[
https://issues.apache.org/jira/browse/HIVE-21671?focusedWorklogId=238726&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-238726
]
ASF GitHub Bot logged work on HIVE-21671:
-----------------------------------------
Author: ASF GitHub Bot
Created on: 07/May/19 19:08
Start Date: 07/May/19 19:08
Worklog Time Spent: 10m
Work Description: sankarh commented on pull request #615: HIVE-21671:
Replicate Streaming ingestion with transactional batch size as 1.
URL: https://github.com/apache/hive/pull/615#discussion_r281788161
##########
File path:
itests/hive-unit/src/test/java/org/apache/hadoop/hive/ql/parse/TestReplicationOfHiveStreaming.java
##########
@@ -0,0 +1,369 @@
+/*
+ * 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.FileSystem;
+import org.apache.hadoop.hdfs.MiniDFSCluster;
+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.hive.shims.Utils;
+import org.apache.hive.streaming.HiveStreamingConnection;
+import org.apache.hive.streaming.StrictDelimitedInputWriter;
+import org.apache.hive.streaming.StreamingConnection;
+
+import org.junit.rules.TestName;
+import org.junit.After;
+import org.junit.Assert;
+import org.junit.Before;
+import org.junit.Rule;
+import org.junit.Test;
+import org.junit.BeforeClass;
+import org.junit.AfterClass;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.HashMap;
+import java.util.Map;
+
+import static
org.apache.hadoop.hive.metastore.ReplChangeManager.SOURCE_OF_REPLICATION;
+
+/**
+ * TestReplicationOfHiveStreaming - test replication for streaming ingest on
ACID tables
+ */
+public class TestReplicationOfHiveStreaming {
+
+ @Rule
+ public final TestName testName = new TestName();
+
+ protected static final Logger LOG =
LoggerFactory.getLogger(TestReplicationOfHiveStreaming.class);
+ private static WarehouseInstance primary;
+ private static WarehouseInstance replica;
+ private static String primaryDbName;
+ private static String replicatedDbName;
+
+ @BeforeClass
+ public static void classLevelSetup() throws Exception {
+ HashMap<String, String> overrides = new HashMap<>();
+ overrides.put(MetastoreConf.ConfVars.EVENT_MESSAGE_FACTORY.getHiveName(),
+ GzipJSONMessageEncoder.class.getCanonicalName());
+
+ internalBeforeClassSetup(overrides, TestReplicationOfHiveStreaming.class);
+ }
+
+ static void internalBeforeClassSetup(Map<String, String> overrides,
+ Class clazz) throws Exception {
+
+ HiveConf conf = new HiveConf(clazz);
+ conf.set("dfs.client.use.datanode.hostname", "true");
+ conf.set("hadoop.proxyuser." + Utils.getUGI().getShortUserName() +
".hosts", "*");
+ MiniDFSCluster miniDFSCluster =
+ new MiniDFSCluster.Builder(conf).numDataNodes(1).format(true).build();
+ HashMap<String, String> acidEnableConf = new HashMap<String, String>() {{
+ put("fs.defaultFS", miniDFSCluster.getFileSystem().getUri().toString());
+ put("hive.support.concurrency", "true");
+ put("hive.txn.manager",
"org.apache.hadoop.hive.ql.lockmgr.DbTxnManager");
+ put("hive.metastore.client.capability.check", "false");
+ put("hive.repl.bootstrap.dump.open.txn.timeout", "1s");
+ put("hive.exec.dynamic.partition.mode", "nonstrict");
+ put("hive.strict.checks.bucketing", "false");
+ put("hive.mapred.mode", "nonstrict");
+ put("mapred.input.dir.recursive", "true");
+ put("hive.metastore.disallow.incompatible.col.type.changes", "false");
+ put("hive.in.repl.test", "true");
+ }};
+
+ acidEnableConf.putAll(overrides);
+
+ primary = new WarehouseInstance(LOG, miniDFSCluster, acidEnableConf);
+ replica = new WarehouseInstance(LOG, miniDFSCluster, acidEnableConf);
+ }
+
+ @AfterClass
+ public static void classLevelTearDown() throws IOException {
+ primary.close();
+ replica.close();
+ }
+
+ @Before
+ public void setup() throws Throwable {
+ primaryDbName = testName.getMethodName() + "_" +
+System.currentTimeMillis();
+ replicatedDbName = "replicated_" + primaryDbName;
+ primary.run("create database " + primaryDbName + " WITH DBPROPERTIES ( '" +
+ SOURCE_OF_REPLICATION + "' = '1,2,3')");
+ }
+
+ @After
+ public void tearDown() throws Throwable {
+ primary.run("drop database if exists " + primaryDbName + " cascade");
+ replica.run("drop database if exists " + replicatedDbName + " cascade");
+ }
+
+ @Test
+ public void testHiveStreamingUnpartitionedWithTxnBatchSizeAsOne() throws
Throwable {
+ WarehouseInstance.Tuple bootstrapDump = primary.dump(primaryDbName, null);
+ replica.loadWithoutExplain(replicatedDbName, bootstrapDump.dumpLocation);
+
+ // Create an ACID table.
+ String tblName = "alerts";
+ primary.run("use " + primaryDbName)
+ .run("create table " + tblName + "( id int , msg string ) " +
+ "clustered by (id) into 5 buckets " +
+ "stored as orc tblproperties(\"transactional\"=\"true\")");
+
+ // Create delimited record writer whose schema exactly matches table schema
+ StrictDelimitedInputWriter writer = StrictDelimitedInputWriter.newBuilder()
+ .withFieldDelimiter(',')
+ .build();
+
+ // Create and open streaming connection (default.src table has to exist
already)
+ // By default, txn batch size is 1.
+ StreamingConnection connection = HiveStreamingConnection.newBuilder()
+ .withDatabase(primaryDbName)
+ .withTable(tblName)
+ .withAgentInfo("example-agent-1")
+ .withRecordWriter(writer)
+ .withHiveConf(primary.getConf())
+ .connect();
+
+ // Begin a transaction, write records and commit 1st transaction
+ connection.beginTransaction();
+ connection.write("1,val1".getBytes());
+ connection.write("2,val2".getBytes());
+ connection.commitTransaction();
+
+ // Replicate the committed data which should be visible.
+ WarehouseInstance.Tuple incrDump = primary.dump(primaryDbName,
bootstrapDump.lastReplicationId);
+ replica.loadWithoutExplain(replicatedDbName, incrDump.dumpLocation)
+ .run("use " + replicatedDbName)
+ .run("select msg from " + tblName + " order by msg")
+ .verifyResults((new String[] {"val1", "val2"}));
+
+ // Begin another transaction, write more records and commit 2nd transaction
Review comment:
Ok. updating the comment.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
Issue Time Tracking
-------------------
Worklog Id: (was: 238726)
Time Spent: 2h 20m (was: 2h 10m)
> Replicate Streaming ingestion with transactional batch size as 1.
> -----------------------------------------------------------------
>
> Key: HIVE-21671
> URL: https://issues.apache.org/jira/browse/HIVE-21671
> Project: Hive
> Issue Type: Sub-task
> Components: repl, Streaming, Transactions
> Affects Versions: 4.0.0
> Reporter: Sankar Hariappan
> Assignee: Sankar Hariappan
> Priority: Major
> Labels: DR, pull-request-available, replication
> Attachments: HIVE-21671.01.patch
>
> Time Spent: 2h 20m
> Remaining Estimate: 0h
>
> Replication streaming ingest HiveStreamingConnection on ACID tables with
> transaction batch size as 1.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
