配置文件的加载是一个难点,在local模式下非常容易,但是submit后一直报找不到文件,后来采用将properties文件放在加载类同一个package下,打包到同一个jar中解决。

import java.io.{BufferedInputStream , InputStream}
import java.util.Properties /**
* Created by wulei on 2018/4/4.
* Description: 参数初始化公共类
*/
object InitPropertiesUtil extends Serializable {
/**
* get kafka's properties
* @return java.util.Properties
*/
def initKafkaPro: Properties = {
val prop: Properties = new Properties
val in: InputStream = getClass.getResourceAsStream("conf/kafka.properties")
if (in == null){
println("ERROR : kafka.properties init failed in is null")
}
prop.load(new BufferedInputStream(in))
prop
} /**
* get redis's properties
* @return java.util.Properties
*/
def initRedisPro: Properties = {
val prop: Properties = new Properties
val in: InputStream = getClass.getResourceAsStream("conf/redis.properties")
prop.load(new BufferedInputStream(in))
prop
}
}

问题: ClassNotFoundException: org.apache.hadoop.hbase.ipc.controller.ClientRpcControllerFactory

java.lang.RuntimeException: java.sql.SQLException: ERROR 103 (08004): Unable to establish connection.
at nl.work.kafkastreamconsumer.phoenix.PhoenixConnection.<init>(PhoenixConnection.java:41)
at nl.work.kafkastreamconsumer.phoenix.LinePersister$1.call(LinePersister.java:40)
at nl.work.kafkastreamconsumer.phoenix.LinePersister$1.call(LinePersister.java:32)
at org.apache.spark.api.java.JavaPairRDD$$anonfun$toScalaFunction$1.apply(JavaPairRDD.scala:999)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at org.apache.spark.rdd.RDD$$anonfun$17.apply(RDD.scala:813)
at org.apache.spark.rdd.RDD$$anonfun$17.apply(RDD.scala:813)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1498)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1498)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
at org.apache.spark.scheduler.Task.run(Task.scala:64)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:203)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.sql.SQLException: ERROR 103 (08004): Unable to establish connection.
at org.apache.phoenix.exception.SQLExceptionCode$Factory$1.newException(SQLExceptionCode.java:362)
at org.apache.phoenix.exception.SQLExceptionInfo.buildException(SQLExceptionInfo.java:133)
at org.apache.phoenix.query.ConnectionQueryServicesImpl.openConnection(ConnectionQueryServicesImpl.java:282)
at org.apache.phoenix.query.ConnectionQueryServicesImpl.access$300(ConnectionQueryServicesImpl.java:166)
at org.apache.phoenix.query.ConnectionQueryServicesImpl$11.call(ConnectionQueryServicesImpl.java:1831)
at org.apache.phoenix.query.ConnectionQueryServicesImpl$11.call(ConnectionQueryServicesImpl.java:1810)
at org.apache.phoenix.util.PhoenixContextExecutor.call(PhoenixContextExecutor.java:77)
at org.apache.phoenix.query.ConnectionQueryServicesImpl.init(ConnectionQueryServicesImpl.java:1810)
at org.apache.phoenix.jdbc.PhoenixDriver.getConnectionQueryServices(PhoenixDriver.java:162)
at org.apache.phoenix.jdbc.PhoenixEmbeddedDriver.connect(PhoenixEmbeddedDriver.java:126)
at org.apache.phoenix.jdbc.PhoenixDriver.connect(PhoenixDriver.java:133)
at java.sql.DriverManager.getConnection(DriverManager.java:571)
at java.sql.DriverManager.getConnection(DriverManager.java:233)
at nl.work.kafkastreamconsumer.phoenix.PhoenixConnection.<init>(PhoenixConnection.java:39)
... 25 more
Caused by: java.io.IOException: java.lang.reflect.InvocationTargetException
at org.apache.hadoop.hbase.client.HConnectionManager.createConnection(HConnectionManager.java:457)
at org.apache.hadoop.hbase.client.HConnectionManager.createConnection(HConnectionManager.java:350)
at org.apache.phoenix.query.HConnectionFactory$HConnectionFactoryImpl.createConnection(HConnectionFactory.java:47)
at org.apache.phoenix.query.ConnectionQueryServicesImpl.openConnection(ConnectionQueryServicesImpl.java:280)
... 36 more
Caused by: java.lang.reflect.InvocationTargetException
at sun.reflect.GeneratedConstructorAccessor8.newInstance(Unknown Source)
at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:526)
at org.apache.hadoop.hbase.client.HConnectionManager.createConnection(HConnectionManager.java:455)
... 39 more
Caused by: java.lang.UnsupportedOperationException: Unable to find org.apache.hadoop.hbase.ipc.controller.ClientRpcControllerFactory
at org.apache.hadoop.hbase.util.ReflectionUtils.instantiateWithCustomCtor(ReflectionUtils.java:36)
at org.apache.hadoop.hbase.ipc.RpcControllerFactory.instantiate(RpcControllerFactory.java:56)
at org.apache.hadoop.hbase.client.HConnectionManager$HConnectionImplementation.<init>(HConnectionManager.java:769)
at org.apache.hadoop.hbase.client.HConnectionManager$HConnectionImplementation.<init>(HConnectionManager.java:689)
... 43 more
Caused by: java.lang.ClassNotFoundException: org.apache.hadoop.hbase.ipc.controller.ClientRpcControllerFactory
at java.net.URLClassLoader$1.run(URLClassLoader.java:366)
at java.net.URLClassLoader$1.run(URLClassLoader.java:355)
at java.security.AccessController.doPrivileged(Native Method)
at java.net.URLClassLoader.findClass(URLClassLoader.java:354)
at java.lang.ClassLoader.loadClass(ClassLoader.java:425)
at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:308)
at java.lang.ClassLoader.loadClass(ClassLoader.java:358)
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:191)
at org.apache.hadoop.hbase.util.ReflectionUtils.instantiateWithCustomCtor(ReflectionUtils.java:32)
... 46 more

