repository\oro\oro\2.0.8\oro-2.0.8.jar;E:\Repository\net\razorvine\pyrolite\4.30\pyrolite-4.30.jar;E:\Repository\net\sf\py4j\py4j\0.10.9\py4j-0.10.9.jar;E:\Repository\org\apache\spark\spark-tags_2.12\3.1.1\spark-tags_2.12-3.1.1.jar;E:\Repository\org\apache\commons\commons-crypto\1.1.0\commons-crypto-1.1.0.jar;E:\Repository\org\spark-project\spark\unused\1.0.0\unused-1.0.0.jar;E:\Repository\org\apache\spark\spark-sql_2.12\3.1.1\spark-sql_2.12-3.1.1.jar;E:\Repository\com\univocity\univocity-parsers\2.9.1\univocity-parsers-2.9.1.jar;E:\Repository\org\apache\spark\spark-sketch_2.12\3.1.1\spark-sketch_2.12-3.1.1.jar;E:\Repository\org\apache\spark\spark-catalyst_2.12\3.1.1\spark-catalyst_2.12-3.1.1.jar;E:\Repository\org\scala-lang\modules\scala-parser-combinators_2.12\1.1.2\scala-parser-combinators_2.12-1.1.2.jar;E:\Repository\org\codehaus\janino\janino\3.0.16\janino-3.0.16.jar;E:\Repository\org\codehaus\janino\commons-compiler\3.0.16\commons-compiler-3.0.16.jar;E:\Repository\org\antlr\antlr4-runtime\4.8-1\antlr4-runtime-4.8-1.jar;E:\Repository\org\apache\arrow\arrow-vector\2.0.0\arrow-vector-2.0.0.jar;E:\Repository\org\apache\arrow\arrow-format\2.0.0\arrow-format-2.0.0.jar;E:\Repository\org\apache\arrow\arrow-memory-core\2.0.0\arrow-memory-core-2.0.0.jar;E:\Repository\com\google\flatbuffers\flatbuffers-java\1.9.0\flatbuffers-java-1.9.0.jar;E:\Repository\org\apache\arrow\arrow-memory-netty\2.0.0\arrow-memory-netty-2.0.0.jar;E:\Repository\org\apache\orc\orc-core\1.5.12\orc-core-1.5.12.jar;E:\Repository\org\apache\orc\orc-shims\1.5.12\orc-shims-1.5.12.jar;E:\Repository\com\google\protobuf\protobuf-java\2.5.0\protobuf-java-2.5.0.jar;E:\Repository\commons-lang\commons-lang\2.6\commons-lang-2.6.jar;E:\Repository\io\airlift\aircompressor\0.10\aircompressor-0.10.jar;E:\Repository\org\threeten\threeten-extra\1.5.0\threeten-extra-1.5.0.jar;E:\Repository\org\apache\orc\orc-mapreduce\1.5.12\orc-mapreduce-1.5.12.jar;E:\Repository\org\apache\hive\hive-storage-api\2.7.2\hive-storage-api-2.7.2.jar;E:\Repository\org\apache\parquet\parquet-column\1.10.1\parquet-column-1.10.1.jar;E:\Repository\org\apache\parquet\parquet-common\1.10.1\parquet-common-1.10.1.jar;E:\Repository\org\apache\parquet\parquet-encoding\1.10.1\parquet-encoding-1.10.1.jar;E:\Repository\org\apache\parquet\parquet-hadoop\1.10.1\parquet-hadoop-1.10.1.jar;E:\Repository\org\apache\parquet\parquet-format\2.4.0\parquet-format-2.4.0.jar;E:\Repository\org\apache\parquet\parquet-jackson\1.10.1\parquet-jackson-1.10.1.jar;E:\Repository\org\apache\spark\spark-yarn_2.12\3.1.1\spark-yarn_2.12-3.1.1.jar;E:\Repository\org\apache\hadoop\hadoop-yarn-api\3.2.0\hadoop-yarn-api-3.2.0.jar;E:\Repository\com\google\guava\guava\11.0.2\guava-11.0.2.jar;E:\Repository\javax\xml\bind\jaxb-api\2.2.11\jaxb-api-2.2.11.jar;E:\Repository\org\apache\hadoop\hadoop-yarn-common\3.2.0\hadoop-yarn-common-3.2.0.jar;E:\Repository\org\apache\hadoop\hadoop-auth\3.2.0\hadoop-auth-3.2.0.jar;E:\Repository\com\nimbusds\nimbus-jose-jwt\4.41.1\nimbus-jose-jwt-4.41.1.jar;E:\Repository\com\github\stephenc\jcip\jcip-annotations\1.0-1\jcip-annotations-1.0-1.jar;E:\Repository\net\minidev\json-smart\2.3\json-smart-2.3.jar;E:\Repository\net\minidev\accessors-smart\1.2\accessors-smart-1.2.jar;E:\Repository\org\eclipse\jetty\jetty-util\9.3.24.v20180605\jetty-util-9.3.24.v20180605.jar;E:\Repository\commons-cli\commons-cli\1.2\commons-cli-1.2.jar;E:\Repository\com\google\inject\extensions\guice-servlet\4.0\guice-servlet-4.0.jar;E:\Repository\commons-io\commons-io\2.5\commons-io-2.5.jar;E:\Repository\com\google\inject\guice\4.0\guice-4.0.jar;E:\Repository\javax\inject\javax.inject\1\javax.inject-1.jar;E:\Repository\aopalliance\aopalliance\1.0\aopalliance-1.0.jar;E:\Repository\com\fasterxml\jackson\module\jackson-module-jaxb-annotations\2.9.5\jackson-module-jaxb-annotations-2.9.5.jar;E:\Repository\com\fasterxml\jackson\jaxrs\jackson-jaxrs-json-provider\2.9.5\jackson-jaxrs-json-provider-2.9.5.jar;E:\Repository\com\fasterxml\jackson\jaxrs\jackson-jaxrs-base\2.9.5\jackson-jaxrs-base-2.9.5.jar;E:\Repository\org\apache\hadoop\hadoop-yarn-server-web-proxy\3.2.0\hadoop-yarn-server-web-proxy-3.2.0.jar;E:\Repository\org\apache\hadoop\hadoop-yarn-server-common\3.2.0\hadoop-yarn-server-common-3.2.0.jar;E:\Repository\org\apache\hadoop\hadoop-yarn-registry\3.2.0\hadoop-yarn-registry-3.2.0.jar;E:\Repository\commons-daemon\commons-daemon\1.0.13\commons-daemon-1.0.13.jar;E:\Repository\org\apache\geronimo\specs\geronimo-jcache_1.0_spec\1.0-alpha-1\geronimo-jcache_1.0_spec-1.0-alpha-1.jar;E:\Repository\org\ehcache\ehcache\3.3.1\ehcache-3.3.1.jar;E:\Repository\org\eclipse\jetty\jetty-server\9.3.24.v20180605\jetty-server-9.3.24.v20180605.jar;E:\Repository\org\eclipse\jetty\jetty-http\9.3.24.v20180605\jetty-http-9.3.24.v20180605.jar;E:\Repository\org\eclipse\jetty\jetty-io\9.3.24.v20180605\jetty-io-9.3.24.v20180605.jar;E:\Repository\org\apache\hadoop\hadoop-yarn-client\3.2.0\hadoop-yarn-client-3.2.0.jar com.zxl.spark.core.BroadcastDemo
Using Spark's default log4j profile: org/apache/spark/log4j-defaults.properties
21/08/18 14:44:44 INFO SparkContext: Running Spark version 3.1.1
21/08/18 14:44:44 INFO ResourceUtils: ==============================================================
21/08/18 14:44:44 INFO ResourceUtils: No custom resources configured for spark.driver.
21/08/18 14:44:44 INFO ResourceUtils: ==============================================================
21/08/18 14:44:44 INFO SparkContext: Submitted application: BroadcastDemo
21/08/18 14:44:44 INFO ResourceProfile: Default ResourceProfile created, executor resources: Map(cores -> name: cores, amount: 1, script: , vendor: , memory -> name: memory, amount: 1024, script: , vendor: , offHeap -> name: offHeap, amount: 0, script: , vendor: ), task resources: Map(cpus -> name: cpus, amount: 1.0)
21/08/18 14:44:44 INFO ResourceProfile: Limiting resource is cpu
21/08/18 14:44:44 INFO ResourceProfileManager: Added ResourceProfile id: 0
21/08/18 14:44:44 INFO SecurityManager: Changing view acls to: 张学亮,ÕÅѧÁÁ
21/08/18 14:44:44 INFO SecurityManager: Changing modify acls to: 张学亮,ÕÅѧÁÁ
21/08/18 14:44:44 INFO SecurityManager: Changing view acls groups to:
21/08/18 14:44:44 INFO SecurityManager: Changing modify acls groups to:
21/08/18 14:44:44 INFO SecurityManager: SecurityManager: authentication disabled; ui acls disabled; users with view permissions: Set(张学亮, ÕÅѧÁÁ); groups with view permissions: Set(); users with modify permissions: Set(张学亮, ÕÅѧÁÁ); groups with modify permissions: Set()
21/08/18 14:44:45 INFO Utils: Successfully started service 'sparkDriver' on port 56188.
