package core.java;
import java.util.Arrays;
import java.util.List; import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaSparkContext; import scala.Tuple2; public class JGroupByKey {
public static void main(String[] args) {
SparkConf conf = new SparkConf();
conf.setMaster("local");
conf.setAppName("union");
System.setProperty("hadoop.home.dir", "C:/hadoop-2.8.2");
JavaSparkContext sc = new JavaSparkContext(conf);
List<Tuple2<String, Integer>> list = Arrays.asList(new Tuple2<String, Integer>("cl1", ),
new Tuple2<String, Integer>("cl2", ),new Tuple2<String, Integer>("cl3", ),
new Tuple2<String, Integer>("cl1", ),new Tuple2<String, Integer>("cl1", ),
new Tuple2<String, Integer>("cl3", ),new Tuple2<String, Integer>("cl2", ));
JavaPairRDD<String, Integer> listRDD = sc.parallelizePairs(list);
JavaPairRDD<String, Iterable<Integer>> results = listRDD.groupByKey();
System.out.println(results.collect());
sc.close();
}
} //SLF4J: Class path contains multiple SLF4J bindings.
//SLF4J: Found binding in [jar:file:/E:/bigdata/spark-1.4.0-bin-hadoop2.6/lib/spark-assembly-1.4.0-hadoop2.6.0.jar!/org/slf4j/impl/StaticLoggerBinder.class]
//SLF4J: Found binding in [jar:file:/E:/bigdata/spark-1.4.0-bin-hadoop2.6/lib/spark-examples-1.4.0-hadoop2.6.0.jar!/org/slf4j/impl/StaticLoggerBinder.class]
//SLF4J: See http://www.slf4j.org/codes.html#multiple_bindings for an explanation.
//SLF4J: Actual binding is of type [org.slf4j.impl.Log4jLoggerFactory]
//Using Spark's default log4j profile: org/apache/spark/log4j-defaults.properties
//17/12/27 20:23:41 INFO SparkContext: Running Spark version 1.4.0
//17/12/27 20:23:43 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
//17/12/27 20:23:44 INFO SecurityManager: Changing view acls to:
//17/12/27 20:23:44 INFO SecurityManager: Changing modify acls to:
//17/12/27 20:23:44 INFO SecurityManager: SecurityManager: authentication disabled; ui acls disabled; users with view permissions: Set(); users with modify permissions: Set()
//17/12/27 20:23:46 INFO Slf4jLogger: Slf4jLogger started
//17/12/27 20:23:47 INFO Remoting: Starting remoting
//17/12/27 20:23:48 INFO Remoting: Remoting started; listening on addresses :[akka.tcp://sparkDriver@172.18.3.6:58955]
//17/12/27 20:23:48 INFO Utils: Successfully started service 'sparkDriver' on port 58955.
//17/12/27 20:23:48 INFO SparkEnv: Registering MapOutputTracker
//17/12/27 20:23:49 INFO SparkEnv: Registering BlockManagerMaster
//17/12/27 20:23:49 INFO DiskBlockManager: Created local directory at C:\Users\\AppData\Local\Temp\spark-c1db5ccf-8e4b-4ef9-9a7f-c6ec66d46664\blockmgr-a60ebb60-8b7c-433c-b035-eded748b261b
//17/12/27 20:23:49 INFO MemoryStore: MemoryStore started with capacity 467.6 MB
//17/12/27 20:23:49 INFO HttpFileServer: HTTP File server directory is C:\Users\\AppData\Local\Temp\spark-c1db5ccf-8e4b-4ef9-9a7f-c6ec66d46664\httpd-f45db3a6-b75c-46a5-a1d1-3539b1698cd0
//17/12/27 20:23:49 INFO HttpServer: Starting HTTP Server
//17/12/27 20:23:49 INFO Utils: Successfully started service 'HTTP file server' on port 58959.
//17/12/27 20:23:49 INFO SparkEnv: Registering OutputCommitCoordinator
//17/12/27 20:23:50 WARN Utils: Service 'SparkUI' could not bind on port 4040. Attempting port 4041.
//17/12/27 20:23:50 INFO Utils: Successfully started service 'SparkUI' on port 4041.
