[
https://issues.apache.org/jira/browse/HIVE-23716?focusedWorklogId=461634&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-461634
]
ASF GitHub Bot logged work on HIVE-23716:
-----------------------------------------
Author: ASF GitHub Bot
Created on: 21/Jul/20 15:05
Start Date: 21/Jul/20 15:05
Worklog Time Spent: 10m
Work Description: pgaref commented on a change in pull request #1147:
URL: https://github.com/apache/hive/pull/1147#discussion_r458169723
##########
File path:
ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/VectorMapJoinAntiJoinMultiKeyOperator.java
##########
@@ -0,0 +1,400 @@
+/*
+ * 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.vector.mapjoin;
+
+import org.apache.hadoop.hive.ql.CompilationOpContext;
+import org.apache.hadoop.hive.ql.exec.JoinUtil;
+import org.apache.hadoop.hive.ql.exec.vector.VectorSerializeRow;
+import org.apache.hadoop.hive.ql.exec.vector.VectorizationContext;
+import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch;
+import org.apache.hadoop.hive.ql.exec.vector.expressions.VectorExpression;
+import
org.apache.hadoop.hive.ql.exec.vector.mapjoin.hashtable.VectorMapJoinBytesHashSet;
+import org.apache.hadoop.hive.ql.metadata.HiveException;
+import org.apache.hadoop.hive.ql.plan.OperatorDesc;
+import org.apache.hadoop.hive.ql.plan.VectorDesc;
+import org.apache.hadoop.hive.serde2.ByteStream.Output;
+import
org.apache.hadoop.hive.serde2.binarysortable.fast.BinarySortableSerializeWrite;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.util.Arrays;
+
+// Multi-Key hash table import.
+// Multi-Key specific imports.
+
+// TODO : Duplicate codes need to merge with semi join.
+/*
+ * Specialized class for doing a vectorized map join that is an anti join on
Multi-Key
+ * using hash set.
+ */
+public class VectorMapJoinAntiJoinMultiKeyOperator extends
VectorMapJoinAntiJoinGenerateResultOperator {
+
+ private static final long serialVersionUID = 1L;
+
+
//------------------------------------------------------------------------------------------------
+
+ private static final String CLASS_NAME =
VectorMapJoinAntiJoinMultiKeyOperator.class.getName();
+ private static final Logger LOG = LoggerFactory.getLogger(CLASS_NAME);
+
+ protected String getLoggingPrefix() {
+ return super.getLoggingPrefix(CLASS_NAME);
+ }
+
+
//------------------------------------------------------------------------------------------------
+
+ // (none)
+
+ // The above members are initialized by the constructor and must not be
+ // transient.
+ //---------------------------------------------------------------------------
+
+ // The hash map for this specialized class.
+ private transient VectorMapJoinBytesHashSet hashSet;
+
+ //---------------------------------------------------------------------------
+ // Multi-Key specific members.
+ //
+
+ // Object that can take a set of columns in row in a vectorized row batch
and serialized it.
+ // Known to not have any nulls.
+ private transient VectorSerializeRow keyVectorSerializeWrite;
+
+ // The BinarySortable serialization of the current key.
+ private transient Output currentKeyOutput;
+
+ // The BinarySortable serialization of the saved key for a possible series
of equal keys.
+ private transient Output saveKeyOutput;
+
+ //---------------------------------------------------------------------------
+ // Pass-thru constructors.
+ //
+
+ /** Kryo ctor. */
+ protected VectorMapJoinAntiJoinMultiKeyOperator() {
+ super();
+ }
+
+ public VectorMapJoinAntiJoinMultiKeyOperator(CompilationOpContext ctx) {
+ super(ctx);
+ }
+
+ public VectorMapJoinAntiJoinMultiKeyOperator(CompilationOpContext ctx,
OperatorDesc conf,
+ VectorizationContext vContext,
VectorDesc vectorDesc) throws HiveException {
+ super(ctx, conf, vContext, vectorDesc);
+ }
+
+ //---------------------------------------------------------------------------
+ // Process Multi-Key Anti Join on a vectorized row batch.
+ //
+
+ @Override
+ protected void commonSetup() throws HiveException {
+ super.commonSetup();
+
+ /*
+ * Initialize Multi-Key members for this specialized class.
+ */
+
+ keyVectorSerializeWrite = new
VectorSerializeRow(BinarySortableSerializeWrite.with(
+ this.getConf().getKeyTblDesc().getProperties(),
bigTableKeyColumnMap.length));
+ keyVectorSerializeWrite.init(bigTableKeyTypeInfos, bigTableKeyColumnMap);
+
+ currentKeyOutput = new Output();
+ saveKeyOutput = new Output();
+ }
+
+ @Override
+ public void hashTableSetup() throws HiveException {
+ super.hashTableSetup();
+
+ /*
+ * Get our Multi-Key hash set information for this specialized class.
+ */
+
+ hashSet = (VectorMapJoinBytesHashSet) vectorMapJoinHashTable;
+ }
+
+ @Override
+ public void processBatch(VectorizedRowBatch batch) throws HiveException {
+
+ try {
+
+ // Do the per-batch setup for an anti join.
+
+ // (Currently none)
Review comment:
leftover?
----------------------------------------------------------------
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: 461634)
Time Spent: 4h 20m (was: 4h 10m)
> Support Anti Join in Hive
> --------------------------
>
> Key: HIVE-23716
> URL: https://issues.apache.org/jira/browse/HIVE-23716
> Project: Hive
> Issue Type: Bug
> Reporter: mahesh kumar behera
> Assignee: mahesh kumar behera
> Priority: Major
> Labels: pull-request-available
> Attachments: HIVE-23716.01.patch
>
> Time Spent: 4h 20m
> Remaining Estimate: 0h
>
> Currently hive does not support Anti join. The query for anti join is
> converted to left outer join and null filter on right side join key is added
> to get the desired result. This is causing
> # Extra computation — The left outer join projects the redundant columns
> from right side. Along with that, filtering is done to remove the redundant
> rows. This is can be avoided in case of anti join as anti join will project
> only the required columns and rows from the left side table.
> # Extra shuffle — In case of anti join the duplicate records moved to join
> node can be avoided from the child node. This can reduce significant amount
> of data movement if the number of distinct rows( join keys) is significant.
> # Extra Memory Usage - In case of map based anti join , hash set is
> sufficient as just the key is required to check if the records matches the
> join condition. In case of left join, we need the key and the non key columns
> also and thus a hash table will be required.
> For a query like
> {code:java}
> select wr_order_number FROM web_returns LEFT JOIN web_sales ON
> wr_order_number = ws_order_number WHERE ws_order_number IS NULL;{code}
> The number of distinct ws_order_number in web_sales table in a typical 10TB
> TPCDS set up is just 10% of total records. So when we convert this query to
> anti join, instead of 7 billion rows, only 600 million rows are moved to join
> node.
> In the current patch, just one conversion is done. The pattern of
> project->filter->left-join is converted to project->anti-join. This will take
> care of sub queries with “not exists” clause. The queries with “not exists”
> are converted first to filter + left-join and then its converted to anti
> join. The queries with “not in” are not handled in the current patch.
> From execution side, both merge join and map join with vectorized execution
> is supported for anti join.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
