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
|
/*
* 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 scala.collection.mutable.HashSet
import org.apache.spark.{Accumulator, AccumulatorParam}
import org.apache.spark.internal.Logging
import org.apache.spark.rdd.RDD
import org.apache.spark.sql._
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.expressions.Attribute
import org.apache.spark.sql.catalyst.expressions.codegen.{CodegenContext, ExprCode}
import org.apache.spark.sql.catalyst.trees.TreeNodeRef
import org.apache.spark.sql.internal.SQLConf
/**
* Contains methods for debugging query execution.
*
* Usage:
* {{{
* import org.apache.spark.sql.execution.debug._
* sql("SELECT key FROM src").debug()
* dataFrame.typeCheck()
* }}}
*/
package object debug {
/**
* Augments [[SQLContext]] with debug methods.
*/
implicit class DebugSQLContext(sqlContext: SQLContext) {
def debug(): Unit = {
sqlContext.setConf(SQLConf.DATAFRAME_EAGER_ANALYSIS, false)
}
}
/**
* Augments [[DataFrame]]s with debug methods.
*/
implicit class DebugQuery(query: DataFrame) extends Logging {
def debug(): Unit = {
val plan = query.queryExecution.executedPlan
val visited = new collection.mutable.HashSet[TreeNodeRef]()
val debugPlan = plan transform {
case s: SparkPlan if !visited.contains(new TreeNodeRef(s)) =>
visited += new TreeNodeRef(s)
DebugNode(s)
}
logDebug(s"Results returned: ${debugPlan.execute().count()}")
debugPlan.foreach {
case d: DebugNode => d.dumpStats()
case _ =>
}
}
}
private[sql] case class DebugNode(child: SparkPlan) extends UnaryNode with CodegenSupport {
def output: Seq[Attribute] = child.output
implicit object SetAccumulatorParam extends AccumulatorParam[HashSet[String]] {
def zero(initialValue: HashSet[String]): HashSet[String] = {
initialValue.clear()
initialValue
}
def addInPlace(v1: HashSet[String], v2: HashSet[String]): HashSet[String] = {
v1 ++= v2
v1
}
}
/**
* A collection of metrics for each column of output.
* @param elementTypes the actual runtime types for the output. Useful when there are bugs
* causing the wrong data to be projected.
*/
case class ColumnMetrics(
elementTypes: Accumulator[HashSet[String]] = sparkContext.accumulator(HashSet.empty))
val tupleCount: Accumulator[Int] = sparkContext.accumulator[Int](0)
val numColumns: Int = child.output.size
val columnStats: Array[ColumnMetrics] = Array.fill(child.output.size)(new ColumnMetrics())
def dumpStats(): Unit = {
logDebug(s"== ${child.simpleString} ==")
logDebug(s"Tuples output: ${tupleCount.value}")
child.output.zip(columnStats).foreach { case (attr, metric) =>
val actualDataTypes = metric.elementTypes.value.mkString("{", ",", "}")
logDebug(s" ${attr.name} ${attr.dataType}: $actualDataTypes")
}
}
protected override def doExecute(): RDD[InternalRow] = {
child.execute().mapPartitions { iter =>
new Iterator[InternalRow] {
def hasNext: Boolean = iter.hasNext
def next(): InternalRow = {
val currentRow = iter.next()
tupleCount += 1
var i = 0
while (i < numColumns) {
val value = currentRow.get(i, output(i).dataType)
if (value != null) {
columnStats(i).elementTypes += HashSet(value.getClass.getName)
}
i += 1
}
currentRow
}
}
}
}
override def upstreams(): Seq[RDD[InternalRow]] = {
child.asInstanceOf[CodegenSupport].upstreams()
}
override def doProduce(ctx: CodegenContext): String = {
child.asInstanceOf[CodegenSupport].produce(ctx, this)
}
override def doConsume(ctx: CodegenContext, input: Seq[ExprCode], row: ExprCode): String = {
consume(ctx, input)
}
}
}
|
