hey,
I did this in my notebook. But still I get the same error. Is this the
right way to do it?
from pyspark import SparkConf
conf = (SparkConf()
.setMaster("local[4]")
.setAppName("My app")
.set("spark.executor.memory", "12g"))
sc.conf = conf
On Wed, Jun 15, 2016 at 5:59 PM, Jeff Zhang <[email protected]> wrote:
> >>> Caused by: java.lang.OutOfMemoryError: GC overhead limit exceeded
>
>
> It is OOM on the executor. Please try to increase executor memory.
> "--executor-memory"
>
>
>
>
>
> On Thu, Jun 16, 2016 at 8:54 AM, spR <[email protected]> wrote:
>
>> Hey,
>>
>> error trace -
>>
>> hey,
>>
>>
>> error trace -
>>
>>
>> ---------------------------------------------------------------------------Py4JJavaError
>> Traceback (most recent call
>> last)<ipython-input-22-925883e4d630> in <module>()----> 1 temp.take(2)
>>
>> /Users/my/Documents/My_Study_folder/spark-1.6.1/python/pyspark/sql/dataframe.pyc
>> in take(self, num) 304 with SCCallSiteSync(self._sc) as css:
>> 305 port =
>> self._sc._jvm.org.apache.spark.sql.execution.EvaluatePython.takeAndServe(-->
>> 306 self._jdf, num) 307 return
>> list(_load_from_socket(port, BatchedSerializer(PickleSerializer())))
>> 308
>>
>> /Users/my/Documents/My_Study_folder/spark-1.6.1/python/lib/py4j-0.9-src.zip/py4j/java_gateway.py
>> in __call__(self, *args) 811 answer =
>> self.gateway_client.send_command(command) 812 return_value =
>> get_return_value(--> 813 answer, self.gateway_client,
>> self.target_id, self.name) 814
>> 815 for temp_arg in temp_args:
>>
>> /Users/my/Documents/My_Study_folder/spark-1.6.1/python/pyspark/sql/utils.pyc
>> in deco(*a, **kw) 43 def deco(*a, **kw): 44 try:---> 45
>> return f(*a, **kw) 46 except
>> py4j.protocol.Py4JJavaError as e: 47 s =
>> e.java_exception.toString()
>> /Users/my/Documents/My_Study_folder/spark-1.6.1/python/lib/py4j-0.9-src.zip/py4j/protocol.py
>> in get_return_value(answer, gateway_client, target_id, name) 306
>> raise Py4JJavaError( 307 "An error occurred
>> while calling {0}{1}{2}.\n".--> 308 format(target_id,
>> ".", name), value) 309 else:
>> 310 raise Py4JError(
>> Py4JJavaError: An error occurred while calling
>> z:org.apache.spark.sql.execution.EvaluatePython.takeAndServe.
>> : org.apache.spark.SparkException: Job aborted due to stage failure: Task 0
>> in stage 3.0 failed 1 times, most recent failure: Lost task 0.0 in stage 3.0
>> (TID 76, localhost): java.lang.OutOfMemoryError: GC overhead limit exceeded
>> at com.mysql.jdbc.MysqlIO.nextRowFast(MysqlIO.java:2205)
>> at com.mysql.jdbc.MysqlIO.nextRow(MysqlIO.java:1984)
>> at com.mysql.jdbc.MysqlIO.readSingleRowSet(MysqlIO.java:3403)
>> at com.mysql.jdbc.MysqlIO.getResultSet(MysqlIO.java:470)
>> at com.mysql.jdbc.MysqlIO.readResultsForQueryOrUpdate(MysqlIO.java:3105)
>> at com.mysql.jdbc.MysqlIO.readAllResults(MysqlIO.java:2336)
>> at com.mysql.jdbc.MysqlIO.sqlQueryDirect(MysqlIO.java:2729)
>> at com.mysql.jdbc.ConnectionImpl.execSQL(ConnectionImpl.java:2549)
>> at
>> com.mysql.jdbc.PreparedStatement.executeInternal(PreparedStatement.java:1861)
>> at
>> com.mysql.jdbc.PreparedStatement.executeQuery(PreparedStatement.java:1962)
>> at
>> org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$$anon$1.<init>(JDBCRDD.scala:363)
>> at
>> org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD.compute(JDBCRDD.scala:339)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at
>> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at
>> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
>> at org.apache.spark.scheduler.Task.run(Task.scala:89)
>> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
>> at
>> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
>> at
>> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
>> at java.lang.Thread.run(Thread.java:745)
>>
>> Driver stacktrace:
>> at org.apache.spark.scheduler.DAGScheduler.org
>> <http://org.apache.spark.scheduler.dagscheduler.org/>$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431)
>> at
>> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419)
>> at
>> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418)
>> at
>> scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
>> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
>> at
>> org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)
>> at
>> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
>> at
>> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
>> at scala.Option.foreach(Option.scala:236)
>> at
>> org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
>> at
>> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640)
>> at
>> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
>> at
>> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
>> at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
>> at
>> org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
>> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
>> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845)
>> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1858)
>> at
>> org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:212)
>> at
>> org.apache.spark.sql.execution.EvaluatePython$$anonfun$takeAndServe$1.apply$mcI$sp(python.scala:126)
>> at
>> org.apache.spark.sql.execution.EvaluatePython$$anonfun$takeAndServe$1.apply(python.scala:124)
>> at
>> org.apache.spark.sql.execution.EvaluatePython$$anonfun$takeAndServe$1.apply(python.scala:124)
>> at
>> org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
>> at
>> org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:2086)
>> at
>> org.apache.spark.sql.execution.EvaluatePython$.takeAndServe(python.scala:124)
>> at
>> org.apache.spark.sql.execution.EvaluatePython.takeAndServe(python.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:498)
>> at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
>> at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381)
>> at py4j.Gateway.invoke(Gateway.java:259)
>> at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
>> at py4j.commands.CallCommand.execute(CallCommand.java:79)
>> at py4j.GatewayConnection.run(GatewayConnection.java:209)
>> at java.lang.Thread.run(Thread.java:745)
>> Caused by: java.lang.OutOfMemoryError: GC overhead limit exceeded
>> at com.mysql.jdbc.MysqlIO.nextRowFast(MysqlIO.java:2205)
>> at com.mysql.jdbc.MysqlIO.nextRow(MysqlIO.java:1984)
>> at com.mysql.jdbc.MysqlIO.readSingleRowSet(MysqlIO.java:3403)
>> at com.mysql.jdbc.MysqlIO.getResultSet(MysqlIO.java:470)
>> at com.mysql.jdbc.MysqlIO.readResultsForQueryOrUpdate(MysqlIO.java:3105)
>> at com.mysql.jdbc.MysqlIO.readAllResults(MysqlIO.java:2336)
>> at com.mysql.jdbc.MysqlIO.sqlQueryDirect(MysqlIO.java:2729)
>> at com.mysql.jdbc.ConnectionImpl.execSQL(ConnectionImpl.java:2549)
>> at
>> com.mysql.jdbc.PreparedStatement.executeInternal(PreparedStatement.java:1861)
>> at
>> com.mysql.jdbc.PreparedStatement.executeQuery(PreparedStatement.java:1962)
>> at
>> org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$$anon$1.<init>(JDBCRDD.scala:363)
>> at
>> org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD.compute(JDBCRDD.scala:339)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at
>> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at
>> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
>> at org.apache.spark.scheduler.Task.run(Task.scala:89)
>> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
>> at
>> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
>> at
>> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
>> ... 1 more
>>
>>
>>
>> On Wed, Jun 15, 2016 at 5:39 PM, Jeff Zhang <[email protected]> wrote:
>>
>>> Could you paste the full stacktrace ?
>>>
>>> On Thu, Jun 16, 2016 at 7:24 AM, spR <[email protected]> wrote:
>>>
>>>> Hi,
>>>> I am getting this error while executing a query using sqlcontext.sql
>>>>
>>>> The table has around 2.5 gb of data to be scanned.
>>>>
>>>> First I get out of memory exception. But I have 16 gb of ram
>>>>
>>>> Then my notebook dies and I get below error
>>>>
>>>> Py4JNetworkError: An error occurred while trying to connect to the Java
>>>> server
>>>>
>>>>
>>>> Thank You
>>>>
>>>
>>>
>>>
>>> --
>>> Best Regards
>>>
>>> Jeff Zhang
>>>
>>
>>
>
>
> --
> Best Regards
>
> Jeff Zhang
>
