diff --git a/pregelix/pregelix-example/data/webmap/webmap_link.txt b/pregelix/pregelix-example/data/webmap/webmap_link.txt
new file mode 100644
index 0000000..2bd5a0e
--- /dev/null
+++ b/pregelix/pregelix-example/data/webmap/webmap_link.txt
@@ -0,0 +1,20 @@
+0 1
+1 1 2
+2 1 2 3
+3 1 2 3 4
+4 1 2 3 4 5
+5 1 2 3 4 5 6
+6 1 2 3 4 5 6 7
+7 1 2 3 4 5 6 7 8
+8 1 2 3 4 5 6 7 8 9
+9 1 2 3 4 5 6 7 8 9 10
+10 11
+11 11 12
+12 11 12 13
+13 11 12 13 14
+14 11 12 13 14 15
+15 11 12 13 14 15 16
+16 11 12 13 14 15 16 17
+17 11 12 13 14 15 16 17 18
+18 11 12 13 14 15 16 17 18 19
+19 0 11 12 13 14 15 16 17 18 19
diff --git a/pregelix/pregelix-example/data/webmapcomplex/webmap_link.txt b/pregelix/pregelix-example/data/webmapcomplex/webmap_link.txt
new file mode 100644
index 0000000..6640a62
--- /dev/null
+++ b/pregelix/pregelix-example/data/webmapcomplex/webmap_link.txt
@@ -0,0 +1,23 @@
+0 1 50
+1 1 2
+2 1 2 3
+3 1 2 3 4
+4 1 2 3 4 5
+5 1 2 3 4 5 6
+6 1 2 3 4 5 6 7
+7 1 2 3 4 5 6 7 8
+8 1 2 3 4 5 6 7 8 9
+9 1 2 3 4 5 6 7 8 9 10
+10 11 99
+11 11 12 101
+12 11 12 13
+13 11 12 13 14
+14 11 12 13 14 15
+15 11 12 13 14 15 16
+16 11 12 13 14 15 16 17
+17 11 12 13 14 15 16 17 18
+18 11 12 13 14 15 16 17 18 19
+19 0 11 12 13 14 15 16 17 18 19
+21 22 23 24
+25
+27
\ No newline at end of file
diff --git a/pregelix/pregelix-example/pom.xml b/pregelix/pregelix-example/pom.xml
new file mode 100644
index 0000000..a53fb8a
--- /dev/null
+++ b/pregelix/pregelix-example/pom.xml
@@ -0,0 +1,129 @@
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+	xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
+	<modelVersion>4.0.0</modelVersion>
+	<groupId>edu.uci.ics.hyracks.pregelix</groupId>
+	<artifactId>pregelix-example</artifactId>
+	<packaging>jar</packaging>
+	<name>pregelix-example</name>
+
+	<parent>
+		<groupId>edu.uci.ics.pregelix</groupId>
+		<artifactId>pregelix</artifactId>
+		<version>0.0.1-SNAPSHOT</version>
+	</parent>
+
+	<build>
+		<plugins>
+			<plugin>
+				<groupId>org.apache.maven.plugins</groupId>
+				<artifactId>maven-compiler-plugin</artifactId>
+				<version>2.0.2</version>
+				<configuration>
+					<source>1.6</source>
+					<target>1.6</target>
+				</configuration>
+			</plugin>
+			<plugin>
+				<groupId>org.apache.maven.plugins</groupId>
+				<artifactId>maven-assembly-plugin</artifactId>
+				<version>2.2</version>
+				<configuration>
+					<outputDirectory>target</outputDirectory>
+					<descriptorRefs>
+						<descriptorRef>jar-with-dependencies</descriptorRef>
+					</descriptorRefs>
+				</configuration>
+			</plugin>
+			<plugin>
+				<groupId>org.apache.maven.plugins</groupId>
+				<artifactId>maven-surefire-plugin</artifactId>
+				<version>2.6</version>
+				<configuration>
+					<systemProperties>
+						<property>
+							<name>prop.jarLocation</name>
+							<value>target/pregelix-example-${project.version}-jar-with-dependencies.jar</value>
+						</property>
+					</systemProperties>
+				</configuration>
+			</plugin>
+			<plugin>
+				<groupId>org.codehaus.mojo</groupId>
+				<artifactId>appassembler-maven-plugin</artifactId>
+				<executions>
+					<execution>
+						<configuration>
+							<programs>
+								<program>
+									<mainClass>edu.uci.ics.pregelix.example.Client</mainClass>
+									<name>pregelix</name>
+								</program>
+							</programs>
+							<repositoryLayout>flat</repositoryLayout>
+							<repositoryName>lib</repositoryName>
+						</configuration>
+						<phase>package</phase>
+						<goals>
+							<goal>assemble</goal>
+						</goals>
+					</execution>
+				</executions>
+			</plugin>
+			<plugin>
+				<groupId>org.apache.maven.plugins</groupId>
+				<artifactId>maven-surefire-plugin</artifactId>
+				<version>2.7.2</version>
+				<configuration>
+					<forkMode>pertest</forkMode>
+					<argLine>-enableassertions -Xmx2047m -Dfile.encoding=UTF-8
+						-Djava.util.logging.config.file=src/test/resources/logging.properties</argLine>
+					<includes>
+						<include>**/*TestSuite.java</include>
+						<include>**/*Test.java</include>
+					</includes>
+				</configuration>
+			</plugin>
+			<plugin>
+				<artifactId>maven-clean-plugin</artifactId>
+				<configuration>
+					<filesets>
+						<fileset>
+							<directory>.</directory>
+							<includes>
+								<include>teststore*</include>
+								<include>edu*</include>
+								<include>actual*</include>
+								<include>build*</include>
+								<include>expect*</include>
+								<include>ClusterController*</include>
+								<include>edu.uci.*</include>
+							</includes>
+						</fileset>
+					</filesets>
+				</configuration>
+			</plugin>
+		</plugins>
+	</build>
+
+	<dependencies>
+		<dependency>
+			<groupId>edu.uci.ics.pregelix</groupId>
+			<artifactId>pregelix-core</artifactId>
+			<version>0.0.1-SNAPSHOT</version>
+			<type>jar</type>
+			<scope>compile</scope>
+		</dependency>
+		<dependency>
+			<groupId>junit</groupId>
+			<artifactId>junit</artifactId>
+			<version>4.8.1</version>
+			<scope>test</scope>
+		</dependency>
+		<dependency>
+			<groupId>com.google.collections</groupId>
+			<artifactId>google-collections</artifactId>
+			<version>1.0</version>
+		</dependency>
+	</dependencies>
+
+</project>
diff --git a/pregelix/pregelix-example/src/main/assembly/binary-assembly.xml b/pregelix/pregelix-example/src/main/assembly/binary-assembly.xml
new file mode 100755
index 0000000..0500499
--- /dev/null
+++ b/pregelix/pregelix-example/src/main/assembly/binary-assembly.xml
@@ -0,0 +1,19 @@
+<assembly>
+  <id>binary-assembly</id>
+  <formats>
+    <format>zip</format>
+    <format>dir</format>
+  </formats>
+  <includeBaseDirectory>false</includeBaseDirectory>
+  <fileSets>
+    <fileSet>
+      <directory>target/appassembler/bin</directory>
+      <outputDirectory>bin</outputDirectory>
+      <fileMode>0755</fileMode>
+    </fileSet>
+    <fileSet>
+      <directory>target/appassembler/lib</directory>
+      <outputDirectory>lib</outputDirectory>
+    </fileSet>
+  </fileSets>
+</assembly>
diff --git a/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/ConnectedComponentsVertex.java b/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/ConnectedComponentsVertex.java
new file mode 100644
index 0000000..55d262b
--- /dev/null
+++ b/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/ConnectedComponentsVertex.java
@@ -0,0 +1,141 @@
+/*
+ * Copyright 2009-2010 by The Regents of the University of California
+ * Licensed 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 from
+ *
+ *     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 edu.uci.ics.pregelix.example;
+
+import java.io.IOException;
+import java.util.Iterator;
+
+import org.apache.hadoop.io.FloatWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapreduce.RecordWriter;
+import org.apache.hadoop.mapreduce.TaskAttemptContext;
+
+import edu.uci.ics.pregelix.api.graph.Edge;
+import edu.uci.ics.pregelix.api.graph.Vertex;
+import edu.uci.ics.pregelix.api.graph.VertexCombiner;
+import edu.uci.ics.pregelix.api.io.VertexWriter;
+import edu.uci.ics.pregelix.api.io.text.TextVertexOutputFormat;
+import edu.uci.ics.pregelix.api.io.text.TextVertexOutputFormat.TextVertexWriter;
+import edu.uci.ics.pregelix.api.job.PregelixJob;
+import edu.uci.ics.pregelix.example.PageRankVertex.SimplePageRankVertexOutputFormat;
+import edu.uci.ics.pregelix.example.client.Client;
+import edu.uci.ics.pregelix.example.inputformat.TextPageRankInputFormat;
+import edu.uci.ics.pregelix.example.io.VLongWritable;
+
+/**
+ * Demonstrates the basic Pregel connected components implementation.
