You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@iceberg.apache.org by "aokolnychyi (via GitHub)" <gi...@apache.org> on 2023/02/16 03:20:09 UTC
[GitHub] [iceberg] aokolnychyi commented on a diff in pull request #6838: Spark 3.3: Add a new Spark SQLConf to influence the write distribution mode
aokolnychyi commented on code in PR #6838:
URL: https://github.com/apache/iceberg/pull/6838#discussion_r1107961291
##########
spark/v3.3/spark/src/test/java/org/apache/iceberg/spark/TestSparkWriteConfDistributionMode.java:
##########
@@ -0,0 +1,142 @@
+/*
+ * 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.iceberg.spark;
+
+import static org.apache.iceberg.TableProperties.WRITE_DISTRIBUTION_MODE;
+import static org.apache.iceberg.TableProperties.WRITE_DISTRIBUTION_MODE_HASH;
+import static org.apache.iceberg.TableProperties.WRITE_DISTRIBUTION_MODE_NONE;
+import static org.apache.iceberg.TableProperties.WRITE_DISTRIBUTION_MODE_RANGE;
+
+import java.util.Map;
+import org.apache.iceberg.DistributionMode;
+import org.apache.iceberg.Table;
+import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap;
+import org.junit.After;
+import org.junit.Assert;
+import org.junit.Before;
+import org.junit.Test;
+
+public class TestSparkWriteConfDistributionMode extends SparkTestBaseWithCatalog {
+
+ @Before
+ public void before() {
+ sql(
+ "CREATE TABLE %s (id BIGINT, data STRING, date DATE, ts TIMESTAMP) "
+ + "USING iceberg "
+ + "PARTITIONED BY (date, days(ts))",
+ tableName);
+ }
+
+ @After
+ public void after() {
+ spark.conf().unset(SparkSQLProperties.SESSION_WRITE_DISTRIBUTION_MODE);
Review Comment:
Instead of unsetting values in `after`, we normally use `withSQLConf()` method in tests.
##########
spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/SparkSQLProperties.java:
##########
@@ -47,4 +47,8 @@ private SparkSQLProperties() {}
public static final String PRESERVE_DATA_GROUPING =
"spark.sql.iceberg.planning.preserve-data-grouping";
public static final boolean PRESERVE_DATA_GROUPING_DEFAULT = false;
+
+ // Controls write distribution mode
+ public static final String SESSION_WRITE_DISTRIBUTION_MODE =
Review Comment:
I don't think we need the `SESSION_` prefix in the name. All SQL properties are session properties.
##########
spark/v3.3/spark/src/test/java/org/apache/iceberg/spark/TestSparkWriteConfDistributionMode.java:
##########
@@ -0,0 +1,142 @@
+/*
+ * 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.iceberg.spark;
+
+import static org.apache.iceberg.TableProperties.WRITE_DISTRIBUTION_MODE;
+import static org.apache.iceberg.TableProperties.WRITE_DISTRIBUTION_MODE_HASH;
+import static org.apache.iceberg.TableProperties.WRITE_DISTRIBUTION_MODE_NONE;
+import static org.apache.iceberg.TableProperties.WRITE_DISTRIBUTION_MODE_RANGE;
+
+import java.util.Map;
+import org.apache.iceberg.DistributionMode;
+import org.apache.iceberg.Table;
+import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap;
+import org.junit.After;
+import org.junit.Assert;
+import org.junit.Before;
+import org.junit.Test;
+
+public class TestSparkWriteConfDistributionMode extends SparkTestBaseWithCatalog {
+
+ @Before
+ public void before() {
+ sql(
+ "CREATE TABLE %s (id BIGINT, data STRING, date DATE, ts TIMESTAMP) "
+ + "USING iceberg "
+ + "PARTITIONED BY (date, days(ts))",
+ tableName);
+ }
+
+ @After
+ public void after() {
+ spark.conf().unset(SparkSQLProperties.SESSION_WRITE_DISTRIBUTION_MODE);
+ sql("DROP TABLE IF EXISTS %s", tableName);
+ }
+
+ @Test
+ public void testSparkWriteConfDistributionDefault() {
+ Table table = validationCatalog.loadTable(tableIdent);
+
+ SparkWriteConf writeConf = new SparkWriteConf(spark, table, ImmutableMap.of());
+
+ Assert.assertEquals(DistributionMode.NONE, writeConf.distributionMode());
+ }
+
+ @Test
+ public void testSparkWriteConfDistributionModeWithWriteOption() {
