Skip to content

[SPARK-10198][SQL] Turn off partition verification by default #8404

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 3 commits into from
Closed

[SPARK-10198][SQL] Turn off partition verification by default #8404

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7cc6741
[SPARK-10198][SQL] Turn off partition verification by default
marmbrus Aug 24, 2015
5826f16
style
marmbrus Aug 25, 2015
6a4d6db
Update QueryPartitionSuite.scala
marmbrus Aug 25, 2015
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion sql/core/src/main/scala/org/apache/spark/sql/SQLConf.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -312,7 +312,7 @@ private[spark] object SQLConf {
doc = "When true, enable filter pushdown for ORC files.")

val HIVE_VERIFY_PARTITION_PATH = booleanConf("spark.sql.hive.verifyPartitionPath",
defaultValue = Some(true),
defaultValue = Some(false),
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why this place use false as default value

doc = "<TODO>")

val HIVE_METASTORE_PARTITION_PRUNING = booleanConf("spark.sql.hive.metastorePartitionPruning",
Expand Down
64 changes: 34 additions & 30 deletions sql/hive/src/test/scala/org/apache/spark/sql/hive/QueryPartitionSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,50 +18,54 @@
package org.apache.spark.sql.hive

import com.google.common.io.Files
import org.apache.spark.sql.test.SQLTestUtils

import org.apache.spark.sql.{QueryTest, _}
import org.apache.spark.util.Utils


class QueryPartitionSuite extends QueryTest {
class QueryPartitionSuite extends QueryTest with SQLTestUtils {

private lazy val ctx = org.apache.spark.sql.hive.test.TestHive
import ctx.implicits._
import ctx.sql

protected def _sqlContext = ctx

test("SPARK-5068: query data when path doesn't exist"){
val testData = ctx.sparkContext.parallelize(
(1 to 10).map(i => TestData(i, i.toString))).toDF()
testData.registerTempTable("testData")
withSQLConf((SQLConf.HIVE_VERIFY_PARTITION_PATH.key, "true")) {
val testData = ctx.sparkContext.parallelize(
(1 to 10).map(i => TestData(i, i.toString))).toDF()
testData.registerTempTable("testData")

val tmpDir = Files.createTempDir()
// create the table for test
sql(s"CREATE TABLE table_with_partition(key int,value string) " +
s"PARTITIONED by (ds string) location '${tmpDir.toURI.toString}' ")
sql("INSERT OVERWRITE TABLE table_with_partition partition (ds='1') " +
"SELECT key,value FROM testData")
sql("INSERT OVERWRITE TABLE table_with_partition partition (ds='2') " +
"SELECT key,value FROM testData")
sql("INSERT OVERWRITE TABLE table_with_partition partition (ds='3') " +
"SELECT key,value FROM testData")
sql("INSERT OVERWRITE TABLE table_with_partition partition (ds='4') " +
"SELECT key,value FROM testData")
val tmpDir = Files.createTempDir()
// create the table for test
sql(s"CREATE TABLE table_with_partition(key int,value string) " +
s"PARTITIONED by (ds string) location '${tmpDir.toURI.toString}' ")
sql("INSERT OVERWRITE TABLE table_with_partition partition (ds='1') " +
"SELECT key,value FROM testData")
sql("INSERT OVERWRITE TABLE table_with_partition partition (ds='2') " +
"SELECT key,value FROM testData")
sql("INSERT OVERWRITE TABLE table_with_partition partition (ds='3') " +
"SELECT key,value FROM testData")
sql("INSERT OVERWRITE TABLE table_with_partition partition (ds='4') " +
"SELECT key,value FROM testData")

// test for the exist path
checkAnswer(sql("select key,value from table_with_partition"),
testData.toDF.collect ++ testData.toDF.collect
++ testData.toDF.collect ++ testData.toDF.collect)
// test for the exist path
checkAnswer(sql("select key,value from table_with_partition"),
testData.toDF.collect ++ testData.toDF.collect
++ testData.toDF.collect ++ testData.toDF.collect)

// delete the path of one partition
tmpDir.listFiles
.find { f => f.isDirectory && f.getName().startsWith("ds=") }
.foreach { f => Utils.deleteRecursively(f) }
// delete the path of one partition
tmpDir.listFiles
.find { f => f.isDirectory && f.getName().startsWith("ds=") }
.foreach { f => Utils.deleteRecursively(f) }

// test for after delete the path
checkAnswer(sql("select key,value from table_with_partition"),
testData.toDF.collect ++ testData.toDF.collect ++ testData.toDF.collect)
// test for after delete the path
checkAnswer(sql("select key,value from table_with_partition"),
testData.toDF.collect ++ testData.toDF.collect ++ testData.toDF.collect)

sql("DROP TABLE table_with_partition")
sql("DROP TABLE createAndInsertTest")
sql("DROP TABLE table_with_partition")
sql("DROP TABLE createAndInsertTest")
}
}
}