and124578963 commented on PR #12799:
URL: https://github.com/apache/iceberg/pull/12799#issuecomment-2912973308
Hey. I had a problem with this commit. As I understand my path start with
s3a://, not s3://. How to configure it?
After removing the commit, all is working well.
```
25/05/27 13:13:38 ERROR org.apache.spark.executor.Executor: Exception in
task 2.0 in stage 2.0 (TID 10)
java.lang.IllegalStateException: [BUG] S3 client for storage path not
available:
s3a://spark-nt/load_test_delete_warehouse/gen_transaction_icb_year/data/TRANSACTION_DATE_year=2003/00115-938-a969331b-32bf-4df2-a897-8c9dbc4a7c1a-0-00001.parquet
at
org.apache.iceberg.relocated.com.google.common.base.Preconditions.checkState(Preconditions.java:603)
~[iceberg-spark-runtime-3.5_2.12-iceberg-comet-trunk.jar:?]
at
org.apache.iceberg.aws.s3.S3FileIO.clientForStoragePath(S3FileIO.java:427)
~[iceberg-spark-runtime-3.5_2.12-iceberg-comet-trunk.jar:?]
at org.apache.iceberg.aws.s3.S3FileIO.newInputFile(S3FileIO.java:184)
~[iceberg-spark-runtime-3.5_2.12-iceberg-comet-trunk.jar:?]
at
org.apache.iceberg.encryption.EncryptingFileIO.wrap(EncryptingFileIO.java:150)
~[iceberg-spark-runtime-3.5_2.12-iceberg-comet-trunk.jar:?]
at
org.apache.iceberg.relocated.com.google.common.collect.Iterators$6.transform(Iterators.java:828)
~[iceberg-spark-runtime-3.5_2.12-iceberg-comet-trunk.jar:?]
at
org.apache.iceberg.relocated.com.google.common.collect.TransformedIterator.next(TransformedIterator.java:51)
~[iceberg-spark-runtime-3.5_2.12-iceberg-comet-trunk.jar:?]
at
org.apache.iceberg.relocated.com.google.common.collect.TransformedIterator.next(TransformedIterator.java:51)
~[iceberg-spark-runtime-3.5_2.12-iceberg-comet-trunk.jar:?]
at
org.apache.iceberg.encryption.EncryptingFileIO.bulkDecrypt(EncryptingFileIO.java:63)
~[iceberg-spark-runtime-3.5_2.12-iceberg-comet-trunk.jar:?]
at
org.apache.iceberg.spark.source.BaseReader.inputFiles(BaseReader.java:177)
~[iceberg-spark-runtime-3.5_2.12-iceberg-comet-trunk.jar:?]
at
org.apache.iceberg.spark.source.BaseReader.getInputFile(BaseReader.java:170)
~[iceberg-spark-runtime-3.5_2.12-iceberg-comet-trunk.jar:?]
at
org.apache.iceberg.spark.source.BatchDataReader.open(BatchDataReader.java:100)
~[iceberg-spark-runtime-3.5_2.12-iceberg-comet-trunk.jar:?]
at
org.apache.iceberg.spark.source.BatchDataReader.open(BatchDataReader.java:43)
~[iceberg-spark-runtime-3.5_2.12-iceberg-comet-trunk.jar:?]
at org.apache.iceberg.spark.source.BaseReader.next(BaseReader.java:134)
~[iceberg-spark-runtime-3.5_2.12-iceberg-comet-trunk.jar:?]
at
org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:120)
~[spark-sql_2.12-3.5.4.jar:3.5.4]
at
org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:158)
~[spark-sql_2.12-3.5.4.jar:3.5.4]
at
org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:63)
~[spark-sql_2.12-3.5.4.jar:3.5.4]
at
org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:63)
~[spark-sql_2.12-3.5.4.jar:3.5.4]
at scala.Option.exists(Option.scala:376) ~[scala-library-2.12.18.jar:?]
at
org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:63)
~[spark-sql_2.12-3.5.4.jar:3.5.4]
at
org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:97)
~[spark-sql_2.12-3.5.4.jar:3.5.4]
at
org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:63)
~[spark-sql_2.12-3.5.4.jar:3.5.4]
at
org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
~[spark-core_2.12-3.5.4.jar:3.5.4]
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
~[scala-library-2.12.18.jar:?]
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$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)
~[spark-sql_2.12-3.5.4.jar:3.5.4]
at
org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
~[spark-sql_2.12-3.5.4.jar:3.5.4]
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
~[scala-library-2.12.18.jar:?]
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
~[scala-library-2.12.18.jar:?]
at
org.apache.spark.util.random.SamplingUtils$.reservoirSampleAndCount(SamplingUtils.scala:41)
~[spark-core_2.12-3.5.4.jar:3.5.4]
at
org.apache.spark.RangePartitioner$.$anonfun$sketch$1(Partitioner.scala:322)
~[spark-core_2.12-3.5.4.jar:3.5.4]
at
org.apache.spark.RangePartitioner$.$anonfun$sketch$1$adapted(Partitioner.scala:320)
~[spark-core_2.12-3.5.4.jar:3.5.4]
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsWithIndex$2(RDD.scala:910)
~[spark-core_2.12-3.5.4.jar:3.5.4]
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsWithIndex$2$adapted(RDD.scala:910)
~[spark-core_2.12-3.5.4.jar:3.5.4]
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
