001/*
002 * Licensed to the Apache Software Foundation (ASF) under one
003 * or more contributor license agreements.  See the NOTICE file
004 * distributed with this work for additional information
005 * regarding copyright ownership.  The ASF licenses this file
006 * to you under the Apache License, Version 2.0 (the
007 * "License"); you may not use this file except in compliance
008 * with the License.  You may obtain a copy of the License at
009 *
010 *     http://www.apache.org/licenses/LICENSE-2.0
011 *
012 * Unless required by applicable law or agreed to in writing, software
013 * distributed under the License is distributed on an "AS IS" BASIS,
014 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
015 * See the License for the specific language governing permissions and
016 * limitations under the License.
017 */
018package org.apache.hadoop.hbase.replication;
019
020import static org.junit.jupiter.api.Assertions.assertEquals;
021import static org.junit.jupiter.api.Assertions.assertTrue;
022
023import java.util.EnumSet;
024import java.util.List;
025import org.apache.hadoop.hbase.ClusterMetrics;
026import org.apache.hadoop.hbase.ClusterMetrics.Option;
027import org.apache.hadoop.hbase.ServerName;
028import org.apache.hadoop.hbase.client.Admin;
029import org.apache.hadoop.hbase.client.Put;
030import org.apache.hadoop.hbase.testclassification.MediumTests;
031import org.apache.hadoop.hbase.testclassification.ReplicationTests;
032import org.apache.hadoop.hbase.util.Bytes;
033import org.junit.jupiter.api.Tag;
034import org.junit.jupiter.api.Test;
035
036@Tag(ReplicationTests.TAG)
037@Tag(MediumTests.TAG)
038public class TestReplicationStatusBothNormalAndRecoveryLagging extends TestReplicationBase {
039
040  @Test
041  public void testReplicationStatusBothNormalAndRecoveryLagging() throws Exception {
042    // stop all region servers, we need to keep the master up as the below assertions need to get
043    // cluster id from remote cluster, if master is also down, we can not get any information from
044    // the remote cluster after source cluster restarts
045    stopAllRegionServers(UTIL2);
046
047    // add some values to cluster 1
048    for (int i = 0; i < NB_ROWS_IN_BATCH; i++) {
049      Put p = new Put(Bytes.toBytes("row" + i));
050      p.addColumn(famName, Bytes.toBytes("col1"), Bytes.toBytes("val" + i));
051      htable1.put(p);
052    }
053    Thread.sleep(10000);
054    restartSourceCluster(1);
055    Admin hbaseAdmin = UTIL1.getAdmin();
056    ServerName serverName = UTIL1.getHBaseCluster().getRegionServer(0).getServerName();
057    Thread.sleep(10000);
058    // add more values to cluster 1, these should cause normal queue to lag
059    for (int i = 0; i < NB_ROWS_IN_BATCH; i++) {
060      Put p = new Put(Bytes.toBytes("row" + i));
061      p.addColumn(famName, Bytes.toBytes("col1"), Bytes.toBytes("val" + i));
062      htable1.put(p);
063    }
064    Thread.sleep(10000);
065    ClusterMetrics metrics = hbaseAdmin.getClusterMetrics(EnumSet.of(Option.LIVE_SERVERS));
066    List<ReplicationLoadSource> loadSources =
067      metrics.getLiveServerMetrics().get(serverName).getReplicationLoadSourceList();
068    assertEquals(2, loadSources.size());
069    boolean foundRecovery = false;
070    boolean foundNormal = false;
071    for (ReplicationLoadSource loadSource : loadSources) {
072      if (loadSource.isRecovered()) {
073        foundRecovery = true;
074      } else {
075        foundNormal = true;
076      }
077      assertTrue(loadSource.hasEditsSinceRestart());
078      assertEquals(0, loadSource.getTimestampOfLastShippedOp());
079      assertTrue(loadSource.getReplicationLag() > 0);
080    }
081    assertTrue(foundNormal, "No normal queue found.");
082    assertTrue(foundRecovery, "No recovery queue found.");
083  }
084}