+ */
+public class ConnectedComponentsVertex extends Vertex<VLongWritable, VLongWritable, FloatWritable, VLongWritable> {
+    /**
+     * Test whether combiner is called to get the minimum ID in the cluster
+     */
+    public static class SimpleMinCombiner implements VertexCombiner<VLongWritable, VLongWritable> {
+        private long min = Long.MAX_VALUE;
+        private VLongWritable agg = new VLongWritable();
+
+        @Override
+        public void step(VLongWritable vertexIndex, VLongWritable msg) throws IOException {
+            long value = msg.get();
+            if (min > value)
+                min = value;
+        }
+
+        @Override
+        public void init() {
+            min = Long.MAX_VALUE;
+        }
+
+        @Override
+        public VLongWritable finish() {
+            agg.set(min);
+            return agg;
+        }
+    }
+
+    private VLongWritable outputValue = new VLongWritable();
+    private VLongWritable vertexValue = new VLongWritable();
+    private long minID;
+
+    @Override
+    public void compute(Iterator<VLongWritable> msgIterator) {
+        if (getSuperstep() == 1) {
+            minID = getVertexId().get();
+            vertexValue.set(minID);
+            setVertexValue(vertexValue);
+            sendOutMsgs();
+        } else {
+            minID = getVertexId().get();
+            while (msgIterator.hasNext()) {
+                minID = Math.min(minID, msgIterator.next().get());
+            }
+            if (minID < getVertexValue().get()) {
+                vertexValue.set(minID);
+                setVertexValue(vertexValue);
+                sendOutMsgs();
+            }
+        }
+        voteToHalt();
+    }
+
+    private void sendOutMsgs() {
+        for (Edge<VLongWritable, FloatWritable> edge : getEdges()) {
+            outputValue.set(minID);
+            sendMsg(edge.getDestVertexId(), outputValue);
+        }
+    }
+
+    public static void main(String[] args) throws Exception {
+        PregelixJob job = new PregelixJob(ConnectedComponentsVertex.class.getSimpleName());
+        job.setVertexClass(ConnectedComponentsVertex.class);
+        job.setVertexInputFormatClass(TextPageRankInputFormat.class);
+        job.setVertexOutputFormatClass(SimplePageRankVertexOutputFormat.class);
+        job.setVertexCombinerClass(ConnectedComponentsVertex.SimpleMinCombiner.class);
+        Client.run(args, job);
+    }
+
+    /**
+     * Simple VertexWriter that support
+     */
+    public static class SimpleConnectedComponentsVertexWriter extends
+            TextVertexWriter<VLongWritable, VLongWritable, FloatWritable> {
+        public SimpleConnectedComponentsVertexWriter(RecordWriter<Text, Text> lineRecordWriter) {
+            super(lineRecordWriter);
+        }
+
+        @Override
+        public void writeVertex(Vertex<VLongWritable, VLongWritable, FloatWritable, ?> vertex) throws IOException,
+                InterruptedException {
+            getRecordWriter().write(new Text(vertex.getVertexId().toString()),
+                    new Text(vertex.getVertexValue().toString()));
+        }
+    }
+
+    /**
+     * output format for connected components
+     */
+    public static class SimpleConnectedComponentsVertexOutputFormat extends
+            TextVertexOutputFormat<VLongWritable, VLongWritable, FloatWritable> {
+
+        @Override
+        public VertexWriter<VLongWritable, VLongWritable, FloatWritable> createVertexWriter(TaskAttemptContext context)
+                throws IOException, InterruptedException {
+            RecordWriter<Text, Text> recordWriter = textOutputFormat.getRecordWriter(context);
+            return new SimpleConnectedComponentsVertexWriter(recordWriter);
+        }
+
+    }
+
+}
diff --git a/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/PageRankVertex.java b/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/PageRankVertex.java
new file mode 100644
index 0000000..ceb30c3
--- /dev/null
+++ b/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/PageRankVertex.java
@@ -0,0 +1,199 @@
+/*
+ * Licensed to Yahoo! under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  Yahoo! 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 edu.uci.ics.pregelix.example;
+
+import java.io.IOException;
+import java.util.Iterator;
+import java.util.Map;
+import java.util.logging.Level;
+import java.util.logging.Logger;
+
+import org.apache.hadoop.io.DoubleWritable;
+import org.apache.hadoop.io.FloatWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapreduce.InputSplit;
+import org.apache.hadoop.mapreduce.RecordWriter;
+import org.apache.hadoop.mapreduce.TaskAttemptContext;
+
+import com.google.common.collect.Maps;
+
+import edu.uci.ics.pregelix.api.graph.Vertex;
+import edu.uci.ics.pregelix.api.graph.VertexCombiner;
+import edu.uci.ics.pregelix.api.io.VertexReader;
+import edu.uci.ics.pregelix.api.io.VertexWriter;
+import edu.uci.ics.pregelix.api.io.generated.GeneratedVertexInputFormat;
+import edu.uci.ics.pregelix.api.io.generated.GeneratedVertexReader;
+import edu.uci.ics.pregelix.api.io.text.TextVertexOutputFormat;
+import edu.uci.ics.pregelix.api.io.text.TextVertexOutputFormat.TextVertexWriter;
+import edu.uci.ics.pregelix.api.job.PregelixJob;
+import edu.uci.ics.pregelix.api.util.BspUtils;
+import edu.uci.ics.pregelix.example.client.Client;
+import edu.uci.ics.pregelix.example.inputformat.TextPageRankInputFormat;
+import edu.uci.ics.pregelix.example.io.VLongWritable;
+
+/**
+ * Demonstrates the basic Pregel PageRank implementation.
+ */
+public class PageRankVertex extends Vertex<VLongWritable, DoubleWritable, FloatWritable, DoubleWritable> {
+
+    public static final String ITERATIONS = "HyracksPageRankVertex.iteration";
+    private DoubleWritable outputValue = new DoubleWritable();
+    private DoubleWritable vertexValue = new DoubleWritable();
+
+    /**
+     * Test whether combiner is called by summing up the messages.
