Skip to content

chore: check missingInput for Comet plan nodes #2795

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

Merged
comphead merged 5 commits into from
Nov 19, 2025
Merged

chore: check missingInput for Comet plan nodes #2795

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
c3de884
chore: check `missingInput` for Comet plan nodes
comphead Nov 17, 2025
7b19a05
chore: check `missingInput` for Comet plan nodes
comphead Nov 17, 2025
0608fc7
chore: check `missingInput` for Comet plan nodes
comphead Nov 18, 2025
11e9ffe
Update spark/src/test/scala/org/apache/spark/sql/CometTestBase.scala
comphead Nov 18, 2025
1b7079e
chore: check `missingInput` for Comet plan nodes
comphead Nov 18, 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
7 changes: 6 additions & 1 deletion spark/src/main/scala/org/apache/spark/sql/comet/CometTakeOrderedAndProjectExec.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ package org.apache.spark.sql.comet
import org.apache.spark.TaskContext
import org.apache.spark.rdd.{ParallelCollectionRDD, RDD}
import org.apache.spark.serializer.Serializer
import org.apache.spark.sql.catalyst.expressions.{Attribute, NamedExpression, SortOrder}
import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeSet, NamedExpression, SortOrder}
import org.apache.spark.sql.catalyst.util.truncatedString
import org.apache.spark.sql.comet.execution.shuffle.{CometShuffledBatchRDD, CometShuffleExchangeExec}
import org.apache.spark.sql.execution.{SparkPlan, TakeOrderedAndProjectExec, UnaryExecNode, UnsafeRowSerializer}
Expand Down Expand Up @@ -98,10 +98,15 @@ case class CometTakeOrderedAndProjectExec(
child: SparkPlan)
extends CometExec
with UnaryExecNode {

override def producedAttributes: AttributeSet = outputSet ++ AttributeSet(projectList)

private lazy val writeMetrics =
SQLShuffleWriteMetricsReporter.createShuffleWriteMetrics(sparkContext)

private lazy val readMetrics =
SQLShuffleReadMetricsReporter.createShuffleReadMetrics(sparkContext)

