smengcl commented on code in PR #10951: URL: https://github.com/apache/ozone/pull/10951#discussion_r3718539047
########## hadoop-ozone/integration-test/src/test/java/org/apache/hadoop/ozone/om/snapshot/TestOmSnapshotCheckpointDbContent.java: ########## @@ -0,0 +1,424 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.hadoop.ozone.om.snapshot; + +import static org.apache.hadoop.ozone.OzoneConfigKeys.OZONE_SNAPSHOT_DELETING_SERVICE_INTERVAL; +import static org.apache.hadoop.ozone.OzoneConsts.OM_KEY_PREFIX; +import static org.apache.hadoop.ozone.om.OMConfigKeys.OZONE_FILESYSTEM_SNAPSHOT_ENABLED_KEY; +import static org.apache.hadoop.ozone.om.OMConfigKeys.OZONE_SNAPSHOT_DEFRAG_SERVICE_INTERVAL; +import static org.apache.hadoop.ozone.om.OMConfigKeys.SNAPSHOT_DEFRAG_LIMIT_PER_TASK; +import static org.apache.hadoop.ozone.om.codec.OMDBDefinition.BUCKET_TABLE; +import static org.apache.hadoop.ozone.om.codec.OMDBDefinition.KEY_TABLE; +import static org.apache.hadoop.ozone.om.codec.OMDBDefinition.MULTIPART_INFO_TABLE; +import static org.apache.hadoop.ozone.om.codec.OMDBDefinition.OPEN_KEY_TABLE; +import static org.apache.hadoop.ozone.om.codec.OMDBDefinition.VOLUME_TABLE; +import static org.junit.jupiter.api.Assertions.assertEquals; +import static org.junit.jupiter.api.Assertions.assertNotNull; +import static org.junit.jupiter.api.Assertions.assertTrue; +import static org.junit.jupiter.api.Assumptions.assumeTrue; + +import java.io.File; +import java.io.IOException; +import java.nio.file.Paths; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Collections; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.SortedMap; +import java.util.TreeMap; +import java.util.UUID; +import java.util.concurrent.TimeUnit; +import java.util.concurrent.TimeoutException; +import org.apache.hadoop.hdds.conf.OzoneConfiguration; +import org.apache.hadoop.hdds.utils.IOUtils; +import org.apache.hadoop.hdds.utils.db.ManagedRawSSTFileReader; +import org.apache.hadoop.hdds.utils.db.RocksDBCheckpoint; +import org.apache.hadoop.hdds.utils.db.Table; +import org.apache.hadoop.hdds.utils.db.Table.KeyValue; +import org.apache.hadoop.hdds.utils.db.Table.KeyValueIterator; +import org.apache.hadoop.hdds.utils.db.TablePrefixInfo; +import org.apache.hadoop.ozone.MiniOzoneCluster; +import org.apache.hadoop.ozone.DataTestUtil; +import org.apache.hadoop.ozone.client.ObjectStore; +import org.apache.hadoop.ozone.client.OzoneBucket; +import org.apache.hadoop.ozone.client.OzoneClient; +import org.apache.hadoop.ozone.om.OMMetadataManager; +import org.apache.hadoop.ozone.om.OmMetadataManagerImpl; +import org.apache.hadoop.ozone.om.OmSnapshot; +import org.apache.hadoop.ozone.om.OmSnapshotManager; +import org.apache.hadoop.ozone.om.OzoneManager; +import org.apache.hadoop.ozone.om.helpers.BucketLayout; +import org.apache.hadoop.ozone.om.helpers.SnapshotInfo; +import org.apache.ozone.test.GenericTestUtils; +import org.apache.ratis.util.function.UncheckedAutoCloseableSupplier; +import org.junit.jupiter.api.AfterEach; +import org.junit.jupiter.api.BeforeEach; +import org.junit.jupiter.api.Test; +import org.junit.jupiter.api.Timeout; + +/** + * HDDS-13217: verify snapshot checkpoint DB content is preserved across defrag iterations. + * + * <p>After defrag compacts a snapshot checkpoint (S' = compact(S)), the on-disk metadata for that + * bucket prefix in the defragged checkpoint must still match the original checkpoint taken at + * snapshot creation time (version 0). + * + * <p>Version-0 checkpoint directories are removed after defrag, so baselines are captured before + * the first defrag