Github user gjacoby126 commented on a diff in the pull request:
https://github.com/apache/phoenix/pull/309#discussion_r218623519
--- Diff:
phoenix-core/src/it/java/org/apache/phoenix/mapreduce/VerifyReplicationToolIT.java
---
@@ -0,0 +1,284 @@
+/*
+ * 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.phoenix.mapreduce;
+
+import java.io.IOException;
+import java.sql.*;
+import java.util.*;
+
+import com.google.common.collect.Lists;
+import com.google.common.collect.Maps;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hbase.TableName;
+import org.apache.hadoop.hbase.util.Bytes;
+import org.apache.hadoop.mapreduce.Counters;
+import org.apache.hadoop.mapreduce.Job;
+import org.apache.phoenix.end2end.BaseUniqueNamesOwnClusterIT;
+import org.apache.phoenix.query.QueryConstants;
+import org.apache.phoenix.util.ByteUtil;
+import org.apache.phoenix.util.EnvironmentEdgeManager;
+import org.apache.phoenix.util.ReadOnlyProps;
+import org.junit.Assert;
+import org.junit.Before;
+import org.junit.BeforeClass;
+import org.junit.Test;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import static org.junit.Assert.assertEquals;
+
+public class VerifyReplicationToolIT extends BaseUniqueNamesOwnClusterIT {
+ private static final Logger LOG =
LoggerFactory.getLogger(VerifyReplicationToolIT.class);
+ private static final String CREATE_USER_TABLE = "CREATE TABLE IF NOT
EXISTS %s ( " +
+ " TENANT_ID VARCHAR NOT NULL, USER_ID VARCHAR NOT NULL, AGE
INTEGER " +
+ " CONSTRAINT pk PRIMARY KEY ( TENANT_ID, USER_ID ))";
+ private static final String UPSERT_USER = "UPSERT INTO %s VALUES (?,
?, ?)";
+ private static final String SELECT_USER =
+ "SELECT * FROM %s WHERE TENANT_ID = ? LIMIT %d";
+ private static final Random RANDOM = new Random();
+ private static final int NUM_USERS = 10;
+ private static final int NUM_TENANTS = 2;
+
+ private static int tenantNum = 0;
+ private static int userNum = 0;
+ /** source table with 4 regions*/
+ private static String sourceTableName;
+ /** target table with 2 regions*/
+ private static String targetTableName;
+ private List<String> sourceTenants;
+ private String sourceOnlyTenant;
+ private String sourceAndTargetTenant;
+ private String targetOnlyTenant;
+ private PreparedStatement sourceStmt;
+ private PreparedStatement targetStmt;
+ private List<byte[]> sourceSplitPoints;
+ private List<byte[]> targetSplitPoints;
+
+ @BeforeClass
+ public static void createTables() throws Exception {
+ NUM_SLAVES_BASE = 4;
+ Map<String,String> props = Maps.newHashMapWithExpectedSize(1);
+ setUpTestDriver(new ReadOnlyProps(props.entrySet().iterator()));
+ Connection conn = DriverManager.getConnection(getUrl());
+ sourceTableName = generateUniqueName();
+ targetTableName = generateUniqueName();
+ // tables will have the same schema, but a different number of
regions
+ conn.createStatement().execute(String.format(CREATE_USER_TABLE,
sourceTableName));
+ conn.createStatement().execute(String.format(CREATE_USER_TABLE,
targetTableName));
+ conn.commit();
+ }
+
+ @Before
+ public void setupTenants() throws Exception {
+ sourceTenants = new ArrayList<>(NUM_TENANTS);
+ sourceTenants.add("tenant" + tenantNum++);
+ sourceTenants.add("tenant" + tenantNum++);
+ sourceOnlyTenant = sourceTenants.get(0);
+ sourceAndTargetTenant = sourceTenants.get(1);
+ targetOnlyTenant = "tenant" + tenantNum++;
+ /* upsert data and spilt table into multiple regions
+ with each relevant region based on splitpoints
+ residing on a different RS*/
+ upsertData();
+ /* splitting source table into 4 regions */
+ splitSource(sourceTableName);
+ /* splitting target table into 2 regions */
+ splitTarget(targetTableName);
+ }
+
+ @Test
+ public void testVerifyRowsMatch() throws Exception {
+ verify(String.format("TENANT_ID = '%s'", sourceAndTargetTenant),
0, 10, 0, 0, 0, 0);
+ }
+
+ @Test
+ public void testVerifySourceOnly() throws Exception {
+ verify(String.format("TENANT_ID = '%s'", sourceOnlyTenant), 0, 0,
10, 10, 0, 0);
+ }
+
+ @Test
+ public void testVerifyRowsDifferent() throws Exception {
+ // change three rows on the source table so they no longer match
on the target
+ upsertSelectData(sourceTableName, sourceAndTargetTenant, -1, 3);
+ verify(String.format("TENANT_ID = '%s'", sourceAndTargetTenant),
0, 7, 3, 0, 0, 3);
+ }
+
--- End diff --
@akshita-malhotra - setup is we have Cluster A and Cluster B:
1. Some rows exist only in cluster A
2. Some rows exist in both A and B
3. Some rows exist only in B.
Assert that your counters are correct. It's essentially combining two of
your existing test cases to make sure that it still works with both cases
present.
---
