Skip to content

[Spark] Make MERGE source materialize depend on checkpointRDDBlockIdNotFoundError error class, not message #3649

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
wants to merge 4 commits into from
Closed

[Spark] Make MERGE source materialize depend on checkpointRDDBlockIdNotFoundError error class, not message #3649

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
68a76ba
f
Sep 5, 2024
436d5d7
fix import
Sep 5, 2024
28b88b1
retrigger
Mar 27, 2025
33a01c5
retrigger
May 28, 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: 2 additions & 6 deletions ...src/main/scala/org/apache/spark/sql/delta/commands/merge/MergeIntoMaterializeSource.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -176,8 +176,8 @@ trait MergeIntoMaterializeSource extends DeltaLogging with DeltaSparkPlanUtils {
// SparkCoreErrors.checkpointRDDBlockIdNotFoundError from LocalCheckpointRDD.compute.
case s: SparkException
if materializedSourceRDD.nonEmpty &&
s.getMessage.matches(
mergeMaterializedSourceRddBlockLostErrorRegex(materializedSourceRDD.get.id)) =>
s.getErrorClass() == "CHECKPOINT_RDD_BLOCK_ID_NOT_FOUND" &&
s.getMessageParameters().get("blockId") == materializedSourceRDD.get.id.toString =>
logWarning(log"Materialized ${MDC(DeltaLogKeys.OPERATION, operation)} source RDD block " +
log"lost. ${MDC(DeltaLogKeys.OPERATION, operation)} needs to be restarted. " +
log"This was attempt number ${MDC(DeltaLogKeys.ATTEMPT, attempt)}.")
Expand Down Expand Up @@ -436,10 +436,6 @@ object MergeIntoMaterializeSource {
MergeIntoMaterializeSourceReason.MATERIALIZED_REASONS.contains(materializeReason))
}

// This depends on SparkCoreErrors.checkpointRDDBlockIdNotFoundError msg
def mergeMaterializedSourceRddBlockLostErrorRegex(rddId: Int): String =
s"(?s).*Checkpoint block rdd_${rddId}_[0-9]+ not found!.*"

/**
* @return The columns of the source plan that are used in this MERGE
*/
Expand Down
6 changes: 2 additions & 4 deletions spark/src/test/scala/org/apache/spark/sql/delta/MergeIntoMaterializeSourceSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,6 @@ import scala.util.control.NonFatal
import com.databricks.spark.util.{Log4jUsageLogger, MetricDefinitions, UsageRecord}
import org.apache.spark.sql.delta.DeltaTestUtils._
import org.apache.spark.sql.delta.commands.merge.{MergeIntoMaterializeSourceError, MergeIntoMaterializeSourceErrorType, MergeIntoMaterializeSourceReason, MergeStats}
import org.apache.spark.sql.delta.commands.merge.MergeIntoMaterializeSource.mergeMaterializedSourceRddBlockLostErrorRegex
import org.apache.spark.sql.delta.sources.DeltaSQLConf
import org.apache.spark.sql.delta.test.DeltaSQLCommandTest
import org.apache.spark.sql.delta.test.DeltaSQLTestUtils
Expand Down Expand Up @@ -175,9 +174,8 @@ trait MergeIntoMaterializeSourceErrorTests extends MergeIntoMaterializeSourceMix
checkpointedDf.collect()
}
assert(ex.isInstanceOf[SparkException], ex)
assert(
ex.getMessage().matches(mergeMaterializedSourceRddBlockLostErrorRegex(rdd.id)),
s"RDD id ${rdd.id}: Message: ${ex.getMessage}")
assert(ex.asInstanceOf[SparkException].getErrorClass() == "CHECKPOINT_RDD_BLOCK_ID_NOT_FOUND")
assert(ex.asInstanceOf[SparkException].getMessageParameters().get("blockId") == rdd.id.toString)
}

for {
Expand Down
Loading