cloud-fan commented on a change in pull request #27933: [SPARK-31170][SQL]
Spark SQL Cli should respect hive-site.xml and spark.sql.warehouse.dir
URL: https://github.com/apache/spark/pull/27933#discussion_r393513526
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/internal/SharedState.scala
##########
@@ -55,44 +54,10 @@ private[sql] class SharedState(
SharedState.setFsUrlStreamHandlerFactory(sparkContext.conf)
- // Load hive-site.xml into hadoopConf and determine the warehouse path we
want to use, based on
- // the config from both hive and Spark SQL. Finally set the warehouse config
value to sparkConf.
- val warehousePath: String = {
- val configFile =
Utils.getContextOrSparkClassLoader.getResource("hive-site.xml")
- if (configFile != null) {
- logInfo(s"loading hive config file: $configFile")
- sparkContext.hadoopConfiguration.addResource(configFile)
- }
-
- // hive.metastore.warehouse.dir only stay in hadoopConf
- sparkContext.conf.remove("hive.metastore.warehouse.dir")
- // Set the Hive metastore warehouse path to the one we use
- val hiveWarehouseDir =
sparkContext.hadoopConfiguration.get("hive.metastore.warehouse.dir")
- if (hiveWarehouseDir != null &&
!sparkContext.conf.contains(WAREHOUSE_PATH.key)) {
- // If hive.metastore.warehouse.dir is set and spark.sql.warehouse.dir is
not set,
- // we will respect the value of hive.metastore.warehouse.dir.
- sparkContext.conf.set(WAREHOUSE_PATH.key, hiveWarehouseDir)
- logInfo(s"${WAREHOUSE_PATH.key} is not set, but
hive.metastore.warehouse.dir " +
- s"is set. Setting ${WAREHOUSE_PATH.key} to the value of " +
- s"hive.metastore.warehouse.dir ('$hiveWarehouseDir').")
- hiveWarehouseDir
- } else {
- // If spark.sql.warehouse.dir is set, we will override
hive.metastore.warehouse.dir using
- // the value of spark.sql.warehouse.dir.
- // When neither spark.sql.warehouse.dir nor hive.metastore.warehouse.dir
is set,
- // we will set hive.metastore.warehouse.dir to the default value of
spark.sql.warehouse.dir.
- val sparkWarehouseDir = sparkContext.conf.get(WAREHOUSE_PATH)
- logInfo(s"Setting hive.metastore.warehouse.dir ('$hiveWarehouseDir') to
the value of " +
- s"${WAREHOUSE_PATH.key} ('$sparkWarehouseDir').")
- sparkContext.hadoopConfiguration.set("hive.metastore.warehouse.dir",
sparkWarehouseDir)
- sparkWarehouseDir
- }
- }
- logInfo(s"Warehouse path is '$warehousePath'.")
-
- // These 2 variables should be initiated after `warehousePath`, because in
the first place we need
Review comment:
shall we keep this comment? Or we can put `SharedState.loadHiveConfFile`
inside `private val (conf, hadoopConf) = {`
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