+     */
+    public static class SimpleSumCombiner implements VertexCombiner<VLongWritable, DoubleWritable> {
+        private double sum = 0.0;
+        private DoubleWritable agg = new DoubleWritable();
+
+        @Override
+        public void step(VLongWritable vertexIndex, DoubleWritable msg) throws IOException {
+            sum += msg.get();
+        }
+
+        @Override
+        public void init() {
+            sum = 0.0;
+        }
+
+        @Override
+        public DoubleWritable finish() {
+            agg.set(sum);
+            return agg;
+        }
+    }
+
+    @Override
+    public void compute(Iterator<DoubleWritable> msgIterator) {
+        int maxIteration = this.getContext().getConfiguration().getInt(ITERATIONS, 10);
+        if (getSuperstep() == 1) {
+            vertexValue.set(1.0 / getNumVertices());
+            setVertexValue(vertexValue);
+        }
+        if (getSuperstep() >= 2 && getSuperstep() <= maxIteration) {
+            double sum = 0;
+            while (msgIterator.hasNext()) {
+                sum += msgIterator.next().get();
+            }
+            vertexValue.set((0.15 / getNumVertices()) + 0.85 * sum);
+            setVertexValue(vertexValue);
+        }
+
+        if (getSuperstep() >= 1 && getSuperstep() < maxIteration) {
+            long edges = getNumOutEdges();
+            outputValue.set(getVertexValue().get() / edges);
+            sendMsgToAllEdges(outputValue);
+        } else {
+            voteToHalt();
+        }
+    }
+
+    /**
+     * Simple VertexReader that supports {@link SimplePageRankVertex}
+     */
+    public static class SimplePageRankVertexReader extends
+            GeneratedVertexReader<VLongWritable, DoubleWritable, FloatWritable, DoubleWritable> {
+        /** Class logger */
+        private static final Logger LOG = Logger.getLogger(SimplePageRankVertexReader.class.getName());
+        private Map<VLongWritable, FloatWritable> edges = Maps.newHashMap();
+
+        public SimplePageRankVertexReader() {
+            super();
+        }
+
+        @Override
+        public boolean nextVertex() {
+            return totalRecords > recordsRead;
+        }
+
+        @Override
+        public Vertex<VLongWritable, DoubleWritable, FloatWritable, DoubleWritable> getCurrentVertex()
+                throws IOException {
+            Vertex<VLongWritable, DoubleWritable, FloatWritable, DoubleWritable> vertex = BspUtils
+                    .createVertex(configuration);
+
+            VLongWritable vertexId = new VLongWritable((inputSplit.getSplitIndex() * totalRecords) + recordsRead);
+            DoubleWritable vertexValue = new DoubleWritable(vertexId.get() * 10d);
+            long destVertexId = (vertexId.get() + 1) % (inputSplit.getNumSplits() * totalRecords);
+            float edgeValue = vertexId.get() * 100f;
+            edges.put(new VLongWritable(destVertexId), new FloatWritable(edgeValue));
+            vertex.initialize(vertexId, vertexValue, edges, null);
+            ++recordsRead;
+            if (LOG.getLevel() == Level.FINE) {
+                LOG.fine("next: Return vertexId=" + vertex.getVertexId().get() + ", vertexValue="
+                        + vertex.getVertexValue() + ", destinationId=" + destVertexId + ", edgeValue=" + edgeValue);
+            }
+            return vertex;
+        }
+    }
+
+    /**
+     * Simple VertexInputFormat that supports {@link SimplePageRankVertex}
+     */
+    public static class SimplePageRankVertexInputFormat extends
+            GeneratedVertexInputFormat<VLongWritable, DoubleWritable, FloatWritable, DoubleWritable> {
+        @Override
+        public VertexReader<VLongWritable, DoubleWritable, FloatWritable, DoubleWritable> createVertexReader(
+                InputSplit split, TaskAttemptContext context) throws IOException {
+            return new SimplePageRankVertexReader();
+        }
+    }
+
+    /**
+     * Simple VertexWriter that supports {@link SimplePageRankVertex}
+     */
+    public static class SimplePageRankVertexWriter extends
+            TextVertexWriter<VLongWritable, DoubleWritable, FloatWritable> {
+        public SimplePageRankVertexWriter(RecordWriter<Text, Text> lineRecordWriter) {
+            super(lineRecordWriter);
+        }
+
+        @Override
+        public void writeVertex(Vertex<VLongWritable, DoubleWritable, FloatWritable, ?> vertex) throws IOException,
+                InterruptedException {
+            getRecordWriter().write(new Text(vertex.getVertexId().toString()),
+                    new Text(vertex.getVertexValue().toString()));
+        }
+    }
+
+    /**
+     * Simple VertexOutputFormat that supports {@link SimplePageRankVertex}
+     */
+    public static class SimplePageRankVertexOutputFormat extends
+            TextVertexOutputFormat<VLongWritable, DoubleWritable, FloatWritable> {
+
+        @Override
+        public VertexWriter<VLongWritable, DoubleWritable, FloatWritable> createVertexWriter(TaskAttemptContext context)
+                throws IOException, InterruptedException {
+            RecordWriter<Text, Text> recordWriter = textOutputFormat.getRecordWriter(context);
+            return new SimplePageRankVertexWriter(recordWriter);
+        }
+    }
+
+    public static void main(String[] args) throws Exception {
+        PregelixJob job = new PregelixJob(PageRankVertex.class.getSimpleName());
+        job.setVertexClass(PageRankVertex.class);
+        job.setVertexInputFormatClass(TextPageRankInputFormat.class);
+        job.setVertexOutputFormatClass(SimplePageRankVertexOutputFormat.class);
+        job.setVertexCombinerClass(PageRankVertex.SimpleSumCombiner.class);
+        Client.run(args, job);
+    }
+
+}
diff --git a/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/ShortestPathsVertex.java b/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/ShortestPathsVertex.java
new file mode 100644
index 0000000..69f0bdc
--- /dev/null
+++ b/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/ShortestPathsVertex.java
@@ -0,0 +1,124 @@
+/*
+ * Licensed to Yahoo! under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  Yahoo! 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 edu.uci.ics.pregelix.example;
+
+import java.io.IOException;
+import java.util.Iterator;
+import java.util.logging.Level;
+import java.util.logging.Logger;
+
+import org.apache.hadoop.io.DoubleWritable;
+import org.apache.hadoop.io.FloatWritable;
+
+import edu.uci.ics.pregelix.api.graph.Edge;
+import edu.uci.ics.pregelix.api.graph.Vertex;
+import edu.uci.ics.pregelix.api.graph.VertexCombiner;
+import edu.uci.ics.pregelix.api.job.PregelixJob;
+import edu.uci.ics.pregelix.example.PageRankVertex.SimplePageRankVertexOutputFormat;
+import edu.uci.ics.pregelix.example.client.Client;
+import edu.uci.ics.pregelix.example.inputformat.TextShortestPathsInputFormat;
+import edu.uci.ics.pregelix.example.io.VLongWritable;
+
+/**
+ * Demonstrates the basic Pregel shortest paths implementation.
+ */
+public class ShortestPathsVertex extends Vertex<VLongWritable, DoubleWritable, FloatWritable, DoubleWritable> {
+    /**
+     * Test whether combiner is called by summing up the messages.
+     */
+    public static class SimpleMinCombiner implements VertexCombiner<VLongWritable, DoubleWritable> {
+        private double min = Double.MAX_VALUE;
+        private DoubleWritable agg = new DoubleWritable();
+
+        @Override
+        public void step(VLongWritable vertexIndex, DoubleWritable msg) throws IOException {
+            double value = msg.get();
+            if (min > value)
+                min = value;
+        }
+
+        @Override
+        public void init() {
+            min = Double.MAX_VALUE;
+        }
+
+        @Override
+        public DoubleWritable finish() {
+            agg.set(min);
+            return agg;
+        }
+    }
+
+    private DoubleWritable outputValue = new DoubleWritable();
+    private DoubleWritable vertexValue = new DoubleWritable();
+    /** Class logger */
+    private static final Logger LOG = Logger.getLogger(ShortestPathsVertex.class.getName());
+    /** The shortest paths id */
+    public static final String SOURCE_ID = "SimpleShortestPathsVertex.sourceId";
+    /** Default shortest paths id */
+    public static final long SOURCE_ID_DEFAULT = 1;
+
+    /**
+     * Is this vertex the source id?