iteration and compared against the active snapshot after defrag completes. + * + * <p>Each test method starts a fresh MiniOzone cluster to avoid cross-test interference on the + * global snapshot defrag chain. + */ +@Timeout(value = 15, unit = TimeUnit.MINUTES) +public class TestOmSnapshotCheckpointDbContent { + + private static final byte[] TEST_KEY_CONTENT = new byte[] {0x61, 0x62, 0x63}; + private static final int CHECKPOINT_WAIT_MS = 120_000; + private static final int DEFRAG_WAIT_MS = 600_000; + + private MiniOzoneCluster cluster; + private OzoneConfiguration conf; + private OzoneClient client; + private ObjectStore store; + + @BeforeEach + void initCluster() throws Exception { + assumeTrue(ManagedRawSSTFileReader.tryLoadLibrary(), + "Snapshot defrag requires rocks-tools native library"); + + conf = new OzoneConfiguration(); + conf.setBoolean(OZONE_FILESYSTEM_SNAPSHOT_ENABLED_KEY, true); + conf.setInt(OZONE_SNAPSHOT_DEFRAG_SERVICE_INTERVAL, 7200); + conf.setInt(SNAPSHOT_DEFRAG_LIMIT_PER_TASK, 10); + conf.setTimeDuration(OZONE_SNAPSHOT_DELETING_SERVICE_INTERVAL, 1, TimeUnit.SECONDS); + + cluster = MiniOzoneCluster.newBuilder(conf).setNumDatanodes(3).build(); + cluster.waitForClusterToBeReady(); + client = cluster.newClient(); + store = client.getObjectStore(); + } + + @AfterEach + void shutdownCluster() { + IOUtils.closeQuietly(client); + IOUtils.closeQuietly(cluster); + } + + /** + * Test#1 from HDDS-13217: create S1, S2, S3 on one bucket, run defrag, and verify each + * defragged checkpoint still matches its version-0 baseline. + */ + @Test + public void testDefragPreservesSnapshotCheckpointContent() + throws Exception { + ThreeSnapshotSetup setup = createThreeSnapshotsOnNewBucket(); + triggerDefragUntilDone(setup.snapshots); + assertCheckpointMatchesBaseline(setup.baselines, setup.snapshots); + } + + /** + * Test#2 from HDDS-13217: after an initial defrag pass, delete the middle snapshot, run defrag + * again, and verify the remaining youngest snapshot checkpoint still matches its baseline. + */ + @Test + public void testDefragAfterSnapshotDeletePreservesRemainingSnapshot() + throws Exception { + ThreeSnapshotSetup setup = createThreeSnapshotsOnNewBucket(); + triggerDefragUntilDone(setup.snapshots); + + SnapshotInfo s2 = setup.snapshots.get(1); + SnapshotInfo s3 = setup.snapshots.get(2); + int s3VersionAfterFirstDefrag = readSnapshotVersion(s3); + + store.deleteSnapshot(setup.volumeName, setup.bucketName, s2.getName()); + waitForSnapshotPurged(s2); + // Reload S3 so pathPreviousSnapshotId reflects the purged chain, not deleted S2. + s3 = loadSnapshotInfo(setup.volumeName, setup.bucketName, s3.getName()); + + triggerDefragUntilVersionIncreases(s3, s3VersionAfterFirstDefrag); + + assertCheckpointMatchesBaseline( + Collections.singletonMap(s3.getSnapshotId(), + setup.baselines.get(s3.getSnapshotId())), + Arrays.asList(s3)); + } + + private ThreeSnapshotSetup createThreeSnapshotsOnNewBucket() + throws IOException, InterruptedException, TimeoutException { + OzoneBucket bucket = + DataTestUtil.createVolumeAndBucket(client, BucketLayout.OBJECT_STORE); + String volumeName = bucket.getVolumeName(); + String bucketName = bucket.getName(); + + DataTestUtil.createKey(bucket, "key-s1", TEST_KEY_CONTENT); + store.createSnapshot(volumeName, bucketName, "snap-s1"); + + DataTestUtil.createKey(bucket, "key-s2", TEST_KEY_CONTENT); Review Comment: Please include an overwrite and a delete between the snapshots. The current sequence only adds keys, so this end-to-end test exercises insert deltas but cannot detect a regression in update or tombstone