//17/12/27 20:23:50 INFO SparkUI: Started SparkUI at http://172.18.3.6:4041
//17/12/27 20:23:50 INFO Executor: Starting executor ID driver on host localhost
//17/12/27 20:23:51 INFO Utils: Successfully started service 'org.apache.spark.network.netty.NettyBlockTransferService' on port 58978.
//17/12/27 20:23:51 INFO NettyBlockTransferService: Server created on 58978
//17/12/27 20:23:51 INFO BlockManagerMaster: Trying to register BlockManager
//17/12/27 20:23:51 INFO BlockManagerMasterEndpoint: Registering block manager localhost:58978 with 467.6 MB RAM, BlockManagerId(driver, localhost, 58978)
//17/12/27 20:23:51 INFO BlockManagerMaster: Registered BlockManager
//17/12/27 20:23:57 INFO SparkContext: Starting job: collect at JGroupByKey.java:27
//17/12/27 20:23:57 INFO DAGScheduler: Registering RDD 0 (parallelizePairs at JGroupByKey.java:25)
//17/12/27 20:23:57 INFO DAGScheduler: Got job 0 (collect at JGroupByKey.java:27) with 1 output partitions (allowLocal=false)
//17/12/27 20:23:57 INFO DAGScheduler: Final stage: ResultStage 1(collect at JGroupByKey.java:27)
//17/12/27 20:23:57 INFO DAGScheduler: Parents of final stage: List(ShuffleMapStage 0)
//17/12/27 20:23:57 INFO DAGScheduler: Missing parents: List(ShuffleMapStage 0)
//17/12/27 20:23:57 INFO DAGScheduler: Submitting ShuffleMapStage 0 (ParallelCollectionRDD[0] at parallelizePairs at JGroupByKey.java:25), which has no missing parents
//17/12/27 20:23:58 INFO MemoryStore: ensureFreeSpace(2832) called with curMem=0, maxMem=490356080
//17/12/27 20:23:58 INFO MemoryStore: Block broadcast_0 stored as values in memory (estimated size 2.8 KB, free 467.6 MB)
//17/12/27 20:23:58 INFO MemoryStore: ensureFreeSpace(1553) called with curMem=2832, maxMem=490356080
//17/12/27 20:23:58 INFO MemoryStore: Block broadcast_0_piece0 stored as bytes in memory (estimated size 1553.0 B, free 467.6 MB)
//17/12/27 20:23:58 INFO BlockManagerInfo: Added broadcast_0_piece0 in memory on localhost:58978 (size: 1553.0 B, free: 467.6 MB)
//17/12/27 20:23:58 INFO SparkContext: Created broadcast 0 from broadcast at DAGScheduler.scala:874
//17/12/27 20:23:58 INFO DAGScheduler: Submitting 1 missing tasks from ShuffleMapStage 0 (ParallelCollectionRDD[0] at parallelizePairs at JGroupByKey.java:25)
//17/12/27 20:23:58 INFO TaskSchedulerImpl: Adding task set 0.0 with 1 tasks
//17/12/27 20:23:58 INFO TaskSetManager: Starting task 0.0 in stage 0.0 (TID 0, localhost, PROCESS_LOCAL, 1627 bytes)
//17/12/27 20:23:58 INFO Executor: Running task 0.0 in stage 0.0 (TID 0)
//17/12/27 20:23:58 INFO Executor: Finished task 0.0 in stage 0.0 (TID 0). 879 bytes result sent to driver
//17/12/27 20:23:58 INFO TaskSetManager: Finished task 0.0 in stage 0.0 (TID 0) in 427 ms on localhost (1/1)
//17/12/27 20:23:58 INFO TaskSchedulerImpl: Removed TaskSet 0.0, whose tasks have all completed, from pool
//17/12/27 20:23:58 INFO DAGScheduler: ShuffleMapStage 0 (parallelizePairs at JGroupByKey.java:25) finished in 0.559 s
//17/12/27 20:23:58 INFO DAGScheduler: looking for newly runnable stages
//17/12/27 20:23:58 INFO DAGScheduler: running: Set()
//17/12/27 20:23:58 INFO DAGScheduler: waiting: Set(ResultStage 1)
//17/12/27 20:23:58 INFO DAGScheduler: failed: Set()
//17/12/27 20:23:58 INFO DAGScheduler: Missing parents for ResultStage 1: List()
