1
0

[HUDI-1331] Adding support for validating entire dataset and long running tests in test suite framework (#2168)

* trigger rebuild

* [HUDI-1156] Remove unused dependencies from HoodieDeltaStreamerWrapper Class (#1927)

* Adding support for validating records and long running tests in test sutie framework

* Adding partial validate node

* Fixing spark session initiation in Validate nodes

* Fixing validation

* Adding hive table validation to ValidateDatasetNode

* Rebasing with latest commits from master

* Addressing feedback

* Addressing comments

Co-authored-by: lamber-ken <lamberken@163.com>
Co-authored-by: linshan-ma <mabin194046@163.com>
This commit is contained in:
Sivabalan Narayanan
2020-12-26 12:29:24 -05:00
committed by GitHub
parent 3ec9270e8e
commit 8cf6a7223f
33 changed files with 1101 additions and 518 deletions

View File

@@ -13,122 +13,56 @@
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
first_insert:
config:
record_size: 70000
num_insert_partitions: 1
repeat_count: 1
num_records_insert: 1000
type: InsertNode
deps: none
second_insert:
config:
record_size: 70000
num_insert_partitions: 1
repeat_count: 1
num_records_insert: 10000
deps: first_insert
type: InsertNode
third_insert:
config:
record_size: 70000
num_insert_partitions: 1
repeat_count: 1
num_records_insert: 300
deps: second_insert
type: InsertNode
first_rollback:
config:
deps: third_insert
type: RollbackNode
first_upsert:
config:
record_size: 70000
num_insert_partitions: 1
num_records_insert: 300
repeat_count: 1
num_records_upsert: 100
num_upsert_partitions: 10
type: UpsertNode
deps: first_rollback
first_hive_sync:
config:
queue_name: "adhoc"
engine: "mr"
type: HiveSyncNode
deps: first_upsert
first_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: 11300
type: HiveQueryNode
deps: first_hive_sync
second_upsert:
config:
record_size: 70000
num_insert_partitions: 1
num_records_insert: 300
repeat_count: 1
num_records_upsert: 100
num_upsert_partitions: 10
type: UpsertNode
deps: first_hive_query
second_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: 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
dag_name: cow-long-running-example.yaml
dag_rounds: 2
dag_intermittent_delay_mins: 1
dag_content:
first_insert:
config:
record_size: 100
num_partitions_insert: 1
repeat_count: 1
num_records_insert: 1000
type: InsertNode
deps: none
second_insert:
config:
record_size: 100
num_partitions_insert: 1
repeat_count: 1
num_records_insert: 10000
deps: first_insert
type: InsertNode
third_insert:
config:
record_size: 100
num_partitions_insert: 1
repeat_count: 1
num_records_insert: 300
deps: second_insert
type: InsertNode
first_validate:
config:
type: ValidateDatasetNode
deps: third_insert
first_upsert:
config:
record_size: 100
num_partitions_insert: 1
num_records_insert: 300
repeat_count: 1
num_records_upsert: 100
num_partitions_upsert: 1
type: UpsertNode
deps: first_validate
first_delete:
config:
num_partitions_delete: 1
num_records_delete: 2000
type: DeleteNode
deps: first_upsert
second_validate:
config:
delete_input_data: true
type: ValidateDatasetNode
deps: first_delete

