Merge pull request #1657 from apache/master

Create a new pull request by comparing changes across two branches

common/utils/src/main/resources/error/error-conditions.json

@@ -3735,6 +3735,18 @@
     ],
     "sqlState" : "42K06"
   },
+  "STATE_STORE_KEY_ROW_FORMAT_VALIDATION_FAILURE" : {
+    "message" : [
+      "The streaming query failed to validate written state for key row.",
+      "The following reasons may cause this:",
+      "1. An old Spark version wrote the checkpoint that is incompatible with the current one",
+      "2. Corrupt checkpoint files",
+      "3. The query changed in an incompatible way between restarts",
+      "For the first case, use a new checkpoint directory or use the original Spark version",
+      "to process the streaming state. Retrieved error_message=<errorMsg>"
+    ],
+    "sqlState" : "XX000"
+  },
   "STATE_STORE_KEY_SCHEMA_NOT_COMPATIBLE" : {
     "message" : [
       "Provided key schema does not match existing state key schema.",
@@ -3769,6 +3781,18 @@
     ],
     "sqlState" : "42802"
   },
+  "STATE_STORE_VALUE_ROW_FORMAT_VALIDATION_FAILURE" : {
+    "message" : [
+      "The streaming query failed to validate written state for value row.",
+      "The following reasons may cause this:",
+      "1. An old Spark version wrote the checkpoint that is incompatible with the current one",
+      "2. Corrupt checkpoint files",
+      "3. The query changed in an incompatible way between restarts",
+      "For the first case, use a new checkpoint directory or use the original Spark version",
+      "to process the streaming state. Retrieved error_message=<errorMsg>"
+    ],
+    "sqlState" : "XX000"
+  },
   "STATE_STORE_VALUE_SCHEMA_NOT_COMPATIBLE" : {
     "message" : [
       "Provided value schema does not match existing state value schema.",

dev/deps/spark-deps-hadoop-3-hive-2.3

@@ -251,7 +251,7 @@ scala-library/2.13.14//scala-library-2.13.14.jar
 scala-parallel-collections_2.13/1.0.4//scala-parallel-collections_2.13-1.0.4.jar
 scala-parser-combinators_2.13/2.4.0//scala-parser-combinators_2.13-2.4.0.jar
 scala-reflect/2.13.14//scala-reflect-2.13.14.jar
-scala-xml_2.13/2.2.0//scala-xml_2.13-2.2.0.jar
+scala-xml_2.13/2.3.0//scala-xml_2.13-2.3.0.jar
 slf4j-api/2.0.13//slf4j-api-2.0.13.jar
 snakeyaml-engine/2.7//snakeyaml-engine-2.7.jar
 snakeyaml/2.2//snakeyaml-2.2.jar

docs/_data/menu-sql.yaml

@@ -63,6 +63,8 @@
       url: sql-performance-tuning.html#optimizing-the-join-strategy
     - text: Adaptive Query Execution
       url: sql-performance-tuning.html#adaptive-query-execution
+    - text: Storage Partition Join
+      url: sql-performance-tuning.html#storage-partition-join
 - text: Distributed SQL Engine
   url: sql-distributed-sql-engine.html
   subitems:

