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
|
/*
* 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.streaming.scheduler.rate
import org.apache.spark.SparkConf
import org.apache.spark.streaming.Duration
/**
* A component that estimates the rate at which an `InputDStream` should ingest
* records, based on updates at every batch completion.
*
* @see [[org.apache.spark.streaming.scheduler.RateController]]
*/
private[streaming] trait RateEstimator extends Serializable {
/**
* Computes the number of records the stream attached to this `RateEstimator`
* should ingest per second, given an update on the size and completion
* times of the latest batch.
*
* @param time The timestamp of the current batch interval that just finished
* @param elements The number of records that were processed in this batch
* @param processingDelay The time in ms that took for the job to complete
* @param schedulingDelay The time in ms that the job spent in the scheduling queue
*/
def compute(
time: Long,
elements: Long,
processingDelay: Long,
schedulingDelay: Long): Option[Double]
}
object RateEstimator {
/**
* Return a new `RateEstimator` based on the value of
* `spark.streaming.backpressure.rateEstimator`.
*
* The only known and acceptable estimator right now is `pid`.
*
* @return An instance of RateEstimator
* @throws IllegalArgumentException if the configured RateEstimator is not `pid`.
*/
def create(conf: SparkConf, batchInterval: Duration): RateEstimator =
conf.get("spark.streaming.backpressure.rateEstimator", "pid") match {
case "pid" =>
val proportional = conf.getDouble("spark.streaming.backpressure.pid.proportional", 1.0)
val integral = conf.getDouble("spark.streaming.backpressure.pid.integral", 0.2)
val derived = conf.getDouble("spark.streaming.backpressure.pid.derived", 0.0)
val minRate = conf.getDouble("spark.streaming.backpressure.pid.minRate", 100)
new PIDRateEstimator(batchInterval.milliseconds, proportional, integral, derived, minRate)
case estimator =>
throw new IllegalArgumentException(s"Unknown rate estimator: $estimator")
}
}
|