Apache spark 此SparkContext可能是现有的。错误

Apache spark 此SparkContext可能是现有的。错误,apache-spark,Apache Spark,我在笔记本电脑中使用spark2.0,这是初始设置: spark = SparkSession.builder \ .appName("NewApp") \ .config("spark.driver.maxResultSize", "600g") \ .config("spark.serializer", "org.apache.spark.serializer.KryoSerializer") \ .config("spark.rpc.message.maxSiz

我在笔记本电脑中使用spark2.0,这是初始设置:

  spark = SparkSession.builder \
   .appName("NewApp") \
   .config("spark.driver.maxResultSize", "600g") \
   .config("spark.serializer", "org.apache.spark.serializer.KryoSerializer") \
   .config("spark.rpc.message.maxSize",10737418240) \
   .config("spark.executor.heartbeatInterval",10000000) \
   .getOrCreate()


/usr/local/spark-2.0.1/python/pyspark/sql/session.py in getOrCreate(self)
167                     for key, value in self._options.items():
168                         sparkConf.set(key, value)
--> 169                     sc = SparkContext.getOrCreate(sparkConf)
170                     # This SparkContext may be an existing one.
171                     for key, value in self._options.items():

/usr/local/spark-2.0.1/python/pyspark/context.py in getOrCreate(cls, conf)
292         with SparkContext._lock:
293             if SparkContext._active_spark_context is None:
--> 294                 SparkContext(conf=conf or SparkConf())
295             return SparkContext._active_spark_context
296 

/usr/local/spark-2.0.1/python/pyspark/context.py in __init__(self, master, appName, sparkHome, pyFiles, environment, batchSize, serializer, conf, gateway, jsc, profiler_cls)
113         try:
114             self._do_init(master, appName, sparkHome, pyFiles, environment, batchSize, serializer,
 --> 115                           conf, jsc, profiler_cls)
116         except:
117             # If an error occurs, clean up in order to allow future SparkContext creation:

  /usr/local/spark-2.0.1/python/pyspark/context.py in _do_init(self, master, appName, sparkHome, pyFiles, environment, batchSize, serializer, conf, jsc, profiler_cls)
166 
167         # Create the Java SparkContext through Py4J
--> 168         self._jsc = jsc or self._initialize_context(self._conf._jconf)
169         # Reset the SparkConf to the one actually used by the SparkContext in JVM.
170         self._conf = SparkConf(_jconf=self._jsc.sc().conf())

     /usr/local/spark-2.0.1/python/pyspark/context.py in _initialize_context(self, jconf)
231         Initialize SparkContext in function to allow subclass specific initialization
232         """
  --> 233         return self._jvm.JavaSparkContext(jconf)
234 
235     @classmethod

     /usr/local/spark-2.0.1/python/lib/py4j-0.10.3-src.zip/py4j/java_gateway.py in __call__(self, *args)
   1399         answer = self._gateway_client.send_command(command)
   1400         return_value = get_return_value(
-> 1401             answer, self._gateway_client, None, self._fqn)
  1402 
  1403         for temp_arg in temp_args:

/usr/local/spark-2.0.1/python/lib/py4j-0.10.3-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
317                 raise Py4JJavaError(
318                     "An error occurred while calling {0}{1}{2}.\n".
--> 319                     format(target_id, ".", name), value)
320             else:
321                 raise Py4JError(