override lazy val metrics: Map[String, SQLMetric] = Map(
"dataSize" -> SQLMetrics.createSizeMetric(sparkContext, "data size"),
"numPartitions" -> SQLMetrics.createMetric(
Expand Down
2 changes: 1 addition & 1 deletion ...pcds-plan-stability/approved-plans-v1_4-spark3_5/q79.native_iceberg_compat/simplified.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
WholeStageCodegen (1)
CometColumnarToRow
InputAdapter
CometTakeOrderedAndProject [c_last_name,c_first_name,substr(s_city, 1, 30),ss_ticket_number,amt,profit,s_city]
CometTakeOrderedAndProject [s_city] [c_last_name,c_first_name,substr(s_city, 1, 30),ss_ticket_number,amt,profit]
CometProject [c_last_name,c_first_name,substr(s_city, 1, 30),ss_ticket_number,amt,profit,s_city]
CometBroadcastHashJoin [ss_ticket_number,ss_customer_sk,s_city,amt,profit,c_customer_sk,c_first_name,c_last_name]
CometHashAggregate [ss_addr_sk,sum,sum] [ss_ticket_number,ss_customer_sk,s_city,amt,profit,sum(UnscaledValue(ss_coupon_amt)),sum(UnscaledValue(ss_net_profit))]
Expand Down
2 changes: 1 addition & 1 deletion ...k/src/test/resources/tpcds-plan-stability/approved-plans-v1_4-spark3_5/q79/simplified.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
WholeStageCodegen (1)
CometColumnarToRow
InputAdapter
CometTakeOrderedAndProject [c_last_name,c_first_name,substr(s_city, 1, 30),ss_ticket_number,amt,profit,s_city]
CometTakeOrderedAndProject [s_city] [c_last_name,c_first_name,substr(s_city, 1, 30),ss_ticket_number,amt,profit]
CometProject [c_last_name,c_first_name,substr(s_city, 1, 30),ss_ticket_number,amt,profit,s_city]
CometBroadcastHashJoin [ss_ticket_number,ss_customer_sk,s_city,amt,profit,c_customer_sk,c_first_name,c_last_name]
CometHashAggregate [ss_addr_sk,sum,sum] [ss_ticket_number,ss_customer_sk,s_city,amt,profit,sum(UnscaledValue(ss_coupon_amt)),sum(UnscaledValue(ss_net_profit))]
Expand Down
2 changes: 1 addition & 1 deletion ...pcds-plan-stability/approved-plans-v1_4-spark3_5/q84.native_iceberg_compat/simplified.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
WholeStageCodegen (1)
CometColumnarToRow
InputAdapter
CometTakeOrderedAndProject [customer_id,customername,c_customer_id]
CometTakeOrderedAndProject [c_customer_id] [customer_id,customername]
CometProject [c_last_name,c_first_name] [customer_id,customername,c_customer_id]
CometBroadcastHashJoin [c_customer_id,c_first_name,c_last_name,cd_demo_sk,sr_cdemo_sk]
CometBroadcastExchange [c_customer_id,c_first_name,c_last_name,cd_demo_sk] #1
Expand Down
2 changes: 1 addition & 1 deletion ...k/src/test/resources/tpcds-plan-stability/approved-plans-v1_4-spark3_5/q84/simplified.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
WholeStageCodegen (1)
CometColumnarToRow
InputAdapter
CometTakeOrderedAndProject [customer_id,customername,c_customer_id]
CometTakeOrderedAndProject [c_customer_id] [customer_id,customername]
CometProject [c_last_name,c_first_name] [customer_id,customername,c_customer_id]
CometBroadcastHashJoin [c_customer_id,c_first_name,c_last_name,cd_demo_sk,sr_cdemo_sk]
CometBroadcastExchange [c_customer_id,c_first_name,c_last_name,cd_demo_sk] #1
Expand Down
2 changes: 1 addition & 1 deletion ...pcds-plan-stability/approved-plans-v1_4-spark4_0/q84.native_iceberg_compat/simplified.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
WholeStageCodegen (1)
CometColumnarToRow
InputAdapter
CometTakeOrderedAndProject [customer_id,customername,c_customer_id]
CometTakeOrderedAndProject [c_customer_id] [customer_id,customername]
CometProject [c_last_name,c_first_name] [customer_id,customername,c_customer_id]
CometBroadcastHashJoin [c_customer_id,c_first_name,c_last_name,cd_demo_sk,sr_cdemo_sk]
CometBroadcastExchange [c_customer_id,c_first_name,c_last_name,cd_demo_sk] #1
Expand Down
2 changes: 1 addition & 1 deletion ...k/src/test/resources/tpcds-plan-stability/approved-plans-v1_4-spark4_0/q84/simplified.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
WholeStageCodegen (1)
CometColumnarToRow
InputAdapter
CometTakeOrderedAndProject [customer_id,customername,c_customer_id]
CometTakeOrderedAndProject [c_customer_id] [customer_id,customername]
CometProject [c_last_name,c_first_name] [customer_id,customername,c_customer_id]
CometBroadcastHashJoin [c_customer_id,c_first_name,c_last_name,cd_demo_sk,sr_cdemo_sk]
CometBroadcastExchange [c_customer_id,c_first_name,c_last_name,cd_demo_sk] #1
Expand Down
2 changes: 1 addition & 1 deletion ...sources/tpcds-plan-stability/approved-plans-v1_4/q79.native_iceberg_compat/simplified.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
WholeStageCodegen (1)
CometColumnarToRow
InputAdapter
CometTakeOrderedAndProject [c_last_name,c_first_name,substr(s_city, 1, 30),ss_ticket_number,amt,profit,s_city]
CometTakeOrderedAndProject [s_city] [c_last_name,c_first_name,substr(s_city, 1, 30),ss_ticket_number,amt,profit]
CometProject [c_last_name,c_first_name,substr(s_city, 1, 30),ss_ticket_number,amt,profit,s_city]
CometBroadcastHashJoin [ss_ticket_number,ss_customer_sk,s_city,amt,profit,c_customer_sk,c_first_name,c_last_name]
CometHashAggregate [ss_addr_sk,sum,sum] [ss_ticket_number,ss_customer_sk,s_city,amt,profit,sum(UnscaledValue(ss_coupon_amt)),sum(UnscaledValue(ss_net_profit))]
