forked from apache/incubator-livy
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
LIVY-233. SparkSession support for Job API. (apache#217)
Added sparkSession to expose Spark 2.0 SparkSession in JobContext. If SparkSession is not supported, it will throw an exception.
Example:
JobHandle<String> handler = client.submit(new Job<String>() {
@OverRide
public String call(JobContext jc) throws Exception {
SparkSession session = jc.sparkSession();
return session.version();
}
});- Loading branch information
1 parent
1ee2ed8
commit 1b72ce9
Showing
11 changed files
with
332 additions
and
6 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
107 changes: 107 additions & 0 deletions
107
integration-test/src/test/spark2/scala/Spark2JobApiIT.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,107 @@ | ||
| /* | ||
| * Licensed to Cloudera, Inc. under one | ||
| * or more contributor license agreements. See the NOTICE file | ||
| * distributed with this work for additional information | ||
| * regarding copyright ownership. Cloudera, Inc. 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. | ||
| */ | ||
|
|
||
| package com.cloudera.livy.test | ||
|
|
||
| import java.io.File | ||
| import java.net.URI | ||
| import java.util.concurrent.{TimeUnit, Future => JFuture} | ||
| import javax.servlet.http.HttpServletResponse | ||
|
|
||
| import com.fasterxml.jackson.databind.ObjectMapper | ||
| import com.fasterxml.jackson.module.scala.DefaultScalaModule | ||
| import org.scalatest.BeforeAndAfterAll | ||
|
|
||
| import com.cloudera.livy._ | ||
| import com.cloudera.livy.client.common.HttpMessages._ | ||
| import com.cloudera.livy.sessions.SessionKindModule | ||
| import com.cloudera.livy.test.framework.BaseIntegrationTestSuite | ||
| import com.cloudera.livy.test.jobs.spark2._ | ||
|
|
||
| class Spark2JobApiIT extends BaseIntegrationTestSuite with BeforeAndAfterAll with Logging { | ||
|
|
||
| private var client: LivyClient = _ | ||
| private var sessionId: Int = _ | ||
| private val mapper = new ObjectMapper() | ||
| .registerModule(DefaultScalaModule) | ||
| .registerModule(new SessionKindModule()) | ||
|
|
||
| override def afterAll(): Unit = { | ||
| super.afterAll() | ||
|
|
||
| if (client != null) { | ||
| client.stop(true) | ||
| } | ||
|
|
||
| livyClient.connectSession(sessionId).stop() | ||
| } | ||
|
|
||
| test("create a new session and upload test jar") { | ||
| val tempClient = createClient(livyEndpoint) | ||
|
|
||
| try { | ||
| // Figure out the session ID by poking at the REST endpoint. We should probably expose this | ||
| // in the Java API. | ||
| val list = sessionList() | ||
| assert(list.total === 1) | ||
| val tempSessionId = list.sessions(0).id | ||
|
|
||
| livyClient.connectSession(tempSessionId).verifySessionIdle() | ||
| waitFor(tempClient.uploadJar(new File(testLib))) | ||
|
|
||
| client = tempClient | ||
| sessionId = tempSessionId | ||
| } finally { | ||
| if (client == null) { | ||
| try { | ||
| if (tempClient != null) { | ||
| tempClient.stop(true) | ||
| } | ||
| } catch { | ||
| case e: Exception => warn("Error stopping client.", e) | ||
| } | ||
| } | ||
| } | ||
| } | ||
|
|
||
| test("run spark2 job") { | ||
| assume(client != null, "Client not active.") | ||
| val result = waitFor(client.submit(new SparkSessionTest())) | ||
| assert(result === 3) | ||
| } | ||
|
|
||
| test("run spark2 dataset job") { | ||
| assume(client != null, "Client not active.") | ||
| val result = waitFor(client.submit(new DatasetTest())) | ||
| assert(result === 2) | ||
| } | ||
|
|
||
| private def waitFor[T](future: JFuture[T]): T = { | ||
| future.get(30, TimeUnit.SECONDS) | ||
| } | ||
|
|
||
| private def sessionList(): SessionList = { | ||
| val response = httpClient.prepareGet(s"$livyEndpoint/sessions/").execute().get() | ||
| assert(response.getStatusCode === HttpServletResponse.SC_OK) | ||
| mapper.readValue(response.getResponseBodyAsStream, classOf[SessionList]) | ||
| } | ||
|
|
||
| private def createClient(uri: String): LivyClient = { | ||
| new LivyClientBuilder().setURI(new URI(uri)).build() | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
64 changes: 64 additions & 0 deletions
64
test-lib/src/main/spark2/java/com/cloudera/livy/test/jobs/spark2/DatasetTest.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,64 @@ | ||
| /* | ||
| * Licensed to Cloudera, Inc. under one | ||
| * or more contributor license agreements. See the NOTICE file | ||
| * distributed with this work for additional information | ||
| * regarding copyright ownership. Cloudera, Inc. 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. | ||
| */ | ||
|
|
||
| package com.cloudera.livy.test.jobs.spark2; | ||
|
|
||
| import java.util.Arrays; | ||
|
|
||
| import org.apache.spark.api.java.JavaRDD; | ||
| import org.apache.spark.api.java.JavaSparkContext; | ||
| import org.apache.spark.api.java.function.FilterFunction; | ||
| import org.apache.spark.api.java.function.Function; | ||
| import org.apache.spark.sql.Dataset; | ||
| import org.apache.spark.sql.Row; | ||
| import org.apache.spark.sql.RowFactory; | ||
| import org.apache.spark.sql.SparkSession; | ||
| import org.apache.spark.sql.types.DataTypes; | ||
| import org.apache.spark.sql.types.StructField; | ||
| import org.apache.spark.sql.types.StructType; | ||
|
|
||
| import com.cloudera.livy.Job; | ||
| import com.cloudera.livy.JobContext; | ||
|
|
||
| public class DatasetTest implements Job<Long> { | ||
|
|
||
| @Override | ||
| public Long call(JobContext jc) throws Exception { | ||
| SparkSession spark = jc.sparkSession(); | ||
|
|
||
| JavaSparkContext sc = new JavaSparkContext(spark.sparkContext()); | ||
| JavaRDD<Row> rdd = sc.parallelize(Arrays.asList(1, 2, 3)).map( | ||
| new Function<Integer, Row>() { | ||
| public Row call(Integer integer) throws Exception { | ||
| return RowFactory.create(integer); | ||
| } | ||
| }); | ||
| StructType schema = DataTypes.createStructType(new StructField[] { | ||
| DataTypes.createStructField("value", DataTypes.IntegerType, false) | ||
| }); | ||
|
|
||
| Dataset<Row> ds = spark.createDataFrame(rdd, schema); | ||
|
|
||
| return ds.filter(new FilterFunction<Row>() { | ||
| @Override | ||
| public boolean call(Row row) throws Exception { | ||
| return row.getInt(0) >= 2; | ||
| } | ||
| }).count(); | ||
| } | ||
| } |
Oops, something went wrong.