I have configured a spark standalone cluster as follows: ``` # start spark master $SPARK_HOME/sbin/start-master.sh
# start 2 spark workers SPARK_WORKER_INSTANCES=2 $SPARK_HOME/sbin/start-worker.sh spark://localhost:7077 # start spark connect $SPARK_HOME/sbin/start-connect-server.sh --properties-file ./connect.properties --master spark://localhost:7077 ``` My properties file is defined as follows: ``` spark.serializer=org.apache.spark.serializer.KryoSerializer spark.plugins=io.dataflint.spark.SparkDataflintPlugin spark.jars.packages org.apache.spark:spark-connect_2.12:3.5.1,org.apache.hadoop:hadoop-aws:3.3.4,org.apache.hudi:hudi-aws:0.15.0,org.apache.hudi:hudi-spark3.5-bundle_2.12:0.15.0,org.apache.spark:spark-avro_2.12:3.5.1,software.amazon.awssdk:sso:2.18.40,io.dataflint:spark_2.12:0.2.2,net.snowflake:spark-snowflake_2.12:2.16.0-spark_3.4,net.snowflake:snowflake-jdbc:3.16.1 spark.driver.extraJavaOptions=-verbose:class spark.executor.extraJavaOptions=-verbose:class ``` Now I start my pyspark job which connects with this remote instance and then tries to query the table. The snowflake query is fired correctly. It shows up in my Snowflake query history, but then I start getting failures. ``` 24/07/07 22:37:26 INFO ErrorUtils: Spark Connect error during: execute. UserId: pbd. SessionId: 462444eb-82d3-475b-8dd0-ce35d5047405. 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 3) (192.168.29.6 executor 1): java.lang.ClassNotFoundException: net.snowflake.spark.snowflake.io.SnowflakeResultSetPartition at org.apache.spark.executor.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:124) at java.base/java.lang.ClassLoader.loadClass(ClassLoader.java:594) at java.base/java.lang.ClassLoader.loadClass(ClassLoader.java:527) at java.base/java.lang.Class.forName0(Native Method) at java.base/java.lang.Class.forName(Class.java:398) at org.apache.spark.serializer.JavaDeserializationStream$$anon$1.resolveClass(JavaSerializer.scala:71) at java.base/java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:2003) at java.base/java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1870) at java.base/java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:2201) at java.base/java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1687) at java.base/java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2496) at java.base/java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:2390) at java.base/java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:2228) at java.base/java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1687) at java.base/java.io.ObjectInputStream.readObject(ObjectInputStream.java:489) at java.base/java.io.ObjectInputStream.readObject(ObjectInputStream.java:447) at org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:87) at org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:129) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:579) at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128) at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628) at java.base/java.lang.Thread.run(Thread.java:829) Caused by: java.lang.ClassNotFoundException: net.snowflake.spark.snowflake.io.SnowflakeResultSetPartition at java.base/java.lang.ClassLoader.findClass(ClassLoader.java:724) at org.apache.spark.util.ParentClassLoader.findClass(ParentClassLoader.java:35) at java.base/java.lang.ClassLoader.loadClass(ClassLoader.java:594) at org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.java:40) at java.base/java.lang.ClassLoader.loadClass(ClassLoader.java:527) at org.apache.spark.executor.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:109) ... 21 more Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2856) at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2792) at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2791) at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62) at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2791) at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1247) at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1247) at scala.Option.foreach(Option.scala:407) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1247) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3060) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2994) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2983) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:989) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2398) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2419) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2438) at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530) at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483) at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:61) at org.apache.spark.sql.Dataset.collectFromPlan(Dataset.scala:4332) at org.apache.spark.sql.Dataset.