注:本文是为了配合《Spark内核设计的艺术 架构设计与实现》一书的内容而编写,目的是为了节省成本、方便读者查阅。书中附录A的内容都在本文呈现。
Utils是Spark最常用的工具类之一,Spark Core大量使用了此类提供的基础功能。即使不关心其实现也不会对理解本书对Spark源码的分析有太多影响。下面将逐个介绍Utils提供的方法。
getSystemProperties
功能描述:获取系统属性的键值对。
def getSystemProperties: Map[String, String] = {
System.getProperties.stringPropertyNames().asScala
.map(key => (key, System.getProperty(key))).toMap
}
localHostName
功能描述:获取本地机器名。
def localHostName(): String = {
customHostname.getOrElse(localIpAddress.getHostAddress)
}
getDefaultPropertiesFile
功能描述:获取默认的Spark属性文件。
def getDefaultPropertiesFile(env: Map[String, String] = sys.env): String = {
env.get("SPARK_CONF_DIR")
.orElse(env.get("SPARK_HOME").map { t => s"$t${File.separator}conf" })
.map { t => new File(s"$t${File.separator}spark-defaults.conf")}
.filter(_.isFile)
.map(_.getAbsolutePath)
.orNull
}
getPropertiesFromFile
功能描述:从文件中获取属性。
def getPropertiesFromFile(filename: String): Map[String, String] = {
val file = new File(filename)
require(file.exists(), s"Properties file $file does not exist")
require(file.isFile(), s"Properties file $file is not a normal file")
val inReader = new InputStreamReader(new FileInputStream(file), StandardCharsets.UTF_8)
try {
val properties = new Properties()
properties.load(inReader)
properties.stringPropertyNames().asScala.map(
k => (k, properties.getProperty(k).trim)).toMap
} catch {
case e: IOException =>
throw new SparkException(s"Failed when loading Spark properties from $filename", e)
} finally {
inReader.close()
}
}
loadDefaultSparkProperties
功能描述:加载指定文件中的Spark属性,如果没有指定文件,则加载默认Spark属性文件的属性。
def loadDefaultSparkProperties(conf: SparkConf, filePath: String = null): String = {
val path = Option(filePath).getOrElse(getDefaultPropertiesFile())
Option(path).foreach { confFile =>
getPropertiesFromFile(confFile).filter { case (k, v) =>
k.startsWith("spark.")
}.foreach { case (k, v) =>
conf.setIfMissing(k, v)
sys.props.getOrElseUpdate(k, v)
}
}
path
}
getCallSite
功能描述:获取当前SparkContext的当前调用堆栈,将栈里最靠近栈底的属于Spark或者Scala核心的类压入callStack的栈顶,并将此类的方法存入lastSparkMethod;将栈里最靠近栈顶的用户类放入callStack,将此类的行号存入firstUserLine,类名存入firstUserFile,最终返回的样例类CallSite存储了最短栈和长度默认为20的最长栈的样例类。在JavaWordCount例子中,获得的数据如下:
最短栈:getOrCreate atJavaWordCount.java:48;
最长栈:org.apache.spark.sql.SparkSession$Builder.getOrCreate(SparkSession.scala:860)
org.apache.spark.examples.JavaWordCount.main(JavaWordCount.java:48)
def getCallSite(skipClass: String => Boolean = sparkInternalExclusionFunction): CallSite = {
var lastSparkMethod = "<unknown>"
var firstUserFile = "<unknown>"
var firstUserLine = 0
var insideSpark = true
var callStack = new ArrayBuffer[String]() :+ "<unknown>"
Thread.currentThread.getStackTrace().foreach { ste: StackTraceElement =>
if (ste != null && ste.getMethodName != null
&& !ste.getMethodName.contains("getStackTrace")) {
if (insideSpark) {
if (skipClass(ste.getClassName)) {
lastSparkMethod = if (ste.getMethodName == "<init>") {
// Spark method is a constructor; get its class name
ste.getClassName.substring(ste.getClassName.lastIndexOf('.') + 1)
} else {
ste.getMethodName
}
callStack(0) = ste.toString // Put last Spark method on top of the stack trace.
} else {
if (ste.getFileName != null) {
firstUserFile = ste.getFileName
if (ste.getLineNumber >= 0) {
firstUserLine = ste.getLineNumber
}
}
callStack += ste.toString
insideSpark = false
}
} else {
callStack += ste.toString
}
}
}
val callStackDepth = System.getProperty("spark.callstack.depth", "20").toInt
val shortForm =
if (firstUserFile == "HiveSessionImpl.java") {
// To be more user friendly, show a nicer string for queries submitted from the JDBC
// server.
"Spark JDBC Server Query"
} else {
s"$lastSparkMethod at $firstUserFile:$firstUserLine"
}
val longForm = callStack.take(callStackDepth).mkString("\n")
CallSite(shortForm, longForm)
}
tryOrStopSparkContext
功能描述:用于在执行目标方法抛出异常后新启一个用于异步停止SparkContext的线程。 def tryOrStopSparkContext(sc: SparkContext)(block: => Unit) {
try {
block
} catch {
case e: ControlThrowable => throw e
case t: Throwable =>
val currentThreadName = Thread.currentThread().getName
if (sc != null) {
logError(s"uncaught error in thread $currentThreadName, stopping SparkContext", t)
sc.stopInNewThread()
}
if (!NonFatal(t)) {
logError(s"throw uncaught fatal error in thread $currentThreadName", t)
throw t
}
}
}
getCurrentUserName
功能描述:用于获取当前用户的用户名。此用户名默认为当前系统的登录用户,也可以通过系统环境变量SPARK_USER进行设置。 def getCurrentUserName(): String = {
Option(System.getenv("SPARK_USER"))
.getOrElse(UserGroupInformation.getCurrentUser().getShortUserName())
}