aboutsummaryrefslogtreecommitdiff
path: root/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLEnv.scala
blob: 268ba2f0bca774167c5302a7ff2937af4c8ddff1 (plain) (blame)
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
/*
 * 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.sql.hive.thriftserver

import java.io.PrintStream

import scala.collection.JavaConverters._

import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.internal.Logging
import org.apache.spark.sql.{SparkSession, SQLContext}
import org.apache.spark.sql.hive.{HiveSessionState, HiveUtils}
import org.apache.spark.util.Utils

/** A singleton object for the master program. The slaves should not access this. */
private[hive] object SparkSQLEnv extends Logging {
  logDebug("Initializing SparkSQLEnv")

  var sqlContext: SQLContext = _
  var sparkContext: SparkContext = _

  def init() {
    if (sqlContext == null) {
      val sparkConf = new SparkConf(loadDefaults = true)
      val maybeSerializer = sparkConf.getOption("spark.serializer")
      val maybeKryoReferenceTracking = sparkConf.getOption("spark.kryo.referenceTracking")
      // If user doesn't specify the appName, we want to get [SparkSQL::localHostName] instead of
      // the default appName [SparkSQLCLIDriver] in cli or beeline.
      val maybeAppName = sparkConf
        .getOption("spark.app.name")
        .filterNot(_ == classOf[SparkSQLCLIDriver].getName)

      sparkConf
        .setAppName(maybeAppName.getOrElse(s"SparkSQL::${Utils.localHostName()}"))
        .set(
          "spark.serializer",
          maybeSerializer.getOrElse("org.apache.spark.serializer.KryoSerializer"))
        .set(
          "spark.kryo.referenceTracking",
          maybeKryoReferenceTracking.getOrElse("false"))

      sparkContext = new SparkContext(sparkConf)
      sqlContext = SparkSession.withHiveSupport(sparkContext).wrapped
      val sessionState = sqlContext.sessionState.asInstanceOf[HiveSessionState]
      sessionState.metadataHive.setOut(new PrintStream(System.out, true, "UTF-8"))
      sessionState.metadataHive.setInfo(new PrintStream(System.err, true, "UTF-8"))
      sessionState.metadataHive.setError(new PrintStream(System.err, true, "UTF-8"))

      sqlContext.setConf("spark.sql.hive.version", HiveUtils.hiveExecutionVersion)

      if (log.isDebugEnabled) {
        sessionState.hiveconf.getAllProperties.asScala.toSeq.sorted
          .foreach { case (k, v) => logDebug(s"HiveConf var: $k=$v") }
      }
    }
  }

  /** Cleans up and shuts down the Spark SQL environments. */
  def stop() {
    logDebug("Shutting down Spark SQL Environment")
    // Stop the SparkContext
    if (SparkSQLEnv.sparkContext != null) {
      sparkContext.stop()
      sparkContext = null
      sqlContext = null
    }
  }
}