Skip to content

[core] Support re-overwrite by spark for chain table #7038

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

Open
Stefanietry wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[core] Support re-overwrite by spark for chain table #7038

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
Binary file modified docs/static/img/chain-table.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
50 changes: 50 additions & 0 deletions paimon-core/src/main/java/org/apache/paimon/utils/ChainTableUtils.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,11 @@
import org.apache.paimon.partition.PartitionTimeExtractor;
import org.apache.paimon.predicate.Predicate;
import org.apache.paimon.predicate.PredicateBuilder;
import org.apache.paimon.table.ChainGroupReadTable;
import org.apache.paimon.table.FallbackReadFileStoreTable;
import org.apache.paimon.table.FileStoreTable;
import org.apache.paimon.table.sink.BatchTableCommit;
import org.apache.paimon.table.sink.CommitMessage;
import org.apache.paimon.types.RowType;

import java.time.LocalDateTime;
Expand Down Expand Up @@ -204,4 +209,49 @@ public static LinkedHashMap<String, String> calPartValues(
}
return res;
}

public static void postCommit(
FileStoreTable table, boolean overwrite, List<CommitMessage> commitMessages) {
if (overwrite) {
FileStoreTable candidateTbl = table;
if (table instanceof FallbackReadFileStoreTable) {
candidateTbl =
((ChainGroupReadTable) ((FallbackReadFileStoreTable) table).fallback())
.wrapped();
}
FileStoreTable snapshotTbl =
candidateTbl.switchToBranch(table.coreOptions().scanFallbackSnapshotBranch());
InternalRowPartitionComputer partitionComputer =
new InternalRowPartitionComputer(
table.coreOptions().partitionDefaultName(),
table.schema().logicalPartitionType(),
table.schema().partitionKeys().toArray(new String[0]),
table.coreOptions().legacyPartitionName());
List<BinaryRow> overwritePartitions =
commitMessages.stream()
.map(CommitMessage::partition)
.distinct()
.collect(Collectors.toList());
if (!overwritePartitions.isEmpty()) {
List<Map<String, String>> candidatePartitions =
overwritePartitions.stream()
.map(partition -> partitionComputer.generatePartValues(partition))
.collect(Collectors.toList());
try (BatchTableCommit commit = snapshotTbl.newBatchWriteBuilder().newCommit()) {
commit.truncatePartitions(candidatePartitions);
} catch (Exception e) {
throw new RuntimeException(
String.format(
"Failed to truncate partitions in snapshot table %s.",
candidatePartitions),
e);
}
}
}
}

public static boolean chainScanFallbackDeltaBranch(CoreOptions options) {
return options.isChainTable()
&& options.scanFallbackDeltaBranch().equalsIgnoreCase(options.branch());
}
}
16 changes: 15 additions & 1 deletion ...n-spark-common/src/main/scala/org/apache/paimon/spark/commands/WriteIntoPaimonTable.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,8 @@ import org.apache.paimon.options.Options
import org.apache.paimon.spark._
import org.apache.paimon.spark.catalyst.analysis.expressions.ExpressionHelper
import org.apache.paimon.table.FileStoreTable
import org.apache.paimon.table.sink.CommitMessage
import org.apache.paimon.utils.ChainTableUtils

import org.apache.spark.internal.Logging
import org.apache.spark.sql.{DataFrame, Row, SparkSession}
Expand Down Expand Up @@ -57,7 +59,7 @@ case class WriteIntoPaimonTable(
}
val commitMessages = writer.write(data)
writer.commit(commitMessages)

postCommit(dynamicPartitionOverwriteMode, overwritePartition, commitMessages)
Seq.empty
}

Expand All @@ -82,6 +84,18 @@ case class WriteIntoPaimonTable(
(dynamicPartitionOverwriteMode, overwritePartition)
}

private def postCommit(
dynamicPartitionOverwrite: Boolean,
staticOverwritePartition: Map[String, String],
commitMessages: Seq[CommitMessage]): Unit = {
if (ChainTableUtils.chainScanFallbackDeltaBranch(table.coreOptions())) {
ChainTableUtils.postCommit(
table,
dynamicPartitionOverwrite || staticOverwritePartition != null,
commitMessages.toList.asJava)
}
}

override def withNewChildrenInternal(newChildren: IndexedSeq[LogicalPlan]): LogicalPlan =
this.asInstanceOf[WriteIntoPaimonTable]
}
38 changes: 38 additions & 0 deletions ...spark/paimon-spark-ut/src/test/java/org/apache/paimon/spark/SparkCatalogWithHiveTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@
import org.apache.paimon.hive.TestHiveMetastore;
import org.apache.paimon.table.FileStoreTableFactory;

import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;
import org.junit.jupiter.api.AfterAll;
Expand Down Expand Up @@ -380,6 +381,24 @@ public void testChainTable(@TempDir java.nio.file.Path tempDir) throws IOExcepti
spark.close();
spark = builder.getOrCreate();

spark.sql("set spark.paimon.branch=delta;");
spark.sql(
"insert overwrite table `my_db1`.`chain_test` values (5, 2, '1', '20250813'),(6, 2, '1', '20250814');");

spark.close();
spark = builder.getOrCreate();
Dataset<Row> df =
spark.sql(
"SELECT t1,t2,t3 FROM `my_db1`.`chain_test$branch_snapshot` where dt = '20250814'");
assertThat(df.count()).isEqualTo(0);
df =
spark.sql(
"SELECT t1,t2,t3 FROM `my_db1`.`chain_test$branch_delta` where dt = '20250814'");
assertThat(df.count()).isEqualTo(1);

spark.close();
spark = builder.getOrCreate();

/** Drop table */
spark.sql("DROP TABLE IF EXISTS `my_db1`.`chain_test`;");

Expand Down Expand Up @@ -593,6 +612,25 @@ public void testHourlyChainTable(@TempDir java.nio.file.Path tempDir) throws IOE
spark.close();
spark = builder.getOrCreate();

spark.sql("set spark.paimon.branch=delta;");
spark.sql(
"insert overwrite table `my_db1`.`chain_test` values (6, 2, '1', '20250811', '02');");

spark.close();
spark = builder.getOrCreate();

Dataset<Row> df =
spark.sql(
"SELECT t1,t2,t3 FROM `my_db1`.`chain_test$branch_snapshot` where dt = '20250811' and hour = '02'");
assertThat(df.count()).isEqualTo(0);
df =
spark.sql(
"SELECT t1,t2,t3 FROM `my_db1`.`chain_test$branch_delta` where dt = '20250811' and hour = '02'");
assertThat(df.count()).isEqualTo(1);

spark.close();
spark = builder.getOrCreate();

/** Drop table */
spark.sql("DROP TABLE IF EXISTS `my_db1`.`chain_test`;");

Expand Down
Loading