Ошибка подключения к искровому кластеру с помощью sparklyr - PullRequest
0 голосов
/ 29 октября 2019

Я пытаюсь использовать sparklyr в режиме клиента пряжи. Вот мой код

library(sparklyr)
library(dplyr) 
sc <- spark_connect(master = "yarn-client", app_name="test4")

Он успешно создает sc, и это содержимое sc

$master
[1] "yarn-client"

$method
[1] "shell"

$app_name
[1] "test4"

$config
$config$spark.env.SPARK_LOCAL_IP.local
[1] "127.0.0.1"

$config$sparklyr.connect.csv.embedded
[1] "^1.*"

$config$spark.sql.catalogImplementation
[1] "hive"

$config$sparklyr.connect.cores.local
[1] 4

$config$spark.sql.shuffle.partitions.local
[1] 4

attr(,"config")
[1] "default"
attr(,"file")
[1] "/usr/lib64/R/library/sparklyr/conf/config-template.yml"

$state
<environment: 0x4ddd610>

$extensions
$extensions$jars
character(0)

$extensions$packages
character(0)

$extensions$initializers
list()

$extensions$catalog_jars
character(0)


$spark_home
[1] "/opt/spark-2.4.3-bin-hadoop2.6"

$backend
A connection with
description "->localhost:8881"
class       "sockconn"
mode        "wb"
text        "binary"
opened      "opened"
can read    "yes"
can write   "yes"

$monitoring
A connection with
description "->localhost:8881"
class       "sockconn"
mode        "wb"
text        "binary"
opened      "opened"
can read    "yes"
can write   "yes"

$gateway
A connection with
description "->localhost:8880"
class       "sockconn"
mode        "rb"
text        "binary"
opened      "opened"
can read    "yes"
can write   "yes"

$output_file
[1] "/tmp/RtmpsAzjOk/file166d0b57b5_spark.log"

$sessionId
[1] 99625

$home_version
[1] "2.4.3"

attr(,"class")
[1] "spark_connection"       "spark_shell_connection" "DBIConnection"

, а затем я пытаюсь прочитать таблицу следующим образом

data <- tbl(sc, sql('SELECT * FROM db_name.table_name LIMIT 10'))

но выдает следующую ошибку

Error: java.lang.IllegalArgumentException: Error while instantiating 'org.apache.spark.sql.hive.HiveSessionStateBuilder':
    at org.apache.spark.sql.SparkSession$.org$apache$spark$sql$SparkSession$$instantiateSessionState(SparkSession.scala:1107)
    at org.apache.spark.sql.SparkSession$$anonfun$sessionState$2.apply(SparkSession.scala:145)
    at org.apache.spark.sql.SparkSession$$anonfun$sessionState$2.apply(SparkSession.scala:144)
    at scala.Option.getOrElse(Option.scala:121)
    at org.apache.spark.sql.SparkSession.sessionState$lzycompute(SparkSession.scala:144)
    at org.apache.spark.sql.SparkSession.sessionState(SparkSession.scala:141)
    at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:642)
    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:498)
    at sparklyr.Invoke.invoke(invoke.scala:147)
    at sparklyr.StreamHandler.handleMethodCall(stream.scala:123)
    at sparklyr.StreamHandler.read(stream.scala:66)
    at sparklyr.BackendHandler.channelRead0(handler.scala:51)
    at sparklyr.BackendHandler.channelRead0(handler.scala:4)
    at io.netty.channel.SimpleChannelInboundHandler.channelRead(SimpleChannelInboundHandler.java:105)
    at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:362)
    at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:348)
    at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:340)
    at io.netty.handler.codec.MessageToMessageDecoder.channelRead(MessageToMessageDecoder.java:102)
    at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:362)
    at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:348)
    at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:340)
    at io.netty.handler.codec.ByteToMessageDecoder.fireChannelRead(ByteToMessageDecoder.java:310)
    at io.netty.handler.codec.ByteToMessageDecoder.channelRead(ByteToMessageDecoder.java:284)
    at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:362)
    at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:348)
    at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:340)
    at io.netty.channel.DefaultChannelPipeline$HeadContext.channelRead(DefaultChannelPipeline.java:1359)
    at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:362)
    at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:348)
    at io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:935)
    at io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:138)
    at io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:645)
    at io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:580)
    at io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:497)
    at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:459)
    at io.netty.util.concurrent.SingleThreadEventExecutor$5.run(SingleThreadEventExecutor.java:858)
    at io.netty.util.concurrent.DefaultThreadFactory$DefaultRunnableDecorator.run(DefaultThreadFactory.java:138)
    at java.lang.Thread.run(Thread.java:748)
Caused by: java.lang.IllegalStateException: LiveListenerBus is stopped.
    at org.apache.spark.scheduler.LiveListenerBus.addToQueue(LiveListenerBus.scala:97)
    at org.apache.spark.scheduler.LiveListenerBus.addToStatusQueue(LiveListenerBus.scala:80)
    at org.apache.spark.sql.internal.SharedState.<init>(SharedState.scala:93)
    at org.apache.spark.sql.SparkSession$$anonfun$sharedState$1.apply(SparkSession.scala:121)
    at org.apache.spark.sql.SparkSession$$anonfun$sharedState$1.apply(SparkSession.scala:121)
    at scala.Option.getOrElse(Option.scala:121)
    at org.apache.spark.sql.SparkSession.sharedState$lzycompute(SparkSession.scala:121)
    at org.apache.spark.sql.SparkSession.sharedState(SparkSession.scala:120)
    at org.apache.spark.sql.internal.BaseSessionStateBuilder.build(BaseSessionStateBuilder.scala:286)
    at org.apache.spark.sql.SparkSession$.org$apache$spark$sql$SparkSession$$instantiateSessionState(SparkSession.scala:1104)
    ... 40 more
Error: java.lang.IllegalStateException: Cannot call methods on a stopped SparkContext.
This stopped SparkContext was created at:

org.apache.spark.sql.SparkSession$Builder.getOrCreate(SparkSession.scala:926)
sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
java.lang.reflect.Method.invoke(Method.java:498)
sparklyr.Invoke.invoke(invoke.scala:147)
sparklyr.StreamHandler.handleMethodCall(stream.scala:123)
sparklyr.StreamHandler.read(stream.scala:66)
sparklyr.BackendHandler.channelRead0(handler.scala:51)
sparklyr.BackendHandler.channelRead0(handler.scala:4)
io.netty.channel.SimpleChannelInboundHandler.channelRead(SimpleChannelInboundHandler.java:105
The currently active SparkContext was created at:

(No active SparkContext.)

    at org.apache.spark.SparkContext.assertNotStopped(SparkContext.scala:100)
    at org.apache.spark.SparkContext.cancelAllJobs(SparkContext.scala:2248)
    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:498)
    at sparklyr.Invoke.invoke(invoke.scala:147)
    at sparklyr.StreamHandler.handleMethodCall(stream.scala:123)
    at sparklyr.StreamHandler.read(stream.scala:66)
    at sparklyr.BackendHandler.channelRead0(handler.scala:51)
    at sparklyr.BackendHandler.channelRead0(handler.scala:4)
    at io.netty.channel.SimpleChannelInboundHandler.channelRead(SimpleChannelInboundHandler.java:105)
    at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:362)
    at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:348)
    at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:340)
    at io.netty.handler.codec.MessageToMessageDecoder.channelRead(MessageToMessageDecoder.java:102)
    at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:362)
    at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:348)
    at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:340)
    at io.netty.handler.codec.ByteToMessageDecoder.fireChannelRead(ByteToMessageDecoder.java:310)
    at io.netty.handler.codec.ByteToMessageDecoder.channelRead(ByteToMessageDecoder.java:284)
    at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:362)
    at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:348)
    at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:340)
    at io.netty.channel.DefaultChannelPipeline$HeadContext.channelRead(DefaultChannelPipeline.java:1359)
    at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:362)
    at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:348)
    at io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:935)
    at io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:138)
    at io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:645)
    at io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:580)
    at io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:497)
    at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:459)
    at io.netty.util.concurrent.SingleThreadEventExecutor$5.run(SingleThreadEventExecutor.java:858)
    at io.netty.util.concurrent.DefaultThreadFactory$DefaultRunnableDecorator.run(DefaultThreadFactory.java:138)
    at java.lang.Thread.run(Thread.java:748)

Что здесь не так?

...