Skip to content

HIVE-29528: Cleanup managed DB dir after async drop #6397

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

Open
VenuReddy2103 wants to merge 2 commits into
base: master
Choose a base branch
from
Open

HIVE-29528: Cleanup managed DB dir after async drop #6397

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7dc7832
HIVE-29528: Cleanup managed DB dir after async drop
Mar 31, 2026
866a22b
Reworked for comments
Apr 2, 2026
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
24 changes: 24 additions & 0 deletions ql/src/java/org/apache/hadoop/hive/ql/txn/compactor/CleanupRequest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,8 @@ public class CleanupRequest {
private final String location;
private final List<Path> obsoleteDirs;
private final boolean purge;
private final boolean softDelete;
private final boolean sourceOfReplication;
private final String runAs;
private final String dbName;
private final String fullPartitionName;
Expand All @@ -38,6 +40,8 @@ public CleanupRequest(CleanupRequestBuilder builder) {
this.location = builder.location;
this.obsoleteDirs = builder.obsoleteDirs;
this.purge = builder.purge;
this.softDelete = builder.softDelete;
this.sourceOfReplication = builder.sourceOfReplication;
this.runAs = builder.runAs;
this.dbName = builder.dbName;
this.fullPartitionName = builder.fullPartitionName;
Expand All @@ -55,6 +59,14 @@ public boolean isPurge() {
return purge;
}

public boolean isSoftDelete() {
return softDelete;
}

public boolean isSourceOfReplication() {
return sourceOfReplication;
}

public String runAs() {
return runAs;
}
Expand All @@ -74,6 +86,8 @@ public static class CleanupRequestBuilder {
private String location;
private List<Path> obsoleteDirs;
private boolean purge;
private boolean softDelete;
private boolean sourceOfReplication;
Copy link
Copy Markdown
Member

@deniskuzZ deniskuzZ Apr 1, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

isSourceOfReplication ?

Copy link
Copy Markdown
Contributor Author

@VenuReddy2103 VenuReddy2103 Apr 2, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Have changed isSoftDelete to softDelete now to keep the naming convention consistent with existing purge field

private String runAs;
private String dbName;
private String fullPartitionName;
Expand All @@ -93,6 +107,16 @@ public CleanupRequestBuilder setPurge(boolean purge) {
return this;
}

public CleanupRequestBuilder setSoftDelete(boolean softDelete) {
this.softDelete = softDelete;
return this;
}

public CleanupRequestBuilder setSourceOfReplication(boolean sourceOfReplication) {
this.sourceOfReplication = sourceOfReplication;
return this;
}

public CleanupRequestBuilder setDbName(String dbName) {
this.dbName = dbName;
return this;
Expand Down
21 changes: 18 additions & 3 deletions ql/src/java/org/apache/hadoop/hive/ql/txn/compactor/FSRemover.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,17 +99,18 @@ private List<Path> removeFiles(CleanupRequest cr)
LOG.info("About to remove {} obsolete directories from {}. {}", cr.getObsoleteDirs().size(),
cr.getLocation(), CompactorUtil.getDebugInfo(cr.getObsoleteDirs()));
boolean needCmRecycle;
Database db = null;
try {
Database db = metadataCache.computeIfAbsent(cr.getDbName(),
db = metadataCache.computeIfAbsent(cr.getDbName(),
() -> CompactorUtil.resolveDatabase(conf, cr.getDbName()));
needCmRecycle = ReplChangeManager.isSourceOfReplication(db);
} catch (NoSuchObjectException ex) {
// can not drop a database which is a source of replication
needCmRecycle = false;
needCmRecycle = cr.isSourceOfReplication();
} catch (RuntimeException ex) {
if (ex.getCause() instanceof NoSuchObjectException) {
// can not drop a database which is a source of replication
needCmRecycle = false;
needCmRecycle = cr.isSourceOfReplication();
} else {
throw ex;
}
Expand All @@ -126,6 +127,20 @@ private List<Path> removeFiles(CleanupRequest cr)
deleted.add(dead);
}
}
removeDatabaseDirIfNecessary(db, cr, fs);
return deleted;
}

