From 1b50e0e0d6fd9d1b815a3bb37647ea659222e3f1 Mon Sep 17 00:00:00 2001
From: Dongjoon Hyun <dongjoon@apache.org>
Date: Tue, 4 Jul 2017 09:48:40 -0700
Subject: [PATCH] [SPARK-20256][SQL] SessionState should be created more lazily
## What changes were proposed in this pull request?
`SessionState` is designed to be created lazily. However, in reality, it created immediately in `SparkSession.Builder.getOrCreate` ([here](https://github.com/apache/spark/blob/master/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala#L943)).
This PR aims to recover the lazy behavior by keeping the options into `initialSessionOptions`. The benefit is like the following. Users can start `spark-shell` and use RDD operations without any problems.
**BEFORE**
```scala
$ bin/spark-shell
java.lang.IllegalArgumentException: Error while instantiating 'org.apache.spark.sql.hive.HiveSessionStateBuilder'
...
Caused by: org.apache.spark.sql.AnalysisException:
org.apache.hadoop.hive.ql.metadata.HiveException:
MetaException(message:java.security.AccessControlException:
Permission denied: user=spark, access=READ,
inode="/apps/hive/warehouse":hive:hdfs:drwx------
```
As reported in SPARK-20256, this happens when the warehouse directory is not allowed for this user.
**AFTER**
```scala
$ bin/spark-shell
...
Welcome to
____ __
/ __/__ ___ _____/ /__
_\ \/ _ \/ _ `/ __/ '_/
/___/ .__/\_,_/_/ /_/\_\ version 2.3.0-SNAPSHOT
/_/
Using Scala version 2.11.8 (Java HotSpot(TM) 64-Bit Server VM, Java 1.8.0_112)
Type in expressions to have them evaluated.
Type :help for more information.
scala> sc.range(0, 10, 1).count()
res0: Long = 10
```
## How was this patch tested?
Manual.
This closes #18512 .
Author: Dongjoon Hyun <dongjoon@apache.org>
Closes #18501 from dongjoon-hyun/SPARK-20256.
---
.../scala/org/apache/spark/sql/SparkSession.scala | 12 ++++++++++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala b/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala
index 2c38f7d7c8..0ddcd2111a 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala
@@ -117,6 +117,12 @@ class SparkSession private(
existingSharedState.getOrElse(new SharedState(sparkContext))
}
+ /**
+ * Initial options for session. This options are applied once when sessionState is created.
+ */
+ @transient
+ private[sql] val initialSessionOptions = new scala.collection.mutable.HashMap[String, String]
+
/**
* State isolated across sessions, including SQL configurations, temporary tables, registered
* functions, and everything else that accepts a [[org.apache.spark.sql.internal.SQLConf]].
@@ -132,9 +138,11 @@ class SparkSession private(
parentSessionState
.map(_.clone(this))
.getOrElse {
- SparkSession.instantiateSessionState(
+ val state = SparkSession.instantiateSessionState(
SparkSession.sessionStateClassName(sparkContext.conf),
self)
+ initialSessionOptions.foreach { case (k, v) => state.conf.setConfString(k, v) }
+ state
}
}
@@ -940,7 +948,7 @@ object SparkSession {
}
session = new SparkSession(sparkContext, None, None, extensions)
- options.foreach { case (k, v) => session.sessionState.conf.setConfString(k, v) }
+ options.foreach { case (k, v) => session.initialSessionOptions.put(k, v) }
defaultSession.set(session)
// Register a successfully instantiated context to the singleton. This should be at the
--
GitLab