[GitHub] [hive] pkumarsinha commented on a change in pull request #2795: HIVE-25708. Implement creation of table_diff.

[GitBox <gi...@apache.org>]

pkumarsinha commented on a change in pull request #2795:
URL: https://github.com/apache/hive/pull/2795#discussion_r755728047



##########
File path: ql/src/java/org/apache/hadoop/hive/ql/exec/repl/OptimisedBootstrapUtils.java
##########
@@ -0,0 +1,276 @@
+/*
+ * 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.hive.ql.exec.repl;
+
+import org.apache.commons.io.IOUtils;
+import org.apache.hadoop.fs.FSDataInputStream;
+import org.apache.hadoop.fs.FileStatus;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.fs.RemoteIterator;
+import org.apache.hadoop.hive.common.FileUtils;
+import org.apache.hadoop.hive.conf.HiveConf;
+import org.apache.hadoop.hive.metastore.api.Database;
+import org.apache.hadoop.hive.metastore.api.NotificationEvent;
+import org.apache.hadoop.hive.metastore.messaging.event.filters.DatabaseAndTableFilter;
+import org.apache.hadoop.hive.metastore.utils.MetaStoreUtils;
+import org.apache.hadoop.hive.ql.metadata.Hive;
+import org.apache.hadoop.hive.ql.metadata.HiveException;
+import org.apache.hadoop.hive.ql.metadata.Partition;
+import org.apache.hadoop.hive.ql.metadata.Table;
+import org.apache.hadoop.hive.ql.parse.SemanticException;
+import org.apache.hadoop.hive.ql.parse.repl.DumpType;
+import org.apache.hadoop.hive.ql.parse.repl.dump.Utils;
+import org.apache.hadoop.hive.ql.parse.repl.load.DumpMetaData;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.io.IOException;
+import java.nio.charset.Charset;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.HashSet;
+import java.util.List;
+import java.util.stream.Collectors;
+
+import static org.apache.hadoop.hive.ql.parse.ReplicationSpec.getLastReplicatedStateFromParameters;
+
+public class OptimisedBootstrapUtils {
+
+  public static final String FILE_ENTRY_SEPERATOR = "###";

Review comment:
       replace with single #

##########
File path: itests/hive-unit/src/test/java/org/apache/hadoop/hive/ql/parse/TestReplicationOptimisedBootstrap.java
##########
@@ -0,0 +1,289 @@
+/*
+ * 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.hive.ql.parse;
+
+import org.apache.hadoop.fs.ContentSummary;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hdfs.DistributedFileSystem;
+import org.apache.hadoop.hive.conf.HiveConf;
+import org.apache.hadoop.hive.metastore.conf.MetastoreConf;
+import org.apache.hadoop.hive.metastore.messaging.json.gzip.GzipJSONMessageEncoder;
+
+import org.apache.hadoop.security.UserGroupInformation;
+import org.junit.After;
+import org.junit.Before;
+import org.junit.BeforeClass;
+import org.junit.Test;
+
+import java.util.Arrays;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.List;
+
+import static org.apache.hadoop.hive.ql.exec.repl.OptimisedBootstrapUtils.EVENT_ACK_FILE;
+import static org.apache.hadoop.hive.ql.exec.repl.OptimisedBootstrapUtils.TABLE_DIFF_COMPLETE_DIRECTORY;
+import static org.apache.hadoop.hive.ql.exec.repl.OptimisedBootstrapUtils.getEventIdFromFile;
+import static org.apache.hadoop.hive.ql.exec.repl.OptimisedBootstrapUtils.getPathsFromTableFile;
+import static org.apache.hadoop.hive.ql.exec.repl.OptimisedBootstrapUtils.getTablesFromTableDiffFile;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertFalse;
+import static org.junit.Assert.assertNotNull;
+import static org.junit.Assert.assertTrue;
+
+public class TestReplicationOptimisedBootstrap extends BaseReplicationAcrossInstances {
+
+  String extraPrimaryDb;
+
+  @BeforeClass
+  public static void classLevelSetup() throws Exception {
+    HashMap<String, String> overrides = new HashMap<>();
+    overrides.put(MetastoreConf.ConfVars.EVENT_MESSAGE_FACTORY.getHiveName(),
+        GzipJSONMessageEncoder.class.getCanonicalName());
+    overrides.put(HiveConf.ConfVars.REPL_DUMP_METADATA_ONLY.varname, "false");
+    overrides.put(HiveConf.ConfVars.REPL_INCLUDE_EXTERNAL_TABLES.varname, "true");
+    overrides.put(HiveConf.ConfVars.HIVE_DISTCP_DOAS_USER.varname, UserGroupInformation.getCurrentUser().getUserName());
+    overrides.put(HiveConf.ConfVars.REPL_RUN_DATA_COPY_TASKS_ON_TARGET.varname, "true");
+
+    internalBeforeClassSetupExclusiveReplica(overrides, overrides, TestReplicationOptimisedBootstrap.class);
+  }
+
+  @Before
+  public void setup() throws Throwable {
+    super.setup();
+    extraPrimaryDb = "extra_" + primaryDbName;
+  }
+
+  @After
+  public void tearDown() throws Throwable {
+    primary.run("drop database if exists " + extraPrimaryDb + " cascade");
+    super.tearDown();
+  }
+
+  @Test
+  public void testBuildTableDiffGeneration() throws Throwable {
+    List<String> withClause = ReplicationTestUtils.includeExternalTableClause(true);
+    withClause.add("'" + HiveConf.ConfVars.REPLDIR.varname + "'='" + primary.repldDir + "'");
+    // Create two external & two managed tables and do a bootstrap dump & load.
+    WarehouseInstance.Tuple tuple = primary.run("use " + primaryDbName)
+        .run("create external table t1 (id int)")

