lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

[HUDI-3032] Do not clean the log files right after compaction for metadata table (#4336)

Browse Source
This commit is contained in:
Danny Chan
2021-12-22 11:10:27 +08:00
committed by GitHub
parent 92f54ce3d8
commit f1286c2c76
3 changed files with 16 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
hudi-client/hudi-client-common/src/main/java/org/apache/hudi/metadata/HoodieBackedTableMetadataWriter.java
View File

@@ -706,7 +706,20 @@ public abstract class HoodieBackedTableMetadataWriter implements HoodieTableMeta
}
}
protected void doClean(AbstractHoodieWriteClient writeClient, String instantTime) {
protected void cleanIfNecessary(AbstractHoodieWriteClient writeClient, String instantTime) {
Option<HoodieInstant> lastCompletedCompactionInstant = metadataMetaClient.reloadActiveTimeline()
.getCommitTimeline().filterCompletedInstants().lastInstant();
if (lastCompletedCompactionInstant.isPresent()
&& metadataMetaClient.getActiveTimeline().filterCompletedInstants()
.findInstantsAfter(lastCompletedCompactionInstant.get().getTimestamp()).countInstants() < 3) {
// do not clean the log files immediately after compaction to give some buffer time for metadata table reader,
// because there is case that the reader has prepared for the log file readers already before the compaction completes
// while before/during the reading of the log files, the cleaning triggers and delete the reading files,
// then a FileNotFoundException(for LogFormatReader) or NPE(for HFileReader) would throw.
// 3 is a value that I think is enough for metadata table reader.
return;
}
// Trigger cleaning with suffixes based on the same instant time. This ensures that any future
// delta commits synced over will not have an instant time lesser than the last completed instant on the
// metadata table.

2
hudi-client/hudi-flink-client/src/main/java/org/apache/hudi/metadata/FlinkHoodieBackedTableMetadataWriter.java
View File

@@ -139,7 +139,7 @@ public class FlinkHoodieBackedTableMetadataWriter extends HoodieBackedTableMetad
metadataMetaClient.reloadActiveTimeline();
if (canTriggerTableService) {
compactIfNecessary(writeClient, instantTime);
doClean(writeClient, instantTime);
cleanIfNecessary(writeClient, instantTime);
writeClient.archive();
}
}

2
hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/metadata/SparkHoodieBackedTableMetadataWriter.java
View File

@@ -154,7 +154,7 @@ public class SparkHoodieBackedTableMetadataWriter extends HoodieBackedTableMetad
metadataMetaClient.reloadActiveTimeline();
if (canTriggerTableService) {
compactIfNecessary(writeClient, instantTime);
doClean(writeClient, instantTime);
cleanIfNecessary(writeClient, instantTime);
writeClient.archive();
}
}