Github user yhuai commented on a diff in the pull request:
https://github.com/apache/spark/pull/8909#discussion_r41428482
--- Diff:
sql/hive/src/main/scala/org/apache/spark/sql/hive/client/IsolatedClientLoader.scala
---
@@ -148,53 +150,88 @@ private[hive] class IsolatedClientLoader(
name.replaceAll("\\.", "/") + ".class"
/** The classloader that is used to load an isolated version of Hive. */
- protected val classLoader: ClassLoader = new URLClassLoader(allJars,
rootClassLoader) {
- override def loadClass(name: String, resolve: Boolean): Class[_] = {
- val loaded = findLoadedClass(name)
- if (loaded == null) doLoadClass(name, resolve) else loaded
- }
+ private[hive] var classLoader: ClassLoader = if (isolationOn) {
+ new URLClassLoader(allJars, rootClassLoader) {
+ val cache = new java.util.concurrent.ConcurrentHashMap[String,
Class[_]]
+
+ override def loadClass(name: String, resolve: Boolean): Class[_] = {
+ var clazz = findLoadedClass(name)
+ if (clazz == null) {
+ clazz = cache.get(name)
+ if (clazz == null) {
+ // always assume resolve is false at this point - we'll
resolve later
+ clazz = doLoadClass(name, resolve = false)
+ val clazz2 = cache.putIfAbsent(name, clazz)
+ // check if someone else beat us to updating the cache entry
+ if (clazz2 != null) {
+ // if so then we should use the cached entry to be consistent
+ clazz = clazz2
+ }
+ }
+ if (resolve) {
+ resolveClass(clazz)
+ }
+ }
+ clazz
+ }
- def doLoadClass(name: String, resolve: Boolean): Class[_] = {
- val classFileName = name.replaceAll("\\.", "/") + ".class"
- if (isBarrierClass(name) && isolationOn) {
- // For barrier classes, we construct a new copy of the class.
- val bytes =
IOUtils.toByteArray(baseClassLoader.getResourceAsStream(classFileName))
- logDebug(s"custom defining: $name -
${util.Arrays.hashCode(bytes)}")
- defineClass(name, bytes, 0, bytes.length)
- } else if (!isSharedClass(name)) {
- logDebug(s"hive class: $name - ${getResource(classToPath(name))}")
- super.loadClass(name, resolve)
- } else {
- // For shared classes, we delegate to baseClassLoader.
- logDebug(s"shared class: $name")
- baseClassLoader.loadClass(name)
+ def doLoadClass(name: String, resolve: Boolean): Class[_] = {
+ val classFileName = name.replaceAll("\\.", "/") + ".class"
+ if (isBarrierClass(name)) {
+ // For barrier classes, we construct a new copy of the class.
+ val bytes =
IOUtils.toByteArray(baseClassLoader.getResourceAsStream(classFileName))
+ logDebug(s"custom defining: $name -
${util.Arrays.hashCode(bytes)}")
+ defineClass(name, bytes, 0, bytes.length)
+ } else if (!isSharedClass(name)) {
+ logDebug(s"hive class: $name -
${getResource(classToPath(name))}")
+ super.loadClass(name, resolve)
+ } else {
+ // For shared classes, we delegate to baseClassLoader.
+ logDebug(s"shared class: $name")
+ baseClassLoader.loadClass(name)
+ }
}
}
+ } else {
+ baseClassLoader
}
- // Pre-reflective instantiation setup.
- logDebug("Initializing the logger to avoid disaster...")
- Thread.currentThread.setContextClassLoader(classLoader)
+ private[hive] def addJar(path: String): Unit = synchronized {
+ val jarURL = new java.io.File(path).toURI.toURL
+ classLoader = new java.net.URLClassLoader(Array(jarURL), classLoader)
--- End diff --
While you are changing this part, can you add a TODO at here saying
something like we should avoid of stacking classloaders (it will be good to use
a single URLClassLoader and add jars to that).
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
