Skip to content

Fix parquet bloom filters impl and tests #9245

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
danny0405 merged 1 commit into from
Jul 21, 2023
Merged

Fix parquet bloom filters impl and tests #9245

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 10 additions & 4 deletions hudi-common/src/main/java/org/apache/hudi/io/storage/HoodieBaseParquetWriter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,24 +87,30 @@ protected WriteSupport getWriteSupport(Configuration conf) {
this.recordCountForNextSizeCheck = ParquetProperties.DEFAULT_MINIMUM_RECORD_COUNT_FOR_CHECK;
}

/**
* Once we get parquet version >= 1.12 among all engines we can cleanup the reflexion hack.
*
* @param parquetWriterbuilder
* @param hadoopConf
*/
protected void handleParquetBloomFilters(ParquetWriter.Builder parquetWriterbuilder, Configuration hadoopConf) {
// inspired from https://github.com/apache/parquet-mr/blob/master/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetOutputFormat.java#L458-L464
hadoopConf.forEach(conf -> {
String key = conf.getKey();
if (key.startsWith(BLOOM_FILTER_ENABLED)) {
String column = key.substring(BLOOM_FILTER_ENABLED.length() + 1, key.length());
try {
Method method = parquetWriterbuilder.getClass().getDeclaredMethod("withBloomFilterEnabled");
method.invoke(column, Boolean.valueOf(conf.getValue()));
Method method = parquetWriterbuilder.getClass().getMethod("withBloomFilterEnabled", String.class, boolean.class);
method.invoke(parquetWriterbuilder, column, Boolean.valueOf(conf.getValue()).booleanValue());
} catch (NoSuchMethodException | IllegalAccessException | InvocationTargetException e) {
// skip
}
}
if (key.startsWith(BLOOM_FILTER_EXPECTED_NDV)) {
String column = key.substring(BLOOM_FILTER_EXPECTED_NDV.length() + 1, key.length());
try {
Method method = parquetWriterbuilder.getClass().getDeclaredMethod("withBloomFilterNDV");
method.invoke(column, Long.valueOf(conf.getValue(), -1));
Method method = parquetWriterbuilder.getClass().getMethod("withBloomFilterNDV", String.class, long.class);
method.invoke(parquetWriterbuilder, column, Long.valueOf(conf.getValue()).longValue());
} catch (NoSuchMethodException | IllegalAccessException | InvocationTargetException e) {
// skip
}
Expand Down
4 changes: 4 additions & 0 deletions hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/TestHoodieParquetBloom.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,6 +62,10 @@ class TestHoodieParquetBloomFilter {
def testBloomFilter(operation: WriteOperationType): Unit = {
// setup hadoop conf with bloom col enabled
spark.sparkContext.hadoopConfiguration.set("parquet.bloom.filter.enabled#bloom_col", "true")
spark.sparkContext.hadoopConfiguration.set("parquet.bloom.filter.expected.ndv#bloom_col", "2")
// ensure nothing but bloom can trigger read skip
spark.sql("set parquet.filter.columnindex.enabled=false")
spark.sql("set parquet.filter.stats.enabled=false")

val basePath = java.nio.file.Files.createTempDirectory("hoodie_bloom_source_path").toAbsolutePath.toString
val opts = Map(
Expand Down