追踪ClientRpcControllerFactory这个类,将会发现是phoenix-core-4.4.0-HBase-1.0.jar中的,根据报错信息,可以知道也确实HBase的连接出现问题,于是我第一步去找是否将phoenix-core-4.4.0-HBase-1.0.jar这个包拷贝到Spark Client下,有的,

第二,我去找自己的spark-submit jars命令中是否对该包的引用有误,比如路径、逗号符号等,错误依然不在此。嗯! 放弃思考,已超出自己的理解范围了,马上在stackoverflow上找到这个原生Bug

I had have same problem. The reason of problem,Phoenix use a custom rpc controller factory which is a Phoenix-specific one to configure the priorities for index and system catalog table in cluster side. It is called ClientRpcControllerFactory.

In sometimes Phoenix-enabled clusters are used from pure-HBase client applications resulting in ClassNotFoundExceptions in application code or MapReduce jobs. Since hbase configuration is shared between Phoenix-clients and HBase clients, having different configurations at the client side is hard. That's why you get this exception. This problem is fixed by HBASE-14960. If you hbase version older than 2.0.0, 1.2.0, 1.3.0, 0.98.17 You can define your client side rpc controller with this setting in hbase-site.xml:

  <property>
<name>hbase.rpc.controllerfactory.class</name>
<value>org.apache.hadoop.hbase.ipc.RpcControllerFactory</value>
</property>

Streaming从Spark2X迁移到Spark1.5 summary的更多相关文章

  1. 转:FSMT:文件服务器从03迁移到08R2实战演练

    另外参见:http://www.canway.net/Lists/CanwayOriginalArticels/DispForm.aspx?ID=282 以前做过一个项目,是把文件服务器从03升级到0 ...

  2. 【大数据处理架构】1.spark streaming

    1. spark 是什么? >Apache Spark 是一个类似hadoop的开源高速集群运算环境  与后者不同的是,spark更快(官方的说法是快近100倍).提供高层JAVA,Scala, ...

  3. 【开源】OSharp框架解说系列(5.2):EntityFramework数据层实现

    OSharp是什么? OSharp是个快速开发框架,但不是一个大而全的包罗万象的框架,严格的说,OSharp中什么都没有实现.与其他大而全的框架最大的不同点,就是OSharp只做抽象封装,不做实现.依 ...

