(parquet-java) branch master updated: GH-3156: Enable vectored IO by default (#3155)

[gangwu]

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

gangwu pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/parquet-java.git


The following commit(s) were added to refs/heads/master by this push:
     new 5468116c1 GH-3156: Enable vectored IO by default (#3155)
5468116c1 is described below

commit 5468116c19a47041faec64a0b513e536aa922fc7
Author: ahmarsuhail <ahmar.suh...@gmail.com>
AuthorDate: Mon Mar 3 15:09:10 2025 +0000

    GH-3156: Enable vectored IO by default (#3155)
---
 .../src/main/java/org/apache/parquet/ParquetReadOptions.java        | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git 
a/parquet-hadoop/src/main/java/org/apache/parquet/ParquetReadOptions.java 
b/parquet-hadoop/src/main/java/org/apache/parquet/ParquetReadOptions.java
index 8c05d0224..895d0670f 100644
--- a/parquet-hadoop/src/main/java/org/apache/parquet/ParquetReadOptions.java
+++ b/parquet-hadoop/src/main/java/org/apache/parquet/ParquetReadOptions.java
@@ -23,6 +23,7 @@ import static 
org.apache.parquet.format.converter.ParquetMetadataConverter.NO_FI
 import static 
org.apache.parquet.hadoop.ParquetInputFormat.BLOOM_FILTERING_ENABLED;
 import static 
org.apache.parquet.hadoop.ParquetInputFormat.COLUMN_INDEX_FILTERING_ENABLED;
 import static 
org.apache.parquet.hadoop.ParquetInputFormat.DICTIONARY_FILTERING_ENABLED;
+import static 
org.apache.parquet.hadoop.ParquetInputFormat.HADOOP_VECTORED_IO_DEFAULT;
 import static 
org.apache.parquet.hadoop.ParquetInputFormat.HADOOP_VECTORED_IO_ENABLED;
 import static 
org.apache.parquet.hadoop.ParquetInputFormat.OFF_HEAP_DECRYPT_BUFFER_ENABLED;
 import static 
org.apache.parquet.hadoop.ParquetInputFormat.PAGE_VERIFY_CHECKSUM_ENABLED;
@@ -56,7 +57,6 @@ public class ParquetReadOptions {
   private static final boolean STATS_FILTERING_ENABLED_DEFAULT = true;
   private static final boolean DICTIONARY_FILTERING_ENABLED_DEFAULT = true;
   private static final boolean COLUMN_INDEX_FILTERING_ENABLED_DEFAULT = true;
-  private static final boolean HADOOP_VECTORED_IO_ENABLED_DEFAULT = false;
   private static final int ALLOCATION_SIZE_DEFAULT = 8388608; // 8MB
   private static final boolean PAGE_VERIFY_CHECKSUM_ENABLED_DEFAULT = false;
   private static final boolean BLOOM_FILTER_ENABLED_DEFAULT = true;
@@ -253,7 +253,7 @@ public class ParquetReadOptions {
     protected boolean useStatsFilter = STATS_FILTERING_ENABLED_DEFAULT;
     protected boolean useDictionaryFilter = 
DICTIONARY_FILTERING_ENABLED_DEFAULT;
     protected boolean useRecordFilter = RECORD_FILTERING_ENABLED_DEFAULT;
-    protected boolean useHadoopVectoredIo = HADOOP_VECTORED_IO_ENABLED_DEFAULT;
+    protected boolean useHadoopVectoredIo = HADOOP_VECTORED_IO_DEFAULT;
     protected boolean useColumnIndexFilter = 
COLUMN_INDEX_FILTERING_ENABLED_DEFAULT;
     protected boolean usePageChecksumVerification = 
PAGE_VERIFY_CHECKSUM_ENABLED_DEFAULT;
     protected boolean useBloomFilter = BLOOM_FILTER_ENABLED_DEFAULT;
@@ -286,7 +286,7 @@ public class ParquetReadOptions {
       withCodecFactory(HadoopCodecs.newFactory(conf, 0));
       withRecordFilter(getFilter(conf));
       withMaxAllocationInBytes(conf.getInt(ALLOCATION_SIZE, 8388608));
-      withUseHadoopVectoredIo(conf.getBoolean(HADOOP_VECTORED_IO_ENABLED, 
HADOOP_VECTORED_IO_ENABLED_DEFAULT));
+      withUseHadoopVectoredIo(conf.getBoolean(HADOOP_VECTORED_IO_ENABLED, 
HADOOP_VECTORED_IO_DEFAULT));
       String badRecordThresh = conf.get(BAD_RECORD_THRESHOLD_CONF_KEY);
       if (badRecordThresh != null) {
         set(BAD_RECORD_THRESHOLD_CONF_KEY, badRecordThresh);