docs/sql-performance-tuning.md

@@ -428,3 +428,122 @@ You can control the details of how AQE works by providing your own cost evaluato
       <td>3.2.0</td>
     </tr>
   </table>
+
+## Storage Partition Join
+
+Storage Partition Join (SPJ) is an optimization technique in Spark SQL that makes use the existing storage layout to avoid the shuffle phase.
+
+This is a generalization of the concept of Bucket Joins, which is only applicable for [bucketed](sql-data-sources-load-save-functions.html#bucketing-sorting-and-partitioning) tables, to tables partitioned by functions registered in FunctionCatalog. Storage Partition Joins are currently supported for compatible V2 DataSources.
+
+The following SQL properties enable Storage Partition Join in different join queries with various optimizations.
+
+  <table class="spark-config">
+    <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>
+        When true, try to eliminate shuffle by using the partitioning reported by a compatible V2 data source.
+      </td>
+      <td>3.3.0</td>
+    </tr>
+    <tr>
+      <td><code>spark.sql.sources.v2.bucketing.pushPartValues.enabled</code></td>
+      <td>true</td>
+      <td>
+        When enabled, try to eliminate shuffle if one side of the join has missing partition values from the other side. This config requires <code>spark.sql.sources.v2.bucketing.enabled</code> to be true.
+      </td>
+      <td>3.4.0</td>
+    </tr>
+    <tr>
+      <td><code>spark.sql.requireAllClusterKeysForCoPartition</code></td>
+      <td>true</td>
+      <td>
+        When true, require the join or MERGE keys to be same and in the same order as the partition keys to eliminate shuffle. Hence, set to <b>false</b> in this situation to eliminate shuffle.
+      </td>
+      <td>3.4.0</td>
+    </tr>
+    <tr>
+      <td><code>spark.sql.sources.v2.bucketing.partiallyClusteredDistribution.enabled</code></td>
+      <td>false</td>
+      <td>
+        When true, and when the join is not a full outer join, enable skew optimizations to handle partitions with large amounts of data when avoiding shuffle. One side will be chosen as the big table based on table statistics, and the splits on this side will be partially-clustered. The splits of the other side will be grouped and replicated to match. This config requires both <code>spark.sql.sources.v2.bucketing.enabled</code> and <code>spark.sql.sources.v2.bucketing.pushPartValues.enabled</code> to be true.
+      </td>
+      <td>3.4.0</td>
+    </tr>
+    <tr>
+      <td><code>spark.sql.sources.v2.bucketing.allowJoinKeysSubsetOfPartitionKeys.enabled</code></td>
+      <td>false</td>
+      <td>
+        When enabled, try to avoid shuffle if join or MERGE condition does not include all partition columns. This config requires both <code>spark.sql.sources.v2.bucketing.enabled</code> and <code>spark.sql.sources.v2.bucketing.pushPartValues.enabled</code> to be true, and <code>spark.sql.requireAllClusterKeysForCoPartition</code> to be false.
+      </td>
+      <td>4.0.0</td>
+    </tr>
+    <tr>
+      <td><code>spark.sql.sources.v2.bucketing.allowCompatibleTransforms.enabled</code></td>
+      <td>false</td>
+      <td>
+        When enabled, try to avoid shuffle if partition transforms are compatible but not identical. This config requires both <code>spark.sql.sources.v2.bucketing.enabled</code> and <code>spark.sql.sources.v2.bucketing.pushPartValues.enabled</code> to be true.
+      </td>
+      <td>4.0.0</td>
+    </tr>
+    <tr>
+      <td><code>spark.sql.sources.v2.bucketing.shuffle.enabled</code></td>
+      <td>false</td>
+      <td>
+        When enabled, try to avoid shuffle on one side of the join, by recognizing the partitioning reported by a V2 data source on the other side.
+      </td>
+      <td>4.0.0</td>
+    </tr>
+  </table>
+
+If Storage Partition Join is performed, the query plan will not contain Exchange nodes prior to the join.
+
+The following example uses Iceberg ([https://iceberg.apache.org/docs/latest/spark-getting-started/](https://iceberg.apache.org/docs/latest/spark-getting-started/)), a Spark V2 DataSource that supports Storage Partition Join.
+```sql
+CREATE TABLE prod.db.target (id INT, salary INT, dep STRING)
+USING iceberg
+PARTITIONED BY (dep, bucket(8, id))
+
+CREATE TABLE prod.db.source (id INT, salary INT, dep STRING)
+USING iceberg
+PARTITIONED BY (dep, bucket(8, id))
+
+EXPLAIN SELECT * FROM target t INNER JOIN source s
+ON t.dep = s.dep AND t.id = s.id
+
+-- Plan without Storage Partition Join
+== Physical Plan ==
+* Project (12)
++- * SortMergeJoin Inner (11)
+   :- * Sort (5)
+   :  +- Exchange (4) // DATA SHUFFLE
+   :     +- * Filter (3)
+   :        +- * ColumnarToRow (2)
+   :           +- BatchScan (1)
+   +- * Sort (10)
+      +- Exchange (9) // DATA SHUFFLE
+         +- * Filter (8)
+            +- * ColumnarToRow (7)
+               +- BatchScan (6)
+
+
+SET 'spark.sql.sources.v2.bucketing.enabled' 'true'
+SET 'spark.sql.iceberg.planning.preserve-data-grouping' 'true'
+SET 'spark.sql.sources.v2.bucketing.pushPartValues.enabled' 'true'
+SET 'spark.sql.requireAllClusterKeysForCoPartition' 'false'
+SET 'spark.sql.sources.v2.bucketing.partiallyClusteredDistribution.enabled' 'true'
+
+-- Plan with Storage Partition Join
+== Physical Plan ==
+* Project (10)
++- * SortMergeJoin Inner (9)
+   :- * Sort (4)
+   :  +- * Filter (3)
+   :     +- * ColumnarToRow (2)
+   :        +- BatchScan (1)
+   +- * Sort (8)
+      +- * Filter (7)
+         +- * ColumnarToRow (6)
+            +- BatchScan (5)
+```

