This is an automated email from the ASF dual-hosted git repository.
sivabalan pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/hudi.git
from cbf9b83ca6 [HUDI-4792] Batch clean files to delete (#6580)
add 5e624698f7 [HUDI-4363] Support Clustering row writer to improve
performance (#6046)
No new revisions were added by this update.
Summary of changes:
.../hudi/client/HoodieInternalWriteStatus.java | 17 ++
.../org/apache/hudi/config/HoodieWriteConfig.java | 6 +-
.../MultipleSparkJobExecutionStrategy.java | 186 +++++++++++++++++----
...onsistentBucketClusteringExecutionStrategy.java | 14 ++
.../SparkSingleFileSortExecutionStrategy.java | 44 ++++-
.../SparkSortAndSizeExecutionStrategy.java | 38 ++++-
.../bulkinsert/RDDSpatialCurveSortPartitioner.java | 37 +---
...ws.java => RowSpatialCurveSortPartitioner.java} | 26 +--
.../SpatialCurveSortPartitionerBase.java | 83 +++++++++
.../hudi/io/storage/row/HoodieRowCreateHandle.java | 28 +++-
.../BulkInsertDataInternalWriterHelper.java | 17 +-
.../hudi/HoodieDatasetBulkInsertHelper.scala | 61 ++++++-
.../scala/org/apache/hudi/HoodieUnsafeRDD.scala | 0
.../org/apache/hudi/SparkAdapterSupport.scala | 8 +-
.../org/apache/spark/sql/HoodieUnsafeUtils.scala | 1 -
.../org/apache/spark/sql/hudi/SparkAdapter.scala | 14 +-
.../apache/hudi/common/config/HoodieConfig.java | 4 +
.../java/org/apache/hudi/common/fs/FSUtils.java | 4 +
.../org/apache/hudi/common/model/HoodieRecord.java | 2 +
.../hudi/hadoop/HoodieROTablePathFilter.java | 13 +-
.../org/apache/hudi/BaseFileOnlyRelation.scala | 1 -
.../main/scala/org/apache/hudi/DefaultSource.scala | 95 ++++++-----
.../TestHoodieSparkMergeOnReadTableClustering.java | 55 ++++--
.../apache/hudi/functional/TestCOWDataSource.scala | 12 ++
.../hudi/functional/TestLayoutOptimization.scala | 37 ++--
.../HoodieBulkInsertDataInternalWriter.java | 1 +
.../apache/spark/sql/adapter/Spark2Adapter.scala | 15 +-
.../HoodieBulkInsertDataInternalWriter.java | 2 +-
.../spark/sql/adapter/BaseSpark3Adapter.scala | 18 +-
29 files changed, 654 insertions(+), 185 deletions(-)
copy
hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/execution/bulkinsert/{NonSortPartitionerWithRows.java
=> RowSpatialCurveSortPartitioner.java} (50%)
create mode 100644
hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/execution/bulkinsert/SpatialCurveSortPartitionerBase.java
rename
{hudi-spark-datasource/hudi-spark-common/src/main/java/org/apache/hudi/internal
=>
hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/table/action/commit}/BulkInsertDataInternalWriterHelper.java
(90%)
rename {hudi-spark-datasource/hudi-spark-common =>
hudi-client/hudi-spark-client}/src/main/scala/org/apache/hudi/HoodieDatasetBulkInsertHelper.scala
(73%)
rename {hudi-spark-datasource/hudi-spark-common =>
hudi-client/hudi-spark-client}/src/main/scala/org/apache/hudi/HoodieUnsafeRDD.scala
(100%)
rename {hudi-spark-datasource/hudi-spark-common =>
hudi-client/hudi-spark-client}/src/main/scala/org/apache/spark/sql/HoodieUnsafeUtils.scala
(99%)
rename {hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/table =>
hudi-spark-datasource/hudi-spark/src/test/java/org/apache/hudi}/functional/TestHoodieSparkMergeOnReadTableClustering.java
(87%)