$anonfun$head$1(Dataset.scala:3314) at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4322) at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546) at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4320) at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125) at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201) at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108) at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66) at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4320) at org.apache.spark.sql.Dataset.head(Dataset.scala:3314) at org.apache.spark.sql.Dataset.take(Dataset.scala:3537) at org.apache.spark.sql.Dataset.getRows(Dataset.scala:280) at org.apache.spark.sql.Dataset.showString(Dataset.scala:315) at org.apache.spark.sql.connect.planner.SparkConnectPlanner.transformShowString(SparkConnectPlanner.scala:249) at org.apache.spark.sql.connect.planner.SparkConnectPlanner.transformRelation(SparkConnectPlanner.scala:104) at org.apache.spark.sql.connect.execution.SparkConnectPlanExecution.handlePlan(SparkConnectPlanExecution.scala:64) at org.apache.spark.sql.connect.execution.ExecuteThreadRunner.handlePlan(ExecuteThreadRunner.scala:191) at org.apache.spark.sql.connect.execution.ExecuteThreadRunner.$anonfun$executeInternal$1(ExecuteThreadRunner.scala:159) at org.apache.spark.sql.connect.execution.ExecuteThreadRunner.$anonfun$executeInternal$1$adapted(ExecuteThreadRunner.scala:132) at org.apache.spark.sql.connect.service.SessionHolder.$anonfun$withSession$2(SessionHolder.scala:189) at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900) at org.apache.spark.sql.connect.service.SessionHolder.$anonfun$withSession$1(SessionHolder.scala:189) at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94) at org.apache.spark.sql.connect.service.SessionHolder.$anonfun$withContextClassLoader$1(SessionHolder.scala:176) at org.apache.spark.util.Utils$.withContextClassLoader(Utils.scala:178) at org.apache.spark.sql.connect.service.SessionHolder.withContextClassLoader(SessionHolder.scala:175) at org.apache.spark.sql.connect.service.SessionHolder.withSession(SessionHolder.scala:188) at org.apache.spark.sql.connect.execution.ExecuteThreadRunner.executeInternal(ExecuteThreadRunner.scala:132) at org.apache.spark.sql.connect.execution.ExecuteThreadRunner.org $apache$spark$sql$connect$execution$ExecuteThreadRunner$$execute(ExecuteThreadRunner.scala:84) at org.apache.spark.sql.connect.execution.ExecuteThreadRunner$ExecutionThread.run(ExecuteThreadRunner.scala:228) Caused by: java.lang.ClassNotFoundException: net.snowflake.spark.snowflake.io.SnowflakeResultSetPartition at org.apache.spark.executor.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:124) at java.base/java.lang.ClassLoader.loadClass(ClassLoader.java:594) at java.base/java.lang.ClassLoader.loadClass(ClassLoader.java:527) at java.base/java.lang.Class.forName0(Native Method) at java.base/java.lang.Class.forName(Class.java:398) at org.apache.spark.serializer.JavaDeserializationStream$$anon$1.resolveClass(JavaSerializer.scala:71) at java.base/java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:2003) at java.base/java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1870) at java.base/java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:2201) at java.base/java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1687) at java.base/java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2496) at java.base/java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:2390) at java.base/java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:2228) at java.base/java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1687) at java.base/java.io.ObjectInputStream.readObject(ObjectInputStream.java:489) at java.base/java.io.ObjectInputStream.readObject(ObjectInputStream.java:447) at org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:87) at org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:129) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:579) at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128) at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628) at java.base/java.lang.Thread.run(Thread.java:829) Caused by: java.lang.ClassNotFoundException: net.snowflake.spark.snowflake.io.SnowflakeResultSetPartition at java.base/java.lang.ClassLoader.findClass(ClassLoader.java:724) at org.apache.spark.util.ParentClassLoader.findClass(ParentClassLoader.java:35) at java.base/java.lang.ClassLoader.loadClass(ClassLoader.java:594) at org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.java:40) at java.base/java.lang.ClassLoader.loadClass(ClassLoader.java:527) at org.apache.spark.executor.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:109) ... 21 more ``` How do I debug & then fix this? Thank you.
