/
ExistingRDD.scala
165 lines (142 loc) · 5.79 KB
/
ExistingRDD.scala
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
/*
* 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.rdd.RDD
import org.apache.spark.sql.{AnalysisException, Row, SQLContext}
import org.apache.spark.sql.catalyst.{CatalystTypeConverters, InternalRow}
import org.apache.spark.sql.catalyst.analysis.MultiInstanceRelation
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.catalyst.plans.logical.{LogicalPlan, Statistics}
import org.apache.spark.sql.catalyst.plans.physical.{HashPartitioning, Partitioning, UnknownPartitioning}
import org.apache.spark.sql.execution.metric.SQLMetrics
import org.apache.spark.sql.sources.{BaseRelation, HadoopFsRelation}
import org.apache.spark.sql.types.DataType
object RDDConversions {
def productToRowRdd[A <: Product](data: RDD[A], outputTypes: Seq[DataType]): RDD[InternalRow] = {
data.mapPartitions { iterator =>
val numColumns = outputTypes.length
val mutableRow = new GenericMutableRow(numColumns)
val converters = outputTypes.map(CatalystTypeConverters.createToCatalystConverter)
iterator.map { r =>
var i = 0
while (i < numColumns) {
mutableRow(i) = converters(i)(r.productElement(i))
i += 1
}
mutableRow
}
}
}
/**
* Convert the objects inside Row into the types Catalyst expected.
*/
def rowToRowRdd(data: RDD[Row], outputTypes: Seq[DataType]): RDD[InternalRow] = {
data.mapPartitions { iterator =>
val numColumns = outputTypes.length
val mutableRow = new GenericMutableRow(numColumns)
val converters = outputTypes.map(CatalystTypeConverters.createToCatalystConverter)
iterator.map { r =>
var i = 0
while (i < numColumns) {
mutableRow(i) = converters(i)(r(i))
i += 1
}
mutableRow
}
}
}
}
/** Logical plan node for scanning data from an RDD. */
private[sql] case class LogicalRDD(
output: Seq[Attribute],
rdd: RDD[InternalRow])(sqlContext: SQLContext)
extends LogicalPlan with MultiInstanceRelation {
override def children: Seq[LogicalPlan] = Nil
override protected final def otherCopyArgs: Seq[AnyRef] = sqlContext :: Nil
override def newInstance(): LogicalRDD.this.type =
LogicalRDD(output.map(_.newInstance()), rdd)(sqlContext).asInstanceOf[this.type]
override def sameResult(plan: LogicalPlan): Boolean = plan match {
case LogicalRDD(_, otherRDD) => rdd.id == otherRDD.id
case _ => false
}
override def producedAttributes: AttributeSet = outputSet
@transient override lazy val statistics: Statistics = Statistics(
// TODO: Instead of returning a default value here, find a way to return a meaningful size
// estimate for RDDs. See PR 1238 for more discussions.
sizeInBytes = BigInt(sqlContext.conf.defaultSizeInBytes)
)
}
/** Physical plan node for scanning data from an RDD. */
private[sql] case class PhysicalRDD(
output: Seq[Attribute],
rdd: RDD[InternalRow],
override val nodeName: String,
override val metadata: Map[String, String] = Map.empty,
isUnsafeRow: Boolean = false,
override val outputPartitioning: Partitioning = UnknownPartitioning(0))
extends LeafNode {
private[sql] override lazy val metrics = Map(
"numOutputRows" -> SQLMetrics.createLongMetric(sparkContext, "number of output rows"))
protected override def doExecute(): RDD[InternalRow] = {
val unsafeRow = if (isUnsafeRow) {
rdd
} else {
rdd.mapPartitionsInternal { iter =>
val proj = UnsafeProjection.create(schema)
iter.map(proj)
}
}
val numOutputRows = longMetric("numOutputRows")
unsafeRow.map { r =>
numOutputRows += 1
r
}
}
override def simpleString: String = {
val metadataEntries = for ((key, value) <- metadata.toSeq.sorted) yield s"$key: $value"
s"Scan $nodeName${output.mkString("[", ",", "]")}${metadataEntries.mkString(" ", ", ", "")}"
}
}
private[sql] object PhysicalRDD {
// Metadata keys
val INPUT_PATHS = "InputPaths"
val PUSHED_FILTERS = "PushedFilters"
def createFromDataSource(
output: Seq[Attribute],
rdd: RDD[InternalRow],
relation: BaseRelation,
metadata: Map[String, String] = Map.empty): PhysicalRDD = {
// All HadoopFsRelations output UnsafeRows
val outputUnsafeRows = relation.isInstanceOf[HadoopFsRelation]
val bucketSpec = relation match {
case r: HadoopFsRelation => r.getBucketSpec
case _ => None
}
def toAttribute(colName: String): Attribute = output.find(_.name == colName).getOrElse {
throw new AnalysisException(s"bucket column $colName not found in existing columns " +
s"(${output.map(_.name).mkString(", ")})")
}
bucketSpec.map { spec =>
val numBuckets = spec.numBuckets
val bucketColumns = spec.bucketColumnNames.map(toAttribute)
val partitioning = HashPartitioning(bucketColumns, numBuckets)
PhysicalRDD(output, rdd, relation.toString, metadata, outputUnsafeRows, partitioning)
}.getOrElse {
PhysicalRDD(output, rdd, relation.toString, metadata, outputUnsafeRows)
}
}
}