From d52d085f273cc32e3fb6e46f6c4c247cfec78361 Mon Sep 17 00:00:00 2001
From: Dongjoon Hyun <dongjoon@apache.org>
Date: Sun, 2 Feb 2025 19:11:13 -0800
Subject: [PATCH 1/2] [SPARK-51064][SQL] Enable
 `spark.sql.sources.v2.bucketing.enabled` by default

---
 .../src/main/scala/org/apache/spark/sql/internal/SQLConf.scala | 2 +-
 .../org/apache/spark/sql/DynamicPartitionPruningSuite.scala    | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala
index ef1a6521eb913..b3c7da3685956 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala
@@ -1729,7 +1729,7 @@ object SQLConf {
         "avoid shuffle if necessary.")
       .version("3.3.0")
       .booleanConf
-      .createWithDefault(false)
+      .createWithDefault(true)
 
   val V2_BUCKETING_PUSH_PART_VALUES_ENABLED =
     buildConf("spark.sql.sources.v2.bucketing.pushPartValues.enabled")
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DynamicPartitionPruningSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DynamicPartitionPruningSuite.scala
index 2c24cc7d570ba..1ed5ea4216a9f 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/DynamicPartitionPruningSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/DynamicPartitionPruningSuite.scala
@@ -1217,7 +1217,8 @@ abstract class DynamicPartitionPruningSuiteBase
   test("SPARK-32509: Unused Dynamic Pruning filter shouldn't affect " +
     "canonicalization and exchange reuse") {
     withSQLConf(SQLConf.DYNAMIC_PARTITION_PRUNING_REUSE_BROADCAST_ONLY.key -> "true") {
-      withSQLConf(SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "-1") {
+      withSQLConf(SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "-1",
+          SQLConf.V2_BUCKETING_ENABLED.key -> "false") {
         val df = sql(
           """ WITH view1 as (
             |   SELECT f.store_id FROM fact_stats f WHERE f.units_sold = 70

From 658b4003bade30d4039d2efb5b551a4ef716b816 Mon Sep 17 00:00:00 2001
From: Dongjoon Hyun <dongjoon@apache.org>
Date: Mon, 3 Feb 2025 10:34:36 -0800
Subject: [PATCH 2/2] Update doc too

---
 docs/sql-performance-tuning.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/sql-performance-tuning.md b/docs/sql-performance-tuning.md
index 12b79828e44cb..39efdc3df3645 100644
--- a/docs/sql-performance-tuning.md
+++ b/docs/sql-performance-tuning.md
@@ -441,7 +441,7 @@ The following SQL properties enable Storage Partition Join in different join que
     <thead><tr><th>Property Name</th><th>Default</th><th>Meaning</th><th>Since Version</th></tr></thead>
     <tr>
       <td><code>spark.sql.sources.v2.bucketing.enabled</code></td>
-      <td>false</td>
+      <td>true</td>
       <td>
         When true, try to eliminate shuffle by using the partitioning reported by a compatible V2 data source.
       </td>