+     * 
+     * @return True if the source id
+     */
+    private boolean isSource() {
+        return (getVertexId().get() == getContext().getConfiguration().getLong(SOURCE_ID, SOURCE_ID_DEFAULT));
+    }
+
+    @Override
+    public void compute(Iterator<DoubleWritable> msgIterator) {
+        if (getSuperstep() == 1) {
+            vertexValue.set(Double.MAX_VALUE);
+            setVertexValue(vertexValue);
+        }
+        double minDist = isSource() ? 0d : Double.MAX_VALUE;
+        while (msgIterator.hasNext()) {
+            minDist = Math.min(minDist, msgIterator.next().get());
+        }
+        if (LOG.getLevel() == Level.FINE) {
+            LOG.fine("Vertex " + getVertexId() + " got minDist = " + minDist + " vertex value = " + getVertexValue());
+        }
+        if (minDist < getVertexValue().get()) {
+            vertexValue.set(minDist);
+            setVertexValue(vertexValue);
+            for (Edge<VLongWritable, FloatWritable> edge : getEdges()) {
+                if (LOG.getLevel() == Level.FINE) {
+                    LOG.fine("Vertex " + getVertexId() + " sent to " + edge.getDestVertexId() + " = "
+                            + (minDist + edge.getEdgeValue().get()));
+                }
+                outputValue.set(minDist + edge.getEdgeValue().get());
+                sendMsg(edge.getDestVertexId(), outputValue);
+            }
+        }
+        voteToHalt();
+    }
+
+    public static void main(String[] args) throws Exception {
+        PregelixJob job = new PregelixJob(ShortestPathsVertex.class.getSimpleName());
+        job.setVertexClass(ShortestPathsVertex.class);
+        job.setVertexInputFormatClass(TextShortestPathsInputFormat.class);
+        job.setVertexOutputFormatClass(SimplePageRankVertexOutputFormat.class);
+        job.setVertexCombinerClass(ShortestPathsVertex.SimpleMinCombiner.class);
+        job.getConfiguration().setLong(SOURCE_ID, 0);
+        Client.run(args, job);
+    }
+
+}
diff --git a/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/VertexAggregator.java b/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/VertexAggregator.java
new file mode 100644
index 0000000..4f5f10f
--- /dev/null
+++ b/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/VertexAggregator.java
@@ -0,0 +1,77 @@
+package edu.uci.ics.pregelix.example;
+
+import java.io.IOException;
+import java.util.Iterator;
+
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.io.LongWritable;
+import org.apache.hadoop.io.NullWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapred.FileInputFormat;
+import org.apache.hadoop.mapred.FileOutputFormat;
+import org.apache.hadoop.mapred.JobClient;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.MapReduceBase;
+import org.apache.hadoop.mapred.Mapper;
+import org.apache.hadoop.mapred.OutputCollector;
+import org.apache.hadoop.mapred.Reducer;
+import org.apache.hadoop.mapred.Reporter;
+import org.apache.hadoop.mapred.TextInputFormat;
+
+@SuppressWarnings("deprecation")
+public class VertexAggregator {
+
+    public static class MapRecordOnly extends MapReduceBase implements
+            Mapper<LongWritable, Text, NullWritable, LongWritable> {
+        private final NullWritable nullValue = NullWritable.get();
+        private final LongWritable count = new LongWritable(1);
+
+        public void map(LongWritable id, Text inputValue, OutputCollector<NullWritable, LongWritable> output,
+                Reporter reporter) throws IOException {
+            output.collect(nullValue, count);
+        }
+    }
+
+    public static class CombineRecordOnly extends MapReduceBase implements
+            Reducer<NullWritable, LongWritable, NullWritable, LongWritable> {
+        private final NullWritable nullValue = NullWritable.get();
+
+        public void reduce(NullWritable inputKey, Iterator<LongWritable> inputValue,
+                OutputCollector<NullWritable, LongWritable> output, Reporter reporter) throws IOException {
+            long count = 0;
+            while (inputValue.hasNext())
+                count += inputValue.next().get();
+            output.collect(nullValue, new LongWritable(count));
+        }
+    }
+
+    public static class ReduceRecordOnly extends MapReduceBase implements
+            Reducer<NullWritable, LongWritable, NullWritable, Text> {
+        private final NullWritable nullValue = NullWritable.get();
+
+        public void reduce(NullWritable inputKey, Iterator<LongWritable> inputValue,
+                OutputCollector<NullWritable, Text> output, Reporter reporter) throws IOException {
+            long count = 0;
+            while (inputValue.hasNext())
+                count += inputValue.next().get();
+            output.collect(nullValue, new Text(Long.toString(count)));
+        }
+    }
+
+    public static void main(String[] args) throws IOException {
+        JobConf job = new JobConf(VertexAggregator.class);
+
+        job.setJobName(VertexAggregator.class.getSimpleName());
+        job.setMapperClass(MapRecordOnly.class);
+        job.setCombinerClass(CombineRecordOnly.class);
+        job.setReducerClass(ReduceRecordOnly.class);
+        job.setMapOutputKeyClass(NullWritable.class);
+        job.setMapOutputValueClass(LongWritable.class);
+
+        job.setInputFormat(TextInputFormat.class);
+        FileInputFormat.setInputPaths(job, args[0]);
+        FileOutputFormat.setOutputPath(job, new Path(args[1]));
+        job.setNumReduceTasks(Integer.parseInt(args[2]));
+        JobClient.runJob(job);
+    }
+}
diff --git a/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/VertexSorter.java b/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/VertexSorter.java
new file mode 100644
index 0000000..695657a
--- /dev/null
+++ b/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/VertexSorter.java
@@ -0,0 +1,61 @@
+package edu.uci.ics.pregelix.example;
+
+import java.io.IOException;
+import java.util.Iterator;
+
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.io.LongWritable;
+import org.apache.hadoop.io.NullWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapred.FileInputFormat;
+import org.apache.hadoop.mapred.FileOutputFormat;
+import org.apache.hadoop.mapred.JobClient;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.MapReduceBase;
+import org.apache.hadoop.mapred.Mapper;
+import org.apache.hadoop.mapred.OutputCollector;
+import org.apache.hadoop.mapred.Reducer;
+import org.apache.hadoop.mapred.Reporter;
+import org.apache.hadoop.mapred.TextInputFormat;
+
+@SuppressWarnings("deprecation")
+public class VertexSorter {
+    public static class MapRecordOnly extends MapReduceBase implements Mapper<LongWritable, Text, LongWritable, Text> {
+        private static String separator = " ";
+
+        public void map(LongWritable id, Text inputValue, OutputCollector<LongWritable, Text> output, Reporter reporter)
+                throws IOException {
+            String[] fields = inputValue.toString().split(separator);
+            LongWritable vertexId = new LongWritable(Long.parseLong(fields[0]));
+            output.collect(vertexId, inputValue);
+        }
+    }
+
+    public static class ReduceRecordOnly extends MapReduceBase implements
+            Reducer<LongWritable, Text, NullWritable, Text> {
+
+        NullWritable key = NullWritable.get();
+
+        public void reduce(LongWritable inputKey, Iterator<Text> inputValue,
+                OutputCollector<NullWritable, Text> output, Reporter reporter) throws IOException {
+            while (inputValue.hasNext())
+                output.collect(key, inputValue.next());
+        }
+    }
+
+    public static void main(String[] args) throws IOException {
+        JobConf job = new JobConf(VertexSorter.class);
+
+        job.setJobName(VertexSorter.class.getSimpleName());
+        job.setMapperClass(MapRecordOnly.class);
+        job.setReducerClass(ReduceRecordOnly.class);
+        job.setMapOutputKeyClass(LongWritable.class);
+        job.setMapOutputValueClass(Text.class);
+
+        job.setInputFormat(TextInputFormat.class);
+        FileInputFormat.setInputPaths(job, args[0]);
+        FileOutputFormat.setOutputPath(job, new Path(args[1]));
+        job.setNumReduceTasks(Integer.parseInt(args[2]));
+        JobClient.runJob(job);
+    }
+}
diff --git a/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/client/Client.java b/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/client/Client.java
new file mode 100644
index 0000000..57e2c71
--- /dev/null
+++ b/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/client/Client.java
@@ -0,0 +1,76 @@
+package edu.uci.ics.pregelix.example.client;
+
+import java.io.IOException;
+
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
+import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
+import org.kohsuke.args4j.CmdLineException;
+import org.kohsuke.args4j.CmdLineParser;
+import org.kohsuke.args4j.Option;
+
+import edu.uci.ics.pregelix.api.job.PregelixJob;
+import edu.uci.ics.pregelix.core.base.IDriver.Plan;
