[SPARK-32019][SQL] Add spark.sql.files.minPartitionNum config

sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala

@@ -1176,6 +1176,15 @@ object SQLConf {
     .longConf
     .createWithDefault(4 * 1024 * 1024)
 
+  val FILES_MIN_PARTITION_NUM = buildConf("spark.sql.files.minPartitionNum")
+    .doc("The suggested (not guaranteed) minimum number of file split partitions. If not set, " +
+      "the default value is the default parallelism of the Spark cluster. This configuration is " +
+      "effective only when using file-based sources such as Parquet, JSON and ORC.")
+    .version("3.1.0")
+    .intConf
+    .checkValue(v => v > 0, "The min partition number must be a positive integer.")
+    .createOptional
+
   val IGNORE_CORRUPT_FILES = buildConf("spark.sql.files.ignoreCorruptFiles")
     .doc("Whether to ignore corrupt files. If true, the Spark jobs will continue to run when " +
       "encountering corrupted files and the contents that have been read will still be returned. " +
@@ -2782,6 +2791,8 @@ class SQLConf extends Serializable with Logging {
 
   def filesOpenCostInBytes: Long = getConf(FILES_OPEN_COST_IN_BYTES)
 
+  def filesMinPartitionNum: Option[Int] = getConf(FILES_MIN_PARTITION_NUM)
+
   def ignoreCorruptFiles: Boolean = getConf(IGNORE_CORRUPT_FILES)
 
   def ignoreMissingFiles: Boolean = getConf(IGNORE_MISSING_FILES)

sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FilePartition.scala

@@ -88,9 +88,10 @@ object FilePartition extends Logging {
       selectedPartitions: Seq[PartitionDirectory]): Long = {
     val defaultMaxSplitBytes = sparkSession.sessionState.conf.filesMaxPartitionBytes
     val openCostInBytes = sparkSession.sessionState.conf.filesOpenCostInBytes
-    val defaultParallelism = sparkSession.sparkContext.defaultParallelism
+    val minPartitionNum = sparkSession.sessionState.conf.filesMinPartitionNum
+      .getOrElse(sparkSession.sparkContext.defaultParallelism)
     val totalBytes = selectedPartitions.flatMap(_.files.map(_.getLen + openCostInBytes)).sum
-    val bytesPerCore = totalBytes / defaultParallelism
+    val bytesPerCore = totalBytes / minPartitionNum
 
     Math.min(defaultMaxSplitBytes, Math.max(openCostInBytes, bytesPerCore))
   }

sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/FileSourceStrategySuite.scala

@@ -528,6 +528,18 @@ class FileSourceStrategySuite extends QueryTest with SharedSparkSession with Pre
     }
   }
 
+  test("Add spark.sql.files.minPartitionNum config") {
+    withSQLConf(SQLConf.FILES_MIN_PARTITION_NUM.key -> "1") {
+      val table =
+        createTable(files = Seq(
+          "file1" -> 1,
+          "file2" -> 1,
+          "file3" -> 1
+        ))
+      assert(table.rdd.partitions.length == 1)
+    }
+  }
+
   // Helpers for checking the arguments passed to the FileFormat.
 
   protected val checkPartitionSchema =