(paimon) branch master updated: [core] Fix parquet performance regression in reader init (#6802)

[lzljs3620320]

This is an automated email from the ASF dual-hosted git repository.

lzljs3620320 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/paimon.git


The following commit(s) were added to refs/heads/master by this push:
     new 8ba32333f9 [core] Fix parquet performance regression in reader init 
(#6802)
8ba32333f9 is described below

commit 8ba32333f945582eb9a8eb2495277f78de56e232
Author: Jiao Mingye <35512473+mxdzs0...@users.noreply.github.com>
AuthorDate: Sun Dec 14 20:30:08 2025 +0800

    [core] Fix parquet performance regression in reader init (#6802)
---
 .../java/org/apache/paimon/format/parquet/ParquetReaderFactory.java   | 4 +++-
 .../src/main/java/org/apache/paimon/format/parquet/ParquetUtil.java   | 3 ++-
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git 
a/paimon-format/src/main/java/org/apache/paimon/format/parquet/ParquetReaderFactory.java
 
b/paimon-format/src/main/java/org/apache/paimon/format/parquet/ParquetReaderFactory.java
index b27c81e332..5611bda959 100644
--- 
a/paimon-format/src/main/java/org/apache/paimon/format/parquet/ParquetReaderFactory.java
+++ 
b/paimon-format/src/main/java/org/apache/paimon/format/parquet/ParquetReaderFactory.java
@@ -36,6 +36,7 @@ import org.apache.paimon.utils.Pair;
 import org.apache.paimon.utils.Preconditions;
 
 import org.apache.parquet.ParquetReadOptions;
+import org.apache.parquet.conf.PlainParquetConfiguration;
 import org.apache.parquet.filter2.compat.FilterCompat;
 import org.apache.parquet.hadoop.ParquetFileReader;
 import org.apache.parquet.hadoop.ParquetInputFormat;
@@ -101,7 +102,8 @@ public class ParquetReaderFactory implements 
FormatReaderFactory {
     public FileRecordReader<InternalRow> 
createReader(FormatReaderFactory.Context context)
             throws IOException {
         ParquetReadOptions.Builder builder =
-                ParquetReadOptions.builder().withRange(0, context.fileSize());
+                ParquetReadOptions.builder(new PlainParquetConfiguration())
+                        .withRange(0, context.fileSize());
         setReadOptions(builder);
 
         ParquetFileReader reader =
diff --git 
a/paimon-format/src/main/java/org/apache/paimon/format/parquet/ParquetUtil.java 
b/paimon-format/src/main/java/org/apache/paimon/format/parquet/ParquetUtil.java
index 0ec4fa162a..26b6a7b4e9 100644
--- 
a/paimon-format/src/main/java/org/apache/paimon/format/parquet/ParquetUtil.java
+++ 
b/paimon-format/src/main/java/org/apache/paimon/format/parquet/ParquetUtil.java
@@ -26,6 +26,7 @@ import org.apache.paimon.utils.Pair;
 
 import org.apache.parquet.ParquetReadOptions;
 import org.apache.parquet.column.statistics.Statistics;
+import org.apache.parquet.conf.PlainParquetConfiguration;
 import org.apache.parquet.hadoop.ParquetFileReader;
 import org.apache.parquet.hadoop.metadata.BlockMetaData;
 import org.apache.parquet.hadoop.metadata.ColumnChunkMetaData;
@@ -83,7 +84,7 @@ public class ParquetUtil {
             throws IOException {
         return new ParquetFileReader(
                 ParquetInputFile.fromPath(fileIO, path, length),
-                ParquetReadOptions.builder().build(),
+                ParquetReadOptions.builder(new 
PlainParquetConfiguration()).build(),
                 null);
     }