+import edu.uci.ics.pregelix.core.driver.Driver;
+import edu.uci.ics.pregelix.example.PageRankVertex;
+import edu.uci.ics.pregelix.example.ShortestPathsVertex;
+
+public class Client {
+
+    private static class Options {
+        @Option(name = "-inputpaths", usage = "comma seprated input paths", required = true)
+        public String inputPaths;
+
+        @Option(name = "-outputpath", usage = "output path", required = true)
+        public String outputPath;
+
+        @Option(name = "-ip", usage = "ip address of cluster controller", required = true)
+        public String ipAddress;
+
+        @Option(name = "-port", usage = "port of cluster controller", required = true)
+        public int port;
+
+        @Option(name = "-plan", usage = "query plan choice", required = true)
+        public Plan planChoice;
+
+        @Option(name = "-vnum", usage = "number of vertices", required = false)
+        public long numVertices;
+
+        @Option(name = "-enum", usage = "number of vertices", required = false)
+        public long numEdges;
+
+        @Option(name = "-source-vertex", usage = "source vertex id, for shortest paths only", required = false)
+        public long sourceId;
+
+        @Option(name = "-num-iteration", usage = "max number of iterations, for pagerank job only", required = false)
+        public long numIteration = -1;
+
+        @Option(name = "-runtime-profiling", usage = "whether to do runtime profifling", required = false)
+        public String profiling = "false";
+    }
+
+    public static void run(String[] args, PregelixJob job) throws Exception {
+        Options options = prepareJob(args, job);
+        Driver driver = new Driver(Client.class);
+        driver.runJob(job, options.planChoice, options.ipAddress, options.port, Boolean.parseBoolean(options.profiling));
+    }
+
+    private static Options prepareJob(String[] args, PregelixJob job) throws CmdLineException, IOException {
+        Options options = new Options();
+        CmdLineParser parser = new CmdLineParser(options);
+        parser.parseArgument(args);
+
+        String[] inputs = options.inputPaths.split(";");
+        FileInputFormat.setInputPaths(job, inputs[0]);
+        for (int i = 1; i < inputs.length; i++)
+            FileInputFormat.addInputPaths(job, inputs[0]);
+        FileOutputFormat.setOutputPath(job, new Path(options.outputPath));
+        job.getConfiguration().setLong(PregelixJob.NUM_VERTICE, options.numVertices);
+        job.getConfiguration().setLong(PregelixJob.NUM_EDGES, options.numEdges);
+        job.getConfiguration().setLong(ShortestPathsVertex.SOURCE_ID, options.sourceId);
+        if (options.numIteration > 0)
+            job.getConfiguration().setLong(PageRankVertex.ITERATIONS, options.numIteration);
+        return options;
+    }
+
+}
diff --git a/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/inputformat/TextConnectedComponentsInputFormat.java b/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/inputformat/TextConnectedComponentsInputFormat.java
new file mode 100644
index 0000000..e7eb933
--- /dev/null
+++ b/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/inputformat/TextConnectedComponentsInputFormat.java
@@ -0,0 +1,113 @@
+/*
+ * Copyright 2009-2010 by The Regents of the University of California
+ * Licensed 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 from
+ *
+ *     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 edu.uci.ics.pregelix.example.inputformat;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+
+import org.apache.hadoop.io.FloatWritable;
+import org.apache.hadoop.io.LongWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapreduce.InputSplit;
+import org.apache.hadoop.mapreduce.RecordReader;
+import org.apache.hadoop.mapreduce.TaskAttemptContext;
+
+import edu.uci.ics.pregelix.api.graph.Vertex;
+import edu.uci.ics.pregelix.api.io.VertexReader;
+import edu.uci.ics.pregelix.api.io.text.TextVertexInputFormat;
+import edu.uci.ics.pregelix.api.io.text.TextVertexInputFormat.TextVertexReader;
+import edu.uci.ics.pregelix.api.util.BspUtils;
+import edu.uci.ics.pregelix.example.io.VLongWritable;
+
+public class TextConnectedComponentsInputFormat extends
+        TextVertexInputFormat<VLongWritable, VLongWritable, FloatWritable, VLongWritable> {
+
+    @Override
+    public VertexReader<VLongWritable, VLongWritable, FloatWritable, VLongWritable> createVertexReader(
+            InputSplit split, TaskAttemptContext context) throws IOException {
+        return new TextConnectedComponentsGraphReader(textInputFormat.createRecordReader(split, context));
+    }
+}
+
+@SuppressWarnings("rawtypes")
+class TextConnectedComponentsGraphReader extends
+        TextVertexReader<VLongWritable, VLongWritable, FloatWritable, VLongWritable> {
+
+    private final static String separator = " ";
+    private Vertex vertex;
+    private VLongWritable vertexId = new VLongWritable();
+    private List<VLongWritable> pool = new ArrayList<VLongWritable>();
+    private int used = 0;
+
+    public TextConnectedComponentsGraphReader(RecordReader<LongWritable, Text> lineRecordReader) {
+        super(lineRecordReader);
+    }
+
+    @Override
+    public boolean nextVertex() throws IOException, InterruptedException {
+        return getRecordReader().nextKeyValue();
+    }
+
+    @SuppressWarnings("unchecked")
+    @Override
+    public Vertex<VLongWritable, VLongWritable, FloatWritable, VLongWritable> getCurrentVertex() throws IOException,
+            InterruptedException {
+        used = 0;
+        if (vertex == null)
+            vertex = (Vertex) BspUtils.createVertex(getContext().getConfiguration());
+        vertex.getMsgList().clear();
+        vertex.getEdges().clear();
+
+        vertex.reset();
+        Text line = getRecordReader().getCurrentValue();
+        String[] fields = line.toString().split(separator);
+
+        if (fields.length > 0) {
+            /**
+             * set the src vertex id
+             */
+            long src = Long.parseLong(fields[0]);
+            vertexId.set(src);
+            vertex.setVertexId(vertexId);
+            long dest = -1L;
+
+            /**
+             * set up edges
+             */
+            for (int i = 1; i < fields.length; i++) {
+                dest = Long.parseLong(fields[i]);
+                VLongWritable destId = allocate();
+                destId.set(dest);
+                vertex.addEdge(destId, null);
+            }
+        }
+        // vertex.sortEdges();
+        return vertex;
+    }
+
+    private VLongWritable allocate() {
+        if (used >= pool.size()) {
+            VLongWritable value = new VLongWritable();
+            pool.add(value);
+            used++;
+            return value;
+        } else {
+            VLongWritable value = pool.get(used);
+            used++;
+            return value;
+        }
+    }
+}
diff --git a/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/inputformat/TextPageRankInputFormat.java b/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/inputformat/TextPageRankInputFormat.java
new file mode 100644
index 0000000..a8a752e
--- /dev/null
+++ b/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/inputformat/TextPageRankInputFormat.java
@@ -0,0 +1,113 @@
+/*
+ * Copyright 2009-2010 by The Regents of the University of California
+ * Licensed 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 from
+ *
+ *     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 edu.uci.ics.pregelix.example.inputformat;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+
+import org.apache.hadoop.io.DoubleWritable;
+import org.apache.hadoop.io.FloatWritable;
+import org.apache.hadoop.io.LongWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapreduce.InputSplit;
+import org.apache.hadoop.mapreduce.RecordReader;
+import org.apache.hadoop.mapreduce.TaskAttemptContext;
+
+import edu.uci.ics.pregelix.api.graph.Vertex;
+import edu.uci.ics.pregelix.api.io.VertexReader;
+import edu.uci.ics.pregelix.api.io.text.TextVertexInputFormat;
+import edu.uci.ics.pregelix.api.io.text.TextVertexInputFormat.TextVertexReader;
+import edu.uci.ics.pregelix.api.util.BspUtils;
+import edu.uci.ics.pregelix.example.io.VLongWritable;
+
+public class TextPageRankInputFormat extends
+        TextVertexInputFormat<VLongWritable, DoubleWritable, FloatWritable, DoubleWritable> {
+
+    @Override
+    public VertexReader<VLongWritable, DoubleWritable, FloatWritable, DoubleWritable> createVertexReader(
+            InputSplit split, TaskAttemptContext context) throws IOException {
+        return new TextPageRankGraphReader(textInputFormat.createRecordReader(split, context));
+    }
+}
+
+@SuppressWarnings("rawtypes")
+class TextPageRankGraphReader extends TextVertexReader<VLongWritable, DoubleWritable, FloatWritable, DoubleWritable> {
+
+    private final static String separator = " ";
+    private Vertex vertex;
+    private VLongWritable vertexId = new VLongWritable();