//17/12/27 20:23:58 INFO DAGScheduler: Submitting ResultStage 1 (MapPartitionsRDD[2] at groupByKey at JGroupByKey.java:26), which is now runnable
//17/12/27 20:23:58 INFO MemoryStore: ensureFreeSpace(4000) called with curMem=4385, maxMem=490356080
//17/12/27 20:23:58 INFO MemoryStore: Block broadcast_1 stored as values in memory (estimated size 3.9 KB, free 467.6 MB)
//17/12/27 20:23:58 INFO MemoryStore: ensureFreeSpace(2129) called with curMem=8385, maxMem=490356080
//17/12/27 20:23:58 INFO MemoryStore: Block broadcast_1_piece0 stored as bytes in memory (estimated size 2.1 KB, free 467.6 MB)
//17/12/27 20:23:58 INFO BlockManagerInfo: Added broadcast_1_piece0 in memory on localhost:58978 (size: 2.1 KB, free: 467.6 MB)
//17/12/27 20:23:58 INFO SparkContext: Created broadcast 1 from broadcast at DAGScheduler.scala:874
//17/12/27 20:23:58 INFO DAGScheduler: Submitting 1 missing tasks from ResultStage 1 (MapPartitionsRDD[2] at groupByKey at JGroupByKey.java:26)
//17/12/27 20:23:58 INFO TaskSchedulerImpl: Adding task set 1.0 with 1 tasks
//17/12/27 20:23:58 INFO TaskSetManager: Starting task 0.0 in stage 1.0 (TID 1, localhost, PROCESS_LOCAL, 1165 bytes)
//17/12/27 20:23:58 INFO Executor: Running task 0.0 in stage 1.0 (TID 1)
//17/12/27 20:23:59 INFO ShuffleBlockFetcherIterator: Getting 1 non-empty blocks out of 1 blocks
//17/12/27 20:23:59 INFO ShuffleBlockFetcherIterator: Started 0 remote fetches in 57 ms
//17/12/27 20:23:59 INFO Executor: Finished task 0.0 in stage 1.0 (TID 1). 5294 bytes result sent to driver
//17/12/27 20:23:59 INFO TaskSetManager: Finished task 0.0 in stage 1.0 (TID 1) in 231 ms on localhost (1/1)
//17/12/27 20:23:59 INFO TaskSchedulerImpl: Removed TaskSet 1.0, whose tasks have all completed, from pool
//17/12/27 20:23:59 INFO DAGScheduler: ResultStage 1 (collect at JGroupByKey.java:27) finished in 0.236 s
//17/12/27 20:23:59 INFO DAGScheduler: Job 0 finished: collect at JGroupByKey.java:27, took 1.963917 s
//[(cl3,[97, 90]), (cl1,[90, 96, 89]), (cl2,[91, 60])]
//17/12/27 20:23:59 INFO SparkUI: Stopped Spark web UI at http://172.18.3.6:4041
//17/12/27 20:23:59 INFO DAGScheduler: Stopping DAGScheduler
//17/12/27 20:23:59 INFO MapOutputTrackerMasterEndpoint: MapOutputTrackerMasterEndpoint stopped!
//17/12/27 20:23:59 INFO Utils: path = C:\Users\\AppData\Local\Temp\spark-c1db5ccf-8e4b-4ef9-9a7f-c6ec66d46664\blockmgr-a60ebb60-8b7c-433c-b035-eded748b261b, already present as root for deletion.
//17/12/27 20:23:59 INFO MemoryStore: MemoryStore cleared
//17/12/27 20:23:59 INFO BlockManager: BlockManager stopped
//17/12/27 20:23:59 INFO BlockManagerMaster: BlockManagerMaster stopped
//17/12/27 20:23:59 INFO OutputCommitCoordinator$OutputCommitCoordinatorEndpoint: OutputCommitCoordinator stopped!
//17/12/27 20:23:59 INFO SparkContext: Successfully stopped SparkContext
//17/12/27 20:23:59 INFO RemoteActorRefProvider$RemotingTerminator: Shutting down remote daemon.
//17/12/27 20:23:59 INFO RemoteActorRefProvider$RemotingTerminator: Remote daemon shut down; proceeding with flushing remote transports.
//17/12/27 20:23:59 INFO Utils: Shutdown hook called
//17/12/27 20:23:59 INFO Utils: Deleting directory C:\Users\\AppData\Local\Temp\spark-c1db5ccf-8e4b-4ef9-9a7f-c6ec66d46664

