diff options
author | Wenchen Fan <wenchen@databricks.com> | 2016-10-11 20:27:08 -0700 |
---|---|---|
committer | gatorsmile <gatorsmile@gmail.com> | 2016-10-11 20:27:08 -0700 |
commit | b9a147181d5e38d9abed0c7215f4c5cb695f579c (patch) | |
tree | e2c3bda2b680a67b914b2fc737bbafb0350efb93 /sql/hive | |
parent | 5b77e66dd6a128c5992ab3bde418613f84be7009 (diff) | |
download | spark-b9a147181d5e38d9abed0c7215f4c5cb695f579c.tar.gz spark-b9a147181d5e38d9abed0c7215f4c5cb695f579c.tar.bz2 spark-b9a147181d5e38d9abed0c7215f4c5cb695f579c.zip |
[SPARK-17720][SQL] introduce static SQL conf
## What changes were proposed in this pull request?
SQLConf is session-scoped and mutable. However, we do have the requirement for a static SQL conf, which is global and immutable, e.g. the `schemaStringThreshold` in `HiveExternalCatalog`, the flag to enable/disable hive support, the global temp view database in https://github.com/apache/spark/pull/14897.
Actually we've already implemented static SQL conf implicitly via `SparkConf`, this PR just make it explicit and expose it to users, so that they can see the config value via SQL command or `SparkSession.conf`, and forbid users to set/unset static SQL conf.
## How was this patch tested?
new tests in SQLConfSuite
Author: Wenchen Fan <wenchen@databricks.com>
Closes #15295 from cloud-fan/global-conf.
Diffstat (limited to 'sql/hive')
5 files changed, 27 insertions, 32 deletions
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala index 261cc6feff..e1c0cad907 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala @@ -37,6 +37,7 @@ import org.apache.spark.sql.execution.command.{ColumnStatStruct, DDLUtils} import org.apache.spark.sql.execution.datasources.CaseInsensitiveMap import org.apache.spark.sql.hive.client.HiveClient import org.apache.spark.sql.internal.HiveSerDe +import org.apache.spark.sql.internal.StaticSQLConf.SCHEMA_STRING_LENGTH_THRESHOLD import org.apache.spark.sql.types.{DataType, StructType} @@ -201,11 +202,7 @@ private[spark] class HiveExternalCatalog(conf: SparkConf, hadoopConf: Configurat // Serialized JSON schema string may be too long to be stored into a single metastore table // property. In this case, we split the JSON string and store each part as a separate table // property. - // TODO: the threshold should be set by `spark.sql.sources.schemaStringLengthThreshold`, - // however the current SQLConf is session isolated, which is not applicable to external - // catalog. We should re-enable this conf instead of hard code the value here, after we have - // global SQLConf. - val threshold = 4000 + val threshold = conf.get(SCHEMA_STRING_LENGTH_THRESHOLD) val schemaJsonString = tableDefinition.schema.json // Split the JSON string. val parts = schemaJsonString.grouped(threshold).toSeq diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveUtils.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveUtils.scala index 39d71e164b..a5ef8723c8 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveUtils.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveUtils.scala @@ -23,7 +23,6 @@ import java.nio.charset.StandardCharsets import java.sql.Timestamp import java.util.concurrent.TimeUnit -import scala.collection.JavaConverters._ import scala.collection.mutable.HashMap import scala.language.implicitConversions @@ -36,11 +35,11 @@ import org.apache.hadoop.util.VersionInfo import org.apache.spark.{SparkConf, SparkContext} import org.apache.spark.internal.Logging -import org.apache.spark.internal.config.CATALOG_IMPLEMENTATION import org.apache.spark.sql._ import org.apache.spark.sql.hive.client._ import org.apache.spark.sql.internal.SQLConf import org.apache.spark.sql.internal.SQLConf._ +import org.apache.spark.sql.internal.StaticSQLConf.CATALOG_IMPLEMENTATION import org.apache.spark.sql.types._ import org.apache.spark.util.Utils diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/test/TestHive.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/test/TestHive.scala index 163f210802..6eb571b91f 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/test/TestHive.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/test/TestHive.scala @@ -30,7 +30,6 @@ import org.apache.hadoop.hive.serde2.`lazy`.LazySimpleSerDe import org.apache.spark.{SparkConf, SparkContext} import org.apache.spark.internal.Logging -import org.apache.spark.internal.config.CATALOG_IMPLEMENTATION import org.apache.spark.sql.