Hi all,
I am reading a parquet file like this and it gives
java.lang.IllegalArgumentException.
However i can work with other parquet files (such as nyc taxi parquet
files) without any issue. I have copied the full error log as well. Can you
please check once and let me know how to fix this?
import pyspark
from pyspark.sql import SparkSession
spark=SparkSession.builder.appName("testPyspark").config("spark.executor.memory",
"20g").config("spark.driver.memory", "50g").getOrCreate()
df=spark.read.parquet("/data/202301/account_cycle")
df.printSchema() # worksfine
df.count() #worksfine
df.show()# getting below error
>>> df.show()
23/07/03 18:07:20 INFO FileSourceStrategy: Pushed Filters:
23/07/03 18:07:20 INFO FileSourceStrategy: Post-Scan Filters:
23/07/03 18:07:20 INFO FileSourceStrategy: Output Data Schema:
struct<account_cycle_serial: bigint, account_serial: bigint,
account_status: string, currency_code: string, opened_dt: date ... 30 more
fields>
23/07/03 18:07:20 INFO MemoryStore: Block broadcast_19 stored as values in
memory (estimated size 540.6 KiB, free 26.5 GiB)
23/07/03 18:07:20 INFO MemoryStore: Block broadcast_19_piece0 stored as
bytes in memory (estimated size 46.0 KiB, free 26.5 GiB)
23/07/03 18:07:20 INFO BlockManagerInfo: Added broadcast_19_piece0 in
memory on mynode:41055 (size: 46.0 KiB, free: 26.5 GiB)
23/07/03 18:07:20 INFO SparkContext: Created broadcast 19 from showString
at NativeMethodAccessorImpl.java:0
23/07/03 18:07:20 INFO FileSourceScanExec: Planning scan with bin packing,
max size: 134217728 bytes, open cost is considered as scanning 4194304
bytes.
23/07/03 18:07:20 INFO SparkContext: Starting job: showString at
NativeMethodAccessorImpl.java:0
23/07/03 18:07:20 INFO DAGScheduler: Got job 13 (showString at
NativeMethodAccessorImpl.java:0) with 1 output partitions
23/07/03 18:07:20 INFO DAGScheduler: Final stage: ResultStage 14
(showString at NativeMethodAccessorImpl.java:0)
23/07/03 18:07:20 INFO DAGScheduler: Parents of final stage: List()
23/07/03 18:07:20 INFO DAGScheduler: Missing parents: List()
23/07/03 18:07:20 INFO DAGScheduler: Submitting ResultStage 14
(MapPartitionsRDD[42] at showString at NativeMethodAccessorImpl.java:0),
which has no missing parents
23/07/03 18:07:20 INFO MemoryStore: Block broadcast_20 stored as values in
memory (estimated size 38.1 KiB, free 26.5 GiB)
23/07/03 18:07:20 INFO MemoryStore: Block broadcast_20_piece0 stored as
bytes in memory (estimated size 10.5 KiB, free 26.5 GiB)
23/07/03 18:07:20 INFO BlockManagerInfo: Added broadcast_20_piece0 in
memory on mynode:41055 (size: 10.5 KiB, free: 26.5 GiB)
23/07/03 18:07:20 INFO SparkContext: Created broadcast 20 from broadcast at
DAGScheduler.scala:1478
23/07/03 18:07:20 INFO DAGScheduler: Submitting 1 missing tasks from
ResultStage 14 (MapPartitionsRDD[42] at showString at
NativeMethodAccessorImpl.java:0) (first 15 tasks are for partitions
Vector(0))
23/07/03 18:07:20 INFO TaskSchedulerImpl: Adding task set 14.0 with 1 tasks
resource profile 0
23/07/03 18:07:20 INFO TaskSetManager: Starting task 0.0 in stage 14.0 (TID
48) (mynode, executor driver, partition 0, PROCESS_LOCAL, 4890 bytes)
taskResourceAssignments Map()
23/07/03 18:07:20 INFO Executor: Running task 0.0 in stage 14.0 (TID 48)
23/07/03 18:07:20 INFO FileScanRDD: Reading File path:
file:///data/202301/account_cycle/account_cycle-202301-53.parquet, range:
0-134217728, partition values: [empty row]
23/07/03 18:07:20 ERROR Executor: Exception in task 0.0 in stage 14.0 (TID
48)
java.lang.IllegalArgumentException
at java.nio.Buffer.limit(Buffer.java:275)
at org.xerial.snappy.Snappy.uncompress(Snappy.java:553)
at
org.apache.parquet.hadoop.codec.SnappyDecompressor.decompress(SnappyDecompressor.java:71)
at
org.apache.parquet.hadoop.codec.NonBlockedDecompressorStream.read(NonBlockedDecompressorStream.java:51)
at java.io.DataInputStream.readFully(DataInputStream.java:195)
at java.io.DataInputStream.readFully(DataInputStream.java:169)
at
org.apache.parquet.bytes.BytesInput$StreamBytesInput.toByteArray(BytesInput.java:286)
at
org.apache.parquet.bytes.BytesInput.toByteBuffer(BytesInput.java:237)
at
org.apache.parquet.bytes.BytesInput.toInputStream(BytesInput.java:246)
at
org.apache.parquet.column.values.dictionary.PlainValuesDictionary$PlainLongDictionary.<init>(PlainValuesDictionary.java:154)
at
org.apache.parquet.column.Encoding$1.initDictionary(Encoding.java:96)
at
