Skip to content
This repository was archived by the owner on Dec 15, 2025. It is now read-only.

Add workload nweight back #324

Merged
carsonwang merged 2 commits into from
Oct 12, 2016
Merged

Add workload nweight back #324

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8f938fe
Add workload NWeight back
carsonwang Oct 11, 2016
dd9a9d8
add license header and fix style
carsonwang Oct 12, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
34 changes: 34 additions & 0 deletions bin/workloads/graph/nweight/prepare/prepare.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
#!/bin/bash
# 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.

current_dir=`dirname "$0"`
root_dir=${current_dir}/../../../../../
workload_config=${root_dir}/conf/workloads/graph/nweight.conf
. "${root_dir}/bin/functions/load-bench-config.sh"

enter_bench NWeightPrepare ${workload_config}
show_bannar start

rmr-hdfs $INPUT_HDFS || true
START_TIME=`timestamp`

run-spark-job com.intel.hibench.sparkbench.graph.nweight.NWeightDataGenerator $MODEL_INPUT $INPUT_HDFS $EDGES

END_TIME=`timestamp`

show_bannar finish
leave_bench

34 changes: 34 additions & 0 deletions bin/workloads/graph/nweight/spark/run.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
#!/bin/bash
# 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.

current_dir=`dirname "$0"`
root_dir=${current_dir}/../../../../../
workload_config=${root_dir}/conf/workloads/graph/nweight.conf
. "${root_dir}/bin/functions/load-bench-config.sh"

enter_bench ScalaSparkNWeight ${workload_config}
show_bannar start

rmr-hdfs $OUTPUT_HDFS || true

SIZE=`dir_size $INPUT_HDFS`
START_TIME=`timestamp`
run-spark-job com.intel.hibench.sparkbench.graph.nweight.NWeight $INPUT_HDFS $OUTPUT_HDFS $DEGREE $MAX_OUT_EDGES $NUM_PARTITION $STORAGE_LEVEL $DISABLE_KRYO $MODEL
END_TIME=`timestamp`

gen_report ${START_TIME} ${END_TIME} ${SIZE}
show_bannar finish
leave_bench
3 changes: 1 addition & 2 deletions conf/hibench.conf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,13 +43,13 @@ hibench.hive.release hive-0.12.0-bin
hibench.hivebench.template.dir ${hibench.dependency.dir}/hivebench/hive_template
hibench.hive.dir.name.input ${hibench.workload.dir.name.input}
hibench.hive.dir.name.ouput ${hibench.workload.dir.name.output}

hibench.bayes.dir.name.input ${hibench.workload.dir.name.input}
hibench.bayes.dir.name.output ${hibench.workload.dir.name.output}
hibench.pagerank.dir.name.input ${hibench.workload.dir.name.input}
hibench.pagerank.dir.name.output ${hibench.workload.dir.name.output}
hibench.pagerank.pegasus.dir ${hibench.dependency.dir}/pegasus/target/pegasus-2.0-SNAPSHOT.jar


hibench.mahout.release.apache mahout-distribution-0.9
hibench.mahout.release.hdp mahout-distribution-0.9
hibench.mahout.release.cdh5 mahout-0.9-cdh5.1.0
Expand All @@ -66,4 +66,3 @@ hibench.nutch.home ${hibench.dependency.dir}/nutchindexing/target/${hibench.nut
hibench.dfsioe.dir.name.input ${hibench.workload.dir.name.input}
hibench.dfsioe.dir.name.output ${hibench.workload.dir.name.output}

hibench.nweight.model_path ${hibench.dependency.dir}/sparkbench/src/main/scala/com/intel/sparkbench/nweight/model/user-features
38 changes: 38 additions & 0 deletions conf/workloads/graph/nweight.conf
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,38 @@
hibench.nweight.tiny.edges 100000
hibench.nweight.tiny.degree 3
hibench.nweight.tiny.max_out_edges 30
hibench.nweight.small.edges 1000000
hibench.nweight.small.degree 3
hibench.nweight.small.max_out_edges 30
hibench.nweight.large.edges 10000000
hibench.nweight.large.degree 3
hibench.nweight.large.max_out_edges 30
hibench.nweight.huge.edges 100000000
hibench.nweight.huge.degree 3
hibench.nweight.huge.max_out_edges 30
hibench.nweight.gigantic.edges 425000000
hibench.nweight.gigantic.degree 3
hibench.nweight.gigantic.max_out_edges 30
hibench.nweight.bigdata.edges 4250000000
hibench.nweight.bigdata.degree 3
hibench.nweight.bigdata.max_out_edges 30

hibench.nweight.edges ${hibench.nweight.${hibench.scale.profile}.edges}
hibench.nweight.degree ${hibench.nweight.${hibench.scale.profile}.degree}
hibench.nweight.max_out_edges ${hibench.nweight.${hibench.scale.profile}.max_out_edges}

hibench.nweight.partitions ${hibench.default.map.parallelism}
# storageLevel for the RDDs 0: off-heap 1: disk_only 3: memory_only 5: memory_ser 7: memory_and_disk 9: memory_and_disk_ser
hibench.nweight.storage_level 7
hibench.nweight.disable_kryo false
# run nweight in graphx or pregel
hibench.nweight.model graphx

hibench.nweight.model_path ${hibench.home}/sparkbench/graph/src/main/resources/nweight-user-features

hibench.sparkbench.jar ${hibench.home}/sparkbench/graph/target/sparkbench-graph-6.0-SNAPSHOT-${hibench.spark.version}-jar-with-dependencies.jar

