Skip to content

[BigQueryIO] Parallelize schema update integration tests #39622

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

[BigQueryIO] Parallelize schema update integration tests #39622

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
3 changes: 2 additions & 1 deletion sdks/java/io/google-cloud-platform/build.gradle
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -283,7 +283,8 @@ task bigQueryEarlyRolloutIntegrationTest(type: Test, dependsOn: processTestResou
include '**/StorageApiDirectWriteProtosIT.class'
include '**/StorageApiSinkFailedRowsIT.class'
include '**/StorageApiSinkRowUpdateIT.class'
include '**/StorageApiSinkSchemaUpdateIT.class'
include '**/StorageApiSinkSchemaUpdateWithInputSchemaIT.class'
include '**/StorageApiSinkSchemaUpdateWithoutInputSchemaIT.class'
include '**/TableRowToStorageApiProtoIT.class'
// file loads
include '**/BigQuerySchemaUpdateOptionsIT.class'
Expand Down
61 changes: 24 additions & 37 deletions ...igquery/StorageApiSinkSchemaUpdateIT.java → ...ery/StorageApiSinkSchemaUpdateITBase.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,44 +70,32 @@
import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.collect.Iterables;
import org.joda.time.Duration;
import org.joda.time.Instant;
import org.junit.AfterClass;
import org.junit.BeforeClass;
import org.junit.Rule;
import org.junit.Test;
import org.junit.rules.TestName;
import org.junit.runner.RunWith;
import org.junit.runners.Parameterized;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

@RunWith(Parameterized.class)
public class StorageApiSinkSchemaUpdateIT {
@Parameterized.Parameters
public static Iterable<Object[]> data() {
return ImmutableList.of(
new Object[] {false, false},
new Object[] {false, true},
new Object[] {true, false},
new Object[] {true, true});
}

@Parameterized.Parameter(0)
public boolean useInputSchema;
abstract class StorageApiSinkSchemaUpdateITBase {
private final boolean useInputSchema;
private final boolean changeTableSchema;
private final String bigQueryDatasetId;

@Parameterized.Parameter(1)
public boolean changeTableSchema;
StorageApiSinkSchemaUpdateITBase(
boolean useInputSchema, boolean changeTableSchema, String bigQueryDatasetId) {
this.useInputSchema = useInputSchema;
this.changeTableSchema = changeTableSchema;
this.bigQueryDatasetId = bigQueryDatasetId;
}

@Rule public TestName testName = new TestName();

private static final Logger LOG = LoggerFactory.getLogger(StorageApiSinkSchemaUpdateIT.class);
private static final Logger LOG = LoggerFactory.getLogger(StorageApiSinkSchemaUpdateITBase.class);

private static final BigqueryClient BQ_CLIENT =
new BigqueryClient("StorageApiSinkSchemaChangeIT");
private static final String PROJECT =
TestPipeline.testingPipelineOptions().as(GcpOptions.class).getProject();
private static final String BIG_QUERY_DATASET_ID =
"storage_api_sink_schema_change_" + System.nanoTime();

private static final String[] FIELDS = {
"BOOL",
"BOOLEAN",
Expand Down Expand Up @@ -149,18 +137,17 @@ public static Iterable<Object[]> data() {
// used when test suite specifies a particular GCP location for BigQuery operations
private static String bigQueryLocation;

@BeforeClass
public static void setUpTestEnvironment() throws IOException, InterruptedException {
static void setUpTestEnvironment(String bigQueryDatasetId)
throws IOException, InterruptedException {
// Create one BQ dataset for all test cases.
bigQueryLocation =
TestPipeline.testingPipelineOptions().as(TestBigQueryOptions.class).getBigQueryLocation();
BQ_CLIENT.createNewDataset(PROJECT, BIG_QUERY_DATASET_ID, null, bigQueryLocation);
BQ_CLIENT.createNewDataset(PROJECT, bigQueryDatasetId, null, bigQueryLocation);
}

@AfterClass
public static void cleanUp() {
LOG.info("Cleaning up dataset {} and tables.", BIG_QUERY_DATASET_ID);
BQ_CLIENT.deleteDataset(PROJECT, BIG_QUERY_DATASET_ID);
static void cleanUp(String bigQueryDatasetId) {
LOG.info("Cleaning up dataset {} and tables.", bigQueryDatasetId);
BQ_CLIENT.deleteDataset(PROJECT, bigQueryDatasetId);
}

private String createTable(TableSchema tableSchema) throws IOException, InterruptedException {
Expand All @@ -178,16 +165,16 @@ private String createTable(TableSchema tableSchema, String suffix)
}
tableId += suffix;

BQ_CLIENT.deleteTable(PROJECT, BIG_QUERY_DATASET_ID, tableId);
BQ_CLIENT.deleteTable(PROJECT, bigQueryDatasetId, tableId);
BQ_CLIENT.createNewTable(
PROJECT,
BIG_QUERY_DATASET_ID,
bigQueryDatasetId,
new Table()
.setSchema(tableSchema)
.setTableReference(
new TableReference()
.setTableId(tableId)
.setDatasetId(BIG_QUERY_DATASET_ID)
.setDatasetId(bigQueryDatasetId)
.setProjectId(PROJECT)));
return tableId;
}
Expand Down Expand Up @@ -395,7 +382,7 @@ private void runStreamingPipelineWithSchemaChange(
makeTableSchemaFromTypes(fieldNamesWithExtra, ImmutableSet.of(extraField));