org.apache.parquet.column.Encoding$5.initDictionary(Encoding.java:163)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedColumnReader.<init>(VectorizedColumnReader.java:114)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.checkEndOfRowGroup(VectorizedParquetRecordReader.java:352)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextBatch(VectorizedParquetRecordReader.java:293)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextKeyValue(VectorizedParquetRecordReader.java:196)
at
org.apache.spark.sql.execution.datasources.RecordReaderIterator.hasNext(RecordReaderIterator.scala:39)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:104)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:191)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:104)
at
org.apache.spark.sql.execution.FileSourceScanExec$$anon$1.hasNext(DataSourceScanExec.scala:522)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.columnartorow_nextBatch_0$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown
Source)
at
org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at
org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:759)
at
org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:350)
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:898)
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:898)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
at
org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:131)
at
org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:506)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1491)
at
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:509)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:750)
23/07/03 18:07:20 WARN TaskSetManager: Lost task 0.0 in stage 14.0 (TID 48)
(mynode executor driver): java.lang.IllegalArgumentException
at java.nio.Buffer.limit(Buffer.java:275)
at org.xerial.snappy.Snappy.uncompress(Snappy.java:553)
at
org.apache.parquet.hadoop.codec.SnappyDecompressor.decompress(SnappyDecompressor.java:71)
at
org.apache.parquet.hadoop.codec.NonBlockedDecompressorStream.read(NonBlockedDecompressorStream.java:51)
at java.io.DataInputStream.readFully(DataInputStream.java:195)
at java.io.DataInputStream.readFully(DataInputStream.java:169)
at
org.apache.parquet.bytes.BytesInput$StreamBytesInput.toByteArray(BytesInput.java:286)
at
org.apache.parquet.bytes.BytesInput.toByteBuffer(BytesInput.java:237)
at
org.apache.parquet.bytes.BytesInput.toInputStream(BytesInput.java:246)
at
org.apache.parquet.column.values.dictionary.PlainValuesDictionary$PlainLongDictionary.<init>(PlainValuesDictionary.java:154)
at
org.apache.parquet.column.Encoding$1.initDictionary(Encoding.java:96)
at
org.apache.parquet.column.Encoding$5.initDictionary(Encoding.java:163)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedColumnReader.<init>(VectorizedColumnReader.java:114)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.checkEndOfRowGroup(VectorizedParquetRecordReader.java:352)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextBatch(VectorizedParquetRecordReader.java:293)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextKeyValue(VectorizedParquetRecordReader.java:196)
at
org.apache.spark.sql.execution.datasources.RecordReaderIterator.hasNext(RecordReaderIterator.scala:39)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:104)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:191)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:104)
at
org.apache.spark.sql.execution.FileSourceScanExec$$anon$1.hasNext(DataSourceScanExec.scala:522)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.columnartorow_nextBatch_0$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown
Source)
at
org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at
org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:759)
at
org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:350)
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:898)
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:898)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
at
org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:131)
at
org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:506)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1491)
at
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:509)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:750)
23/07/03 18:07:20 ERROR TaskSetManager: Task 0 in stage 14.0 failed 1
times; aborting job
23/07/03 18:07:20 INFO TaskSchedulerImpl: Removed TaskSet 14.0, whose tasks
have all completed, from pool