# export for shell script
hibench.workload.input ${hibench.hdfs.data.dir}/NWeight/Input
hibench.workload.output ${hibench.hdfs.data.dir}/NWeight/Output
hibench.workload.edges ${hibench.nweight.edges}
229 changes: 229 additions & 0 deletions sparkbench/graph/pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,4 +13,233 @@
<packaging>jar</packaging>
<version>6.0-SNAPSHOT</version>
<name>sparkbench-graph</name>


<dependencies>
<dependency>
<groupId>com.intel.hibench.sparkbench</groupId>
<artifactId>sparkbench-common</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
<version>${scala.version}</version>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>${junit.version}</version>
<scope>test</scope>
</dependency>

<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_${scala.binary.version}</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-yarn_${scala.binary.version}</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_${scala.binary.version}</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-mllib_${scala.binary.version}</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-hive_${scala.binary.version}</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-graphx_${scala.binary.version}</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>com.github.scopt</groupId>
<artifactId>scopt_2.10</artifactId>
<version>${scopt.version}</version>
</dependency>
<dependency>
<groupId>log4j</groupId>
<artifactId>log4j</artifactId>
<version>${log4j.version}</version>
<scope>compile</scope>
</dependency>
<dependency>
<groupId>org.apache.mahout</groupId>
<artifactId>mahout-core</artifactId>
<version>${mahout.version}</version>
<exclusions>
<exclusion>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-core</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.mahout</groupId>
<artifactId>mahout-math</artifactId>
<version>${mahout.version}</version>
</dependency>
<dependency>
<groupId>it.unimi.dsi</groupId>
<artifactId>fastutil</artifactId>
<version>${fastutil.version}</version>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>${maven-compiler-plugin.version}</version>
</plugin>
<plugin>
<groupId>net.alchim31.maven</groupId>
<artifactId>scala-maven-plugin</artifactId>
<configuration>
<scalaCompatVersion>${scala.binary.version}</scalaCompatVersion>
<scalaVersion>${scala.version}</scalaVersion>
</configuration>
<executions>
<execution>
<id>scala-compile-first</id>
<phase>process-resources</phase>
<goals>
<goal>add-source</goal>
<goal>compile</goal>
</goals>
</execution>
<execution>
<id>scala-test-compile</id>
<phase>process-test-resources</phase>
<goals>
<goal>testCompile</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-jar-plugin</artifactId>
<executions>
<execution>
<id>default-jar</id>
<phase>package</phase>
<goals>
<goal>jar</goal>
</goals>
<configuration>
<finalName>${project.artifactId}-${project.version}-spark${spark.bin.version}</finalName>
</configuration>
</execution>
</executions>
</plugin>

<plugin>
<artifactId>maven-assembly-plugin</artifactId>
<version>${maven-assembly-plugin.version}</version>
<configuration>
<finalName>${project.build.finalName}-spark${spark.bin.version}</finalName>
<descriptorRefs>
<descriptorRef>jar-with-dependencies</descriptorRef>
</descriptorRefs>
</configuration>
<executions>
<execution>
<id>make-assembly</id>
<phase>package</phase>
<goals>
<goal>single</goal>
</goals>
</execution>
</executions>
</plugin>

</plugins>
</build>
<profiles>
<profile>
<id>spark1.6</id>
<properties>
<spark.version>1.6.0</spark.version>
<spark.bin.version>1.6</spark.bin.version>
</properties>
<activation>
<property>
<name>spark</name>
<value>1.6</value>
</property>
</activation>
</profile>

<profile>
<id>spark2.0</id>
<properties>
<spark.version>2.0.0</spark.version>
<spark.bin.version>2.0</spark.bin.version>
</properties>
<activation>
<property>
<name>spark</name>
<value>2.0</value>
</property>
</activation>
</profile>

<profile>
<id>defaultspark</id>
<properties>
<spark.version>1.6.0</spark.version>
<spark.bin.version>1.6</spark.bin.version>
</properties>
<activation>
<property>
<name>!spark</name>
</property>
</activation>
</profile>

<profile>
<id>MR2</id>
<dependencies>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-examples</artifactId>
<version>${hadoop.mr2.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>${hadoop.mr2.version}</version>
<exclusions>
<exclusion>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
</exclusion>
</exclusions>
</dependency>
</dependencies>
<activation>
<property><name>!MR1</name></property>
</activation>
</profile>

</profiles>
</project>

0 ...el/sparkbench/nweight/model/user-features → .../src/main/resources/nweight-user-features
View file
Open in desktop
File renamed without changes.
25 changes: 18 additions & 7 deletions ...com/intel/sparkbench/nweight/Driver.scala → ...nch/sparkbench/graph/nweight/Driver.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,15 +1,26 @@
package com.intel.sparkbench.nweight
/*
* 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 com.intel.hibench.sparkbench.graph.nweight

import org.apache.spark.{SparkContext, SparkConf}
import org.apache.spark.SparkContext._
import org.apache.spark.rdd.RDD
import org.apache.spark.storage.StorageLevel
import org.apache.spark.scheduler.{JobLogger, StatsReportListener}

import com.esotericsoftware.kryo.{Kryo, Serializer => KSerializer}
import com.esotericsoftware.kryo.io.{Input => KryoInput, Output => KryoOutput}
import com.esotericsoftware.kryo.serializers.{JavaSerializer => KryoJavaSerializer}

/**
* Compute NWeight for Graph G(V, E) as defined below
* Weight(1)(u, v) = edge(u, v)
Expand Down
Loading