-
Notifications
You must be signed in to change notification settings - Fork 29k
[SPARK-17912][SQL] Refactor code generation to get data for ColumnVector/ColumnarBatch #15467
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Closed
Closed
Changes from all commits
Commits
Show all changes
2 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
133 changes: 133 additions & 0 deletions
133
sql/core/src/main/scala/org/apache/spark/sql/execution/ColumnarBatchScan.scala
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,133 @@ | ||
| /* | ||
| * 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.spark.sql.execution | ||
|
|
||
| import org.apache.spark.sql.catalyst.expressions.UnsafeRow | ||
| import org.apache.spark.sql.catalyst.expressions.codegen.{CodegenContext, ExprCode} | ||
| import org.apache.spark.sql.execution.columnar.InMemoryTableScanExec | ||
| import org.apache.spark.sql.execution.metric.SQLMetrics | ||
| import org.apache.spark.sql.execution.vectorized.{ColumnarBatch, ColumnVector} | ||
| import org.apache.spark.sql.types.DataType | ||
|
|
||
|
|
||
| /** | ||
| * Helper trait for abstracting scan functionality using | ||
| * [[org.apache.spark.sql.execution.vectorized.ColumnarBatch]]es. | ||
| */ | ||
| private[sql] trait ColumnarBatchScan extends CodegenSupport { | ||
|
|
||
| val inMemoryTableScan: InMemoryTableScanExec = null | ||
|
|
||
| override lazy val metrics = Map( | ||
| "numOutputRows" -> SQLMetrics.createMetric(sparkContext, "number of output rows"), | ||
| "scanTime" -> SQLMetrics.createTimingMetric(sparkContext, "scan time")) | ||
|
|
||
| /** | ||
| * Generate [[ColumnVector]] expressions for our parent to consume as rows. | ||
| * This is called once per [[ColumnarBatch]]. | ||
| */ | ||
| private def genCodeColumnVector( | ||
| ctx: CodegenContext, | ||
| columnVar: String, | ||
| ordinal: String, | ||
| dataType: DataType, | ||
| nullable: Boolean): ExprCode = { | ||
| val javaType = ctx.javaType(dataType) | ||
| val value = ctx.getValue(columnVar, dataType, ordinal) | ||
| val isNullVar = if (nullable) { ctx.freshName("isNull") } else { "false" } | ||
| val valueVar = ctx.freshName("value") | ||
| val str = s"columnVector[$columnVar, $ordinal, ${dataType.simpleString}]" | ||
| val code = s"${ctx.registerComment(str)}\n" + (if (nullable) { | ||
| s""" | ||
| boolean $isNullVar = $columnVar.isNullAt($ordinal); | ||
| $javaType $valueVar = $isNullVar ? ${ctx.defaultValue(dataType)} : ($value); | ||
| """ | ||
| } else { | ||
| s"$javaType $valueVar = $value;" | ||
| }).trim | ||
| ExprCode(code, isNullVar, valueVar) | ||
| } | ||
|
|
||
| /** | ||
| * Produce code to process the input iterator as [[ColumnarBatch]]es. | ||
| * This produces an [[UnsafeRow]] for each row in each batch. | ||
| */ | ||
| // TODO: return ColumnarBatch.Rows instead | ||
| override protected def doProduce(ctx: CodegenContext): String = { | ||
| val input = ctx.freshName("input") | ||
| // PhysicalRDD always just has one input | ||
| ctx.addMutableState("scala.collection.Iterator", input, s"$input = inputs[0];") | ||
|
|
||
| // metrics | ||
| val numOutputRows = metricTerm(ctx, "numOutputRows") | ||
| val scanTimeMetric = metricTerm(ctx, "scanTime") | ||
| val scanTimeTotalNs = ctx.freshName("scanTime") | ||
| ctx.addMutableState("long", scanTimeTotalNs, s"$scanTimeTotalNs = 0;") | ||
|
|
||
| val columnarBatchClz = "org.apache.spark.sql.execution.vectorized.ColumnarBatch" | ||
| val batch = ctx.freshName("batch") | ||
| ctx.addMutableState(columnarBatchClz, batch, s"$batch = null;") | ||
|
|
||
| val columnVectorClz = "org.apache.spark.sql.execution.vectorized.ColumnVector" | ||
| val idx = ctx.freshName("batchIdx") | ||
| ctx.addMutableState("int", idx, s"$idx = 0;") | ||
| val colVars = output.indices.map(i => ctx.freshName("colInstance" + i)) | ||
| val columnAssigns = colVars.zipWithIndex.map { case (name, i) => | ||
| ctx.addMutableState(columnVectorClz, name, s"$name = null;") | ||
| s"$name = $batch.column($i);" | ||
| } | ||
|
|
||
| val nextBatch = ctx.freshName("nextBatch") | ||
| ctx.addNewFunction(nextBatch, | ||
| s""" | ||
| |private void $nextBatch() throws java.io.IOException { | ||
| | long getBatchStart = System.nanoTime(); | ||
| | if ($input.hasNext()) { | ||
| | $batch = ($columnarBatchClz)$input.next(); | ||
| | $numOutputRows.add($batch.numRows()); | ||
| | $idx = 0; | ||
| | ${columnAssigns.mkString("", "\n", "\n")} | ||
| | } | ||
| | $scanTimeTotalNs += System.nanoTime() - getBatchStart; | ||
| |}""".stripMargin) | ||
|
|
||
| ctx.currentVars = null | ||
| val rowidx = ctx.freshName("rowIdx") | ||
| val columnsBatchInput = (output zip colVars).map { case (attr, colVar) => | ||
| genCodeColumnVector(ctx, colVar, rowidx, attr.dataType, attr.nullable) | ||
| } | ||
| s""" | ||
| |if ($batch == null) { | ||
| | $nextBatch(); | ||
| |} | ||
| |while ($batch != null) { | ||
| | int numRows = $batch.numRows(); | ||
| | while ($idx < numRows) { | ||
| | int $rowidx = $idx++; | ||
| | ${consume(ctx, columnsBatchInput).trim} | ||
| | if (shouldStop()) return; | ||
| | } | ||
| | $batch = null; | ||
| | $nextBatch(); | ||
| |} | ||
| |$scanTimeMetric.add($scanTimeTotalNs / (1000 * 1000)); | ||
| |$scanTimeTotalNs = 0; | ||
| """.stripMargin | ||
| } | ||
|
|
||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
nit: this is unused right?