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
|
/*
* 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.streaming
import org.apache.spark.sql.SQLContext
import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
import org.apache.spark.sql.catalyst.rules.Rule
import org.apache.spark.sql.execution.{QueryExecution, SparkPlan, SparkPlanner, UnaryNode}
/**
* A variant of [[QueryExecution]] that allows the execution of the given [[LogicalPlan]]
* plan incrementally. Possibly preserving state in between each execution.
*/
class IncrementalExecution(
ctx: SQLContext,
logicalPlan: LogicalPlan,
checkpointLocation: String,
currentBatchId: Long) extends QueryExecution(ctx, logicalPlan) {
// TODO: make this always part of planning.
val stateStrategy = sqlContext.sessionState.planner.StatefulAggregationStrategy :: Nil
// Modified planner with stateful operations.
override def planner: SparkPlanner =
new SparkPlanner(
sqlContext.sparkContext,
sqlContext.conf,
stateStrategy)
/**
* Records the current id for a given stateful operator in the query plan as the `state`
* preperation walks the query plan.
*/
private var operatorId = 0
/** Locates save/restore pairs surrounding aggregation. */
val state = new Rule[SparkPlan] {
override def apply(plan: SparkPlan): SparkPlan = plan transform {
case StateStoreSave(keys, None,
UnaryNode(agg,
StateStoreRestore(keys2, None, child))) =>
val stateId = OperatorStateId(checkpointLocation, operatorId, currentBatchId - 1)
operatorId += 1
StateStoreSave(
keys,
Some(stateId),
agg.withNewChildren(
StateStoreRestore(
keys,
Some(stateId),
child) :: Nil))
}
}
override def preparations: Seq[Rule[SparkPlan]] = state +: super.preparations
}
|