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
|
/*
* 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.state
import scala.reflect.ClassTag
import org.apache.spark.{Partition, TaskContext}
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.types.StructType
import org.apache.spark.util.SerializableConfiguration
/**
* An RDD that allows computations to be executed against [[StateStore]]s. It
* uses the [[StateStoreCoordinator]] to get the locations of loaded state stores
* and use that as the preferred locations.
*/
class StateStoreRDD[T: ClassTag, U: ClassTag](
dataRDD: RDD[T],
storeUpdateFunction: (StateStore, Iterator[T]) => Iterator[U],
checkpointLocation: String,
operatorId: Long,
storeVersion: Long,
keySchema: StructType,
valueSchema: StructType,
storeConf: StateStoreConf,
@transient private val storeCoordinator: Option[StateStoreCoordinatorRef])
extends RDD[U](dataRDD) {
// A Hadoop Configuration can be about 10 KB, which is pretty big, so broadcast it
private val confBroadcast = dataRDD.context.broadcast(
new SerializableConfiguration(dataRDD.context.hadoopConfiguration))
override protected def getPartitions: Array[Partition] = dataRDD.partitions
override def getPreferredLocations(partition: Partition): Seq[String] = {
val storeId = StateStoreId(checkpointLocation, operatorId, partition.index)
storeCoordinator.flatMap(_.getLocation(storeId)).toSeq
}
override def compute(partition: Partition, ctxt: TaskContext): Iterator[U] = {
var store: StateStore = null
val storeId = StateStoreId(checkpointLocation, operatorId, partition.index)
store = StateStore.get(
storeId, keySchema, valueSchema, storeVersion, storeConf, confBroadcast.value.value)
val inputIter = dataRDD.iterator(partition, ctxt)
storeUpdateFunction(store, inputIter)
}
}
|