23/07/03 18:07:20 INFO TaskSchedulerImpl: Cancelling stage 14
23/07/03 18:07:20 INFO TaskSchedulerImpl: Killing all running tasks in
stage 14: Stage cancelled
23/07/03 18:07:20 INFO DAGScheduler: ResultStage 14 (showString at
NativeMethodAccessorImpl.java:0) failed in 0.278 s due to Job aborted due
to stage failure: Task 0 in stage 14.0 failed 1 times, most recent failure:
Lost task 0.0 in stage 14.0 (TID 48) (mynode executor driver):
java.lang.IllegalArgumentException
at java.nio.Buffer.limit(Buffer.java:275)
at org.xerial.snappy.Snappy.uncompress(Snappy.java:553)
at
org.apache.parquet.hadoop.codec.SnappyDecompressor.decompress(SnappyDecompressor.java:71)
at
org.apache.parquet.hadoop.codec.NonBlockedDecompressorStream.read(NonBlockedDecompressorStream.java:51)
at java.io.DataInputStream.readFully(DataInputStream.java:195)
at java.io.DataInputStream.readFully(DataInputStream.java:169)
at
org.apache.parquet.bytes.BytesInput$StreamBytesInput.toByteArray(BytesInput.java:286)
at
org.apache.parquet.bytes.BytesInput.toByteBuffer(BytesInput.java:237)
at
org.apache.parquet.bytes.BytesInput.toInputStream(BytesInput.java:246)
at
org.apache.parquet.column.values.dictionary.PlainValuesDictionary$PlainLongDictionary.<init>(PlainValuesDictionary.java:154)
at
org.apache.parquet.column.Encoding$1.initDictionary(Encoding.java:96)
at
org.apache.parquet.column.Encoding$5.initDictionary(Encoding.java:163)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedColumnReader.<init>(VectorizedColumnReader.java:114)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.checkEndOfRowGroup(VectorizedParquetRecordReader.java:352)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextBatch(VectorizedParquetRecordReader.java:293)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextKeyValue(VectorizedParquetRecordReader.java:196)
at
org.apache.spark.sql.execution.datasources.RecordReaderIterator.hasNext(RecordReaderIterator.scala:39)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:104)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:191)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:104)
at
org.apache.spark.sql.execution.FileSourceScanExec$$anon$1.hasNext(DataSourceScanExec.scala:522)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.columnartorow_nextBatch_0$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown
Source)
at
org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at
org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:759)
at
org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:350)
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:898)
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:898)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
at
org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:131)
at
org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:506)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1491)
at
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:509)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:750)
Driver stacktrace:
23/07/03 18:07:20 INFO DAGScheduler: Job 13 failed: showString at
NativeMethodAccessorImpl.java:0, took 0.280998 s
23/07/03 18:07:21 INFO BlockManagerInfo: Removed broadcast_5_piece0 on
mynode:41055 in memory (size: 10.5 KiB, free: 26.5 GiB)
23/07/03 18:07:21 INFO BlockManagerInfo: Removed broadcast_16_piece0 on
mynode:41055 in memory (size: 46.0 KiB, free: 26.5 GiB)
23/07/03 18:07:21 INFO BlockManagerInfo: Removed broadcast_10_piece0 on
mynode:41055 in memory (size: 46.0 KiB, free: 26.5 GiB)
23/07/03 18:07:21 INFO BlockManagerInfo: Removed broadcast_15_piece0 on
mynode:41055 in memory (size: 46.9 KiB, free: 26.5 GiB)
23/07/03 18:07:21 INFO BlockManagerInfo: Removed broadcast_18_piece0 on
mynode:41055 in memory (size: 46.9 KiB, free: 26.5 GiB)
23/07/03 18:07:21 INFO BlockManagerInfo: Removed broadcast_8_piece0 on
mynode:41055 in memory (size: 10.5 KiB, free: 26.5 GiB)
23/07/03 18:07:21 INFO BlockManagerInfo: Removed broadcast_6_piece0 on
mynode:41055 in memory (size: 46.9 KiB, free: 26.5 GiB)
23/07/03 18:07:21 INFO BlockManagerInfo: Removed broadcast_11_piece0 on
mynode:41055 in memory (size: 10.5 KiB, free: 26.5 GiB)
23/07/03 18:07:21 INFO BlockManagerInfo: Removed broadcast_14_piece0 on
mynode:41055 in memory (size: 10.5 KiB, free: 26.5 GiB)
23/07/03 18:07:21 INFO BlockManagerInfo: Removed broadcast_12_piece0 on
mynode:41055 in memory (size: 46.9 KiB, free: 26.5 GiB)
23/07/03 18:07:21 INFO BlockManagerInfo: Removed broadcast_7_piece0 on