     Py4JJavaError: An error occurred while calling None.org.apache.spark.api.java.JavaSparkContext.
   : java.lang.NumberFormatException: For input string: "10737418240"
at                 java.lang.NumberFormatException.forInputString(NumberFormatException.java:65)
at java.lang.Integer.parseInt(Integer.java:583)
at java.lang.Integer.parseInt(Integer.java:615)
at scala.collection.immutable.StringLike$class.toInt(StringLike.scala:272)
at scala.collection.immutable.StringOps.toInt(StringOps.scala:29)
at org.apache.spark.SparkConf$$anonfun$getInt$2.apply(SparkConf.scala:375)
at org.apache.spark.SparkConf$$anonfun$getInt$2.apply(SparkConf.scala:375)
at scala.Option.map(Option.scala:146)
at org.apache.spark.SparkConf.getInt(SparkConf.scala:375)
at org.apache.spark.util.RpcUtils$.maxMessageSizeBytes(RpcUtils.scala:61)
at org.apache.spark.MapOutputTrackerMaster.<init>(MapOutputTracker.scala:293)
at org.apache.spark.SparkEnv$.create(SparkEnv.scala:284)
at org.apache.spark.SparkEnv$.createDriverEnv(SparkEnv.scala:165)
at org.apache.spark.SparkContext.createSparkEnv(SparkContext.scala:256)
at org.apache.spark.SparkContext.<init>(SparkContext.scala:420)
at org.apache.spark.api.java.JavaSparkContext.<init>(JavaSparkContext.scala:58)
spark=SparkSession.builder\
.appName(“NewApp”)\
.config(“spark.driver.maxResultSize”,“600g”)\
.config(“spark.serializer”、“org.apache.spark.serializer.KryoSerializer”)\
.config(“spark.rpc.message.maxSize”,10737418240)\
.config(“spark.executor.heartbeatInterval”,10000000)\
.getOrCreate()
/getOrCreate(self)中的usr/local/spark-2.0.1/python/pyspark/sql/session.py
167对于键,值在self.\u options.items()中:
168 sparkConf.集合(键、值)
-->169 sc=SparkContext.getOrCreate(sparkConf)
170#此SparkContext可能是现有的。
171对于键,值在self.\u options.items()中:
/getOrCreate(cls,conf)中的usr/local/spark-2.0.1/python/pyspark/context.py
292带SparkContext.\u锁:
293如果SparkContext.\u active\u spark\u上下文为无:
-->294 SparkContext(conf=conf或SparkConf())
295返回SparkContext.\u活动\u spark\u上下文
296
/usr/local/spark-2.0.1/python/pyspark/context.py in_u_________(self、master、appName、sparkHome、pyFiles、environment、batchSize、serializer、conf、gateway、jsc、profiler_cls)
113尝试:
114 self.\u do\u init(主程序、appName、sparkHome、pyFiles、环境、batchSize、序列化程序、,
-->115形态、jsc、探查器(cls)
116除:
117#如果发生错误,请清理以允许将来创建SparkContext:
/init中的usr/local/spark-2.0.1/python/pyspark/context.py(self、master、appName、sparkHome、pyFiles、environment、batchSize、serializer、conf、jsc、profiler\u cls)
166
167#通过Py4J创建Java SparkContext
-->168 self.\u jsc=jsc或self.\u初始化上下文(self.\u conf.\u jconf)
169#将SparkConf重置为JVM中SparkContext实际使用的一个。
170 self.\u conf=SparkConf(\u jconf=self.\u jsc.sc().conf())
/usr/local/spark-2.0.1/python/pyspark/context.py in_initialize_context(self,jconf)
231在函数中初始化SparkContext以允许子类特定的初始化
232         """
-->233返回self._jvm.JavaSparkContext(jconf)
234
235@classmethod
/usr/local/spark-2.0.1/python/lib/py4j-0.10.3-src.zip/py4j/java_gateway.py in__调用(self,*args)
1399 answer=self.\u gateway\u client.send\u命令(command)
1400返回值=获取返回值(
->1401回答,自。\网关\客户端,无,自。\ fqn)
1402
1403对于临时参数中的临时参数:
/获取返回值中的usr/local/spark-2.0.1/python/lib/py4j-0.10.3-src.zip/py4j/protocol.py(答案、网关客户端、目标id、名称)
317 raise Py4JJavaError(
318“调用{0}{1}{2}时出错。\n”。
-->319格式(目标id,“.”,名称),值)
320其他:
321升起Py4JError(
Py4JJavaError:调用None.org.apache.spark.api.java.JavaSparkContext时出错。
:java.lang.NumberFormatException:对于输入字符串:“10737418240”
位于java.lang.NumberFormatException.forInputString(NumberFormatException.java:65)
位于java.lang.Integer.parseInt(Integer.java:583)
在java.lang.Integer.parseInt(Integer.java:615)
在scala.collection.immutable.StringLike$class.toInt(StringLike.scala:272)中
位于scala.collection.immutable.StringOps.toInt(StringOps.scala:29)
位于org.apache.spark.SparkConf$$anonfun$getInt$2.apply(SparkConf.scala:375)
位于org.apache.spark.SparkConf$$anonfun$getInt$2.apply(SparkConf.scala:375)
在scala.Option.map处(Option.scala:146)
位于org.apache.spark.SparkConf.getInt(SparkConf.scala:375)
位于org.apache.spark.util.RpcUtils$.maxMessageSizeBytes(RpcUtils.scala:61)
位于org.apache.spark.MapOutputRackerMaster。(MapOutputRacker.scala:293)
在org.apache.spark.SparkEnv$.create上(SparkEnv.scala:284)
在org.apache.spark.SparkEnv$.createDriverEnv上(SparkEnv.scala:165)
位于org.apache.spark.SparkContext.createSparkEnv(SparkContext.scala:256)
位于org.apache.spark.SparkContext(SparkContext.scala:420)
位于org.apache.spark.api.java.JavaSparkContext(JavaSparkContext.scala:58)
如何解决此问题?我尝试了SparkContext.stop(),但它提供: TypeError:stop()缺少1个必需的位置参数:“self”


另一个问题是我的初始设置是getOrCreate(),据我所知,如果有,那么获取它,如果没有创建它,它仍然会出现此问题。

以下是错误的来源:

:java.lang.NumberFormatException:对于输入字符串:“10737418240” 位于java.lang.NumberFormatException.forInputString(NumberFormatException.java:65) 位于java.lang.Integer.parseInt(Integer.java:583)

10737418240大于
Int.MaxValue
(2147483647)。调用时使用较小的值:

.config("spark.rpc.message.maxSize", ...) \