private void removeDatabaseDirIfNecessary(Database db, CleanupRequest cr, FileSystem fs) throws IOException {
if (db != null || !cr.isSoftDelete()) {
return;
}
Path databasePath = new Path(cr.getLocation()).getParent();
if (FileUtils.isDirEmpty(fs, databasePath)) {
if (cr.isSourceOfReplication()) {
replChangeManager.recycle(databasePath, ReplChangeManager.RecycleType.MOVE, cr.isPurge());
}
FileUtils.deleteDir(fs, databasePath, cr.isPurge(), conf);
}
}
}
2 changes: 2 additions & 0 deletions ql/src/java/org/apache/hadoop/hive/ql/txn/compactor/handler/CompactionCleaner.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -286,6 +286,8 @@ private CleanupRequest getCleaningRequestBasedOnLocation(CompactionInfo ci, Stri
.setFullPartitionName(ci.getFullPartitionName())
.setRunAs(ci.runAs)
.setPurge(ifPurge)
.setSoftDelete(ci.isSoftDelete())
.setSourceOfReplication(ci.isSourceOfReplication())
.setObsoleteDirs(Collections.singletonList(obsoletePath))
.build();
}
Expand Down
9 changes: 4 additions & 5 deletions ql/src/test/org/apache/hadoop/hive/ql/TestTxnCommands.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@
package org.apache.hadoop.hive.ql;

import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.util.ArrayList;
Expand Down Expand Up @@ -1827,11 +1828,9 @@ private void dropDatabaseCascadeNonBlocking() throws Exception {

runCleaner(hiveConf);

stat = fs.listStatus(new Path(getWarehouseDir(), database + ".db"),
t -> t.getName().matches("(mv_)?" + tableName + "2" + SOFT_DELETE_TABLE_PATTERN));
if (stat.length != 0) {
Assert.fail("Table data was not removed from FS");
}
Assert.assertThrows(database + ".db directory should not exist", FileNotFoundException.class, () -> {
fs.listStatus(new Path(getWarehouseDir(), database + ".db"));
});
}

@Test
Expand Down
2 changes: 2 additions & 0 deletions ...gen/thrift/gen-javabean/org/apache/hadoop/hive/metastore/api/hive_metastoreConstants.java
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

5 changes: 5 additions & 0 deletions ...metastore-common/src/main/java/org/apache/hadoop/hive/metastore/utils/MetaStoreUtils.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1344,4 +1344,9 @@ public static String getHttpPath(String httpPath) {
public static boolean isDatabaseRemote(Database db) {
return db != null && db.getType() == DatabaseType.REMOTE;
}

/**
* Soft delete operation types.
*/
public enum SoftDeleteOperation {DROP_DATABASE, DROP_TABLE}
}
12 changes: 12 additions & 0 deletions ...re/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/AcidEventListener.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@
package org.apache.hadoop.hive.metastore;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hive.common.repl.ReplConst;
import org.apache.hadoop.hive.metastore.api.CompactionRequest;
import org.apache.hadoop.hive.metastore.api.CompactionType;
import org.apache.hadoop.hive.metastore.api.Database;
Expand All @@ -39,6 +40,7 @@
import org.apache.hadoop.hive.metastore.events.DropTableEvent;
import org.apache.hadoop.hive.metastore.txn.TxnStore;
import org.apache.hadoop.hive.metastore.txn.TxnUtils;
import org.apache.hadoop.hive.metastore.utils.MetaStoreUtils;