+ Table table = validationCatalog.loadTable(tableIdent);
+
+ Map<String, String> writeOptions =
+ ImmutableMap.of(SparkWriteOptions.DISTRIBUTION_MODE, DistributionMode.HASH.modeName());
+
+ SparkWriteConf writeConf = new SparkWriteConf(spark, table, writeOptions);
+ Assert.assertEquals(DistributionMode.HASH, writeConf.distributionMode());
+ }
+
+ @Test
+ public void testSparkWriteConfDistributionModeWithSessionConfig() {
+ Table table = validationCatalog.loadTable(tableIdent);
+
+ spark
+ .conf()
+ .set(SparkSQLProperties.SESSION_WRITE_DISTRIBUTION_MODE, DistributionMode.HASH.modeName());
+
+ SparkWriteConf writeConf = new SparkWriteConf(spark, table, ImmutableMap.of());
+ Assert.assertEquals(DistributionMode.HASH, writeConf.distributionMode());
+ }
+
+ @Test
+ public void testSparkWriteConfDistributionModeWithTableProperties() {
+ Table table = validationCatalog.loadTable(tableIdent);
+
+ table.updateProperties().set(WRITE_DISTRIBUTION_MODE, WRITE_DISTRIBUTION_MODE_HASH).commit();
+
+ SparkWriteConf writeConf = new SparkWriteConf(spark, table, ImmutableMap.of());
+ Assert.assertEquals(DistributionMode.HASH, writeConf.distributionMode());
+ }
+
+ @Test
+ public void testSparkWriteConfDistributionModeWithTblPropAndSessionConfig() {
+ Table table = validationCatalog.loadTable(tableIdent);
+
+ table.updateProperties().set(WRITE_DISTRIBUTION_MODE, WRITE_DISTRIBUTION_MODE_RANGE).commit();
+
+ spark
Review Comment:
Such calls should be replaced with `withSQLConf()`.
##########
spark/v3.3/spark/src/test/java/org/apache/iceberg/spark/TestSparkWriteConfDistributionMode.java:
##########
@@ -0,0 +1,169 @@
+/*
+ * 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.iceberg.spark;
+
+import static org.apache.iceberg.TableProperties.WRITE_DISTRIBUTION_MODE;
+import static org.apache.iceberg.TableProperties.WRITE_DISTRIBUTION_MODE_HASH;
+import static org.apache.iceberg.TableProperties.WRITE_DISTRIBUTION_MODE_NONE;
+import static org.apache.iceberg.TableProperties.WRITE_DISTRIBUTION_MODE_RANGE;
+
+import java.util.Map;
+import org.apache.iceberg.DistributionMode;
+import org.apache.iceberg.Table;
+import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap;
+import org.junit.After;
+import org.junit.Assert;
+import org.junit.Test;
+
+public class TestSparkWriteConfDistributionMode extends SparkTestBaseWithCatalog {
Review Comment:
What about calling it `TestSparkWriteConf` so that it becomes generic? We may add more tests for other configs in the future. I think it is fine to purely test the config.
##########
spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/SparkWriteConf.java:
##########
@@ -207,6 +207,7 @@ public DistributionMode distributionMode() {
confParser
.stringConf()
.option(SparkWriteOptions.DISTRIBUTION_MODE)
+ .sessionConf(SparkSQLProperties.SESSION_WRITE_DISTRIBUTION_MODE)
Review Comment:
Once we merge #6828, this SQL conf must be also respected in other distribution modes wherever we respect the corresponding write option (e.g. DELETE, UPDATE, MERGE commands).
##########
spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/SparkSQLProperties.java:
##########
@@ -47,4 +47,8 @@ private SparkSQLProperties() {}
public static final String PRESERVE_DATA_GROUPING =
"spark.sql.iceberg.planning.preserve-data-grouping";
public static final boolean PRESERVE_DATA_GROUPING_DEFAULT = false;
+
+ // Controls write distribution mode
+ public static final String SESSION_WRITE_DISTRIBUTION_MODE =
Review Comment:
I see our SQL configs rarely include read/write prefixes. What about this then?
```
public static final String DISTRIBUTION_MODE = "spark.sql.iceberg.distribution-mode"
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: issues-unsubscribe@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@iceberg.apache.org
For additional commands, e-mail: issues-help@iceberg.apache.org