Spark_JGroupByKey的更多相关文章

随机推荐

  1. vsCode配置C++调试环境

    1.下载安装VSCode,安装mscpptools ,直接搜索c++,或者mscpptools 2.下载MinGW 安装好,一般默认安装到C:\MinGW 安装好后直接启动. 选择需要的gcc ,g+ ...

  2. 确界原理 supremum and infimum principle 戴德金定理 Dedekind theorem

    确界原理  supremum and infimum principle  戴德金定理  Dedekind theorem http://www.math.ubc.ca/~cass/courses/m ...

  3. [skill][funny] 一个很厉害的for循环

    int DSSL_MoveServerToMissingKeyList( DSSL_Env* env, DSSL_ServerInfo* si ) { DSSL_ServerInfo** new_se ...

  4. python server

    #!/usr/bin/env python #coding=utf-8 # modifyDate: 20120808 ~ 20120810 # 原作者为:bones7456, http://li2z. ...

  5. 贪吃蛇java版

    主要的蛇的类 import java.awt.Color; import java.awt.Graphics; import java.awt.HeadlessException; import ja ...

  6. oracle中并行执行不一定比串行执行快

    并行执行与串行执行相比,能否缩短执行时间,取决于如下几个方面:1.待执行的目标SQL是否适合并行执行,有些SQL是不太适合并行执行的,比如走索引的嵌套循环连接.2.数据库服务器上的硬件资源(如CPU. ...

  7. 【Mock】【接口测试】【面试】mock-server 环境搭建—加分项!

    mock-server 环境搭建 前言 mock 除了用在单元测试过程中,还有一个用途,当前端开发在开发页面的需要服务端提供 API 接口 此时服务端没开发完成,或者说没搭建测试环境,这个时候前端开发 ...

  8. linux dmesg 查看系统故障信息

    dmesg 可以查看linux 内核信息 dmesg’命令设备故障的诊断是非常重要的.在‘dmesg’命令的帮助下进行硬件的连接或断开连接操作时,我们可以看到硬件的检测或者断开连接的信息.‘dmesg ...

  9. centos安装卸载Postgresql数据库PGSQL10

    这几天ytkah正在测试Odoo,而Odoo12一定要PGSQL10否则安装数据库的时候会出错,所以就直接安装gpsql10.首先卸载旧版本postgresql yum remove postgres ...

  10. 20181017 PL/SQL 记录

    1. 配置DB 链接文件,帮助中找到tnsnames.ora文件路径,进行注册数据库信息,登陆即可. 这只是个客户端,具体服务器段数据库情况不清楚. 2.写法区别PL/SQL 和SQL 变量定义 赋值 ...