lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

[HUDI-4273] Support inline schedule clustering for Flink stream (#5890)

Browse Source 
* [HUDI-4273] Support inline schedule clustering for Flink stream

* delete deprecated clustering plan strategy and add clustering ITTest
This commit is contained in:
Zhaojing Yu
2022-06-24 11:28:06 +08:00
committed by GitHub
parent af9f09047d
commit 6456bd3a51
29 changed files with 1116 additions and 385 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
hudi-client/hudi-client-common/src/main/java/org/apache/hudi/table/action/cluster/strategy/ClusteringPlanStrategy.java
View File

@@ -70,9 +70,6 @@ public abstract class ClusteringPlanStrategy<T extends HoodieRecordPayload,I,K,O
String sparkSizeBasedClassName = HoodieClusteringConfig.SPARK_SIZED_BASED_CLUSTERING_PLAN_STRATEGY;
String sparkSelectedPartitionsClassName = "org.apache.hudi.client.clustering.plan.strategy.SparkSelectedPartitionsClusteringPlanStrategy";
String sparkRecentDaysClassName = "org.apache.hudi.client.clustering.plan.strategy.SparkRecentDaysClusteringPlanStrategy";
String flinkSizeBasedClassName = HoodieClusteringConfig.FLINK_SIZED_BASED_CLUSTERING_PLAN_STRATEGY;
String flinkSelectedPartitionsClassName = "org.apache.hudi.client.clustering.plan.strategy.FlinkSelectedPartitionsClusteringPlanStrategy";
String flinkRecentDaysClassName = "org.apache.hudi.client.clustering.plan.strategy.FlinkRecentDaysClusteringPlanStrategy";
String javaSelectedPartitionClassName = "org.apache.hudi.client.clustering.plan.strategy.JavaRecentDaysClusteringPlanStrategy";
String javaSizeBasedClassName = HoodieClusteringConfig.JAVA_SIZED_BASED_CLUSTERING_PLAN_STRATEGY;
@@ -85,14 +82,6 @@ public abstract class ClusteringPlanStrategy<T extends HoodieRecordPayload,I,K,O
config.setValue(HoodieClusteringConfig.PLAN_PARTITION_FILTER_MODE_NAME, ClusteringPlanPartitionFilterMode.SELECTED_PARTITIONS.name());
LOG.warn(String.format(logStr, className, sparkSizeBasedClassName, HoodieClusteringConfig.PLAN_PARTITION_FILTER_MODE_NAME.key(), ClusteringPlanPartitionFilterMode.SELECTED_PARTITIONS.name()));
return sparkSizeBasedClassName;
} else if (flinkRecentDaysClassName.equals(className)) {
config.setValue(HoodieClusteringConfig.PLAN_PARTITION_FILTER_MODE_NAME, ClusteringPlanPartitionFilterMode.RECENT_DAYS.name());
LOG.warn(String.format(logStr, className, sparkSizeBasedClassName, HoodieClusteringConfig.PLAN_PARTITION_FILTER_MODE_NAME.key(), ClusteringPlanPartitionFilterMode.RECENT_DAYS.name()));
return flinkSizeBasedClassName;
} else if (flinkSelectedPartitionsClassName.equals(className)) {
config.setValue(HoodieClusteringConfig.PLAN_PARTITION_FILTER_MODE_NAME, ClusteringPlanPartitionFilterMode.SELECTED_PARTITIONS.name());
LOG.warn(String.format(logStr, className, sparkSizeBasedClassName, HoodieClusteringConfig.PLAN_PARTITION_FILTER_MODE_NAME.key(), ClusteringPlanPartitionFilterMode.SELECTED_PARTITIONS.name()));
return flinkSizeBasedClassName;
} else if (javaSelectedPartitionClassName.equals(className)) {
config.setValue(HoodieClusteringConfig.PLAN_PARTITION_FILTER_MODE_NAME, ClusteringPlanPartitionFilterMode.RECENT_DAYS.name());
LOG.warn(String.format(logStr, className, javaSizeBasedClassName, HoodieClusteringConfig.PLAN_PARTITION_FILTER_MODE_NAME.key(), ClusteringPlanPartitionFilterMode.SELECTED_PARTITIONS.name()));
@@ -173,7 +162,7 @@ public abstract class ClusteringPlanStrategy<T extends HoodieRecordPayload,I,K,O
return metrics;
}
protected HoodieTable<T,I,K, O> getHoodieTable() {
protected HoodieTable<T, I, K, O> getHoodieTable() {
return this.hoodieTable;
}

2
hudi-client/hudi-client-common/src/main/java/org/apache/hudi/table/action/compact/ScheduleCompactionActionExecutor.java
View File

@@ -71,7 +71,7 @@ public class ScheduleCompactionActionExecutor<T extends HoodieRecordPayload, I,
if (!config.getWriteConcurrencyMode().supportsOptimisticConcurrencyControl()
&& !config.getFailedWritesCleanPolicy().isLazy()) {
// TODO(yihua): this validation is removed for Java client used by kafka-connect. Need to revisit this.
if (config.getEngineType() != EngineType.JAVA) {
if (config.getEngineType() == EngineType.SPARK) {
// if there are inflight writes, their instantTime must not be less than that of compaction instant time
table.getActiveTimeline().getCommitsTimeline().filterPendingExcludingCompaction().firstInstant()
.ifPresent(earliestInflight -> ValidationUtils.checkArgument(