+    private List<VLongWritable> pool = new ArrayList<VLongWritable>();
+    private int used = 0;
+
+    public TextPageRankGraphReader(RecordReader<LongWritable, Text> lineRecordReader) {
+        super(lineRecordReader);
+    }
+
+    @Override
+    public boolean nextVertex() throws IOException, InterruptedException {
+        return getRecordReader().nextKeyValue();
+    }
+
+    @SuppressWarnings("unchecked")
+    @Override
+    public Vertex<VLongWritable, DoubleWritable, FloatWritable, DoubleWritable> getCurrentVertex() throws IOException,
+            InterruptedException {
+        used = 0;
+        if (vertex == null)
+            vertex = (Vertex) BspUtils.createVertex(getContext().getConfiguration());
+        vertex.getMsgList().clear();
+        vertex.getEdges().clear();
+
+        vertex.reset();
+        Text line = getRecordReader().getCurrentValue();
+        String[] fields = line.toString().split(separator);
+
+        if (fields.length > 0) {
+            /**
+             * set the src vertex id
+             */
+            long src = Long.parseLong(fields[0]);
+            vertexId.set(src);
+            vertex.setVertexId(vertexId);
+            long dest = -1L;
+
+            /**
+             * set up edges
+             */
+            for (int i = 1; i < fields.length; i++) {
+                dest = Long.parseLong(fields[i]);
+                VLongWritable destId = allocate();
+                destId.set(dest);
+                vertex.addEdge(destId, null);
+            }
+        }
+        // vertex.sortEdges();
+        return vertex;
+    }
+
+    private VLongWritable allocate() {
+        if (used >= pool.size()) {
+            VLongWritable value = new VLongWritable();
+            pool.add(value);
+            used++;
+            return value;
+        } else {
+            VLongWritable value = pool.get(used);
+            used++;
+            return value;
+        }
+    }
+}
diff --git a/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/inputformat/TextShortestPathsInputFormat.java b/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/inputformat/TextShortestPathsInputFormat.java
new file mode 100644
index 0000000..d445935
--- /dev/null
+++ b/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/inputformat/TextShortestPathsInputFormat.java
@@ -0,0 +1,114 @@
+/*
+ * Copyright 2009-2010 by The Regents of the University of California
+ * Licensed 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 from
+ *
+ *     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 edu.uci.ics.pregelix.example.inputformat;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+
+import org.apache.hadoop.io.DoubleWritable;
+import org.apache.hadoop.io.FloatWritable;
+import org.apache.hadoop.io.LongWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapreduce.InputSplit;
+import org.apache.hadoop.mapreduce.RecordReader;
+import org.apache.hadoop.mapreduce.TaskAttemptContext;
+
+import edu.uci.ics.pregelix.api.graph.Vertex;
+import edu.uci.ics.pregelix.api.io.VertexReader;
+import edu.uci.ics.pregelix.api.io.text.TextVertexInputFormat;
+import edu.uci.ics.pregelix.api.io.text.TextVertexInputFormat.TextVertexReader;
+import edu.uci.ics.pregelix.api.util.BspUtils;
+import edu.uci.ics.pregelix.example.io.VLongWritable;
+
+public class TextShortestPathsInputFormat extends
+        TextVertexInputFormat<VLongWritable, DoubleWritable, FloatWritable, DoubleWritable> {
+
+    @Override
+    public VertexReader<VLongWritable, DoubleWritable, FloatWritable, DoubleWritable> createVertexReader(
+            InputSplit split, TaskAttemptContext context) throws IOException {
+        return new TextShortestPathsGraphReader(textInputFormat.createRecordReader(split, context));
+    }
+}
+
+@SuppressWarnings("rawtypes")
+class TextShortestPathsGraphReader extends
+        TextVertexReader<VLongWritable, DoubleWritable, FloatWritable, DoubleWritable> {
+
+    private final static String separator = " ";
+    private Vertex vertex;
+    private FloatWritable initValue = new FloatWritable(1.0f);
+    private VLongWritable vertexId = new VLongWritable();
+    private List<VLongWritable> pool = new ArrayList<VLongWritable>();
+    private int used = 0;
+
+    public TextShortestPathsGraphReader(RecordReader<LongWritable, Text> lineRecordReader) {
+        super(lineRecordReader);
+    }
+
+    @Override
+    public boolean nextVertex() throws IOException, InterruptedException {
+        return getRecordReader().nextKeyValue();
+    }
+
+    @SuppressWarnings("unchecked")
+    @Override
+    public Vertex<VLongWritable, DoubleWritable, FloatWritable, DoubleWritable> getCurrentVertex() throws IOException,
+            InterruptedException {
+        used = 0;
+        if (vertex == null)
+            vertex = (Vertex) BspUtils.createVertex(getContext().getConfiguration());
+
+        vertex.getMsgList().clear();
+        vertex.getEdges().clear();
+        Text line = getRecordReader().getCurrentValue();
+        String[] fields = line.toString().split(separator);
+
+        if (fields.length > 0) {
+            /**
+             * set the src vertex id
+             */
+            long src = Long.parseLong(fields[0]);
+            vertexId.set(src);
+            vertex.setVertexId(vertexId);
+            long dest = -1L;
+
+            /**
+             * set up edges
+             */
+            for (int i = 1; i < fields.length; i++) {
+                dest = Long.parseLong(fields[i]);
+                VLongWritable destId = allocate();
+                destId.set(dest);
+                vertex.addEdge(destId, initValue);
+            }
+        }
+        // vertex.sortEdges();
+        return vertex;
+    }
+
+    private VLongWritable allocate() {
+        if (used >= pool.size()) {
+            VLongWritable value = new VLongWritable();
+            pool.add(value);
+            used++;
+            return value;
+        } else {
+            VLongWritable value = pool.get(used);
+            used++;
+            return value;
+        }
+    }
+}
diff --git a/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/io/VLongWritable.java b/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/io/VLongWritable.java
new file mode 100644
index 0000000..77a758a
--- /dev/null
+++ b/pregelix/pregelix-example/src/main/java/edu/uci/ics/pregelix/example/io/VLongWritable.java
@@ -0,0 +1,116 @@
+/**
+ * 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 edu.uci.ics.pregelix.example.io;
+
+import java.io.DataInput;
+import java.io.DataOutput;
+import java.io.IOException;
+
+import org.apache.hadoop.io.WritableComparable;
+import org.apache.hadoop.io.WritableComparator;
+
+import edu.uci.ics.pregelix.api.util.SerDeUtils;
+
+/**
+ * A WritableComparable for longs in a variable-length format. Such values take
+ * between one and five bytes. Smaller values take fewer bytes.
+ * 
+ * @see org.apache.hadoop.io.WritableUtils#readVLong(DataInput)
+ */
+@SuppressWarnings("rawtypes")
+public class VLongWritable implements WritableComparable {
+    private long value;
+
+    public VLongWritable() {
+    }
+
+    public VLongWritable(long value) {
+        set(value);
+    }
+
+    /** Set the value of this LongWritable. */
+    public void set(long value) {
+        this.value = value;
+    }
+
+    /** Return the value of this LongWritable. */
+    public long get() {
+        return value;
+    }
+
+    public void readFields(DataInput in) throws IOException {
+        value = SerDeUtils.readVLong(in);
+    }
+
+    public void write(DataOutput out) throws IOException {
+        SerDeUtils.writeVLong(out, value);
+    }
+
+    /** Returns true iff <code>o</code> is a VLongWritable with the same value. */
+    public boolean equals(Object o) {
+        if (!(o instanceof VLongWritable))
+            return false;
+        VLongWritable other = (VLongWritable) o;
+        return this.value == other.value;
+    }
+
+    public int hashCode() {
+        return (int) value;
+    }
+
+    /** Compares two VLongWritables. */
+    public int compareTo(Object o) {
+        long thisValue = this.value;
+        long thatValue = ((VLongWritable) o).value;
+        return (thisValue < thatValue ? -1 : (thisValue == thatValue ? 0 : 1));
+    }
+
+    public String toString() {
+        return Long.toString(value);
+    }
+
+    /** A Comparator optimized for LongWritable. */
+    public static class Comparator extends WritableComparator {
+        public Comparator() {
+            super(VLongWritable.class);
+        }
+
+        public int compare(byte[] b1, int s1, int l1, byte[] b2, int s2, int l2) {
+            long thisValue = SerDeUtils.readVLong(b1, s1, l1);
+            long thatValue = SerDeUtils.readVLong(b2, s2, l2);
+            return (thisValue < thatValue ? -1 : (thisValue == thatValue ? 0 : 1));
+        }
+    }
+
+    /** A decreasing Comparator optimized for LongWritable. */
+    public static class DecreasingComparator extends Comparator {