reconstruction. For example, overwrite one S1 key before S2 and delete another key before S3, then compare each defragged checkpoint with its baseline. ########## hadoop-ozone/integration-test/src/test/java/org/apache/hadoop/ozone/om/snapshot/TestOmSnapshotCheckpointDbContent.java: ########## @@ -0,0 +1,424 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.hadoop.ozone.om.snapshot; + +import static org.apache.hadoop.ozone.OzoneConfigKeys.OZONE_SNAPSHOT_DELETING_SERVICE_INTERVAL; +import static org.apache.hadoop.ozone.OzoneConsts.OM_KEY_PREFIX; +import static org.apache.hadoop.ozone.om.OMConfigKeys.OZONE_FILESYSTEM_SNAPSHOT_ENABLED_KEY; +import static org.apache.hadoop.ozone.om.OMConfigKeys.OZONE_SNAPSHOT_DEFRAG_SERVICE_INTERVAL; +import static org.apache.hadoop.ozone.om.OMConfigKeys.SNAPSHOT_DEFRAG_LIMIT_PER_TASK; +import static org.apache.hadoop.ozone.om.codec.OMDBDefinition.BUCKET_TABLE; +import static org.apache.hadoop.ozone.om.codec.OMDBDefinition.KEY_TABLE; +import static org.apache.hadoop.ozone.om.codec.OMDBDefinition.MULTIPART_INFO_TABLE; +import static org.apache.hadoop.ozone.om.codec.OMDBDefinition.OPEN_KEY_TABLE; +import static org.apache.hadoop.ozone.om.codec.OMDBDefinition.VOLUME_TABLE; +import static org.junit.jupiter.api.Assertions.assertEquals; +import static org.junit.jupiter.api.Assertions.assertNotNull; +import static org.junit.jupiter.api.Assertions.assertTrue; +import static org.junit.jupiter.api.Assumptions.assumeTrue; + +import java.io.File; +import java.io.IOException; +import java.nio.file.Paths; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Collections; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.SortedMap; +import java.util.TreeMap; +import java.util.UUID; +import java.util.concurrent.TimeUnit; +import java.util.concurrent.TimeoutException; +import org.apache.hadoop.hdds.conf.OzoneConfiguration; +import org.apache.hadoop.hdds.utils.IOUtils; +import org.apache.hadoop.hdds.utils.db.ManagedRawSSTFileReader; +import org.apache.hadoop.hdds.utils.db.RocksDBCheckpoint; +import org.apache.hadoop.hdds.utils.db.Table; +import org.apache.hadoop.hdds.utils.db.Table.KeyValue; +import org.apache.hadoop.hdds.utils.db.Table.KeyValueIterator; +import org.apache.hadoop.hdds.utils.db.TablePrefixInfo; +import org.apache.hadoop.ozone.MiniOzoneCluster; +import org.apache.hadoop.ozone.DataTestUtil; +import org.apache.hadoop.ozone.client.ObjectStore; +import org.apache.hadoop.ozone.client.OzoneBucket; +import org.apache.hadoop.ozone.client.OzoneClient; +import org.apache.hadoop.ozone.om.OMMetadataManager; +import org.apache.hadoop.ozone.om.OmMetadataManagerImpl; +import org.apache.hadoop.ozone.om.OmSnapshot; +import org.apache.hadoop.ozone.om.OmSnapshotManager; +import org.apache.hadoop.ozone.om.OzoneManager; +import org.apache.hadoop.ozone.om.helpers.BucketLayout; +import org.apache.hadoop.ozone.om.helpers.SnapshotInfo; +import org.apache.ozone.test.GenericTestUtils; +import org.apache.ratis.util.function.UncheckedAutoCloseableSupplier; +import org.junit.jupiter.api.AfterEach; +import org.junit.jupiter.api.BeforeEach; +import org.junit.jupiter.api.Test; +import org.junit.jupiter.api.Timeout; + +/** + * HDDS-13217: verify snapshot checkpoint DB content is preserved across defrag iterations. + * + * <p>After defrag compacts a snapshot checkpoint (S' = compact(S)), the on-disk metadata for that + * bucket prefix in the defragged checkpoint must still match the original checkpoint taken at + * snapshot creation time (version 0). + * + * <p>Version-0 checkpoint directories are removed after defrag, so baselines