1
0

[HUDI-3135] Make delete partitions lazy to be executed by the cleaner (#4489)

As of now, delete partitions will ensure all file groups are deleted, but the partition as such is not deleted. So, get all partitions might be returning the deleted partitions as well. but no data will be served since all file groups are deleted. With this patch, we are fixing it. We are letting cleaner take care of deleting the partitions when all file groups pertaining to a partitions are deleted.

- Fixed the CleanPlanActionExecutor to return meta info about list of partitions to be deleted. If there are no valid file groups for a partition, clean planner will include the partition to be deleted.
- Fixed HoodieCleanPlan avro schema to include the list of partitions to be deleted
- CleanActionExecutor is fixed to delete partitions if any (as per clean plan)
- Same info is added to HoodieCleanMetadata
- Metadata table when applying clean metadata, will check for partitions to be deleted and will update the "all_partitions" record for the deleted partitions.

Co-authored-by: sivabalan <n.siva.b@gmail.com>
This commit is contained in:
ForwardXu
2022-03-31 15:35:39 +08:00
committed by GitHub
parent 3cdb590e15
commit 80011df995
20 changed files with 306 additions and 76 deletions

View File

@@ -47,6 +47,9 @@ class TestAlterTableDropPartition extends TestHoodieSqlBase {
checkExceptionContain(s"alter table $tableName drop partition (dt='2021-10-01')")(
s"$tableName is a non-partitioned table that is not allowed to drop partition")
// show partitions
checkAnswer(s"show partitions $tableName")(Seq.empty: _*)
}
test("Purge drop non-partitioned table") {
@@ -71,6 +74,9 @@ class TestAlterTableDropPartition extends TestHoodieSqlBase {
checkExceptionContain(s"alter table $tableName drop partition (dt='2021-10-01') purge")(
s"$tableName is a non-partitioned table that is not allowed to drop partition")
// show partitions
checkAnswer(s"show partitions $tableName")(Seq.empty: _*)
}
Seq(false, true).foreach { urlencode =>
@@ -113,6 +119,13 @@ class TestAlterTableDropPartition extends TestHoodieSqlBase {
}
checkAnswer(s"select dt from $tableName")(Seq(s"2021/10/02"))
assertResult(true)(existsPath(s"${tmp.getCanonicalPath}/$tableName/$partitionPath"))
// show partitions
if (urlencode) {
checkAnswer(s"show partitions $tableName")(Seq(PartitionPathEncodeUtils.escapePathName("2021/10/02")))
} else {
checkAnswer(s"show partitions $tableName")(Seq("2021/10/02"))
}
}
}
}
@@ -157,6 +170,13 @@ class TestAlterTableDropPartition extends TestHoodieSqlBase {
}
checkAnswer(s"select dt from $tableName")(Seq(s"2021/10/02"))
assertResult(false)(existsPath(s"${tmp.getCanonicalPath}/$tableName/$partitionPath"))
// show partitions
if (urlencode) {
checkAnswer(s"show partitions $tableName")(Seq(PartitionPathEncodeUtils.escapePathName("2021/10/02")))
} else {
checkAnswer(s"show partitions $tableName")(Seq("2021/10/02"))
}
}
}
}
@@ -189,7 +209,10 @@ class TestAlterTableDropPartition extends TestHoodieSqlBase {
// drop 2021-10-01 partition
spark.sql(s"alter table $tableName drop partition (dt='2021-10-01')")
checkAnswer(s"select id, name, ts, dt from $tableName") (Seq(2, "l4", "v1", "2021-10-02"))
checkAnswer(s"select id, name, ts, dt from $tableName")(Seq(2, "l4", "v1", "2021-10-02"))
// show partitions
checkAnswer(s"show partitions $tableName")(Seq("dt=2021-10-02"))
}
Seq(false, true).foreach { hiveStyle =>
@@ -232,6 +255,13 @@ class TestAlterTableDropPartition extends TestHoodieSqlBase {
checkAnswer(s"select id, name, ts, year, month, day from $tableName")(
Seq(2, "l4", "v1", "2021", "10", "02")
)
// show partitions
if (hiveStyle) {
checkAnswer(s"show partitions $tableName")(Seq("year=2021/month=10/day=02"))
} else {
checkAnswer(s"show partitions $tableName")(Seq("2021/10/02"))
}
}
}
}
@@ -274,6 +304,13 @@ class TestAlterTableDropPartition extends TestHoodieSqlBase {
)
assertResult(false)(existsPath(
s"${tmp.getCanonicalPath}/$tableName/year=2021/month=10/day=01"))
// show partitions
if (hiveStyle) {
checkAnswer(s"show partitions $tableName")(Seq("year=2021/month=10/day=02"))
} else {
checkAnswer(s"show partitions $tableName")(Seq("2021/10/02"))
}
}
}
}