pom.xml

@@ -1120,7 +1120,7 @@
       <dependency>
         <groupId>org.scala-lang.modules</groupId>
         <artifactId>scala-xml_${scala.binary.version}</artifactId>
-        <version>2.2.0</version>
+        <version>2.3.0</version>
       </dependency>
       <dependency>
         <groupId>org.scala-lang</groupId>

python/pyspark/sql/connect/column.py

@@ -27,13 +27,15 @@
     Any,
     Union,
     Optional,
+    cast,
 )
 
 from pyspark.sql.column import Column as ParentColumn
 from pyspark.errors import PySparkTypeError, PySparkAttributeError, PySparkValueError
 from pyspark.sql.types import DataType
 
 import pyspark.sql.connect.proto as proto
+from pyspark.sql.connect.functions import builtin as F
 from pyspark.sql.connect.expressions import (
     Expression,
     UnresolvedFunction,
@@ -308,14 +310,12 @@ def when(self, condition: ParentColumn, value: Any) -> ParentColumn:
                 message_parameters={},
             )
 
-        if isinstance(value, Column):
-            _value = value._expr
-        else:
-            _value = LiteralExpression._from_value(value)
-
-        _branches = self._expr._branches + [(condition._expr, _value)]
-
-        return Column(CaseWhen(branches=_branches, else_value=None))
+        return Column(
+            CaseWhen(
+                branches=self._expr._branches + [(condition._expr, F.lit(value)._expr)],
+                else_value=None,
+            )
+        )
 
     def otherwise(self, value: Any) -> ParentColumn:
         if not isinstance(self._expr, CaseWhen):
@@ -328,12 +328,12 @@ def otherwise(self, value: Any) -> ParentColumn:
                 "otherwise() can only be applied once on a Column previously generated by when()"
             )
 
-        if isinstance(value, Column):
-            _value = value._expr
-        else:
-            _value = LiteralExpression._from_value(value)
-
-        return Column(CaseWhen(branches=self._expr._branches, else_value=_value))
+        return Column(
+            CaseWhen(
+                branches=self._expr._branches,
+                else_value=cast(Expression, F.lit(value)._expr),
+            )
+        )
 
     def like(self: ParentColumn, other: str) -> ParentColumn:
         return _bin_op("like", self, other)
@@ -457,14 +457,11 @@ def isin(self, *cols: Any) -> ParentColumn:
         else:
             _cols = list(cols)
 
-        _exprs = [self._expr]
-        for c in _cols:
-            if isinstance(c, Column):
-                _exprs.append(c._expr)
-            else:
-                _exprs.append(LiteralExpression._from_value(c))
-
-        return Column(UnresolvedFunction("in", _exprs))
+        return Column(
+            UnresolvedFunction(
+                "in", [self._expr] + [cast(Expression, F.lit(c)._expr) for c in _cols]
+            )
+        )
 
     def between(
         self,
@@ -554,10 +551,8 @@ def __getitem__(self, k: Any) -> ParentColumn:
                     message_parameters={},
                 )
             return self.substr(k.start, k.stop)
-        elif isinstance(k, Column):
-            return Column(UnresolvedExtractValue(self._expr, k._expr))
         else:
-            return Column(UnresolvedExtractValue(self._expr, LiteralExpression._from_value(k)))
+            return Column(UnresolvedExtractValue(self._expr, cast(Expression, F.lit(k)._expr)))
 
     def __iter__(self) -> None:
         raise PySparkTypeError(