String tableId = createTable(bqTableSchema);
String tableSpec = PROJECT + ":" + BIG_QUERY_DATASET_ID + "." + tableId;
String tableSpec = PROJECT + ":" + bigQueryDatasetId + "." + tableId;

// build write transform
Write<TableRow> write =
Expand Down Expand Up @@ -462,7 +449,7 @@ private void runStreamingPipelineWithSchemaChange(
"Update Schema",
ParDo.of(
new UpdateSchemaDoFn(
PROJECT, BIG_QUERY_DATASET_ID, ImmutableMap.of(tableId, updatedSchema))));
PROJECT, bigQueryDatasetId, ImmutableMap.of(tableId, updatedSchema))));
}
WriteResult result = rows.apply("Stream to BigQuery", write);
if (useIgnoreUnknownValues) {
Expand Down Expand Up @@ -648,7 +635,7 @@ public void runDynamicDestinationsWithAutoSchemaUpdate(boolean useAtLeastOnce) t
GenerateRowFunc generateRowFunc = new GenerateRowFunc(fieldNamesOrigin, fieldNamesWithExtra);

String tableId = createTable(bqTableSchema, "_dynamic_" + i);
String tableSpec = PROJECT + ":" + BIG_QUERY_DATASET_ID + "." + tableId;
String tableSpec = PROJECT + ":" + bigQueryDatasetId + "." + tableId;

rowFuncs.put((long) i, generateRowFunc);
destinations.put((long) i, tableSpec);
Expand Down Expand Up @@ -727,7 +714,7 @@ public void runDynamicDestinationsWithAutoSchemaUpdate(boolean useAtLeastOnce) t
.apply("Add a dummy key", WithKeys.of(1))
.apply(
"Update Schema",
ParDo.of(new UpdateSchemaDoFn(PROJECT, BIG_QUERY_DATASET_ID, updatedSchemas)));
ParDo.of(new UpdateSchemaDoFn(PROJECT, bigQueryDatasetId, updatedSchemas)));
}

WriteResult result = rows.apply("Stream to BigQuery", write);
Expand Down
50 changes: 50 additions & 0 deletions ...java/org/apache/beam/sdk/io/gcp/bigquery/StorageApiSinkSchemaUpdateWithInputSchemaIT.java
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,50 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.beam.sdk.io.gcp.bigquery;

import java.io.IOException;
import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.collect.ImmutableList;
import org.junit.AfterClass;
import org.junit.BeforeClass;
import org.junit.runner.RunWith;
import org.junit.runners.Parameterized;

@RunWith(Parameterized.class)
public class StorageApiSinkSchemaUpdateWithInputSchemaIT extends StorageApiSinkSchemaUpdateITBase {
private static final String BIG_QUERY_DATASET_ID =
"storage_api_sink_schema_change_with_input_" + System.nanoTime();

@Parameterized.Parameters(name = "changeTableSchema={0}")
public static Iterable<Object[]> data() {
return ImmutableList.of(new Object[] {false}, new Object[] {true});
}

public StorageApiSinkSchemaUpdateWithInputSchemaIT(boolean changeTableSchema) {
super(true, changeTableSchema, BIG_QUERY_DATASET_ID);
}

@BeforeClass
public static void setUpTestEnvironment() throws IOException, InterruptedException {
StorageApiSinkSchemaUpdateITBase.setUpTestEnvironment(BIG_QUERY_DATASET_ID);
}

@AfterClass
public static void cleanUp() {
StorageApiSinkSchemaUpdateITBase.cleanUp(BIG_QUERY_DATASET_ID);
}
}
51 changes: 51 additions & 0 deletions ...a/org/apache/beam/sdk/io/gcp/bigquery/StorageApiSinkSchemaUpdateWithoutInputSchemaIT.java
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,51 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.beam.sdk.io.gcp.bigquery;

import java.io.IOException;
import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.collect.ImmutableList;
import org.junit.AfterClass;
import org.junit.BeforeClass;
import org.junit.runner.RunWith;
import org.junit.runners.Parameterized;

@RunWith(Parameterized.class)
public class StorageApiSinkSchemaUpdateWithoutInputSchemaIT
extends StorageApiSinkSchemaUpdateITBase {
private static final String BIG_QUERY_DATASET_ID =
"storage_api_sink_schema_change_without_input_" + System.nanoTime();

@Parameterized.Parameters(name = "changeTableSchema={0}")
public static Iterable<Object[]> data() {
return ImmutableList.of(new Object[] {false}, new Object[] {true});
}

public StorageApiSinkSchemaUpdateWithoutInputSchemaIT(boolean changeTableSchema) {
super(false, changeTableSchema, BIG_QUERY_DATASET_ID);
}

@BeforeClass
public static void setUpTestEnvironment() throws IOException, InterruptedException {
StorageApiSinkSchemaUpdateITBase.setUpTestEnvironment(BIG_QUERY_DATASET_ID);
}

@AfterClass
public static void cleanUp() {
StorageApiSinkSchemaUpdateITBase.cleanUp(BIG_QUERY_DATASET_ID);
}
}
Loading