Parquet: Enable vectorized reads by default (#4196)

apache · Feb 23, 2022 · ec2f1ad · ec2f1ad
1 parent caefd6e
commit ec2f1ad
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 2 deletions.
diff --git a/core/src/main/java/org/apache/iceberg/TableProperties.java b/core/src/main/java/org/apache/iceberg/TableProperties.java
@@ -148,7 +148,7 @@ private TableProperties() {
   public static final long SPLIT_OPEN_FILE_COST_DEFAULT = 4 * 1024 * 1024; // 4MB
 
   public static final String PARQUET_VECTORIZATION_ENABLED = "read.parquet.vectorization.enabled";
-  public static final boolean PARQUET_VECTORIZATION_ENABLED_DEFAULT = false;
+  public static final boolean PARQUET_VECTORIZATION_ENABLED_DEFAULT = true;
 
   public static final String PARQUET_BATCH_SIZE = "read.parquet.vectorization.batch-size";
   public static final int PARQUET_BATCH_SIZE_DEFAULT = 5000;

diff --git a/.../src/test/java/org/apache/iceberg/spark/source/TestSparkTableUtilWithInMemoryCatalog.java b/.../src/test/java/org/apache/iceberg/spark/source/TestSparkTableUtilWithInMemoryCatalog.java
@@ -451,9 +451,10 @@ public void testImportTableWithInt96Timestamp() throws IOException {
       );
       Table table = TABLES.create(schema, PartitionSpec.unpartitioned(), tableLocation);
 
-      // assign a custom metrics config
+      // assign a custom metrics config and disable vectorized reads
       table.updateProperties()
           .set(TableProperties.DEFAULT_WRITE_METRICS_MODE, "full")
+          .set(TableProperties.PARQUET_VECTORIZATION_ENABLED, "false")
           .commit();
 
       File stagingDir = temp.newFolder("staging-dir");