mynode:41055 in memory (size: 46.0 KiB, free: 26.5 GiB)
23/07/03 18:07:21 INFO BlockManagerInfo: Removed broadcast_13_piece0 on
mynode:41055 in memory (size: 46.0 KiB, free: 26.5 GiB)
23/07/03 18:07:21 INFO BlockManagerInfo: Removed broadcast_3_piece0 on
mynode:41055 in memory (size: 5.5 KiB, free: 26.5 GiB)
23/07/03 18:07:21 INFO BlockManagerInfo: Removed broadcast_17_piece0 on
mynode:41055 in memory (size: 10.5 KiB, free: 26.5 GiB)
23/07/03 18:07:21 INFO BlockManagerInfo: Removed broadcast_4_piece0 on
mynode:41055 in memory (size: 46.0 KiB, free: 26.5 GiB)
23/07/03 18:07:21 INFO BlockManagerInfo: Removed broadcast_9_piece0 on
mynode:41055 in memory (size: 46.9 KiB, free: 26.5 GiB)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File
"/nix/store/jkyamgd3bd97bjy8vd4nawlnyz23lk2w-spark-3.2.2/lib/spark-3.2.2/python/pyspark/sql/dataframe.py",
line 494, in show
print(self._jdf.showString(n, 20, vertical))
File
"/nix/store/jkyamgd3bd97bjy8vd4nawlnyz23lk2w-spark-3.2.2/lib/spark-3.2.2/python/lib/py4j-0.10.9.5-src.zip/py4j/java_gateway.py",
line 1321, in __call__
File
"/nix/store/jkyamgd3bd97bjy8vd4nawlnyz23lk2w-spark-3.2.2/lib/spark-3.2.2/python/pyspark/sql/utils.py",
line 111, in deco
return f(*a, **kw)
File
"/nix/store/jkyamgd3bd97bjy8vd4nawlnyz23lk2w-spark-3.2.2/lib/spark-3.2.2/python/lib/py4j-0.10.9.5-src.zip/py4j/protocol.py",
line 326, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o64.showString.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0
in stage 14.0 failed 1 times, most recent failure: Lost task 0.0 in stage
14.0 (TID 48) (mynode executor driver): java.lang.IllegalArgumentException
at java.nio.Buffer.limit(Buffer.java:275)
at org.xerial.snappy.Snappy.uncompress(Snappy.java:553)
at
org.apache.parquet.hadoop.codec.SnappyDecompressor.decompress(SnappyDecompressor.java:71)
at
org.apache.parquet.hadoop.codec.NonBlockedDecompressorStream.read(NonBlockedDecompressorStream.java:51)
at java.io.DataInputStream.readFully(DataInputStream.java:195)
at java.io.DataInputStream.readFully(DataInputStream.java:169)
at
org.apache.parquet.bytes.BytesInput$StreamBytesInput.toByteArray(BytesInput.java:286)
at
org.apache.parquet.bytes.BytesInput.toByteBuffer(BytesInput.java:237)
at
org.apache.parquet.bytes.BytesInput.toInputStream(BytesInput.java:246)
at
org.apache.parquet.column.values.dictionary.PlainValuesDictionary$PlainLongDictionary.<init>(PlainValuesDictionary.java:154)
at
org.apache.parquet.column.Encoding$1.initDictionary(Encoding.java:96)
at
org.apache.parquet.column.Encoding$5.initDictionary(Encoding.java:163)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedColumnReader.<init>(VectorizedColumnReader.java:114)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.checkEndOfRowGroup(VectorizedParquetRecordReader.java:352)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextBatch(VectorizedParquetRecordReader.java:293)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextKeyValue(VectorizedParquetRecordReader.java:196)
at
org.apache.spark.sql.execution.datasources.RecordReaderIterator.hasNext(RecordReaderIterator.scala:39)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:104)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:191)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:104)
at
org.apache.spark.sql.execution.FileSourceScanExec$$anon$1.hasNext(DataSourceScanExec.scala:522)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.columnartorow_nextBatch_0$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown
Source)
at
org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at
org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:759)
at
org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:350)
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:898)
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:898)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
at
org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:131)
at
org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:506)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1491)
at
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:509)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:750)
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2454)
at
org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2403)
at
org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2402)
at
scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at
scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at
scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2402)
at
org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1160)
at
org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1160)
at scala.Option.foreach(Option.scala:407)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1160)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2642)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2584)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2573)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at
org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:938)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2214)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2235)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2254)
at
org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:492)
at
org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:445)
at
org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:48)
at org.apache.spark.sql.Dataset.collectFromPlan(Dataset.scala:3715)
at org.apache.spark.sql.Dataset.$anonfun$head$1(Dataset.scala:2728)
at
org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3706)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
at
org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
at
org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3704)
at org.apache.spark.sql.Dataset.head(Dataset.scala:2728)
at org.apache.spark.sql.Dataset.take(Dataset.scala:2935)
at org.apache.spark.sql.Dataset.getRows(Dataset.scala:287)
at org.apache.spark.sql.Dataset.showString(Dataset.scala:326)
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:282)
at
py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at
py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)
at py4j.ClientServerConnection.run(ClientServerConnection.java:106)
at java.lang.Thread.run(Thread.java:750)
Caused by: java.lang.IllegalArgumentException
at java.nio.Buffer.limit(Buffer.java:275)
at org.xerial.snappy.Snappy.uncompress(Snappy.java:553)
at
org.apache.parquet.hadoop.codec.SnappyDecompressor.decompress(SnappyDecompressor.java:71)
at
org.apache.parquet.hadoop.codec.NonBlockedDecompressorStream.read(NonBlockedDecompressorStream.java:51)
at java.io.DataInputStream.readFully(DataInputStream.java:195)
at java.io.DataInputStream.readFully(DataInputStream.java:169)
at
org.apache.parquet.bytes.BytesInput$StreamBytesInput.toByteArray(BytesInput.java:286)
at
org.apache.parquet.bytes.BytesInput.toByteBuffer(BytesInput.java:237)
at
org.apache.parquet.bytes.BytesInput.toInputStream(BytesInput.java:246)
at
org.apache.parquet.column.values.dictionary.PlainValuesDictionary$PlainLongDictionary.<init>(PlainValuesDictionary.java:154)
at
org.apache.parquet.column.Encoding$1.initDictionary(Encoding.java:96)
at
org.apache.parquet.column.Encoding$5.initDictionary(Encoding.java:163)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedColumnReader.<init>(VectorizedColumnReader.java:114)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.checkEndOfRowGroup(VectorizedParquetRecordReader.java:352)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextBatch(VectorizedParquetRecordReader.java:293)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextKeyValue(VectorizedParquetRecordReader.java:196)
at
org.apache.spark.sql.execution.datasources.RecordReaderIterator.hasNext(RecordReaderIterator.scala:39)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:104)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:191)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:104)
at
org.apache.spark.sql.execution.FileSourceScanExec$$anon$1.hasNext(DataSourceScanExec.scala:522)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.columnartorow_nextBatch_0$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown
Source)
at
org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at
org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:759)
at
org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:350)
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:898)
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:898)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
at
org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:131)
at
org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:506)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1491)
at
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:509)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
... 1 more
Thanks,
Elango
--
Thanks,
Elango
