Skip to content

Commit

Permalink
Merge pull request #1 from apache/master
Browse files Browse the repository at this point in the history
同步 hudi master
  • Loading branch information
loukey-lj committed Jan 26, 2021
2 parents 56866a1 + c4afd17 commit ee9ae14
Show file tree
Hide file tree
Showing 526 changed files with 22,236 additions and 3,229 deletions.
6 changes: 4 additions & 2 deletions .travis.yml
Original file line number Diff line number Diff line change
Expand Up @@ -20,10 +20,12 @@ jdk:
- openjdk8
jobs:
include:
- name: "Unit tests except hudi-spark-client"
env: MODE=unit MODULES='!hudi-client/hudi-spark-client' HUDI_QUIETER_LOGGING=1
- name: "Unit tests for hudi-spark-client"
env: MODE=unit MODULES=hudi-client/hudi-spark-client HUDI_QUIETER_LOGGING=1
- name: "Unit tests for hudi-utilities"
env: MODE=unit MODULES=hudi-utilities HUDI_QUIETER_LOGGING=1
- name: "All other unit tests"
env: MODE=unit MODULES='!hudi-utilities,!hudi-client/hudi-spark-client' HUDI_QUIETER_LOGGING=1
- name: "Functional tests"
env: MODE=functional HUDI_QUIETER_LOGGING=1
- name: "Integration tests"
Expand Down
2 changes: 2 additions & 0 deletions LICENSE
Original file line number Diff line number Diff line change
Expand Up @@ -246,6 +246,8 @@ This product includes code from Apache Spark

* org.apache.hudi.AvroConversionHelper copied from classes in org/apache/spark/sql/avro package

* org.apache.hudi.HoodieSparkUtils.scala copied some methods from org.apache.spark.deploy.SparkHadoopUtil.scala

Copyright: 2014 and onwards The Apache Software Foundation
Home page: http://spark.apache.org/
License: http://www.apache.org/licenses/LICENSE-2.0
Expand Down
8 changes: 8 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -76,6 +76,14 @@ The default Scala version supported is 2.11. To build for Scala 2.12 version, bu
mvn clean package -DskipTests -Dscala-2.12
```

### Build with Spark 3.0.0

The default Spark version supported is 2.4.4. To build for Spark 3.0.0 version, build using `spark3` profile

```
mvn clean package -DskipTests -Dspark3
```

### Build without spark-avro module

The default hudi-jar bundles spark-avro module. To build without spark-avro module, build using `spark-shade-unbundle-avro` profile
Expand Down
172 changes: 53 additions & 119 deletions docker/demo/config/test-suite/complex-dag-cow.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -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
Loading

0 comments on commit ee9ae14

Please sign in to comment.