1
0

[HUDI-1338] Adding Delete support to test suite framework (#2172)

- Adding Delete support to test suite. 
         Added DeleteNode 
         Added support to generate delete records
This commit is contained in:
Sivabalan Narayanan
2020-11-01 00:15:41 -04:00
committed by GitHub
parent 6310a2307a
commit a205dd10fa
16 changed files with 472 additions and 121 deletions

View File

@@ -59,15 +59,13 @@ first_hive_sync:
deps: first_upsert
first_hive_query:
config:
hive_props:
prop2: "set spark.yarn.queue="
prop3: "set hive.strict.checks.large.query=false"
prop4: "set hive.stats.autogather=false"
queue_name: "adhoc"
engine: "mr"
hive_queries:
query1: "select count(*) from testdb.table1 group by `_row_key` having count(*) > 1"
result1: 0
query2: "select count(*) from testdb.table1"
result2: 11600
result2: 11300
type: HiveQueryNode
deps: first_hive_sync
second_upsert:
@@ -82,14 +80,55 @@ second_upsert:
deps: first_hive_query
second_hive_query:
config:
hive_props:
prop2: "set mapred.job.queue.name="
prop3: "set hive.strict.checks.large.query=false"
prop4: "set hive.stats.autogather=false"
queue_name: "adhoc"
engine: "mr"
hive_queries:
query1: "select count(*) from testdb.table1 group by `_row_key` having count(*) > 1"
result1: 0
query2: "select count(*) from testdb.table1"
result2: 11900
result2: 11600
type: HiveQueryNode
deps: second_upsert
fourth_insert:
config:
record_size: 70000
num_insert_partitions: 1
repeat_count: 1
num_records_insert: 1000
deps: second_hive_query
type: InsertNode
third_hive_query:
config:
queue_name: "adhoc"
engine: "mr"
hive_queries:
query1: "select count(*) from testdb.table1 group by `_row_key` having count(*) > 1"
result1: 0
query2: "select count(*) from testdb.table1"
result2: 12600
type: HiveQueryNode
deps: fourth_insert
first_delete:
config:
record_size: 70000
num_partitions_delete: 1
num_records_delete: 200
deps: third_hive_query
type: DeleteNode
fourth_hive_sync:
config:
queue_name: "adhoc"
engine: "mr"
type: HiveSyncNode
deps: first_delete
fourth_hive_query:
config:
queue_name: "adhoc"
engine: "mr"
hive_queries:
query1: "select count(*) from testdb.table1 group by `_row_key` having count(*) > 1"
result1: 0
query2: "select count(*) from testdb.table1"
result2: 12400
type: HiveQueryNode
deps: fourth_hive_sync

View File

@@ -46,6 +46,10 @@
}, {
"name" : "fare",
"type" : "double"
} ]
}, {
"name" : "_hoodie_is_deleted",
"type" : "boolean",
"default" : false
}]
}

View File

@@ -46,6 +46,10 @@
}, {
"name" : "fare",
"type" : "double"
}, {
"name" : "_hoodie_is_deleted",
"type" : "boolean",
"default" : false
}, {
"name" : "haversine_distance",
"type" : "double"

View File

@@ -0,0 +1,27 @@
hoodie.insert.shuffle.parallelism=100
hoodie.upsert.shuffle.parallelism=100
hoodie.bulkinsert.shuffle.parallelism=100
hoodie.deltastreamer.source.test.num_partitions=100
hoodie.deltastreamer.source.test.datagen.use_rocksdb_for_storing_existing_keys=false
hoodie.deltastreamer.source.test.max_unique_records=100000000
hoodie.embed.timeline.server=false
hoodie.deltastreamer.source.input.selector=org.apache.hudi.integ.testsuite.helpers.DFSTestSuitePathSelector
hoodie.datasource.write.recordkey.field=_row_key
hoodie.datasource.write.keygenerator.class=org.apache.hudi.keygen.TimestampBasedKeyGenerator
hoodie.datasource.write.partitionpath.field=timestamp
hoodie.deltastreamer.source.dfs.root=/user/hive/warehouse/hudi-integ-test-suite/input
hoodie.deltastreamer.schemaprovider.target.schema.file=file:/var/hoodie/ws/docker/demo/config/test-suite/source.avsc
hoodie.deltastreamer.schemaprovider.source.schema.file=file:/var/hoodie/ws/docker/demo/config/test-suite/source.avsc
hoodie.deltastreamer.keygen.timebased.timestamp.type=UNIX_TIMESTAMP
hoodie.deltastreamer.keygen.timebased.output.dateformat=yyyy/MM/dd
hoodie.datasource.hive_sync.jdbcurl=jdbc:hive2://hiveserver:10000/
hoodie.datasource.hive_sync.database=testdb
hoodie.datasource.hive_sync.table=table1
hoodie.datasource.hive_sync.assume_date_partitioning=false
hoodie.datasource.hive_sync.partition_fields=_hoodie_partition_path
hoodie.datasource.hive_sync.partition_extractor_class=org.apache.hudi.hive.SlashEncodedDayPartitionValueExtractor