嗨，我有以下python代码:
from __future__ import print_function
import sys
from pyspark.sql import SparkSession
from data import Data
if __name__ == "__main__":
if len(sys.argv) != 2:
print("Usage: runner <number_of_executors>", file=sys.stderr)
exit(-1)
spark = SparkSession \
.builder \
.master("spark://138.xxx.xxx.xxx:7077") \
.config("spark.num-executors", sys.argv[1]) \
.config("spark.driver.memory", "1g") \
.config("spark.executor.memory", "1g") \
.config("spark.executor.cores", "4") \
.appName("APP") \
.getOrCreate()
data = Data(spark)
spark.stop()
Data 类将加载各种 csv 文件的位置，但这并不重要。
我在 ~/.bash_profile 中添加了以下几行:
export SPARK_HOME=/home/tsar/spark
export PATH=$SPARK_HOME/bin:$SPARK_HOME/sbin:$SPARK_HOME/conf:$PATH
export PYTHONPATH=$SPARK_HOME/python:$SPARK_HOME/python/build
我还有以下配置文件:
带有节点列表的
spark.master spark://138.xxx.xxx.xxx:7077
spark.driver.memory 1g
spark.executor.memory 1g
spark.executor.cores 4
export SPARK_MASTER_HOST=138.xxx.xxx.xxx
export SPARK_MASTER_MEMORY=5g
export SPARK_WORKER_MEMORY=1024m
接下来发生的是:
Using Spark's default log4j profile: org/apache/spark/log4j-defaults.properties
Setting default log level to "WARN".
To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).
17/03/26 19:58:11 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
17/03/26 19:59:12 ERROR StandaloneSchedulerBackend: Application has been killed. Reason: All masters are unresponsive! Giving up.
17/03/26 19:59:12 WARN StandaloneSchedulerBackend: Application ID is not initialized yet.
17/03/26 19:59:12 WARN StandaloneAppClient$ClientEndpoint: Drop UnregisterApplication(null) because has not yet connected to master
17/03/26 19:59:12 ERROR TransportResponseHandler: Still have 3 requests outstanding when connection from /xxx.xxx.xxx.xxx:7077 is closed
17/03/26 19:59:12 ERROR SparkContext: Error initializing SparkContext.
java.lang.IllegalArgumentException: requirement failed: Can only call getServletHandlers on a running MetricsSystem
at scala.Predef$.require(Predef.scala:224)
at org.apache.spark.metrics.MetricsSystem.getServletHandlers(MetricsSystem.scala:91)
at org.apache.spark.SparkContext.<init>(SparkContext.scala:524)
at org.apache.spark.api.java.JavaSparkContext.<init>(JavaSparkContext.scala:58)
at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:423)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:247)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:236)
at py4j.commands.ConstructorCommand.invokeConstructor(ConstructorCommand.java:80)
at py4j.commands.ConstructorCommand.execute(ConstructorCommand.java:69)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:745)
Traceback (most recent call last):
File "main.py", line 21, in <module>
.appName("CS5052-01 Processing") \
File "/cs/home/bbt/spark/python/pyspark/sql/session.py", line 169, in getOrCreate
sc = SparkContext.getOrCreate(sparkConf)
File "/cs/home/bbt/spark/python/pyspark/context.py", line 307, in getOrCreate
SparkContext(conf=conf or SparkConf())
File "/cs/home/bbt/spark/python/pyspark/context.py", line 118, in __init__
conf, jsc, profiler_cls)
File "/cs/home/bbt/spark/python/pyspark/context.py", line 179, in _do_init
self._jsc = jsc or self._initialize_context(self._conf._jconf)
File "/cs/home/bbt/spark/python/pyspark/context.py", line 246, in _initialize_context
return self._jvm.JavaSparkContext(jconf)
File "/cs/home/bbt/spark/python/lib/py4j-0.10.4-src.zip/py4j/java_gateway.py", line 1401, in __call__
File "/cs/home/bbt/spark/python/lib/py4j-0.10.4-src.zip/py4j/protocol.py", line 319, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling None.org.apache.spark.api.java.JavaSparkContext.
: java.lang.IllegalArgumentException: requirement failed: Can only call getServletHandlers on a running MetricsSystem
at scala.Predef$.require(Predef.scala:224)
at org.apache.spark.metrics.MetricsSystem.getServletHandlers(MetricsSystem.scala:91)
at org.apache.spark.SparkContext.<init>(SparkContext.scala:524)
at org.apache.spark.api.java.JavaSparkContext.<init>(JavaSparkContext.scala:58)
at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:423)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:247)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:236)
at py4j.commands.ConstructorCommand.invokeConstructor(ConstructorCommand.java:80)
at py4j.commands.ConstructorCommand.execute(ConstructorCommand.java:69)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:745)最后一种运行方式与其他方式有何不同？ spark master 100% 存在于 IP 地址并且可以访问。
最佳答案
我有一个类似的问题，主从肯定可以通信，但是当我去运行一项工作时，我遇到了同样的晦涩错误:
java.lang.IllegalArgumentException: requirement failed: Can only call getServletHandlers on a running MetricsSystem
对此的正常解释是主从无法通信，但在我的情况下，我在从节点上运行 spark 的用户没有写入日志文件的权限。我通过转到 spark 母版页(默认母版:8080)并从失败的应用程序链接深入到从服务器的工作人员 stderr 输出中发现了这一点。
是否有关于标准错误或 Spark 日志(默认/opt/spark/logs/spark-xxx)中的错误的更多详细信息？
关于python-2.7 - 运行 PySpark 时出错，无法连接到 master，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/43033505/