lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

[HUDI-2393] Add yamls for large scale testing (#3594)

Browse Source
This commit is contained in:
Sagar Sumit
2021-09-10 18:32:01 +05:30
committed by GitHub
parent 44b9bc145e
commit cf15431852
4 changed files with 292 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

71
docker/demo/config/test-suite/large-scale/cow-large-scale-long-running.yaml Normal file
View File

@@ -0,0 +1,71 @@
# 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.
#
# Sanity yaml to test simple operations.
dag_name: cow-large-scale-long-running.yaml
dag_rounds: 50
dag_intermittent_delay_mins: 1
dag_content:
first_insert:
config:
record_size: 1000
num_partitions_insert: 10
repeat_count: 1
num_records_insert: 1000000 # this will generate about 1.5 GB data
type: InsertNode
deps: none
second_insert:
config:
record_size: 1000
num_partitions_insert: 10
repeat_count: 1
num_records_insert: 100000
deps: first_insert
type: InsertNode
third_insert:
config:
record_size: 1000
num_partitions_insert: 5
repeat_count: 1
num_records_insert: 300000
deps: second_insert
type: InsertNode
first_validate:
config:
validate_hive: false
type: ValidateDatasetNode
deps: third_insert
first_upsert:
config:
record_size: 1000
num_partitions_insert: 2
num_records_insert: 3000
repeat_count: 1
num_records_upsert: 100000
num_partitions_upsert: 10
type: UpsertNode
deps: first_validate
first_delete:
config:
num_partitions_delete: 5
num_records_delete: 8000
type: DeleteNode
deps: first_upsert
second_validate:
config:
validate_hive: false
type: ValidateDatasetNode
deps: first_delete

71
docker/demo/config/test-suite/large-scale/cow-large-scale-sanity.yaml Normal file
View File

@@ -0,0 +1,71 @@
# 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.
#
# Sanity yaml to test simple operations.
dag_name: cow-large-scale-sanity.yaml
dag_rounds: 1
dag_intermittent_delay_mins: 1
dag_content:
first_insert:
config:
record_size: 1000
num_partitions_insert: 100
repeat_count: 1
num_records_insert: 3000000 # this will generate about 60GB data
type: InsertNode
deps: none
second_insert:
config:
record_size: 1000
num_partitions_insert: 50
repeat_count: 1
num_records_insert: 1000000
deps: first_insert
type: InsertNode
third_insert:
config:
record_size: 1000
num_partitions_insert: 5
repeat_count: 1
num_records_insert: 300000
deps: second_insert
type: InsertNode
first_validate:
config:
validate_hive: false
type: ValidateDatasetNode
deps: third_insert
first_upsert:
config:
record_size: 1000
num_partitions_insert: 2
num_records_insert: 3000
repeat_count: 1
num_records_upsert: 100000
num_partitions_upsert: 20
type: UpsertNode
deps: first_validate
first_delete:
config:
num_partitions_delete: 5
num_records_delete: 8000
type: DeleteNode
deps: first_upsert
second_validate:
config:
validate_hive: false
type: ValidateDatasetNode
deps: first_delete

75
docker/demo/config/test-suite/large-scale/mor-large-scale-long-running.yaml Normal file
View File

@@ -0,0 +1,75 @@
# 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.
#
# Sanity yaml to test simple operations.
dag_name: mor-large-scale-long-running.yaml
dag_rounds: 50
dag_intermittent_delay_mins: 1
dag_content:
first_insert:
config:
record_size: 1000
num_partitions_insert: 10
repeat_count: 1
num_records_insert: 1000000 # this will generate about 1.5 GB data
type: InsertNode
deps: none
second_insert:
config:
record_size: 1000
num_partitions_insert: 10
repeat_count: 1
num_records_insert: 100000
deps: first_insert
type: InsertNode
third_insert:
config:
record_size: 1000
num_partitions_insert: 5
repeat_count: 1
num_records_insert: 300000
deps: second_insert
type: InsertNode
first_validate:
config:
validate_hive: false
type: ValidateDatasetNode
deps: third_insert
first_upsert:
config:
record_size: 1000
num_partitions_insert: 2
num_records_insert: 3000
repeat_count: 1
num_records_upsert: 100000
num_partitions_upsert: 10
type: UpsertNode
deps: first_validate
first_schedule_compact:
config:
type: ScheduleCompactNode
deps: first_upsert
first_delete:
config:
num_partitions_delete: 5
num_records_delete: 8000
type: DeleteNode
deps: first_schedule_compact
second_validate:
config:
validate_hive: false
type: ValidateDatasetNode
deps: first_delete

75
docker/demo/config/test-suite/large-scale/mor-large-scale-sanity.yaml Normal file
View File

@@ -0,0 +1,75 @@
# 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.
#
# Sanity yaml to test simple operations.
dag_name: mor-large-scale-sanity.yaml
dag_rounds: 1
dag_intermittent_delay_mins: 1
dag_content:
first_insert:
config:
record_size: 1000
num_partitions_insert: 100
repeat_count: 1
num_records_insert: 3000000 # this will generate about 60GB data
type: InsertNode
deps: none
second_insert:
config:
record_size: 1000
num_partitions_insert: 50
repeat_count: 1
num_records_insert: 1000000
deps: first_insert
type: InsertNode
third_insert:
config:
record_size: 1000
num_partitions_insert: 5
repeat_count: 1
num_records_insert: 300000
deps: second_insert
type: InsertNode
first_validate:
config:
validate_hive: false
type: ValidateDatasetNode
deps: third_insert
first_upsert:
config:
record_size: 1000
num_partitions_insert: 2
num_records_insert: 3000
repeat_count: 1
num_records_upsert: 100000
num_partitions_upsert: 20
type: UpsertNode
deps: first_validate
first_schedule_compact:
config:
type: ScheduleCompactNode
deps: first_upsert
first_delete:
config:
num_partitions_delete: 5
num_records_delete: 8000
type: DeleteNode
deps: first_schedule_compact
second_validate:
config:
validate_hive: false
type: ValidateDatasetNode
deps: first_delete