lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

[MINOR] Fixing spark long running yaml for non-partitioned (#5607)

Browse Source
This commit is contained in:
Sivabalan Narayanan
2022-05-17 09:58:18 -04:00
committed by GitHub
parent 99555c897a
commit f8b9399615
1 changed files with 5 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
docker/demo/config/test-suite/spark-long-running-non-partitioned.yaml
View File

@@ -14,24 +14,24 @@
# See the License for the specific language governing permissions and
# limitations under the License.
dag_name: cow-spark-deltastreamer-long-running-multi-partitions.yaml
dag_rounds: 6
dag_intermittent_delay_mins: 0
dag_rounds: 10
dag_intermittent_delay_mins: 1
dag_content:
first_insert:
config:
record_size: 200
num_partitions_insert: 1
repeat_count: 1
num_records_insert: 10000
num_records_insert: 1000
type: SparkInsertNode
deps: none
first_upsert:
config:
record_size: 200
num_partitions_insert: 1
num_records_insert: 300
num_records_insert: 1000
repeat_count: 1
num_records_upsert: 3000
num_records_upsert: 1000
num_partitions_upsert: 1
type: SparkUpsertNode
deps: first_insert
@@ -43,7 +43,6 @@ dag_content:
deps: first_upsert
second_validate:
config:
validate_once_every_itr : 3
validate_hive: false
delete_input_data: true
type: ValidateDatasetNode