Expand Down
2 changes: 1 addition & 1 deletion spark/src/test/resources/tpcds-plan-stability/approved-plans-v1_4/q79/simplified.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
WholeStageCodegen (1)
CometColumnarToRow
InputAdapter
CometTakeOrderedAndProject [c_last_name,c_first_name,substr(s_city, 1, 30),ss_ticket_number,amt,profit,s_city]
CometTakeOrderedAndProject [s_city] [c_last_name,c_first_name,substr(s_city, 1, 30),ss_ticket_number,amt,profit]
CometProject [c_last_name,c_first_name,substr(s_city, 1, 30),ss_ticket_number,amt,profit,s_city]
CometBroadcastHashJoin [ss_ticket_number,ss_customer_sk,s_city,amt,profit,c_customer_sk,c_first_name,c_last_name]
CometHashAggregate [ss_addr_sk,sum,sum] [ss_ticket_number,ss_customer_sk,s_city,amt,profit,sum(UnscaledValue(ss_coupon_amt)),sum(UnscaledValue(ss_net_profit))]
Expand Down
2 changes: 1 addition & 1 deletion ...sources/tpcds-plan-stability/approved-plans-v1_4/q84.native_iceberg_compat/simplified.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
WholeStageCodegen (1)
CometColumnarToRow
InputAdapter
CometTakeOrderedAndProject [customer_id,customername,c_customer_id]
CometTakeOrderedAndProject [c_customer_id] [customer_id,customername]
CometProject [c_last_name,c_first_name] [customer_id,customername,c_customer_id]
CometBroadcastHashJoin [c_customer_id,c_first_name,c_last_name,cd_demo_sk,sr_cdemo_sk]
CometBroadcastExchange [c_customer_id,c_first_name,c_last_name,cd_demo_sk] #1
Expand Down
2 changes: 1 addition & 1 deletion spark/src/test/resources/tpcds-plan-stability/approved-plans-v1_4/q84/simplified.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
WholeStageCodegen (1)
CometColumnarToRow
InputAdapter
CometTakeOrderedAndProject [customer_id,customername,c_customer_id]
CometTakeOrderedAndProject [c_customer_id] [customer_id,customername]
CometProject [c_last_name,c_first_name] [customer_id,customername,c_customer_id]
CometBroadcastHashJoin [c_customer_id,c_first_name,c_last_name,cd_demo_sk,sr_cdemo_sk]
CometBroadcastExchange [c_customer_id,c_first_name,c_last_name,cd_demo_sk] #1
Expand Down
2 changes: 1 addition & 1 deletion ...tpcds-plan-stability/approved-plans-v2_7-spark3_5/q6.native_iceberg_compat/simplified.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
WholeStageCodegen (1)
CometColumnarToRow
InputAdapter
CometTakeOrderedAndProject [state,cnt,ca_state]
CometTakeOrderedAndProject [ca_state] [state,cnt]
CometFilter [state,cnt,ca_state]
CometHashAggregate [count] [state,cnt,ca_state,count(1)]
CometExchange [ca_state] #1
Expand Down
2 changes: 1 addition & 1 deletion spark/src/test/resources/tpcds-plan-stability/approved-plans-v2_7-spark3_5/q6/simplified.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
WholeStageCodegen (1)
CometColumnarToRow
InputAdapter
CometTakeOrderedAndProject [state,cnt,ca_state]
CometTakeOrderedAndProject [ca_state] [state,cnt]
CometFilter [state,cnt,ca_state]
CometHashAggregate [count] [state,cnt,ca_state,count(1)]
CometExchange [ca_state] #1
Expand Down
2 changes: 1 addition & 1 deletion ...esources/tpcds-plan-stability/approved-plans-v2_7/q6.native_iceberg_compat/simplified.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
WholeStageCodegen (1)
CometColumnarToRow
InputAdapter
CometTakeOrderedAndProject [state,cnt,ca_state]
CometTakeOrderedAndProject [ca_state] [state,cnt]
CometFilter [state,cnt,ca_state]
CometHashAggregate [count] [state,cnt,ca_state,count(1)]
CometExchange [ca_state] #1
Expand Down
2 changes: 1 addition & 1 deletion spark/src/test/resources/tpcds-plan-stability/approved-plans-v2_7/q6/simplified.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
WholeStageCodegen (1)
CometColumnarToRow
InputAdapter
CometTakeOrderedAndProject [state,cnt,ca_state]
CometTakeOrderedAndProject [ca_state] [state,cnt]
CometFilter [state,cnt,ca_state]
CometHashAggregate [count] [state,cnt,ca_state,count(1)]
CometExchange [ca_state] #1
Expand Down
24 changes: 24 additions & 0 deletions spark/src/test/scala/org/apache/spark/sql/CometTestBase.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -385,6 +385,8 @@ abstract class CometTestBase
s"plan: ${new ExtendedExplainInfo().generateExtendedInfo(plan)}")
case _ =>
}

checkPlanNotMissingInput(plan)
}

protected def findFirstNonCometOperator(
Expand All @@ -406,6 +408,28 @@ abstract class CometTestBase
None
}

// checks the plan node has no missing inputs
// such nodes represented in plan with exclamation mark !
// example: !CometWindowExec
protected def checkPlanNotMissingInput(plan: SparkPlan): Unit = {
def hasMissingInput(node: SparkPlan): Boolean = {
node.missingInput.nonEmpty && node.children.nonEmpty
}

val isCometNode = plan.nodeName.startsWith("Comet")

if (isCometNode && hasMissingInput(plan)) {
assert(
false,
s"Plan node `${plan.nodeName}` has invalid missingInput: ${plan.missingInput}")
}

// Otherwise recursively check children
plan.children.foreach { child =>
checkPlanNotMissingInput(child)
}
}

private def checkPlanContains(plan: SparkPlan, includePlans: Class[_]*): Unit = {
includePlans.foreach { case planClass =>
if (plan.find(op => planClass.isAssignableFrom(op.getClass)).isEmpty) {
Expand Down
Loading