This is an automated email from the ASF dual-hosted git repository.
danny0405 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/hudi.git
The following commit(s) were added to refs/heads/master by this push:
new 863f84a08864 fix(sync): drop the duplicate UpdateTable in
updateTableSchema (#19762)
863f84a08864 is described below
commit 863f84a08864ac4916c31b1412ec1eab737a1b73
Author: niranjan-1408 <[email protected]>
AuthorDate: Thu Aug 27 19:22:41 2026 -0700
fix(sync): drop the duplicate UpdateTable in updateTableSchema (#19762)
updateTableSchema issued the same UpdateTable request object twice. The
second call
sat outside the if (cascade) block, so it fired unconditionally, including
on
non-partitioned tables where cascade is false.
Nothing between the two calls mutates the request, and the cascade branch
writes
partitions rather than the table, so the second call was a no-op that Glue
still
counted as a new table version. Every schema change therefore consumed two
table
versions where one would do.
The first call is kept rather than the second because the cascade re-reads
the table
to source the columns it propagates: with the update first it sees the new
columns,
whereas keeping only the second would have it propagate stale ones.
---
.../hudi/aws/sync/AWSGlueCatalogSyncClient.java | 1 -
.../hudi/aws/sync/TestAWSGlueSyncClient.java | 28 ++++++++++++++++++++++
2 files changed, 28 insertions(+), 1 deletion(-)
diff --git
a/hudi-aws/src/main/java/org/apache/hudi/aws/sync/AWSGlueCatalogSyncClient.java
b/hudi-aws/src/main/java/org/apache/hudi/aws/sync/AWSGlueCatalogSyncClient.java
index f587882dfdf8..342b75783d96 100644
---
a/hudi-aws/src/main/java/org/apache/hudi/aws/sync/AWSGlueCatalogSyncClient.java
+++
b/hudi-aws/src/main/java/org/apache/hudi/aws/sync/AWSGlueCatalogSyncClient.java
@@ -628,7 +628,6 @@ public class AWSGlueCatalogSyncClient extends
HoodieSyncClient {
if (cascade) {
cascadeColumnsToPartitions(tableName, getAllPartitions(tableName));
}
- awsGlue.updateTable(request).get();
} catch (Exception e) {
throw new HoodieGlueSyncException("Fail to update definition for table "
+ tableId(databaseName, tableName), e);
}
diff --git
a/hudi-aws/src/test/java/org/apache/hudi/aws/sync/TestAWSGlueSyncClient.java
b/hudi-aws/src/test/java/org/apache/hudi/aws/sync/TestAWSGlueSyncClient.java
index 6400198f0ac7..5ff5ca1c738b 100644
--- a/hudi-aws/src/test/java/org/apache/hudi/aws/sync/TestAWSGlueSyncClient.java
+++ b/hudi-aws/src/test/java/org/apache/hudi/aws/sync/TestAWSGlueSyncClient.java
@@ -982,4 +982,32 @@ class TestAWSGlueSyncClient {
inOrder.verify(mockAwsGlue).updateTable(any(UpdateTableRequest.class));
inOrder.verify(mockAwsGlue).batchUpdatePartition(any(BatchUpdatePartitionRequest.class));
}
+
+ @Test
+ void testUpdateTableSchema_issuesOneUpdateTable() {
+ String tableName = GlueTestUtil.TABLE_NAME;
+ Table table = Table.builder()
+ .name(tableName)
+ .databaseName(GlueTestUtil.DB_NAME)
+ .storageDescriptor(StorageDescriptor.builder()
+ .location("s3://base")
+ .columns(Column.builder().name("name").type("string").build())
+ .build())
+ .partitionKeys(Column.builder().name("datestr").type("string").build())
+ .build();
+ when(mockAwsGlue.getTable(any(GetTableRequest.class)))
+
.thenReturn(CompletableFuture.completedFuture(GetTableResponse.builder().table(table).build()));
+ when(mockAwsGlue.updateTable(any(UpdateTableRequest.class)))
+
.thenReturn(CompletableFuture.completedFuture(UpdateTableResponse.builder().build()));
+
+ HoodieSchema schema = GlueTestUtil.getSimpleSchema();
+ SchemaDifference schemaDiff = SchemaDifference.newBuilder(schema, new
HashMap<>())
+ .addTableColumn("added", "string")
+ .build();
+
+ awsGlueSyncClient.updateTableSchema(tableName, schema, schemaDiff);
+
+ verify(mockAwsGlue, times(1)).updateTable(any(UpdateTableRequest.class));
+ verify(mockAwsGlue,
never()).batchUpdatePartition(any(BatchUpdatePartitionRequest.class));
+ }
}
