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
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
|
/*
* 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.metrics
import java.util.Properties
import java.util.concurrent.TimeUnit
import scala.collection.mutable
import com.codahale.metrics.{Metric, MetricFilter, MetricRegistry}
import org.eclipse.jetty.servlet.ServletContextHandler
import org.apache.spark.{SecurityManager, SparkConf}
import org.apache.spark.internal.Logging
import org.apache.spark.metrics.sink.{MetricsServlet, Sink}
import org.apache.spark.metrics.source.Source
import org.apache.spark.util.Utils
/**
* Spark Metrics System, created by specific "instance", combined by source,
* sink, periodically poll source metrics data to sink destinations.
*
* "instance" specify "who" (the role) use metrics system. In spark there are several roles
* like master, worker, executor, client driver, these roles will create metrics system
* for monitoring. So instance represents these roles. Currently in Spark, several instances
* have already implemented: master, worker, executor, driver, applications.
*
* "source" specify "where" (source) to collect metrics data. In metrics system, there exists
* two kinds of source:
* 1. Spark internal source, like MasterSource, WorkerSource, etc, which will collect
* Spark component's internal state, these sources are related to instance and will be
* added after specific metrics system is created.
* 2. Common source, like JvmSource, which will collect low level state, is configured by
* configuration and loaded through reflection.
*
* "sink" specify "where" (destination) to output metrics data to. Several sinks can be
* coexisted and flush metrics to all these sinks.
*
* Metrics configuration format is like below:
* [instance].[sink|source].[name].[options] = xxxx
*
* [instance] can be "master", "worker", "executor", "driver", "applications" which means only
* the specified instance has this property.
* wild card "*" can be used to replace instance name, which means all the instances will have
* this property.
*
* [sink|source] means this property belongs to source or sink. This field can only be
* source or sink.
*
* [name] specify the name of sink or source, it is custom defined.
*
* [options] is the specific property of this source or sink.
*/
private[spark] class MetricsSystem private (
val instance: String,
conf: SparkConf,
securityMgr: SecurityManager)
extends Logging {
private[this] val metricsConfig = new MetricsConfig(conf)
private val sinks = new mutable.ArrayBuffer[Sink]
private val sources = new mutable.ArrayBuffer[Source]
private val registry = new MetricRegistry()
private var running: Boolean = false
// Treat MetricsServlet as a special sink as it should be exposed to add handlers to web ui
private var metricsServlet: Option[MetricsServlet] = None
/**
* Get any UI handlers used by this metrics system; can only be called after start().
*/
def getServletHandlers: Array[ServletContextHandler] = {
require(running, "Can only call getServletHandlers on a running MetricsSystem")
metricsServlet.map(_.getHandlers(conf)).getOrElse(Array())
}
metricsConfig.initialize()
def start() {
require(!running, "Attempting to start a MetricsSystem that is already running")
running = true
registerSources()
registerSinks()
sinks.foreach(_.start)
}
def stop() {
if (running) {
sinks.foreach(_.stop)
} else {
logWarning("Stopping a MetricsSystem that is not running")
}
running = false
}
def report() {
sinks.foreach(_.report())
}
/**
* Build a name that uniquely identifies each metric source.
* The name is structured as follows: <app ID>.<executor ID (or "driver")>.<source name>.
* If either ID is not available, this defaults to just using <source name>.
*
* @param source Metric source to be named by this method.
* @return An unique metric name for each combination of
* application, executor/driver and metric source.
*/
private[spark] def buildRegistryName(source: Source): String = {
val appId = conf.getOption("spark.app.id")
val executorId = conf.getOption("spark.executor.id")
val defaultName = MetricRegistry.name(source.sourceName)
if (instance == "driver" || instance == "executor") {
if (appId.isDefined && executorId.isDefined) {
MetricRegistry.name(appId.get, executorId.get, source.sourceName)
} else {
// Only Driver and Executor set spark.app.id and spark.executor.id.
// Other instance types, e.g. Master and Worker, are not related to a specific application.
val warningMsg = s"Using default name $defaultName for source because %s is not set."
if (appId.isEmpty) { logWarning(warningMsg.format("spark.app.id")) }
if (executorId.isEmpty) { logWarning(warningMsg.format("spark.executor.id")) }
defaultName
}
} else { defaultName }
}
def getSourcesByName(sourceName: String): Seq[Source] =
sources.filter(_.sourceName == sourceName)
def registerSource(source: Source) {
sources += source
try {
val regName = buildRegistryName(source)
registry.register(regName, source.metricRegistry)
} catch {
case e: IllegalArgumentException => logInfo("Metrics already registered", e)
}
}
def removeSource(source: Source) {
sources -= source
val regName = buildRegistryName(source)
registry.removeMatching(new MetricFilter {
def matches(name: String, metric: Metric): Boolean = name.startsWith(regName)
})
}
private def registerSources() {
val instConfig = metricsConfig.getInstance(instance)
val sourceConfigs = metricsConfig.subProperties(instConfig, MetricsSystem.SOURCE_REGEX)
// Register all the sources related to instance
sourceConfigs.foreach { kv =>
val classPath = kv._2.getProperty("class")
try {
val source = Utils.classForName(classPath).newInstance()
registerSource(source.asInstanceOf[Source])
} catch {
case e: Exception => logError("Source class " + classPath + " cannot be instantiated", e)
}
}
}
private def registerSinks() {
val instConfig = metricsConfig.getInstance(instance)
val sinkConfigs = metricsConfig.subProperties(instConfig, MetricsSystem.SINK_REGEX)
sinkConfigs.foreach { kv =>
val classPath = kv._2.getProperty("class")
if (null != classPath) {
try {
val sink = Utils.classForName(classPath)
.getConstructor(classOf[Properties], classOf[MetricRegistry], classOf[SecurityManager])
.newInstance(kv._2, registry, securityMgr)
if (kv._1 == "servlet") {
metricsServlet = Some(sink.asInstanceOf[MetricsServlet])
} else {
sinks += sink.asInstanceOf[Sink]
}
} catch {
case e: Exception =>
logError("Sink class " + classPath + " cannot be instantiated")
throw e
}
}
}
}
}
private[spark] object MetricsSystem {
val SINK_REGEX = "^sink\\.(.+)\\.(.+)".r
val SOURCE_REGEX = "^source\\.(.+)\\.(.+)".r
private[this] val MINIMAL_POLL_UNIT = TimeUnit.SECONDS
private[this] val MINIMAL_POLL_PERIOD = 1
def checkMinimalPollingPeriod(pollUnit: TimeUnit, pollPeriod: Int) {
val period = MINIMAL_POLL_UNIT.convert(pollPeriod, pollUnit)
if (period < MINIMAL_POLL_PERIOD) {
throw new IllegalArgumentException("Polling period " + pollPeriod + " " + pollUnit +
" below than minimal polling period ")
}
}
def createMetricsSystem(
instance: String, conf: SparkConf, securityMgr: SecurityManager): MetricsSystem = {
new MetricsSystem(instance, conf, securityMgr)
}
}
|