21/08/18 14:44:45 INFO SparkEnv: Registering MapOutputTracker
21/08/18 14:44:45 INFO SparkEnv: Registering BlockManagerMaster
21/08/18 14:44:45 INFO BlockManagerMasterEndpoint: Using org.apache.spark.storage.DefaultTopologyMapper for getting topology information
21/08/18 14:44:45 INFO BlockManagerMasterEndpoint: BlockManagerMasterEndpoint up
21/08/18 14:44:45 INFO SparkEnv: Registering BlockManagerMasterHeartbeat
21/08/18 14:44:45 INFO DiskBlockManager: Created local directory at C:\Users\zhang\AppData\Local\Temp\blockmgr-9d014bd5-0519-4a17-8982-462103a3e295
21/08/18 14:44:45 INFO MemoryStore: MemoryStore started with capacity 1987.5 MiB
21/08/18 14:44:45 INFO SparkEnv: Registering OutputCommitCoordinator
21/08/18 14:44:45 INFO Utils: Successfully started service 'SparkUI' on port 4040.
21/08/18 14:44:45 INFO SparkUI: Bound SparkUI to 0.0.0.0, and started at http://ZXLT:4040
21/08/18 14:44:46 INFO Executor: Starting executor ID driver on host ZXLT
21/08/18 14:44:46 INFO Utils: Successfully started service 'org.apache.spark.network.netty.NettyBlockTransferService' on port 56223.
21/08/18 14:44:46 INFO NettyBlockTransferService: Server created on ZXLT:56223
21/08/18 14:44:46 INFO BlockManager: Using org.apache.spark.storage.RandomBlockReplicationPolicy for block replication policy
21/08/18 14:44:46 INFO BlockManagerMaster: Registering BlockManager BlockManagerId(driver, ZXLT, 56223, None)
21/08/18 14:44:46 INFO BlockManagerMasterEndpoint: Registering block manager ZXLT:56223 with 1987.5 MiB RAM, BlockManagerId(driver, ZXLT, 56223, None)
21/08/18 14:44:46 INFO BlockManagerMaster: Registered BlockManager BlockManagerId(driver, ZXLT, 56223, None)
21/08/18 14:44:46 INFO BlockManager: Initialized BlockManager: BlockManagerId(driver, ZXLT, 56223, None)
21/08/18 14:44:46 INFO MemoryStore: Block broadcast_0 stored as values in memory (estimated size 488.0 B, free 1987.5 MiB)
21/08/18 14:44:46 INFO MemoryStore: Block broadcast_0_piece0 stored as bytes in memory (estimated size 326.0 B, free 1987.5 MiB)
21/08/18 14:44:46 INFO BlockManagerInfo: Added broadcast_0_piece0 in memory on ZXLT:56223 (size: 326.0 B, free: 1987.5 MiB)
21/08/18 14:44:46 INFO SparkContext: Created broadcast 0 from broadcast at BroadcastDemo.scala:13
21/08/18 14:44:46 INFO SparkContext: Starting job: collect at BroadcastDemo.scala:14
21/08/18 14:44:46 INFO DAGScheduler: Got job 0 (collect at BroadcastDemo.scala:14) with 4 output partitions
21/08/18 14:44:46 INFO DAGScheduler: Final stage: ResultStage 0 (collect at BroadcastDemo.scala:14)
21/08/18 14:44:46 INFO DAGScheduler: Parents of final stage: List()
21/08/18 14:44:46 INFO DAGScheduler: Missing parents: List()
21/08/18 14:44:46 INFO DAGScheduler: Submitting ResultStage 0 (MapPartitionsRDD[1] at map at BroadcastDemo.scala:14), which has no missing parents
21/08/18 14:44:46 INFO MemoryStore: Block broadcast_1 stored as values in memory (estimated size 3.5 KiB, free 1987.5 MiB)
21/08/18 14:44:46 INFO MemoryStore: Block broadcast_1_piece0 stored as bytes in memory (estimated size 2013.0 B, free 1987.5 MiB)
21/08/18 14:44:46 INFO BlockManagerInfo: Added broadcast_1_piece0 in memory on ZXLT:56223 (size: 2013.0 B, free: 1987.5 MiB)
21/08/18 14:44:46 INFO SparkContext: Created broadcast 1 from broadcast at DAGScheduler.scala:1383
21/08/18 14:44:46 INFO DAGScheduler: Submitting 4 missing tasks from ResultStage 0 (MapPartitionsRDD[1] at map at BroadcastDemo.scala:14) (first 15 tasks are for partitions Vector(0, 1, 2, 3))