import java.io.IOException;
import java.util.Iterator;
Expand Down Expand Up @@ -91,6 +93,7 @@ public void onDropTable(DropTableEvent tableEvent) throws MetaException {
rqst.setRunas(TxnUtils.findUserToRunAs(table.getSd().getLocation(), table, conf));
rqst.putToProperties("location", table.getSd().getLocation());
rqst.putToProperties("ifPurge", Boolean.toString(isMustPurge(tableEvent.getEnvironmentContext(), table)));
addSoftDeletePropertiesToRequest(tableEvent.getEnvironmentContext(), rqst);
txnHandler.submitForCleanup(rqst, table.getWriteId(), currentTxn);
} catch (InterruptedException | IOException e) {
throwMetaException(e);
Expand Down Expand Up @@ -244,4 +247,13 @@ private long getTxnId(EnvironmentContext context) {
.map(Long::parseLong)
.orElse(0L);
}

private void addSoftDeletePropertiesToRequest(EnvironmentContext context, CompactionRequest request) {
request.putToProperties(hive_metastoreConstants.SOFT_DELETE_OPERATION,
Optional.ofNullable(context.getProperties().get(hive_metastoreConstants.SOFT_DELETE_OPERATION))
.orElse(MetaStoreUtils.SoftDeleteOperation.DROP_TABLE.name()));
if (Boolean.parseBoolean(context.getProperties().get(ReplConst.SOURCE_OF_REPLICATION))) {
request.putToProperties(ReplConst.SOURCE_OF_REPLICATION, Boolean.TRUE.toString());
}
}
}
6 changes: 6 additions & 0 deletions ...re-server/src/main/java/org/apache/hadoop/hive/metastore/handler/DropDatabaseHandler.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@
import java.util.concurrent.atomic.AtomicReference;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hive.common.repl.ReplConst;
import org.apache.hadoop.hive.metastore.Batchable;
import org.apache.hadoop.hive.metastore.HMSHandler;
import org.apache.hadoop.hive.metastore.IHMSHandler;
Expand Down Expand Up @@ -136,6 +137,11 @@ public DropDatabaseResult execute() throws TException, IOException {
if (isSoftDelete) {
context = new EnvironmentContext();
context.putToProperties(hive_metastoreConstants.TXN_ID, String.valueOf(request.getTxnId()));
context.putToProperties(hive_metastoreConstants.SOFT_DELETE_OPERATION,
MetaStoreUtils.SoftDeleteOperation.DROP_DATABASE.name());
if (ReplChangeManager.isSourceOfReplication(db)) {
context.putToProperties(ReplConst.SOURCE_OF_REPLICATION, Boolean.TRUE.toString());
}
request.setDeleteManagedDir(false);
}
DropTableRequest dropRequest = new DropTableRequest(name, table.getTableName());
Expand Down
10 changes: 10 additions & 0 deletions ...re-server/src/main/java/org/apache/hadoop/hive/metastore/txn/entities/CompactionInfo.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,8 +19,10 @@

import org.apache.commons.lang3.builder.ToStringBuilder;
import org.apache.hadoop.hive.common.ValidCompactorWriteIdList;
import org.apache.hadoop.hive.common.repl.ReplConst;
import org.apache.hadoop.hive.metastore.api.CompactionInfoStruct;
import org.apache.hadoop.hive.metastore.api.CompactionType;
import org.apache.hadoop.hive.metastore.api.hive_metastoreConstants;
import org.apache.hadoop.hive.metastore.api.MetaException;
import org.apache.hadoop.hive.metastore.api.OptionalCompactionInfoStruct;
import org.apache.hadoop.hive.metastore.api.TableValidWriteIds;
Expand Down Expand Up @@ -368,4 +370,12 @@ public void setWriteIds(boolean hasUncompactedAborts, Set<Long> writeIds) {
public boolean isAbortedTxnCleanup() {
return type == CompactionType.ABORT_TXN_CLEANUP;
}

public boolean isSoftDelete() {
return getProperty(hive_metastoreConstants.SOFT_DELETE_OPERATION) != null;
}

public boolean isSourceOfReplication() {
return Boolean.parseBoolean(getProperty(ReplConst.SOURCE_OF_REPLICATION));
}
}
Loading