Hi Spark users and developers, Does anyone encounter any issue when a spark SQL job produces a lot of files (over 1 millions), the job hangs on the refresh method? I'm using spark 1.5.1. Below is the stack trace. I saw the parquet files are produced but the driver is doing something very intensively (it uses all the cpus). Does it mean Spark SQL cannot be used to produce over 1 million files in a single job?
Thread 528: (state = BLOCKED) - java.util.Arrays.copyOf(char[], int) @bci=1, line=2367 (Compiled frame) - java.lang.AbstractStringBuilder.expandCapacity(int) @bci=43, line=130 (Compiled frame) - java.lang.AbstractStringBuilder.ensureCapacityInternal(int) @bci=12, line=114 (Compiled frame) - java.lang.AbstractStringBuilder.append(java.lang.String) @bci=19, line=415 (Compiled frame) - java.lang.StringBuilder.append(java.lang.String) @bci=2, line=132 (Compiled frame) - org.apache.hadoop.fs.Path.toString() @bci=128, line=384 (Compiled frame) - org.apache.spark.sql.sources.HadoopFsRelation$FileStatusCache$$anonfun$listLeafFiles$1.apply(org.apache.hadoop.fs.FileStatus) @bci=4, line=447 (Compiled frame) - org.apache.spark.sql.sources.HadoopFsRelation$FileStatusCache$$anonfun$listLeafFiles$1.apply(java.lang.Object) @bci=5, line=447 (Compiled frame) - scala.collection.TraversableLike$$anonfun$map$1.apply(java.lang.Object) @bci=9, line=244 (Compiled frame) - scala.collection.TraversableLike$$anonfun$map$1.apply(java.lang.Object) @bci=2, line=244 (Compiled frame) - scala.collection.IndexedSeqOptimized$class.foreach(scala.collection.IndexedSeqOptimized, scala.Function1) @bci=22, line=33 (Compiled frame) - scala.collection.mutable.ArrayOps$ofRef.foreach(scala.Function1) @bci=2, line=108 (Compiled frame) - scala.collection.TraversableLike$class.map(scala.collection.TraversableLike, scala.Function1, scala.collection.generic.CanBuildFrom) @bci=17, line=244 (Compiled frame) - scala.collection.mutable.ArrayOps$ofRef.map(scala.Function1, scala.collection.generic.CanBuildFrom) @bci=3, line=108 (Interpreted frame) - org.apache.spark.sql.sources.HadoopFsRelation$FileStatusCache.listLeafFiles(java.lang.String[]) @bci=279, line=447 (Interpreted frame) - org.apache.spark.sql.sources.HadoopFsRelation$FileStatusCache.refresh() @bci=8, line=453 (Interpreted frame) - org.apache.spark.sql.sources.HadoopFsRelation.org$apache$spark$sql$sources$HadoopFsRelation$$fileStatusCache$lzycompute() @bci=26, line=465 (Interpreted frame) - org.apache.spark.sql.sources.HadoopFsRelation.org$apache$spark$sql$sources$HadoopFsRelation$$fileStatusCache() @bci=12, line=463 (Interpreted frame) - org.apache.spark.sql.sources.HadoopFsRelation.refresh() @bci=1, line=540 (Interpreted frame) - org.apache.spark.sql.execution.datasources.parquet.ParquetRelation.refresh() @bci=1, line=204 (Interpreted frame) - org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply$mcV$sp() @bci=392, line=152 (Interpreted frame) - org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply() @bci=1, line=108 (Interpreted frame) - org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply() @bci=1, line=108 (Interpreted frame) - org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(org.apache.spark.sql.SQLContext, org.apache.spark.sql.SQLContext$QueryExecution, scala.Function0) @bci=96, line=56 (Interpreted frame) - org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation.run(org.apache.spark.sql.SQLContext) @bci=718, line=108 (Interpreted frame) - org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute() @bci=20, line=57 (Interpreted frame) - org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult() @bci=15, line=57 (Interpreted frame) - org.apache.spark.sql.execution.ExecutedCommand.doExecute() @bci=12, line=69 (Interpreted frame) - org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply() @bci=11, line=140 (Interpreted frame) - org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply() @bci=1, line=138 (Interpreted frame) - org.apache.spark.rdd.RDDOperationScope$.withScope(org.apache.spark.SparkContext, java.lang.String, boolean, boolean, scala.Function0) @bci=131, line=147 (Interpreted frame) - org.apache.spark.sql.execution.SparkPlan.execute() @bci=189, line=138 (Interpreted frame) - org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute() @bci=21, line=933 (Interpreted frame) - org.apache.spark.sql.SQLContext$QueryExecution.toRdd() @bci=13, line=933 (Interpreted frame) - org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(org.apache.spark.sql.SQLContext, java.lang.String, java.lang.String[], org.apache.spark.sql.SaveMode, scala.collection.immutable.Map, org.apache.spark.sql.DataFrame) @bci=293, line=197 (Interpreted frame) - org.apache.spark.sql.DataFrameWriter.save() @bci=64, line=146 (Interpreted frame) - org.apache.spark.sql.DataFrameWriter.save(java.lang.String) @bci=24, line=137 (Interpreted frame) - org.apache.spark.sql.DataFrameWriter.parquet(java.lang.String) @bci=8, line=304 (Interpreted frame) Best Regards, Jerry
