lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

[MINOR] Moving spark scheduling configs out of DataSourceOptions (#4843)

Browse Source
This commit is contained in:
Sivabalan Narayanan
2022-02-20 13:49:18 -05:00
committed by GitHub
parent 83279971a1
commit 66ac1446dd
5 changed files with 59 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/DataSourceOptions.scala
View File

@@ -479,32 +479,6 @@ object DataSourceWriteOptions {
+ "Use this when you are in the process of migrating from "
+ "com.uber.hoodie to org.apache.hudi. Stop using this after you migrated the table definition to org.apache.hudi input format")
// spark data source write pool name. Incase of streaming sink, users might be interested to set custom scheduling configs
// for regular writes and async compaction. In such cases, this pool name will be used for spark datasource writes.
val SPARK_DATASOURCE_WRITER_POOL_NAME = "sparkdatasourcewrite"
/*
When async compaction is enabled (deltastreamer or streaming sink), users might be interested to set custom
scheduling configs for regular writes and async compaction. This is the property used to set custom scheduler config
file with spark. In Deltastreamer, the file is generated within hudi and set if necessary. Where as in case of streaming
sink, users have to set this property when they invoke spark shell.
Sample format of the file contents.
<?xml version="1.0"?>
<allocations>
<pool name="sparkdatasourcewrite">
<schedulingMode>FAIR</schedulingMode>
<weight>4</weight>
<minShare>2</minShare>
</pool>
<pool name="hoodiecompact">
<schedulingMode>FAIR</schedulingMode>
<weight>3</weight>
<minShare>1</minShare>
</pool>
</allocations>
*/
val SPARK_SCHEDULER_ALLOCATION_FILE_KEY = "spark.scheduler.allocation.file"
/** @deprecated Use {@link HIVE_SYNC_MODE} instead of this config from 0.9.0 */
@Deprecated
val HIVE_USE_JDBC: ConfigProperty[String] = ConfigProperty

4
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/HoodieSparkSqlWriter.scala
View File

@@ -124,8 +124,8 @@ object HoodieSparkSqlWriter {
val jsc = new JavaSparkContext(sparkContext)
if (asyncCompactionTriggerFn.isDefined) {
if (jsc.getConf.getOption(DataSourceWriteOptions.SPARK_SCHEDULER_ALLOCATION_FILE_KEY).isDefined) {
jsc.setLocalProperty("spark.scheduler.pool", DataSourceWriteOptions.SPARK_DATASOURCE_WRITER_POOL_NAME)
if (jsc.getConf.getOption(SparkConfigs.SPARK_SCHEDULER_ALLOCATION_FILE_KEY).isDefined) {
jsc.setLocalProperty("spark.scheduler.pool", SparkConfigs.SPARK_DATASOURCE_WRITER_POOL_NAME)
}
}
val instantTime = HoodieActiveTimeline.createNewInstantTime()

50
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/SparkConfigs.scala Normal file
View File

@@ -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.hudi
object SparkConfigs {
// spark data source write pool name. Incase of streaming sink, users might be interested to set custom scheduling configs
// for regular writes and async compaction. In such cases, this pool name will be used for spark datasource writes.
val SPARK_DATASOURCE_WRITER_POOL_NAME = "sparkdatasourcewrite"
/*
When async compaction is enabled (deltastreamer or streaming sink), users might be interested to set custom
scheduling configs for regular writes and async compaction. This is the property used to set custom scheduler config
file with spark. In Deltastreamer, the file is generated within hudi and set if necessary. Where as in case of streaming
sink, users have to set this property when they invoke spark shell.
Sample format of the file contents.
<?xml version="1.0"?>
<allocations>
<pool name="sparkdatasourcewrite">
<schedulingMode>FAIR</schedulingMode>
<weight>4</weight>
<minShare>2</minShare>
</pool>
<pool name="hoodiecompact">
<schedulingMode>FAIR</schedulingMode>
<weight>3</weight>
<minShare>1</minShare>
</pool>
</allocations>
*/
val SPARK_SCHEDULER_ALLOCATION_FILE_KEY = "spark.scheduler.allocation.file"
}