  4. 【转】最近搞Hadoop集群迁移踩的坑杂记

    http://ju.outofmemory.cn/entry/237491 Overview 最近一段时间都在搞集群迁移.最早公司的hadoop数据集群实在阿里云上的,机器不多,大概4台的样子,据说每 ...

  5. How Cigna Tuned Its Spark Streaming App for Real-time Processing with Apache Kafka

    Explore the configuration changes that Cigna’s Big Data Analytics team has made to optimize the perf ...

  6. 浅议Grpc传输机制和WCF中的回调机制的代码迁移

    浅议Grpc传输机制和WCF中的回调机制的代码迁移 一.引子 如您所知,gRPC是目前比较常见的rpc框架,可以方便的作为服务与服务之间的通信基础设施,为构建微服务体系提供非常强有力的支持. 而基于. ...

  7. Spark踩坑记——Spark Streaming+Kafka

    [TOC] 前言 在WeTest舆情项目中,需要对每天千万级的游戏评论信息进行词频统计,在生产者一端,我们将数据按照每天的拉取时间存入了Kafka当中,而在消费者一端,我们利用了spark strea ...

  8. Spark Streaming+Kafka

    Spark Streaming+Kafka 前言 在WeTest舆情项目中,需要对每天千万级的游戏评论信息进行词频统计,在生产者一端,我们将数据按照每天的拉取时间存入了Kafka当中,而在消费者一端, ...

  9. Spark入门实战系列--7.Spark Streaming(上)--实时流计算Spark Streaming原理介绍

    [注]该系列文章以及使用到安装包/测试数据 可以在<倾情大奉送--Spark入门实战系列>获取 .Spark Streaming简介 1.1 概述 Spark Streaming 是Spa ...

随机推荐

  1. vue 版本升级配置修改

  2. 解决Chrome 70版本以后谷歌不再信任赛门铁克证书问题

    Google 从 2018 年 10 月发布的 Chrome 70 就停止信任赛门铁克的旧证书了,而 Mozilla 也将在 10 月底发布 Firefox 63 时停止信任赛门铁克的旧证书. 导致大 ...

  3. fiddler 中显示请求 IP

    在 Rules -> Customize Rules... 中,static function Main() 中加一行 FiddlerObject.UI.lvSessions.AddBoundC ...

  4. Python学习笔记——发邮件

    参考:Python3实现163邮箱SMTP发送邮件 1.首先需要注册一个网易的邮箱,开启smtp服务,并使用其授权码 2.发送邮件的Python脚本 #!/usr/bin/python # -*- c ...

  5. Redis 数据结构的实现

    Redis 数据结构的实现 先看个对照关系: Redis数据结构 实现一 实现二 string 整数(如果value能够表示为整数) 字符串 hash 压缩列表(只包含少量键值对, 并且每个键值对的键 ...

  6. Java接口的幂等性设计

    转载:https://www.cnblogs.com/jack87224088/p/8688948.html 在微服务架构下,我们在完成一个订单流程时经常遇到下面的场景: 一个订单创建接口,第一次调用 ...

  7. Django 跨域问题

    当使用Django 做接口时,被html5 或者app访问时 存在跨域问题 导致无法请求到数据,具体解决办法如下: 跨域问题解决 安装pip install django-cors-headers修改 ...

  8. Nginx 反向代理获取设备真实的IP地址

    package com.das.common.util; import org.apache.commons.lang3.StringUtils; import org.springframework ...

  9. C# StackExchange.Redis 用法总结

    安装 StackExchange.Redis 在 NuGet 中搜索 StackExchange.Redis 和 Newtonsoft.Json,直接点击按钮安装即可. StackExchange.R ...

  10. MQTT 嵌入式端通讯协议解析(转)

    MQTT,目前物联网的最主要的协议,基本所有收费的云平台都是基于MQTT协议,比如机智云,和所有的开放云平台比如中国移动的oneNet.百度的云平台也都支持MQTT的接入.虽然MQTT很火,但是目前对 ...