[
https://issues.apache.org/jira/browse/SPARK-46032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17788582#comment-17788582
]
Bobby Wang edited comment on SPARK-46032 at 11/22/23 12:54 AM:
---------------------------------------------------------------
h1. *Submit the spark application via pyspark*
I installed the pyspark connect dependencies by *`pip install pyspark[connect]`*
h2. pyspark location
```
*(pyspark-connect) xxx@spark-bobby:~/Desktop/spark-connect$ which pyspark*
/home/xxx/github/mytools/spark.home/spark-3.5.0-bin-hadoop3/bin/pyspark
```
*(pyspark-connect) xxx@spark-bobby:~/Desktop/spark-connect$ pyspark --remote
sc://localhost*
Python 3.10.0 (default, Mar 3 2022, 09:58:08) [GCC 7.5.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
Welcome to
____ __
/ _{_}/{_} \{_}___ _____/ /{_}_
{_}\ \/ _ \/ _ `/ __/ '{_}/
/__ / ._{_}/_,{_}/{_}/ /{_}/_\ version 3.5.0
/_/
Using Python version 3.10.0 (default, Mar 3 2022 09:58:08)
Client connected to the Spark Connect server at localhost
SparkSession available as 'spark'.
>>> spark.range(100).filter("id > 2").collect()
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File
"/home/xxx/github/mytools/spark.home/spark-3.5.0-bin-hadoop3/python/pyspark/sql/connect/dataframe.py",
line 1645, in collect
table, schema = self._session.client.to_table(query)
File
"/home/xxx/github/mytools/spark.home/spark-3.5.0-bin-hadoop3/python/pyspark/sql/connect/client/core.py",
line 858, in to_table
table, schema, _, _, _ = self._execute_and_fetch(req)
File
"/home/xxx/github/mytools/spark.home/spark-3.5.0-bin-hadoop3/python/pyspark/sql/connect/client/core.py",
line 1282, in _execute_and_fetch
for response in self._execute_and_fetch_as_iterator(req):
File
"/home/xxx/github/mytools/spark.home/spark-3.5.0-bin-hadoop3/python/pyspark/sql/connect/client/core.py",
line 1263, in _execute_and_fetch_as_iterator
self._handle_error(error)
File
"/home/xxx/github/mytools/spark.home/spark-3.5.0-bin-hadoop3/python/pyspark/sql/connect/client/core.py",
line 1502, in _handle_error
self._handle_rpc_error(error)
File
"/home/xxx/github/mytools/spark.home/spark-3.5.0-bin-hadoop3/python/pyspark/sql/connect/client/core.py",
line 1538, in _handle_rpc_error
raise convert_exception(info, status.message) from None
pyspark.errors.exceptions.connect.SparkConnectGrpcException:
(org.apache.spark.SparkException) Job aborted due to stage failure: Task 0 in
stage 0.0 failed 4 times, most recent failure: Lost task 0.3 in stage 0.0 (TID
33) (192.168.31.236 executor 0): java.lang.ClassCastException: cannot assign
instance of java.lang.invoke.SerializedLambda to field
org.apache.spark.rdd.MapPartitionsRDD.f of type scala.Function3 in instance of
org.apache.spark.rdd.MapPartitionsRDD
at
java.base/java.io.ObjectStreamClass$FieldReflector.setObjFieldValues(ObjectStreamClass.java:2096)
at
java.base/java.io.ObjectStreamClass$FieldReflector.checkObjectFieldValueTypes(ObjectStreamClass.java:2060)
at
java.base/java.io.ObjectStreamClass.checkObjFieldValueTypes(ObjectStreamClass.java:1347)
at
java.base/java.io.ObjectInputStream$FieldValues.defaultCheckFieldValues(ObjectInputStream.java:2679)
at
java.base/java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:2486)
at
java.base/java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:2257)
at java.base/java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1733)
at
java.base/java.io.ObjectInputStream$FieldValues.<init>(ObjectInputStream.java:2606)
at
java.base/java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:2457)
at
java.base/java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:2257)
at java.base/java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1733)
at java.base/java.io.ObjectInputStream.readObject(ObjectInputStream.java:509)
at java.base/java.io.ObjectInputStream.readObject(ObjectInputStream.java:467)
at
org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:87)
at
org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:129)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:86)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:161)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at
org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:620)
at org.apache.spark.util.SparkErr...
