Skip to content
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

Jump to bottom

[SPARK-34055][SQL][3.1] Refresh cache in ALTER TABLE .. ADD PARTITION #31115

Closed
wants to merge 1 commit into from
Closed

[SPARK-34055][SQL][3.1] Refresh cache in ALTER TABLE .. ADD PARTITION #31115

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
1 change: 1 addition & 0 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/command/ddl.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -485,6 +485,7 @@ case class AlterTableAddPartitionCommand(
catalog.createPartitions(table.identifier, batch, ignoreIfExists = ifNotExists)
}

sparkSession.catalog.refreshTable(table.identifier.quotedString)
if (table.stats.nonEmpty) {
if (sparkSession.sessionState.conf.autoSizeUpdateEnabled) {
val addedSize = CommandUtils.calculateMultipleLocationSizes(sparkSession, table.identifier,
Expand Down
29 changes: 29 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/CachedTableSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,8 @@ import java.nio.file.{Files, Paths}
import scala.collection.mutable.HashSet
import scala.concurrent.duration._

import org.apache.commons.io.FileUtils

import org.apache.spark.CleanerListener
import org.apache.spark.executor.DataReadMethod._
import org.apache.spark.executor.DataReadMethod.DataReadMethod
Expand Down Expand Up @@ -1335,4 +1337,31 @@ class CachedTableSuite extends QueryTest with SQLTestUtils
QueryTest.checkAnswer(sql("SELECT * FROM t"), Seq(Row(0, 2), Row(1, 1)))
}
}

test("SPARK-34055: refresh cache in partition adding") {
withTable("t") {
sql("CREATE TABLE t (id int, part int) USING parquet PARTITIONED BY (part)")
sql("INSERT INTO t PARTITION (part=0) SELECT 0")
assert(!spark.catalog.isCached("t"))
sql("CACHE TABLE t")
assert(spark.catalog.isCached("t"))
checkAnswer(sql("SELECT * FROM t"), Seq(Row(0, 0)))

// Create new partition (part = 1) in the filesystem
val information = sql("SHOW TABLE EXTENDED LIKE 't' PARTITION (part = 0)")
.select("information")
.first().getString(0)
val part0Loc = information
.split("\\r?\\n")
.filter(_.startsWith("Location:"))
.head
.replace("Location: file:", "")
val part1Loc = part0Loc.replace("part=0", "part=1")
FileUtils.copyDirectory(new File(part0Loc), new File(part1Loc))

sql(s"ALTER TABLE t ADD PARTITION (part=1) LOCATION '$part1Loc'")
assert(spark.catalog.isCached("t"))
checkAnswer(sql("SELECT * FROM t"), Seq(Row(0, 0), Row(0, 1)))
}
}
}
29 changes: 29 additions & 0 deletions sql/hive/src/test/scala/org/apache/spark/sql/hive/CachedTableSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,8 @@ package org.apache.spark.sql.hive

import java.io.File

import org.apache.commons.io.FileUtils

import org.apache.spark.sql.{AnalysisException, Dataset, QueryTest, Row, SaveMode}
import org.apache.spark.sql.catalyst.parser.ParseException
import org.apache.spark.sql.execution.columnar.InMemoryTableScanExec
Expand Down Expand Up @@ -469,4 +471,31 @@ class CachedTableSuite extends QueryTest with SQLTestUtils with TestHiveSingleto
QueryTest.checkAnswer(sql("SELECT * FROM t"), Seq(Row(0, 2), Row(1, 1)))
}
}

test("SPARK-34055: refresh cache in partition adding") {
withTable("t") {
sql("CREATE TABLE t (id int, part int) USING hive PARTITIONED BY (part)")
sql("INSERT INTO t PARTITION (part=0) SELECT 0")
assert(!spark.catalog.isCached("t"))
sql("CACHE TABLE t")
assert(spark.catalog.isCached("t"))
checkAnswer(sql("SELECT * FROM t"), Seq(Row(0, 0)))

// Create new partition (part = 1) in the filesystem
val information = sql("SHOW TABLE EXTENDED LIKE 't' PARTITION (part = 0)")
.select("information")
.first().getString(0)
val part0Loc = information
.split("\\r?\\n")
.filter(_.startsWith("Location:"))
.head
.replace("Location: file:", "")
val part1Loc = part0Loc.replace("part=0", "part=1")
FileUtils.copyDirectory(new File(part0Loc), new File(part1Loc))

sql(s"ALTER TABLE t ADD PARTITION (part=1) LOCATION '$part1Loc'")
assert(spark.catalog.isCached("t"))
checkAnswer(sql("SELECT * FROM t"), Seq(Row(0, 0), Row(0, 1)))
}
}
}