Spark Connector错误：WARN NettyUtil：发现Netty的本机epoll传输，但不在基于Linux的操作系统上运行。 使用NIO代替

Question

这是我的规格：

• Casssandra版本：3.0.0
• 操作系统：Mac OSX Yosemite 10.10.5
• Spark版本：1.4.1

语境：

我在Cassandra中创建了一个键空间“电影”和一个表“movieinfo。我已经按照这篇文章的指导安装并组装了一个jar文件。我编写了一个小脚本（下面）来测试我的连接：

scala> sc.stop

scala> import com.datastax.spark.connector._
import com.datastax.spark.connector._

scala> import org.apache.spark.SparkConf
import org.apache.spark.SparkConf

scala> import org.apache.spark.SparkContext._
import org.apache.spark.SparkContext._

scala> import org.apache.spark.SparkContext
import org.apache.spark.SparkContext

scala> val conf = new SparkConf()
conf: org.apache.spark.SparkConf = org.apache.spark.SparkConf@2ae92511

scala> conf.set("cassandra.connection.host", "127.0.0.1")
res1: org.apache.spark.SparkConf = org.apache.spark.SparkConf@2ae92511

scala> val sc = new SparkContext("local[*]", "Cassandra Test", conf)
sc: org.apache.spark.SparkContext = org.apache.spark.SparkContext@59b5251d

scala> val table = sc.cassandraTable("movies", "movieinfo")
table: com.datastax.spark.connector.rdd.CassandraTableScanRDD[com.datastax.spark.connector.CassandraRow] = CassandraTableScanRDD[0] at RDD at CassandraRDD.scala:15

scala> table.count

但是，我收到了进行中的tracelog。

15/11/24 09:21:30 WARN NettyUtil: Found Netty's native epoll transport, but not running on linux-based operating system. Using NIO instead.
java.io.IOException: Failed to open native connection to Cassandra at {10.223.134.106}:9042
    at com.datastax.spark.connector.cql.CassandraConnector$.com$datastax$spark$connector$cql$CassandraConnector$$createSession(CassandraConnector.scala:164)
    at com.datastax.spark.connector.cql.CassandraConnector$$anonfun$2.apply(CassandraConnector.scala:150)
    at com.datastax.spark.connector.cql.CassandraConnector$$anonfun$2.apply(CassandraConnector.scala:150)
    at com.datastax.spark.connector.cql.RefCountedCache.createNewValueAndKeys(RefCountedCache.scala:31)
    at com.datastax.spark.connector.cql.RefCountedCache.acquire(RefCountedCache.scala:56)
    at com.datastax.spark.connector.cql.CassandraConnector.openSession(CassandraConnector.scala:81)
    at com.datastax.spark.connector.cql.CassandraConnector.withSessionDo(CassandraConnector.scala:109)
    at com.datastax.spark.connector.cql.CassandraConnector.withClusterDo(CassandraConnector.scala:120)
    at com.datastax.spark.connector.cql.Schema$.fromCassandra(Schema.scala:249)
    at com.datastax.spark.connector.rdd.CassandraTableRowReaderProvider$class.tableDef(CassandraTableRowReaderProvider.scala:51)
    at com.datastax.spark.connector.rdd.CassandraTableScanRDD.tableDef$lzycompute(CassandraTableScanRDD.scala:59)
    at com.datastax.spark.connector.rdd.CassandraTableScanRDD.tableDef(CassandraTableScanRDD.scala:59)
    at com.datastax.spark.connector.rdd.CassandraTableRowReaderProvider$class.verify(CassandraTableRowReaderProvider.scala:146)
    at com.datastax.spark.connector.rdd.CassandraTableScanRDD.verify(CassandraTableScanRDD.scala:59)
    at com.datastax.spark.connector.rdd.CassandraTableScanRDD.getPartitions(CassandraTableScanRDD.scala:143)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217)
    at scala.Option.getOrElse(Option.scala:120)
    at org.apache.spark.rdd.RDD.partitions(RDD.scala:217)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1781)
    at org.apache.spark.rdd.RDD.count(RDD.scala:1099)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:34)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:39)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:41)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:43)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:45)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:47)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:49)
    at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:51)
    at $iwC$$iwC$$iwC$$iwC.<init>(<console>:53)
    at $iwC$$iwC$$iwC.<init>(<console>:55)
    at $iwC$$iwC.<init>(<console>:57)
    at $iwC.<init>(<console>:59)
    at <init>(<console>:61)
    at .<init>(<console>:65)
    at .<clinit>(<console>)
    at .<init>(<console>:7)
    at .<clinit>(<console>)
    at $print(<console>)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:497)
    at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
    at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1338)
    at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
    at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
    at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
    at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
    at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
    at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
    at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
    at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
    at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670)
    at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997)
    at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
    at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
    at scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
    at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945)
    at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059)
    at org.apache.spark.repl.Main$.main(Main.scala:31)
    at org.apache.spark.repl.Main.main(Main.scala)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:497)
    at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:665)
    at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:170)
    at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:193)
    at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:112)
    at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: com.datastax.driver.core.exceptions.NoHostAvailableException: All host(s) tried for query failed (tried: /10.223.134.106:9042 (com.datastax.driver.core.TransportException: [/10.223.134.106:9042] Cannot connect))
    at com.datastax.driver.core.ControlConnection.reconnectInternal(ControlConnection.java:220)
    at com.datastax.driver.core.ControlConnection.connect(ControlConnection.java:79)
    at com.datastax.driver.core.Cluster$Manager.init(Cluster.java:1393)
    at com.datastax.driver.core.Cluster.getMetadata(Cluster.java:402)
    at com.datastax.spark.connector.cql.CassandraConnector$.com$datastax$spark$connector$cql$CassandraConnector$$createSession(CassandraConnector.scala:157)
    ... 70 more

我相信我可能需要修改pom.xml文件中的设置和依赖项（引用这篇文章 ）。 但是，由于我是Spark和Java的新手，我将不胜感激任何关于如何最好地进行的指导或反馈。 谢谢您的支持。

Answer 1

此警告来自Java驱动程序。 它告诉你的是它已经在你的类路径Netty的本地传输中找到了 ，但是这个功能仅在Linux下可用，而你在Mac OS X上运行。

如果您使用的是Maven，请检查您的依赖项，看看您是否手动（或传递）包含此依赖项：

    <dependency>
      <groupId>io.netty</groupId>
      <artifactId>netty-transport-native-epoll</artifactId>
      <version>...</version>
    </dependency>

如果是这样，只需删除它。 否则，忽略此警告是安全的。

Answer 2

在运行spark-shell Mac OS上遇到同样的问题。 解决方案是将--conf spark.driver.host=localhost传递给spark-shell 。

出于某种原因，在Mac OS上，默认情况下将计算机的本地ip分配给spark.driver.host 。

在浏览器中打开http://<local ip>:4040不起作用，但打开http://localhost:4040可以正常工作。