>>>
was (Author: wbo4958):
h1. *Submit the spark application via pyspark*
I installed the pyspark connect dependencies by *`pip install pyspark[connect]`*
h2. pyspark location
```
*(pyspark-connect) xxx@spark-bobby:~/Desktop/spark-connect$ which pyspark*
/home/xxx/github/mytools/spark.home/spark-3.5.0-bin-hadoop3/bin/pyspark
```
*(pyspark-connect) xxx@spark-bobby:~/Desktop/spark-connect$ pyspark --remote
sc://localhost*
Python 3.10.0 (default, Mar 3 2022, 09:58:08) [GCC 7.5.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
Welcome to
____ __
/ __/__ ___ _____/ /__
_\ \/ _ \/ _ `/ __/ '_/
/__ / .__/\_,_/_/ /_/\_\ version 3.5.0
/_/
Using Python version 3.10.0 (default, Mar 3 2022 09:58:08)
Client connected to the Spark Connect server at localhost
SparkSession available as 'spark'.
>>> spark.range(100).filter("id > 2").collect()
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File
"/home/bobwang/github/mytools/spark.home/spark-3.5.0-bin-hadoop3/python/pyspark/sql/connect/dataframe.py",
line 1645, in collect
table, schema = self._session.client.to_table(query)
File
"/home/bobwang/github/mytools/spark.home/spark-3.5.0-bin-hadoop3/python/pyspark/sql/connect/client/core.py",
line 858, in to_table
table, schema, _, _, _ = self._execute_and_fetch(req)
File
"/home/bobwang/github/mytools/spark.home/spark-3.5.0-bin-hadoop3/python/pyspark/sql/connect/client/core.py",
line 1282, in _execute_and_fetch
for response in self._execute_and_fetch_as_iterator(req):
File
"/home/bobwang/github/mytools/spark.home/spark-3.5.0-bin-hadoop3/python/pyspark/sql/connect/client/core.py",
line 1263, in _execute_and_fetch_as_iterator
self._handle_error(error)
File
"/home/bobwang/github/mytools/spark.home/spark-3.5.0-bin-hadoop3/python/pyspark/sql/connect/client/core.py",
line 1502, in _handle_error
self._handle_rpc_error(error)
File
"/home/bobwang/github/mytools/spark.home/spark-3.5.0-bin-hadoop3/python/pyspark/sql/connect/client/core.py",
line 1538, in _handle_rpc_error
raise convert_exception(info, status.message) from None
pyspark.errors.exceptions.connect.SparkConnectGrpcException:
(org.apache.spark.SparkException) Job aborted due to stage failure: Task 0 in
stage 0.0 failed 4 times, most recent failure: Lost task 0.3 in stage 0.0 (TID
33) (192.168.31.236 executor 0): java.lang.ClassCastException: cannot assign
instance of java.lang.invoke.SerializedLambda to field
org.apache.spark.rdd.MapPartitionsRDD.f of type scala.Function3 in instance of
org.apache.spark.rdd.MapPartitionsRDD
at
java.base/java.io.ObjectStreamClass$FieldReflector.setObjFieldValues(ObjectStreamClass.java:2096)
at
java.base/java.io.ObjectStreamClass$FieldReflector.checkObjectFieldValueTypes(ObjectStreamClass.java:2060)
at
java.base/java.io.ObjectStreamClass.checkObjFieldValueTypes(ObjectStreamClass.java:1347)
at
java.base/java.io.ObjectInputStream$FieldValues.defaultCheckFieldValues(ObjectInputStream.java:2679)
at
java.base/java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:2486)
at
java.base/java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:2257)
at java.base/java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1733)
at
java.base/java.io.ObjectInputStream$FieldValues.<init>(ObjectInputStream.java:2606)
at
java.base/java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:2457)
at
java.base/java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:2257)
at java.base/java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1733)
at java.base/java.io.ObjectInputStream.readObject(ObjectInputStream.java:509)
at java.base/java.io.ObjectInputStream.readObject(ObjectInputStream.java:467)
at
org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:87)
at
org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:129)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:86)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:161)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at
org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:620)
at org.apache.spark.util.SparkErr...
>>>
> connect: cannot assign instance of java.lang.invoke.SerializedLambda to field
> org.apache.spark.rdd.MapPartitionsRDD.f
> ---------------------------------------------------------------------------------------------------------------------
>
> Key: SPARK-46032
> URL: https://issues.apache.org/jira/browse/SPARK-46032
> Project: Spark
> Issue Type: Bug
> Components: Connect
> Affects Versions: 3.5.0
> Reporter: Bobby Wang
> Priority: Major
>
> I downloaded spark 3.5 from the spark official website, and then I started a
> Spark Standalone cluster in which both master and the only worker are in the
> same node.
