You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hudi.apache.org by fo...@apache.org on 2023/02/11 02:33:39 UTC
[hudi] 12/20: [HUDI-5543] Description of clustering.plan.partition.filter.mode supports DAY_ROLLING strategy (#7656)
This is an automated email from the ASF dual-hosted git repository.
forwardxu pushed a commit to branch release-0.12.1
in repository https://gitbox.apache.org/repos/asf/hudi.git
commit 94ee9a133adf72c5c79b89ea2c9ce601d6b7f494
Author: Nicholas Jiang <pr...@163.com>
AuthorDate: Fri Jan 13 10:59:26 2023 +0800
[HUDI-5543] Description of clustering.plan.partition.filter.mode supports DAY_ROLLING strategy (#7656)
(cherry picked from commit 669e567672557ffa6d58fd37918f6b37eb842d39)
---
.../src/main/java/org/apache/hudi/config/HoodieClusteringConfig.java | 4 +++-
.../src/main/java/org/apache/hudi/configuration/FlinkOptions.java | 4 +++-
2 files changed, 6 insertions(+), 2 deletions(-)
diff --git a/hudi-client/hudi-client-common/src/main/java/org/apache/hudi/config/HoodieClusteringConfig.java b/hudi-client/hudi-client-common/src/main/java/org/apache/hudi/config/HoodieClusteringConfig.java
index 8db88178f8d..6e3224c3e50 100644
--- a/hudi-client/hudi-client-common/src/main/java/org/apache/hudi/config/HoodieClusteringConfig.java
+++ b/hudi-client/hudi-client-common/src/main/java/org/apache/hudi/config/HoodieClusteringConfig.java
@@ -153,7 +153,9 @@ public class HoodieClusteringConfig extends HoodieConfig {
+ "RECENT_DAYS: keep a continuous range of partitions, worked together with configs '" + DAYBASED_LOOKBACK_PARTITIONS.key() + "' and '"
+ PLAN_STRATEGY_SKIP_PARTITIONS_FROM_LATEST.key() + "."
+ "SELECTED_PARTITIONS: keep partitions that are in the specified range ['" + PARTITION_FILTER_BEGIN_PARTITION.key() + "', '"
- + PARTITION_FILTER_END_PARTITION.key() + "'].");
+ + PARTITION_FILTER_END_PARTITION.key() + "']."
+ + "DAY_ROLLING: clustering partitions on a rolling basis by the hour to avoid clustering all partitions each time, "
+ + "which strategy sorts the partitions asc and chooses the partition of which index is divided by 24 and the remainder is equal to the current hour.");
public static final ConfigProperty<String> PLAN_STRATEGY_MAX_BYTES_PER_OUTPUT_FILEGROUP = ConfigProperty
.key(CLUSTERING_STRATEGY_PARAM_PREFIX + "max.bytes.per.group")
diff --git a/hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/configuration/FlinkOptions.java b/hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/configuration/FlinkOptions.java
index 68f22c6f7e7..b885791daeb 100644
--- a/hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/configuration/FlinkOptions.java
+++ b/hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/configuration/FlinkOptions.java
@@ -702,7 +702,9 @@ public class FlinkOptions extends HoodieConfig {
+ "RECENT_DAYS: keep a continuous range of partitions, worked together with configs '" + DAYBASED_LOOKBACK_PARTITIONS.key() + "' and '"
+ PLAN_STRATEGY_SKIP_PARTITIONS_FROM_LATEST.key() + "."
+ "SELECTED_PARTITIONS: keep partitions that are in the specified range ['" + PARTITION_FILTER_BEGIN_PARTITION.key() + "', '"
- + PARTITION_FILTER_END_PARTITION.key() + "'].");
+ + PARTITION_FILTER_END_PARTITION.key() + "']."
+ + "DAY_ROLLING: clustering partitions on a rolling basis by the hour to avoid clustering all partitions each time, "
+ + "which strategy sorts the partitions asc and chooses the partition of which index is divided by 24 and the remainder is equal to the current hour.");
public static final ConfigOption<Long> CLUSTERING_PLAN_STRATEGY_TARGET_FILE_MAX_BYTES = ConfigOptions
.key("clustering.plan.strategy.target.file.max.bytes")