View File

@@ -13,103 +13,107 @@
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
first_insert:
config:
record_size: 70000
num_insert_partitions: 1
repeat_count: 1
num_records_insert: 100
type: InsertNode
deps: none
second_insert:
config:
record_size: 70000
num_insert_partitions: 1
repeat_count: 1
num_records_insert: 100
deps: first_insert
type: InsertNode
third_insert:
config:
record_size: 70000
num_insert_partitions: 1
repeat_count: 1
num_records_insert: 300
deps: second_insert
type: InsertNode
first_rollback:
config:
deps: third_insert
type: RollbackNode
first_upsert:
config:
record_size: 70000
num_insert_partitions: 1
num_records_insert: 300
repeat_count: 1
num_records_upsert: 100
num_upsert_partitions: 10
type: UpsertNode
deps: first_rollback
first_hive_sync:
config:
queue_name: "adhoc"
engine: "mr"
type: HiveSyncNode
deps: first_upsert
first_hive_query:
config:
queue_name: "adhoc"
engine: "mr"
type: HiveQueryNode
deps: first_hive_sync
second_upsert:
config:
record_size: 70000
num_insert_partitions: 1
num_records_insert: 300
repeat_count: 1
num_records_upsert: 100
num_upsert_partitions: 10
type: UpsertNode
deps: first_hive_query
second_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: 1100
type: HiveQueryNode
deps: second_upsert
first_schedule_compact:
config:
type: ScheduleCompactNode
deps: second_hive_query
third_upsert:
config:
record_size: 70000
num_insert_partitions: 1
num_records_insert: 300
repeat_count: 1
num_records_upsert: 100
num_upsert_partitions: 10
type: UpsertNode
deps: first_schedule_compact
first_compact:
config:
type: CompactNode
deps: first_schedule_compact
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: 1400
type: HiveQueryNode
deps: first_compact
dag_name: complex-dag-mor.yaml
dag_rounds: 1
dag_intermittent_delay_mins: 10
dag_content:
first_insert:
config:
record_size: 70000
num_partitions_insert: 1
repeat_count: 5
num_records_insert: 100
type: InsertNode
deps: none
second_insert:
config:
record_size: 70000
num_partitions_insert: 1
repeat_count: 5
num_records_insert: 100
deps: first_insert
type: InsertNode
third_insert:
config:
record_size: 70000
num_partitions_insert: 1
repeat_count: 2
num_records_insert: 300
deps: second_insert
type: InsertNode
first_rollback:
config:
deps: third_insert
type: RollbackNode
first_upsert:
config:
record_size: 70000
num_partitions_insert: 1
num_records_insert: 300
repeat_count: 1
num_records_upsert: 100
num_partitions_upsert: 10
type: UpsertNode
deps: first_rollback
first_hive_sync:
config:
queue_name: "adhoc"
engine: "mr"
type: HiveSyncNode
deps: first_upsert
first_hive_query:
config:
queue_name: "adhoc"
engine: "mr"
type: HiveQueryNode
deps: first_hive_sync
second_upsert:
config:
record_size: 70000
num_partitions_insert: 1
num_records_insert: 300
repeat_count: 1
num_records_upsert: 100
num_partitions_upsert: 10
type: UpsertNode
deps: first_hive_query
second_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: 1100
type: HiveQueryNode
deps: second_upsert
first_schedule_compact:
config:
type: ScheduleCompactNode
deps: second_hive_query
third_upsert:
config:
record_size: 70000
num_partitions_insert: 1
num_records_insert: 300
repeat_count: 1
num_records_upsert: 100
num_partitions_upsert: 10
type: UpsertNode
deps: first_schedule_compact
first_compact:
config:
type: CompactNode
deps: first_schedule_compact
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: 1400
type: HiveQueryNode
deps: first_compact

View File

@@ -0,0 +1,68 @@
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
dag_name: cow-long-running-example.yaml
dag_rounds: 20
dag_intermittent_delay_mins: 10
dag_content:
first_insert:
config:
record_size: 100
num_partitions_insert: 1
repeat_count: 1
num_records_insert: 1000
type: InsertNode
deps: none
second_insert:
config:
record_size: 100
num_partitions_insert: 1
repeat_count: 1
num_records_insert: 10000
deps: first_insert
type: InsertNode
third_insert:
config:
record_size: 100
num_partitions_insert: 1
repeat_count: 1
num_records_insert: 300
deps: second_insert
type: InsertNode
first_validate:
config:
type: ValidateDatasetNode
deps: third_insert
first_upsert:
config:
record_size: 100
num_partitions_insert: 1
num_records_insert: 300
repeat_count: 1
num_records_upsert: 100
num_partitions_upsert: 1
type: UpsertNode
deps: first_validate
first_delete:
config:
num_partitions_delete: 1
num_records_delete: 2000
type: DeleteNode
deps: first_upsert
second_validate:
config:
delete_input_data: true
type: ValidateDatasetNode
deps: first_delete

View File

@@ -1,37 +0,0 @@
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# write configs
hoodie.datasource.write.recordkey.field=_row_key
hoodie.datasource.write.keygenerator.class=org.apache.hudi.keygen.TimestampBasedKeyGenerator
hoodie.datasource.write.partitionpath.field=timestamp
# deltastreamer configs
hoodie.deltastreamer.keygen.timebased.output.dateformat=yyyy/MM/dd
hoodie.deltastreamer.keygen.timebased.timestamp.type=UNIX_TIMESTAMP
hoodie.deltastreamer.source.dfs.root=/user/hive/warehouse/hudi-bench/input
hoodie.deltastreamer.schemaprovider.source.schema.file=/var/hoodie/ws/docker/demo/config/test-suite/source.avsc
hoodie.deltastreamer.schemaprovider.target.schema.file=/var/hoodie/ws/docker/demo/config/bench/source.avsc
#hive sync
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.use_jdbc=false
hoodie.datasource.hive_sync.partition_extractor_class=org.apache.hudi.hive.SlashEncodedDayPartitionValueExtractor
hoodie.datasource.hive_sync.assume_date_partitioning=true
hoodie.datasource.hive_sync.use_pre_apache_input_format=true

View File

@@ -1,3 +1,4 @@
hoodie.insert.shuffle.parallelism=100
hoodie.upsert.shuffle.parallelism=100
hoodie.bulkinsert.shuffle.parallelism=100
@@ -8,6 +9,13 @@ 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.insert.shuffle.parallelism=100
hoodie.upsert.shuffle.parallelism=100
hoodie.bulkinsert.shuffle.parallelism=100
hoodie.deltastreamer.source.input.selector=org.apache.hudi.integ.testsuite.helpers.DFSTestSuitePathSelector
hoodie.datasource.hive_sync.skip_ro_suffix=true
hoodie.datasource.write.recordkey.field=_row_key
hoodie.datasource.write.keygenerator.class=org.apache.hudi.keygen.TimestampBasedKeyGenerator
hoodie.datasource.write.partitionpath.field=timestamp