blob: d4201b558f72d77a41c6f335d798d1bc5689a515 [file] [log] [blame]
/*
* 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.
*/
package org.apache.tinkerpop.gremlin.spark.process.computer;
import org.apache.tinkerpop.gremlin.GraphProvider;
import org.apache.tinkerpop.gremlin.LoadGraphWith;
import org.apache.tinkerpop.gremlin.groovy.util.SugarTestHelper;
import org.apache.tinkerpop.gremlin.hadoop.Constants;
import org.apache.tinkerpop.gremlin.hadoop.HadoopGraphProvider;
import org.apache.tinkerpop.gremlin.hadoop.groovy.plugin.HadoopGremlinPluginCheck;
import org.apache.tinkerpop.gremlin.hadoop.structure.io.FileSystemStorageCheck;
import org.apache.tinkerpop.gremlin.process.computer.Computer;
import org.apache.tinkerpop.gremlin.process.computer.GraphComputer;
import org.apache.tinkerpop.gremlin.process.traversal.dsl.graph.GraphTraversalSource;
import org.apache.tinkerpop.gremlin.process.traversal.engine.ComputerTraversalEngine;
import org.apache.tinkerpop.gremlin.process.traversal.step.map.GroovyPageRankTest;
import org.apache.tinkerpop.gremlin.process.traversal.step.map.GroovyPeerPressureTest;
import org.apache.tinkerpop.gremlin.process.traversal.step.map.GroovyProgramTest;
import org.apache.tinkerpop.gremlin.process.traversal.step.map.PageRankTest;
import org.apache.tinkerpop.gremlin.process.traversal.step.map.PeerPressureTest;
import org.apache.tinkerpop.gremlin.process.traversal.step.map.ProgramTest;
import org.apache.tinkerpop.gremlin.spark.structure.Spark;
import org.apache.tinkerpop.gremlin.spark.structure.io.PersistedOutputRDD;
import org.apache.tinkerpop.gremlin.spark.structure.io.SparkContextStorageCheck;
import org.apache.tinkerpop.gremlin.spark.structure.io.ToyGraphInputRDD;
import org.apache.tinkerpop.gremlin.spark.structure.io.gryo.GryoSerializer;
import org.apache.tinkerpop.gremlin.structure.Graph;
import java.util.Map;
/**
* @author Marko A. Rodriguez (http://markorodriguez.com)
*/
@GraphProvider.Descriptor(computer = SparkGraphComputer.class)
public class SparkHadoopGraphProvider extends HadoopGraphProvider {
@Override
public Map<String, Object> getBaseConfiguration(final String graphName, final Class<?> test, final String testMethodName, final LoadGraphWith.GraphData loadGraphWith) {
final Map<String, Object> config = super.getBaseConfiguration(graphName, test, testMethodName, loadGraphWith);
config.put(Constants.GREMLIN_SPARK_PERSIST_CONTEXT, true); // this makes the test suite go really fast
// toy graph inputRDD does not have corresponding outputRDD so where jobs chain, it fails (failing makes sense)
if (null != loadGraphWith &&
!test.equals(ProgramTest.Traversals.class) &&
!test.equals(GroovyProgramTest.Traversals.class) &&
!test.equals(PageRankTest.Traversals.class) &&
!test.equals(GroovyPageRankTest.Traversals.class) &&
!test.equals(PeerPressureTest.Traversals.class) &&
!test.equals(GroovyPeerPressureTest.Traversals.class) &&
!test.equals(FileSystemStorageCheck.class) &&
!testMethodName.equals("shouldSupportJobChaining") && // GraphComputerTest.shouldSupportJobChaining
RANDOM.nextBoolean()) {
config.put(RANDOM.nextBoolean() ? Constants.GREMLIN_SPARK_GRAPH_INPUT_RDD : Constants.GREMLIN_HADOOP_GRAPH_READER, ToyGraphInputRDD.class.getCanonicalName());
}
// tests persisted RDDs
if (test.equals(SparkContextStorageCheck.class)) {
config.put(RANDOM.nextBoolean() ? Constants.GREMLIN_SPARK_GRAPH_INPUT_RDD : Constants.GREMLIN_HADOOP_GRAPH_READER, ToyGraphInputRDD.class.getCanonicalName());
config.put(RANDOM.nextBoolean() ? Constants.GREMLIN_SPARK_GRAPH_OUTPUT_RDD : Constants.GREMLIN_HADOOP_GRAPH_WRITER, PersistedOutputRDD.class.getCanonicalName());
}
// sugar plugin causes meta-method issues with a persisted context
if (test.equals(HadoopGremlinPluginCheck.class)) {
Spark.close();
SugarTestHelper.clearRegistry(this);
}
config.put(Constants.GREMLIN_HADOOP_DEFAULT_GRAPH_COMPUTER, SparkGraphComputer.class.getCanonicalName());
config.put("spark.master", "local[4]");
config.put("spark.serializer", GryoSerializer.class.getCanonicalName());
config.put("spark.kryo.registrationRequired", true);
return config;
}
@Override
public GraphTraversalSource traversal(final Graph graph) {
return RANDOM.nextBoolean() ?
RANDOM.nextBoolean() ?
graph.traversal(GraphTraversalSource.build().engine(ComputerTraversalEngine.build().computer(SparkGraphComputer.class).workers(RANDOM.nextInt(3) + 1))) :
graph.traversal().withComputer(Computer.compute(SparkGraphComputer.class).workers(RANDOM.nextInt(3) + 1)) :
RANDOM.nextBoolean() ?
graph.traversal(GraphTraversalSource.computer(SparkGraphComputer.class)) :
graph.traversal().withComputer();
}
@Override
public GraphComputer getGraphComputer(final Graph graph) {
return RANDOM.nextBoolean() ?
graph.compute().workers(RANDOM.nextInt(3) + 1) :
graph.compute(SparkGraphComputer.class);
}
}