Skip to content

[SPARK-51559][SQL] Make max broadcast table size configurable #50327

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
sunchao wants to merge 2 commits into from
Closed

[SPARK-51559][SQL] Make max broadcast table size configurable #50327

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2543455
initial commit
sunchao Mar 19, 2025
4052912
address comments
sunchao Mar 19, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1534,6 +1534,12 @@ object SQLConf {
.timeConf(TimeUnit.SECONDS)
.createWithDefaultString(s"${5 * 60}")

val MAX_BROADCAST_TABLE_SIZE = buildConf("spark.sql.maxBroadcastTableSize")
.doc("The maximum table size in bytes that can be broadcast in broadcast joins.")
.version("4.1.0")
.bytesConf(ByteUnit.BYTE)
.createWithDefault(8L << 30)

val INTERRUPT_ON_CANCEL = buildConf("spark.sql.execution.interruptOnCancel")
.doc("When true, all running tasks will be interrupted if one cancels a query.")
.version("4.0.0")
Expand Down Expand Up @@ -6155,6 +6161,8 @@ class SQLConf extends Serializable with Logging with SqlApiConf {
if (timeoutValue < 0) Long.MaxValue else timeoutValue
}

def maxBroadcastTableSizeInBytes: Long = getConf(MAX_BROADCAST_TABLE_SIZE)

def defaultDataSourceName: String = getConf(DEFAULT_DATA_SOURCE_NAME)

def convertCTAS: Boolean = getConf(CONVERT_CTAS)
Expand Down
8 changes: 3 additions & 5 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/BroadcastExchangeExec.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -125,7 +125,6 @@ trait BroadcastExchangeLike extends Exchange {
case class BroadcastExchangeExec(
mode: BroadcastMode,
child: SparkPlan) extends BroadcastExchangeLike {
import BroadcastExchangeExec._

override lazy val metrics = Map(
"dataSize" -> SQLMetrics.createSizeMetric(sparkContext, "data size"),
Expand Down Expand Up @@ -203,9 +202,10 @@ case class BroadcastExchangeExec(
}

longMetric("dataSize") += dataSize
if (dataSize >= MAX_BROADCAST_TABLE_BYTES) {
val maxBroadcastTableSizeInBytes = conf.maxBroadcastTableSizeInBytes
if (dataSize >= maxBroadcastTableSizeInBytes) {
throw QueryExecutionErrors.cannotBroadcastTableOverMaxTableBytesError(
MAX_BROADCAST_TABLE_BYTES, dataSize)
maxBroadcastTableSizeInBytes, dataSize)
}

val beforeBroadcast = System.nanoTime()
Expand Down Expand Up @@ -268,8 +268,6 @@ case class BroadcastExchangeExec(
}

object BroadcastExchangeExec {
val MAX_BROADCAST_TABLE_BYTES = 8L << 30

private[execution] val executionContext = ExecutionContext.fromExecutorService(
ThreadUtils.newDaemonCachedThreadPool("broadcast-exchange",
SQLConf.get.getConf(StaticSQLConf.BROADCAST_EXCHANGE_MAX_THREAD_THRESHOLD)))
Expand Down