Review comment:
        add assertion for managed as well

##########
File path: itests/hive-unit/src/test/java/org/apache/hadoop/hive/ql/parse/TestReplicationOptimisedBootstrap.java
##########
@@ -0,0 +1,289 @@
+/*
+ * 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.hive.ql.parse;
+
+import org.apache.hadoop.fs.ContentSummary;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hdfs.DistributedFileSystem;
+import org.apache.hadoop.hive.conf.HiveConf;
+import org.apache.hadoop.hive.metastore.conf.MetastoreConf;
+import org.apache.hadoop.hive.metastore.messaging.json.gzip.GzipJSONMessageEncoder;
+
+import org.apache.hadoop.security.UserGroupInformation;
+import org.junit.After;
+import org.junit.Before;
+import org.junit.BeforeClass;
+import org.junit.Test;
+
+import java.util.Arrays;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.List;
+
+import static org.apache.hadoop.hive.ql.exec.repl.OptimisedBootstrapUtils.EVENT_ACK_FILE;
+import static org.apache.hadoop.hive.ql.exec.repl.OptimisedBootstrapUtils.TABLE_DIFF_COMPLETE_DIRECTORY;
+import static org.apache.hadoop.hive.ql.exec.repl.OptimisedBootstrapUtils.getEventIdFromFile;
+import static org.apache.hadoop.hive.ql.exec.repl.OptimisedBootstrapUtils.getPathsFromTableFile;
+import static org.apache.hadoop.hive.ql.exec.repl.OptimisedBootstrapUtils.getTablesFromTableDiffFile;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertFalse;
+import static org.junit.Assert.assertNotNull;
+import static org.junit.Assert.assertTrue;
+
+public class TestReplicationOptimisedBootstrap extends BaseReplicationAcrossInstances {
+
+  String extraPrimaryDb;
+
+  @BeforeClass
+  public static void classLevelSetup() throws Exception {
+    HashMap<String, String> overrides = new HashMap<>();
+    overrides.put(MetastoreConf.ConfVars.EVENT_MESSAGE_FACTORY.getHiveName(),
+        GzipJSONMessageEncoder.class.getCanonicalName());
+    overrides.put(HiveConf.ConfVars.REPL_DUMP_METADATA_ONLY.varname, "false");
+    overrides.put(HiveConf.ConfVars.REPL_INCLUDE_EXTERNAL_TABLES.varname, "true");
+    overrides.put(HiveConf.ConfVars.HIVE_DISTCP_DOAS_USER.varname, UserGroupInformation.getCurrentUser().getUserName());
+    overrides.put(HiveConf.ConfVars.REPL_RUN_DATA_COPY_TASKS_ON_TARGET.varname, "true");
+
+    internalBeforeClassSetupExclusiveReplica(overrides, overrides, TestReplicationOptimisedBootstrap.class);
+  }
+
+  @Before
+  public void setup() throws Throwable {
+    super.setup();
+    extraPrimaryDb = "extra_" + primaryDbName;
+  }
+
+  @After
+  public void tearDown() throws Throwable {
+    primary.run("drop database if exists " + extraPrimaryDb + " cascade");
+    super.tearDown();
+  }
+
+  @Test
+  public void testBuildTableDiffGeneration() throws Throwable {
+    List<String> withClause = ReplicationTestUtils.includeExternalTableClause(true);
+    withClause.add("'" + HiveConf.ConfVars.REPLDIR.varname + "'='" + primary.repldDir + "'");
+    // Create two external & two managed tables and do a bootstrap dump & load.
+    WarehouseInstance.Tuple tuple = primary.run("use " + primaryDbName)
+        .run("create external table t1 (id int)")
+        .run("insert into table t1 values (1)")
+        .run("insert into table t1 values (2),(3),(4)")
+        .run("create external table t2 (place string) partitioned by (country string)")
+        .run("insert into table t2 partition(country='india') values ('chennai')")
+        .run("insert into table t2 partition(country='us') values ('new york')")
+        .run("create  table t1_managed (id int)")
+        .run("insert into table t1_managed values (10)")
+        .run("insert into table t1_managed values (20),(31),(42)")
+        .run("create external table t2_managed (place string) partitioned by (country string)")
+        .run("insert into table t2_managed partition(country='india') values ('bangalore')")
+        .run("insert into table t2_managed partition(country='us') values ('austin')")
+        .dump(primaryDbName, withClause);
+
+    replica.load(replicatedDbName, primaryDbName, withClause)
+        .run("repl status " + replicatedDbName)
+        .verifyResult(tuple.lastReplicationId).run("use " + replicatedDbName)
+        .run("show tables like 't1'")
+        .verifyResult("t1")
+        .run("show tables like 't2'")
+        .verifyResult("t2")
+        .verifyReplTargetProperty(replicatedDbName);
+
+    // Trigger reverse dump just after the bootstrap cycle.

Review comment:
       first incremental should be mandated, no?




-- 
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: gitbox-unsubscribe@hive.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: gitbox-unsubscribe@hive.apache.org
For additional commands, e-mail: gitbox-help@hive.apache.org