Skip to content

[HUDI-3001] Clean up the marker directory when finish bootstrap operation #4298

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
yihua merged 1 commit into from
Dec 16, 2021
Merged

[HUDI-3001] Clean up the marker directory when finish bootstrap operation #4298

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions .../main/java/org/apache/hudi/table/action/bootstrap/SparkBootstrapCommitActionExecutor.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,6 +77,7 @@
import org.apache.avro.generic.IndexedRecord;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hudi.table.marker.WriteMarkersFactory;
import org.apache.log4j.LogManager;
import org.apache.log4j.Logger;
import org.apache.parquet.avro.AvroParquetReader;
Expand Down Expand Up @@ -144,6 +145,9 @@ public HoodieBootstrapWriteMetadata execute() {
Option<HoodieWriteMetadata> metadataResult = metadataBootstrap(partitionSelections.get(BootstrapMode.METADATA_ONLY));
// if there are full bootstrap to be performed, perform that too
Option<HoodieWriteMetadata> fullBootstrapResult = fullBootstrap(partitionSelections.get(BootstrapMode.FULL_RECORD));
// Delete the marker directory for the instant
WriteMarkersFactory.get(config.getMarkersType(), table, instantTime)
.quietDeleteMarkerDir(context, config.getMarkersDeleteParallelism());
return new HoodieBootstrapWriteMetadata(metadataResult, fullBootstrapResult);
} catch (IOException ioe) {
throw new HoodieIOException(ioe.getMessage(), ioe);
Expand Down
9 changes: 7 additions & 2 deletions ...rce/hudi-spark/src/test/scala/org/apache/hudi/functional/TestDataSourceForBootstrap.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@

package org.apache.hudi.functional

import org.apache.hadoop.fs.FileSystem
import org.apache.hadoop.fs.{FileSystem, Path}
import org.apache.hudi.bootstrap.SparkParquetBootstrapDataProvider
import org.apache.hudi.client.bootstrap.selector.FullRecordBootstrapModeSelector
import org.apache.hudi.common.fs.FSUtils
Expand All @@ -31,9 +31,9 @@ import org.apache.spark.sql.{SaveMode, SparkSession}
import org.junit.jupiter.api.Assertions.assertEquals
import org.junit.jupiter.api.io.TempDir
import org.junit.jupiter.api.{AfterEach, BeforeEach, Test}

import java.time.Instant
import java.util.Collections

import scala.collection.JavaConverters._

class TestDataSourceForBootstrap {
Expand Down Expand Up @@ -106,6 +106,8 @@ class TestDataSourceForBootstrap {
DataSourceWriteOptions.COW_TABLE_TYPE_OPT_VAL,
extraOpts = Map(DataSourceWriteOptions.KEYGENERATOR_CLASS_NAME.key -> "org.apache.hudi.keygen.NonpartitionedKeyGenerator")
)
// check marked directory clean up
assert(!fs.exists(new Path(basePath, ".hoodie/.temp/00000000000001")))

// Read bootstrapped table and verify count
var hoodieROViewDF1 = spark.read.format("hudi").load(basePath + "/*")
Expand Down Expand Up @@ -161,6 +163,9 @@ class TestDataSourceForBootstrap {
Some("datestr"),
Map(DataSourceWriteOptions.HIVE_STYLE_PARTITIONING.key -> "true"))

// check marked directory clean up
assert(!fs.exists(new Path(basePath, ".hoodie/.temp/00000000000001")))

// Read bootstrapped table and verify count
val hoodieROViewDF1 = spark.read.format("hudi").load(basePath + "/*")
assertEquals(numRecords, hoodieROViewDF1.count())
Expand Down