Skip to content

fix(bigquery-jdbc): limit Storage Read API Arrow batch queue to 32 batches #14709

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
logachev wants to merge 1 commit into
base: main
Choose a base branch
from
+35 −1
Open

fix(bigquery-jdbc): limit Storage Read API Arrow batch queue to 32 batches #14709

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
7 changes: 6 additions & 1 deletion java-bigquery-jdbc/src/main/java/com/google/cloud/bigquery/jdbc/BigQueryStatement.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,6 +104,7 @@ public class BigQueryStatement extends BigQueryNoOpsStatement {

private final BigQueryJdbcCustomLogger LOG = new BigQueryJdbcCustomLogger(this.toString());
public static final int DEFAULT_BUFFER_SIZE = BigQuerySettings.DEFAULT_NUM_BUFFERED_ROWS * 2;
static final int DEFAULT_ARROW_BUFFER_SIZE = 32;
private static final String DEFAULT_DATASET_NAME = "_google_jdbc";
private static final String DEFAULT_TABLE_NAME = "temp_table_";
private static final String JDBC_JOB_PREFIX = "google-jdbc-";
Expand Down Expand Up @@ -931,7 +932,7 @@ ResultSet processArrowResultSet(TableResult results, Job job) throws SQLExceptio
.setMaxStreamCount(1);

ReadSession readSession = getReadSession(builder.build());
this.arrowBatchWrapperBlockingQueue = new LinkedBlockingDeque<>(getBufferSize());
this.arrowBatchWrapperBlockingQueue = new LinkedBlockingDeque<>(getArrowBufferSize());
// deserialize and populate the buffer async, so that the client isn't blocked
populateBufferWorker =
populateArrowBufferedQueue(
Expand Down Expand Up @@ -1512,6 +1513,10 @@ private int getBufferSize() {
: Math.min(this.querySettings.getNumBufferedRows() * 2, 100000));
}

int getArrowBufferSize() {
return DEFAULT_ARROW_BUFFER_SIZE;
}
Comment on lines +1516 to +1518

@gemini-code-assist gemini-code-assist Bot Oct 21, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The getArrowBufferSize() method is only used internally within the BigQueryStatement class. To adhere to encapsulation principles and minimize the class's API surface, its visibility should be restricted to private.

Suggested change
int getArrowBufferSize() {
return DEFAULT_ARROW_BUFFER_SIZE;
}
private int getArrowBufferSize() {
return DEFAULT_ARROW_BUFFER_SIZE;
}


/** Returns the destinationTable from jobId by calling `jobs.get` API */
TableId getDestinationTable(JobId jobId) {
Job job = this.bigQuery.getJob(jobId);
Expand Down
29 changes: 29 additions & 0 deletions java-bigquery-jdbc/src/test/java/com/google/cloud/bigquery/jdbc/BigQueryStatementTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1318,4 +1318,33 @@ public void testJoblessQueryPopulatesQueryStatistics() throws Exception {

verify(bigquery, Mockito.never()).getJob(any(JobId.class));
}

@Test
public void testProcessArrowResultSetUsesBoundedQueueCapacity() throws SQLException {
BigQueryStatement defaultStmtSpy = Mockito.spy(bigQueryStatement);
BigQueryReadClient bigQueryReadClient = mock(BigQueryReadClient.class);
Schema schema = Schema.of(fieldList);
ReadSession readSession = ReadSession.getDefaultInstance();
doReturn(bigQueryReadClient).when(defaultStmtSpy).getBigQueryReadClient();
doReturn(readSession).when(defaultStmtSpy).getReadSession(any(CreateReadSessionRequest.class));
Future<?> mockWorker = mock(Future.class);
@SuppressWarnings("unchecked")
ArgumentCaptor<BlockingQueue<BigQueryArrowBatchWrapper>> defaultQueueCaptor =
ArgumentCaptor.forClass(BlockingQueue.class);
doReturn(mockWorker)
.when(defaultStmtSpy)
.populateArrowBufferedQueue(
any(ReadSession.class), defaultQueueCaptor.capture(), any(BigQueryReadClient.class));
doReturn(arrowSchema).when(defaultStmtSpy).getArrowSchema(any(ReadSession.class));

TableResult result = mock(TableResult.class);
doReturn(schema).when(result).getSchema();
doReturn(10L).when(result).getTotalRows();
doReturn(TABLE_ID).when(defaultStmtSpy).getDestinationTable(any());

defaultStmtSpy.processArrowResultSet(result, null);
assertEquals(
BigQueryStatement.DEFAULT_ARROW_BUFFER_SIZE,
defaultQueueCaptor.getValue().remainingCapacity());
}
}
Loading