{SparkSession, SQLContext} import org.apache.spark.sql.catalyst.analysis._ import org.apache.spark.sql.catalyst.analysis.FunctionRegistry.FunctionBuilder @@ -40,6 +39,7 @@ import org.apache.spark.sql.execution.QueryExecution import org.apache.spark.sql.execution.command.CacheTableCommand import org.apache.spark.sql.hive._ import org.apache.spark.sql.internal.{SharedState, SQLConf} +import org.apache.spark.sql.internal.StaticSQLConf.CATALOG_IMPLEMENTATION import org.apache.spark.util.{ShutdownHookManager, Utils} // SPARK-3729: Test key required to check for initialization errors with config. diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/MetastoreDataSourcesSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/MetastoreDataSourcesSuite.scala index 51670649ad..0477122fc6 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/MetastoreDataSourcesSuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/MetastoreDataSourcesSuite.scala @@ -26,12 +26,12 @@ import org.apache.hadoop.fs.Path import org.apache.spark.sql._ import org.apache.spark.sql.catalyst.TableIdentifier import org.apache.spark.sql.catalyst.catalog.{CatalogStorageFormat, CatalogTable, CatalogTableType} -import org.apache.spark.sql.catalyst.parser.ParseException import org.apache.spark.sql.execution.datasources.{HadoopFsRelation, LogicalRelation} import org.apache.spark.sql.hive.HiveExternalCatalog._ import org.apache.spark.sql.hive.client.HiveClient import org.apache.spark.sql.hive.test.TestHiveSingleton import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.internal.StaticSQLConf.SCHEMA_STRING_LENGTH_THRESHOLD import org.apache.spark.sql.test.SQLTestUtils import org.apache.spark.sql.types._ import org.apache.spark.util.Utils @@ -699,28 +699,27 @@ class MetastoreDataSourcesSuite extends QueryTest with SQLTestUtils with TestHiv } test("SPARK-6024 wide schema support") { - withSQLConf(SQLConf.SCHEMA_STRING_LENGTH_THRESHOLD.key -> "4000") { - withTable("wide_schema") { - withTempDir { tempDir => - // We will need 80 splits for this schema if the threshold is 4000. - val schema = StructType((1 to 5000).map(i => StructField(s"c_$i", StringType))) - - val tableDesc = CatalogTable( - identifier = TableIdentifier("wide_schema"), - tableType = CatalogTableType.EXTERNAL, - storage = CatalogStorageFormat.empty.copy( - properties = Map("path" -> tempDir.getCanonicalPath) - ), - schema = schema, - provider = Some("json") - ) - spark.sessionState.catalog.createTable(tableDesc, ignoreIfExists = false) - - sessionState.refreshTable("wide_schema") - - val actualSchema = table("wide_schema").schema - assert(schema === actualSchema) - } + assert(spark.sparkContext.conf.get(SCHEMA_STRING_LENGTH_THRESHOLD) == 4000) + withTable("wide_schema") { + withTempDir { tempDir => + // We will need 80 splits for this schema if the threshold is 4000. + val schema = StructType((1 to 5000).map(i => StructField(s"c_$i", StringType))) + + val tableDesc = CatalogTable( + identifier = TableIdentifier("wide_schema"), + tableType = CatalogTableType.EXTERNAL, + storage = CatalogStorageFormat.empty.copy( + properties = Map("path" -> tempDir.getCanonicalPath) + ), + schema = schema, + provider = Some("json") + ) + spark.sessionState.catalog.createTable(tableDesc, ignoreIfExists = false) + + sessionState.refreshTable("wide_schema") + + val actualSchema = table("wide_schema").schema + assert(schema === actualSchema) } } } diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveDDLSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveDDLSuite.scala index 751e976c7b..8bff6de008 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveDDLSuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveDDLSuite.scala @@ -22,7 +22,6 @@ import java.io.File import org.apache.hadoop.fs.Path import org.scalatest.BeforeAndAfterEach -import org.apache.spark.internal.config._ import org.apache.spark.sql.{AnalysisException, QueryTest, Row, SaveMode} import org.apache.spark.sql.catalyst.analysis.TableAlreadyExistsException import org.apache.spark.sql.catalyst.catalog.{CatalogDatabase, CatalogTable, CatalogTableType} @@ -32,6 +31,7 @@ import org.apache.spark.sql.execution.datasources.CaseInsensitiveMap import org.apache.spark.sql.hive.HiveExternalCatalog import org.apache.spark.sql.hive.test.TestHiveSingleton import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.internal.StaticSQLConf.CATALOG_IMPLEMENTATION import org.apache.spark.sql.test.SQLTestUtils class HiveDDLSuite |