>
> Then I started the connect server by
> {code:java}
> start-connect-server.sh \
> --master spark://10.19.183.93:7077 \
> --packages org.apache.spark:spark-connect_2.12:3.5.0 \
> --conf spark.executor.cores=12 \
> --conf spark.task.cpus=1 \
> --executor-memory 30G \
> --conf spark.executor.resource.gpu.amount=1 \
> --conf spark.task.resource.gpu.amount=0.08 \
> --driver-memory 1G{code}
>
> I can 100% ensure the spark standalone cluster, the connect server and spark
> driver are started observed from the webui.
>
> Finally, I tried to run a very simple spark job
> (spark.range(100).filter("id>2").collect()) from spark-connect-client using
> pyspark, but I got the below error.
>
> _pyspark --remote sc://localhost_
> _Python 3.10.0 (default, Mar 3 2022, 09:58:08) [GCC 7.5.0] on linux_
> _Type "help", "copyright", "credits" or "license" for more information._
> _Welcome to_
> _____ ___
> _/ __/_ {{_}}{_}__ ___{_}{{_}}/ /{{_}}{_}_
> {_}{{_}}\ \/ _ \/ _ `/ {_}{{_}}/ '{_}/{_}
> {_}/{_}_ / .{_}{{_}}/{_},{_}/{_}/ /{_}/{_}\ version 3.5.0{_}
> {_}/{_}/_
>
> _Using Python version 3.10.0 (default, Mar 3 2022 09:58:08)_
> _Client connected to the Spark Connect server at localhost_
> _SparkSession available as 'spark'._
> _>>> spark.range(100).filter("id > 3").collect()_
> _Traceback (most recent call last):_
> _File "<stdin>", line 1, in <module>_
> _File
> "/home/xxx/github/mytools/spark.home/spark-3.5.0-bin-hadoop3/python/pyspark/sql/connect/dataframe.py",
> line 1645, in collect_
> _table, schema = self._session.client.to_table(query)_
> _File
> "/home/xxx/github/mytools/spark.home/spark-3.5.0-bin-hadoop3/python/pyspark/sql/connect/client/core.py",
> line 858, in to_table_
> _table, schema, _, _, _ = self._execute_and_fetch(req)_
> _File
> "/home/xxx/github/mytools/spark.home/spark-3.5.0-bin-hadoop3/python/pyspark/sql/connect/client/core.py",
> line 1282, in _execute_and_fetch_
> _for response in self._execute_and_fetch_as_iterator(req):_
> _File
> "/home/xxx/github/mytools/spark.home/spark-3.5.0-bin-hadoop3/python/pyspark/sql/connect/client/core.py",
> line 1263, in _execute_and_fetch_as_iterator_
> _self._handle_error(error)_
> _File
> "/home/xxx/github/mytools/spark.home/spark-3.5.0-bin-hadoop3/python/pyspark/sql/connect/client/core.py",
> line 1502, in _handle_error_
> _self._handle_rpc_error(error)_
> _File
> "/home/xxx/github/mytools/spark.home/spark-3.5.0-bin-hadoop3/python/pyspark/sql/connect/client/core.py",
> line 1538, in _handle_rpc_error_
> _raise convert_exception(info, status.message) from None_
> _pyspark.errors.exceptions.connect.SparkConnectGrpcException:
> (org.apache.spark.SparkException) Job aborted due to stage failure: Task 0 in
> stage 0.0 failed 4 times, most recent failure: Lost task 0.3 in stage 0.0
> (TID 35) (10.19.183.93 executor 0): java.lang.ClassCastException: cannot
> assign instance of java.lang.invoke.SerializedLambda to field
> org.apache.spark.rdd.MapPartitionsRDD.f of type scala.Function3 in instance
> of org.apache.spark.rdd.MapPartitionsRDD_
> _at
> java.io.ObjectStreamClass$FieldReflector.setObjFieldValues(ObjectStreamClass.java:2301)_
> _at java.io.ObjectStreamClass.setObjFieldValues(ObjectStreamClass.java:1431)_
> _at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2437)_
> _at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:2355)_
> _at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:2213)_
> _at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1669)_
> _at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2431)_
> _at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:2355)_
> _at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:2213)_
> _at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1669)_
> _at java.io.ObjectInputStream.readObject(ObjectInputStream.java:503)_
> _at java.io.ObjectInputStream.readObject(ObjectInputStream.java:461)_
> _at
> org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:87)_
> _at
> org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:129)_
> _at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:86)_
> _at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:161)_
> _at org.apache.spark.scheduler.Task.run(Task.scala:141)_
> _at
> org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:620)_
> _at
> org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)_
> _at
> org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)_
> _at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)_
> _at org.apache.spark.executor.Executor$TaskRunner..._
>
>
>
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