+        public int compare(WritableComparable a, WritableComparable b) {
+            return -super.compare(a, b);
+        }
+
+        public int compare(byte[] b1, int s1, int l1, byte[] b2, int s2, int l2) {
+            return -super.compare(b1, s1, l1, b2, s2, l2);
+        }
+    }
+
+    static { // register default comparator
+        WritableComparator.define(VLongWritable.class, new Comparator());
+    }
+
+}
diff --git a/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/dataload/DataLoadTest.java b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/dataload/DataLoadTest.java
new file mode 100644
index 0000000..414293e
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/dataload/DataLoadTest.java
@@ -0,0 +1,179 @@
+/*
+ * Copyright 2009-2010 by The Regents of the University of California
+ * Licensed 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 from
+ *
+ *     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 edu.uci.ics.pregelix.example.dataload;
+
+import java.io.File;
+import java.io.IOException;
+import java.util.logging.Logger;
+
+import org.apache.commons.io.FileUtils;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hdfs.MiniDFSCluster;
+import org.apache.hadoop.io.DoubleWritable;
+import org.apache.hadoop.io.FloatWritable;
+import org.apache.hadoop.io.LongWritable;
+import org.apache.hadoop.io.Writable;
+import org.apache.hadoop.io.WritableComparable;
+import org.apache.hadoop.mapred.JobConf;
+import org.junit.Test;
+
+import edu.uci.ics.hyracks.api.job.JobSpecification;
+import edu.uci.ics.pregelix.api.job.PregelixJob;
+import edu.uci.ics.pregelix.core.jobgen.JobGenOuterJoin;
+import edu.uci.ics.pregelix.core.jobgen.clusterconfig.ClusterConfig;
+import edu.uci.ics.pregelix.core.util.PregelixHyracksIntegrationUtil;
+import edu.uci.ics.pregelix.example.PageRankVertex;
+import edu.uci.ics.pregelix.example.PageRankVertex.SimplePageRankVertexInputFormat;
+import edu.uci.ics.pregelix.example.util.TestUtils;
+
+@SuppressWarnings("deprecation")
+public class DataLoadTest {
+    private static final String EXPECT_RESULT_DIR = "expected";
+    private static final String ACTUAL_RESULT_DIR = "actual";
+    private static final String NC1 = "nc1";
+
+    private static final Logger LOGGER = Logger.getLogger(DataLoadTest.class.getName());
+
+    private static final String PATH_TO_HADOOP_CONF = "src/test/resources/hadoop/conf";
+    private static final String PATH_TO_CLUSTER_STORE = "src/test/resources/cluster/data.properties";
+
+    private static final String HYRACKS_APP_NAME = "giraph";
+    private static final String GIRAPH_JOB_NAME = "DataLoadTest";
+
+    private MiniDFSCluster dfsCluster;
+
+    private JobConf conf = new JobConf();
+    private int numberOfNC = 2;
+    private JobGenOuterJoin giraphTestJobGen;
+    private PregelixJob job;
+
+    public DataLoadTest() throws Exception {
+        job = new PregelixJob(GIRAPH_JOB_NAME);
+        job.setVertexClass(PageRankVertex.class);
+        job.setVertexInputFormatClass(SimplePageRankVertexInputFormat.class);
+        job.getConfiguration().setClass(PregelixJob.VERTEX_INDEX_CLASS, LongWritable.class, WritableComparable.class);
+        job.getConfiguration().setClass(PregelixJob.VERTEX_VALUE_CLASS, DoubleWritable.class, Writable.class);
+        job.getConfiguration().setClass(PregelixJob.EDGE_VALUE_CLASS, FloatWritable.class, Writable.class);
+        job.getConfiguration().setClass(PregelixJob.MESSAGE_VALUE_CLASS, DoubleWritable.class, Writable.class);
+        giraphTestJobGen = new JobGenOuterJoin(job);
+    }
+
+    public void setUp() throws Exception {
+        ClusterConfig.setStorePath(PATH_TO_CLUSTER_STORE);
+        cleanupStores();
+        PregelixHyracksIntegrationUtil.init();
+        PregelixHyracksIntegrationUtil.createApp(HYRACKS_APP_NAME);
+        LOGGER.info("Hyracks mini-cluster started");
+        startHDFS();
+        FileUtils.forceMkdir(new File(EXPECT_RESULT_DIR));
+        FileUtils.forceMkdir(new File(ACTUAL_RESULT_DIR));
+        FileUtils.cleanDirectory(new File(EXPECT_RESULT_DIR));
+        FileUtils.cleanDirectory(new File(ACTUAL_RESULT_DIR));
+
+    }
+
+    private void cleanupStores() throws IOException {
+        FileUtils.forceMkdir(new File("teststore"));
+        FileUtils.forceMkdir(new File("build"));
+        FileUtils.cleanDirectory(new File("teststore"));
+        FileUtils.cleanDirectory(new File("build"));
+    }
+
+    private void startHDFS() throws IOException {
+        conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/core-site.xml"));
+        conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/mapred-site.xml"));
+        conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/hdfs-site.xml"));
+        FileSystem lfs = FileSystem.getLocal(new Configuration());
+        lfs.delete(new Path("build"), true);
+        System.setProperty("hadoop.log.dir", "logs");
+        dfsCluster = new MiniDFSCluster(conf, numberOfNC, true, null);
+    }
+
+    /**
+     * cleanup hdfs cluster
+     */
+    private void cleanupHDFS() throws Exception {
+        dfsCluster.shutdown();
+    }
+
+    public void tearDown() throws Exception {
+        PregelixHyracksIntegrationUtil.destroyApp(HYRACKS_APP_NAME);
+        PregelixHyracksIntegrationUtil.deinit();
+        LOGGER.info("Hyracks mini-cluster shut down");
+        cleanupHDFS();
+    }
+
+    @Test
+    public void test() throws Exception {
+        setUp();
+        runDataScan();
+        runCreation();
+        runDataLoad();
+        runIndexScan();
+        try {
+            compareResults();
+        } catch (Exception e) {
+            tearDown();
+            throw e;
+        }
+        tearDown();
+    }
+
+    private void runCreation() throws Exception {
+        try {
+            JobSpecification bulkLoadJobSpec = giraphTestJobGen.generateCreatingJob();
+            PregelixHyracksIntegrationUtil.runJob(bulkLoadJobSpec, HYRACKS_APP_NAME);
+        } catch (Exception e) {
+            throw e;
+        }
+    }
+
+    private void runDataLoad() throws Exception {
+        try {
+            JobSpecification bulkLoadJobSpec = giraphTestJobGen.generateLoadingJob();
+            PregelixHyracksIntegrationUtil.runJob(bulkLoadJobSpec, HYRACKS_APP_NAME);
+        } catch (Exception e) {
+            throw e;
+        }
+    }
+
+    private void runDataScan() throws Exception {
+        try {
+            JobSpecification scanSortPrintJobSpec = giraphTestJobGen.scanSortPrintGraph(NC1, EXPECT_RESULT_DIR
+                    + File.separator + job.getJobName());
+            PregelixHyracksIntegrationUtil.runJob(scanSortPrintJobSpec, HYRACKS_APP_NAME);
+        } catch (Exception e) {
+            throw e;
+        }
+    }
+
+    private void runIndexScan() throws Exception {
+        try {
+            JobSpecification scanSortPrintJobSpec = giraphTestJobGen.scanIndexPrintGraph(NC1, ACTUAL_RESULT_DIR
+                    + File.separator + job.getJobName());
+            PregelixHyracksIntegrationUtil.runJob(scanSortPrintJobSpec, HYRACKS_APP_NAME);
+        } catch (Exception e) {
+            throw e;
+        }
+    }
+
+    private void compareResults() throws Exception {
+        PregelixJob job = new PregelixJob(GIRAPH_JOB_NAME);
+        TestUtils.compareWithResult(new File(EXPECT_RESULT_DIR + File.separator + job.getJobName()), new File(
+                ACTUAL_RESULT_DIR + File.separator + job.getJobName()));
+    }
+}
diff --git a/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/jobgen/JobGenerator.java b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/jobgen/JobGenerator.java
new file mode 100644
index 0000000..fb7dc6c
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/jobgen/JobGenerator.java
@@ -0,0 +1,153 @@
+/*
+ * Copyright 2009-2010 by The Regents of the University of California
+ * Licensed 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 from
+ *
+ *     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 edu.uci.ics.pregelix.example.jobgen;
+
+import java.io.File;
+import java.io.FileOutputStream;
+import java.io.IOException;
+
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
+import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
+
+import edu.uci.ics.pregelix.api.job.PregelixJob;
+import edu.uci.ics.pregelix.example.ConnectedComponentsVertex;
+import edu.uci.ics.pregelix.example.ConnectedComponentsVertex.SimpleConnectedComponentsVertexOutputFormat;
+import edu.uci.ics.pregelix.example.PageRankVertex;
+import edu.uci.ics.pregelix.example.PageRankVertex.SimplePageRankVertexInputFormat;
+import edu.uci.ics.pregelix.example.PageRankVertex.SimplePageRankVertexOutputFormat;
+import edu.uci.ics.pregelix.example.ShortestPathsVertex;
+import edu.uci.ics.pregelix.example.inputformat.TextConnectedComponentsInputFormat;
+import edu.uci.ics.pregelix.example.inputformat.TextPageRankInputFormat;
+import edu.uci.ics.pregelix.example.inputformat.TextShortestPathsInputFormat;
+
+public class JobGenerator {