21/08/18 14:44:46 INFO TaskSchedulerImpl: Adding task set 0.0 with 4 tasks resource profile 0
21/08/18 14:44:46 INFO TaskSetManager: Starting task 0.0 in stage 0.0 (TID 0) (ZXLT, executor driver, partition 0, PROCESS_LOCAL, 4508 bytes) taskResourceAssignments Map()
21/08/18 14:44:46 INFO TaskSetManager: Starting task 1.0 in stage 0.0 (TID 1) (ZXLT, executor driver, partition 1, PROCESS_LOCAL, 4508 bytes) taskResourceAssignments Map()
21/08/18 14:44:46 INFO TaskSetManager: Starting task 2.0 in stage 0.0 (TID 2) (ZXLT, executor driver, partition 2, PROCESS_LOCAL, 4508 bytes) taskResourceAssignments Map()
21/08/18 14:44:46 INFO TaskSetManager: Starting task 3.0 in stage 0.0 (TID 3) (ZXLT, executor driver, partition 3, PROCESS_LOCAL, 4508 bytes) taskResourceAssignments Map()
21/08/18 14:44:46 INFO Executor: Running task 1.0 in stage 0.0 (TID 1)
21/08/18 14:44:46 INFO Executor: Running task 3.0 in stage 0.0 (TID 3)
21/08/18 14:44:46 INFO Executor: Running task 2.0 in stage 0.0 (TID 2)
21/08/18 14:44:46 INFO Executor: Running task 0.0 in stage 0.0 (TID 0)
21/08/18 14:44:46 INFO Executor: Finished task 0.0 in stage 0.0 (TID 0). 1063 bytes result sent to driver
21/08/18 14:44:46 INFO Executor: Finished task 2.0 in stage 0.0 (TID 2). 1063 bytes result sent to driver
21/08/18 14:44:46 INFO Executor: Finished task 1.0 in stage 0.0 (TID 1). 1063 bytes result sent to driver
21/08/18 14:44:46 INFO Executor: Finished task 3.0 in stage 0.0 (TID 3). 1063 bytes result sent to driver
21/08/18 14:44:46 INFO TaskSetManager: Finished task 2.0 in stage 0.0 (TID 2) in 265 ms on ZXLT (executor driver) (1/4)
21/08/18 14:44:46 INFO TaskSetManager: Finished task 0.0 in stage 0.0 (TID 0) in 288 ms on ZXLT (executor driver) (2/4)
21/08/18 14:44:46 INFO TaskSetManager: Finished task 3.0 in stage 0.0 (TID 3) in 267 ms on ZXLT (executor driver) (3/4)
21/08/18 14:44:46 INFO TaskSetManager: Finished task 1.0 in stage 0.0 (TID 1) in 268 ms on ZXLT (executor driver) (4/4)
21/08/18 14:44:46 INFO TaskSchedulerImpl: Removed TaskSet 0.0, whose tasks have all completed, from pool
21/08/18 14:44:46 INFO DAGScheduler: ResultStage 0 (collect at BroadcastDemo.scala:14) finished in 0.339 s
21/08/18 14:44:46 INFO DAGScheduler: Job 0 is finished. Cancelling potential speculative or zombie tasks for this job
21/08/18 14:44:46 INFO TaskSchedulerImpl: Killing all running tasks in stage 0: Stage finished
21/08/18 14:44:46 INFO DAGScheduler: Job 0 finished: collect at BroadcastDemo.scala:14, took 0.387019 s
(a,(1,4))
(b,(2,5))
(c,(3,6))
(d,(4,7))
21/08/18 14:44:47 INFO SparkContext: Invoking stop() from shutdown hook
21/08/18 14:44:47 INFO SparkUI: Stopped Spark web UI at http://ZXLT:4040
21/08/18 14:44:47 INFO BlockManagerInfo: Removed broadcast_1_piece0 on ZXLT:56223 in memory (size: 2013.0 B, free: 1987.5 MiB)
21/08/18 14:44:47 INFO MapOutputTrackerMasterEndpoint: MapOutputTrackerMasterEndpoint stopped!
21/08/18 14:44:47 INFO MemoryStore: MemoryStore cleared
21/08/18 14:44:47 INFO BlockManager: BlockManager stopped
21/08/18 14:44:47 INFO BlockManagerMaster: BlockManagerMaster stopped
21/08/18 14:44:47 INFO OutputCommitCoordinator$OutputCommitCoordinatorEndpoint: OutputCommitCoordinator stopped!
21/08/18 14:44:47 INFO SparkContext: Successfully stopped SparkContext
21/08/18 14:44:47 INFO ShutdownHookManager: Shutdown hook called
21/08/18 14:44:47 INFO ShutdownHookManager: Deleting directory C:\Users\zhang\AppData\Local\Temp\spark-5620def7-287d-406e-8806-49265b19bf44
Process finished with exit code 0