are captured before + * the first defrag iteration and compared against the active snapshot after defrag completes. + * + * <p>Each test method starts a fresh MiniOzone cluster to avoid cross-test interference on the + * global snapshot defrag chain. + */ +@Timeout(value = 15, unit = TimeUnit.MINUTES) +public class TestOmSnapshotCheckpointDbContent { + + private static final byte[] TEST_KEY_CONTENT = new byte[] {0x61, 0x62, 0x63}; + private static final int CHECKPOINT_WAIT_MS = 120_000; + private static final int DEFRAG_WAIT_MS = 600_000; + + private MiniOzoneCluster cluster; + private OzoneConfiguration conf; + private OzoneClient client; + private ObjectStore store; + + @BeforeEach + void initCluster() throws Exception { + assumeTrue(ManagedRawSSTFileReader.tryLoadLibrary(), + "Snapshot defrag requires rocks-tools native library"); + + conf = new OzoneConfiguration(); + conf.setBoolean(OZONE_FILESYSTEM_SNAPSHOT_ENABLED_KEY, true); + conf.setInt(OZONE_SNAPSHOT_DEFRAG_SERVICE_INTERVAL, 7200); + conf.setInt(SNAPSHOT_DEFRAG_LIMIT_PER_TASK, 10); + conf.setTimeDuration(OZONE_SNAPSHOT_DELETING_SERVICE_INTERVAL, 1, TimeUnit.SECONDS); + + cluster = MiniOzoneCluster.newBuilder(conf).setNumDatanodes(3).build(); + cluster.waitForClusterToBeReady(); + client = cluster.newClient(); + store = client.getObjectStore(); + } + + @AfterEach + void shutdownCluster() { + IOUtils.closeQuietly(client); + IOUtils.closeQuietly(cluster); + } + + /** + * Test#1 from HDDS-13217: create S1, S2, S3 on one bucket, run defrag, and verify each + * defragged checkpoint still matches its version-0 baseline. + */ + @Test + public void testDefragPreservesSnapshotCheckpointContent() + throws Exception { + ThreeSnapshotSetup setup = createThreeSnapshotsOnNewBucket(); + triggerDefragUntilDone(setup.snapshots); + assertCheckpointMatchesBaseline(setup.baselines, setup.snapshots); + } + + /** + * Test#2 from HDDS-13217: after an initial defrag pass, delete the middle snapshot, run defrag + * again, and verify the remaining youngest snapshot checkpoint still matches its baseline. + */ + @Test + public void testDefragAfterSnapshotDeletePreservesRemainingSnapshot() + throws Exception { + ThreeSnapshotSetup setup = createThreeSnapshotsOnNewBucket(); + triggerDefragUntilDone(setup.snapshots); + + SnapshotInfo s2 = setup.snapshots.get(1); + SnapshotInfo s3 = setup.snapshots.get(2); + int s3VersionAfterFirstDefrag = readSnapshotVersion(s3); + + store.deleteSnapshot(setup.volumeName, setup.bucketName, s2.getName()); + waitForSnapshotPurged(s2); + // Reload S3 so pathPreviousSnapshotId reflects the purged chain, not deleted S2. + s3 = loadSnapshotInfo(setup.volumeName, setup.bucketName, s3.getName()); + + triggerDefragUntilVersionIncreases(s3, s3VersionAfterFirstDefrag); + + assertCheckpointMatchesBaseline( + Collections.singletonMap(s3.getSnapshotId(), + setup.baselines.get(s3.getSnapshotId())), + Arrays.asList(s3)); + } + + private ThreeSnapshotSetup createThreeSnapshotsOnNewBucket() + throws IOException, InterruptedException, TimeoutException { + OzoneBucket bucket = + DataTestUtil.createVolumeAndBucket(client, BucketLayout.OBJECT_STORE); Review Comment: Please cover the FSO defrag path too. This setup hard-codes `OBJECT_STORE`, so the test validates `keyTable` only. Snapshot defrag reconstructs `keyTable`, `directoryTable`, and `fileTable`; the current integration test never checks two of those three tables. Add an FSO bucket to the merged scenario and compare its directory and file tables with their version-0 baselines. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
