97 lines
2.8 KiB
YAML
97 lines
2.8 KiB
YAML
# 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.
|
|
first_insert:
|
|
config:
|
|
record_size: 70000
|
|
num_insert_partitions: 1
|
|
repeat_count: 5
|
|
num_records_insert: 1000
|
|
type: InsertNode
|
|
deps: none
|
|
second_insert:
|
|
config:
|
|
record_size: 70000
|
|
num_insert_partitions: 1
|
|
repeat_count: 5
|
|
num_records_insert: 10000
|
|
deps: first_insert
|
|
type: InsertNode
|
|
third_insert:
|
|
config:
|
|
record_size: 70000
|
|
num_insert_partitions: 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_insert_partitions: 1
|
|
num_records_insert: 300
|
|
repeat_count: 5
|
|
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:
|
|
hive_props:
|
|
prop1: "set hive.execution.engine=spark"
|
|
prop2: "set spark.yarn.queue="
|
|
prop3: "set hive.strict.checks.large.query=false"
|
|
prop4: "set hive.stats.autogather=false"
|
|
hive_queries:
|
|
query1: "select count(*) from testdb1.table1 group by `_row_key` having count(*) > 1"
|
|
result1: 0
|
|
query2: "select count(*) from testdb1.table1"
|
|
result2: 22100000
|
|
type: HiveQueryNode
|
|
deps: first_hive_sync
|
|
second_upsert:
|
|
config:
|
|
record_size: 70000
|
|
num_insert_partitions: 1
|
|
num_records_insert: 300
|
|
repeat_count: 5
|
|
num_records_upsert: 100
|
|
num_upsert_partitions: 10
|
|
type: UpsertNode
|
|
deps: first_hive_query
|
|
second_hive_query:
|
|
config:
|
|
hive_props:
|
|
prop1: "set hive.execution.engine=mr"
|
|
prop2: "set mapred.job.queue.name="
|
|
prop3: "set hive.strict.checks.large.query=false"
|
|
prop4: "set hive.stats.autogather=false"
|
|
hive_queries:
|
|
query1: "select count(*) from testdb1.table1 group by `_row_key` having count(*) > 1"
|
|
result1: 0
|
|
query2: "select count(*) from testdb1.table1"
|
|
result2: 22100
|
|
type: HiveQueryNode
|
|
deps: second_upsert |