尝试运行配置单元查询pyspark时出现以下错误
火花代码
from pyspark.sql import SparkSession, Row
from pyspark.sql.functions import *
# Create a spark session
spark = SparkSession.builder.appName("app name").getOrCreate()
sc = spark.sparkContext
query = "some query"
df = spark.sql(query)
df.show()
我遇到如下异常：
Py4JJavaError: An error occurred while calling o268.showString.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 150 in stage 65.0 failed 4 times, most recent failure: Lost task 150.3 in stage 65.0 (TID 54677, phyrhc105d4-prd, executor 4431): ExecutorLostFailure (executor 4431 exited caused by one of the running tasks) Reason: Container marked as failed: container_e103_1575680207115_1732381_01_004463 on host: phyrhc105d4-prd. Exit status: 143. Diagnostics: Container killed on request. Exit code is 143
Container exited with a non-zero exit code 143
Killed by external signal
错误日志
Py4JJavaErrorTraceback (most recent call last)
<ipython-input-11-3106d06b6e49> in <module>()
----> 1 df.show()
/usr/local/lib/python2.7/site-packages/pyspark/sql/dataframe.pyc in show(self, n, truncate)
334 """
335 if isinstance(truncate, bool) and truncate:
--> 336 print(self._jdf.showString(n, 20))
337 else:
338 print(self._jdf.showString(n, int(truncate)))
/usr/local/lib/python2.7/site-packages/py4j/java_gateway.pyc in __call__(self, *args)
1131 answer = self.gateway_client.send_command(command)
1132 return_value = get_return_value(
-> 1133 answer, self.gateway_client, self.target_id, self.name)
1134
1135 for temp_arg in temp_args:
/usr/local/lib/python2.7/site-packages/pyspark/sql/utils.pyc in deco(*a, **kw)
61 def deco(*a, **kw):
62 try:
---> 63 return f(*a, **kw)
64 except py4j.protocol.Py4JJavaError as e:
65 s = e.java_exception.toString()
/usr/local/lib/python2.7/site-packages/py4j/protocol.pyc 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 o268.showString.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 150 in stage 65.0 failed 4 times, most recent failure: Lost task 150.3 in stage 65.0 (TID 54677, phyrhc105d4-prd, executor 4431): ExecutorLostFailure (executor 4431 exited caused by one of the running tasks) Reason: Container marked as failed: container_e103_1575680207115_1732381_01_004463 on host: phyrhc105d4-prd. Exit status: 143. Diagnostics: Container killed on request. Exit code is 143
Container exited with a non-zero exit code 143
Killed by external signal
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1499)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1487)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1486)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1486)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:814)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1714)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1669)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1658)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:630)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2022)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2043)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2062)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:336)
at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38)
at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collectFromPlan(Dataset.scala:2853)
at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2153)
at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2153)
at org.apache.spark.sql.Dataset$$anonfun$55.apply(Dataset.scala:2837)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:65)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:2836)
at org.apache.spark.sql.Dataset.head(Dataset.scala:2153)
at org.apache.spark.sql.Dataset.take(Dataset.scala:2366)
at org.apache.spark.sql.Dataset.showString(Dataset.scala:245)
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 py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:745)