+    private static String outputBase = "src/test/resources/jobs/";
+    private static String HDFS_INPUTPATH = "/webmap";
+    private static String HDFS_OUTPUTPAH = "/result";
+
+    private static String HDFS_INPUTPATH2 = "/webmapcomplex";
+    private static String HDFS_OUTPUTPAH2 = "/resultcomplex";
+
+    private static void generatePageRankJobReal(String jobName, String outputPath) throws IOException {
+        PregelixJob job = new PregelixJob(jobName);
+        job.setVertexClass(PageRankVertex.class);
+        job.setVertexInputFormatClass(TextPageRankInputFormat.class);
+        job.setVertexOutputFormatClass(SimplePageRankVertexOutputFormat.class);
+        job.setVertexCombinerClass(PageRankVertex.SimpleSumCombiner.class);
+        FileInputFormat.setInputPaths(job, HDFS_INPUTPATH);
+        FileOutputFormat.setOutputPath(job, new Path(HDFS_OUTPUTPAH));
+        job.getConfiguration().setLong(PregelixJob.NUM_VERTICE, 20);
+        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+    }
+
+    private static void generatePageRankJobRealComplex(String jobName, String outputPath) throws IOException {
+        PregelixJob job = new PregelixJob(jobName);
+        job.setVertexClass(PageRankVertex.class);
+        job.setVertexInputFormatClass(TextPageRankInputFormat.class);
+        job.setVertexOutputFormatClass(SimplePageRankVertexOutputFormat.class);
+        job.setVertexCombinerClass(PageRankVertex.SimpleSumCombiner.class);
+        FileInputFormat.setInputPaths(job, HDFS_INPUTPATH2);
+        FileOutputFormat.setOutputPath(job, new Path(HDFS_OUTPUTPAH2));
+        job.getConfiguration().setLong(PregelixJob.NUM_VERTICE, 23);
+        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+    }
+
+    private static void generateShortestPathJobReal(String jobName, String outputPath) throws IOException {
+        PregelixJob job = new PregelixJob(jobName);
+        job.setVertexClass(ShortestPathsVertex.class);
+        job.setVertexInputFormatClass(TextShortestPathsInputFormat.class);
+        job.setVertexOutputFormatClass(SimplePageRankVertexOutputFormat.class);
+        job.setVertexCombinerClass(ShortestPathsVertex.SimpleMinCombiner.class);
+        FileInputFormat.setInputPaths(job, HDFS_INPUTPATH);
+        FileOutputFormat.setOutputPath(job, new Path(HDFS_OUTPUTPAH));
+        job.getConfiguration().setLong(PregelixJob.NUM_VERTICE, 20);
+        job.getConfiguration().setLong(ShortestPathsVertex.SOURCE_ID, 0);
+        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+    }
+
+    private static void generateConnectedComponentsJobReal(String jobName, String outputPath) throws IOException {
+        PregelixJob job = new PregelixJob(jobName);
+        job.setVertexClass(ConnectedComponentsVertex.class);
+        job.setVertexInputFormatClass(TextConnectedComponentsInputFormat.class);
+        job.setVertexOutputFormatClass(SimpleConnectedComponentsVertexOutputFormat.class);
+        job.setVertexCombinerClass(ConnectedComponentsVertex.SimpleMinCombiner.class);
+        FileInputFormat.setInputPaths(job, HDFS_INPUTPATH);
+        FileOutputFormat.setOutputPath(job, new Path(HDFS_OUTPUTPAH));
+        job.getConfiguration().setLong(PregelixJob.NUM_VERTICE, 20);
+        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+    }
+
+    private static void generateConnectedComponentsJobRealComplex(String jobName, String outputPath) throws IOException {
+        PregelixJob job = new PregelixJob(jobName);
+        job.setVertexClass(ConnectedComponentsVertex.class);
+        job.setVertexInputFormatClass(TextConnectedComponentsInputFormat.class);
+        job.setVertexOutputFormatClass(SimpleConnectedComponentsVertexOutputFormat.class);
+        job.setVertexCombinerClass(ConnectedComponentsVertex.SimpleMinCombiner.class);
+        FileInputFormat.setInputPaths(job, HDFS_INPUTPATH2);
+        FileOutputFormat.setOutputPath(job, new Path(HDFS_OUTPUTPAH2));
+        job.getConfiguration().setLong(PregelixJob.NUM_VERTICE, 23);
+        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+    }
+
+    private static void generatePageRankJob(String jobName, String outputPath) throws IOException {
+        PregelixJob job = new PregelixJob(jobName);
+        job.setVertexClass(PageRankVertex.class);
+        job.setVertexInputFormatClass(SimplePageRankVertexInputFormat.class);
+        job.setVertexCombinerClass(PageRankVertex.SimpleSumCombiner.class);
+        job.setVertexOutputFormatClass(SimplePageRankVertexOutputFormat.class);
+        FileInputFormat.setInputPaths(job, HDFS_INPUTPATH);
+        FileOutputFormat.setOutputPath(job, new Path(HDFS_OUTPUTPAH));
+        job.getConfiguration().setLong(PregelixJob.NUM_VERTICE, 20);
+        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+    }
+
+    private static void genPageRank() throws IOException {
+        generatePageRankJob("PageRank", outputBase + "PageRank.xml");
+        generatePageRankJobReal("PageRank", outputBase + "PageRankReal.xml");
+        generatePageRankJobRealComplex("PageRank", outputBase + "PageRankRealComplex.xml");
+    }
+
+    private static void generateShortestPathJob(String jobName, String outputPath) throws IOException {
+        PregelixJob job = new PregelixJob(jobName);
+        job.setVertexClass(ShortestPathsVertex.class);
+        job.setVertexInputFormatClass(SimplePageRankVertexInputFormat.class);
+        job.setVertexCombinerClass(ShortestPathsVertex.SimpleMinCombiner.class);
+        job.setVertexOutputFormatClass(SimplePageRankVertexOutputFormat.class);
+        FileInputFormat.setInputPaths(job, HDFS_INPUTPATH);
+        FileOutputFormat.setOutputPath(job, new Path(HDFS_OUTPUTPAH));
+        job.getConfiguration().setLong(PregelixJob.NUM_VERTICE, 20);
+        job.getConfiguration().setLong(ShortestPathsVertex.SOURCE_ID, 0);
+        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+    }
+
+    private static void genShortestPath() throws IOException {
+        generateShortestPathJob("ShortestPaths", outputBase + "ShortestPaths.xml");
+        generateShortestPathJobReal("ShortestPaths", outputBase + "ShortestPathsReal.xml");
+    }
+
+    private static void genConnectedComponents() throws IOException {
+        generateConnectedComponentsJobReal("ConnectedComponents", outputBase + "ConnectedComponentsReal.xml");
+        generateConnectedComponentsJobRealComplex("ConnectedComponents", outputBase
+                + "ConnectedComponentsRealComplex.xml");
+    }
+
+    public static void main(String[] args) throws IOException {
+        genPageRank();
+        genShortestPath();
+        genConnectedComponents();
+    }
+
+}
diff --git a/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/jobrun/RunJobTestCase.java b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/jobrun/RunJobTestCase.java
new file mode 100644
index 0000000..81aace0
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/jobrun/RunJobTestCase.java
@@ -0,0 +1,164 @@
+package edu.uci.ics.pregelix.example.jobrun;
+
+import java.io.File;
+
+import junit.framework.TestCase;
+
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
+import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
+import org.junit.Test;
+
+import edu.uci.ics.hyracks.api.job.JobSpecification;
+import edu.uci.ics.pregelix.api.job.PregelixJob;
+import edu.uci.ics.pregelix.core.jobgen.JobGen;
+import edu.uci.ics.pregelix.core.jobgen.JobGenInnerJoin;
+import edu.uci.ics.pregelix.core.jobgen.JobGenOuterJoin;
+import edu.uci.ics.pregelix.core.jobgen.JobGenOuterJoinSingleSort;
+import edu.uci.ics.pregelix.core.jobgen.JobGenOuterJoinSort;
+import edu.uci.ics.pregelix.core.util.PregelixHyracksIntegrationUtil;
+import edu.uci.ics.pregelix.dataflow.util.IterationUtils;
+import edu.uci.ics.pregelix.example.util.TestUtils;
+
+public class RunJobTestCase extends TestCase {
+    private static final String NC1 = "nc1";
+    private static final String HYRACKS_APP_NAME = "giraph";
+    private static String HDFS_INPUTPATH = "/webmap";
+    private static String HDFS_OUTPUTPAH = "/result";
+
+    private static String HDFS_INPUTPATH2 = "/webmapcomplex";
+    private static String HDFS_OUTPUTPAH2 = "/resultcomplex";
+
+    private final PregelixJob job;
+    private JobGen[] giraphJobGens;
+    private final String resultFileName;
+    private final String expectedFileName;
+    private final String jobFile;
+
+    public RunJobTestCase(String hadoopConfPath, String jobName, String jobFile, String resultFile, String expectedFile)
+            throws Exception {
+        super("test");
+        this.jobFile = jobFile;
+        this.job = new PregelixJob("test");
+        this.job.getConfiguration().addResource(new Path(jobFile));
+        this.job.getConfiguration().addResource(new Path(hadoopConfPath));
+        Path[] inputPaths = FileInputFormat.getInputPaths(job);
+        if (inputPaths[0].toString().endsWith(HDFS_INPUTPATH)) {
+            FileInputFormat.setInputPaths(job, HDFS_INPUTPATH);
+            FileOutputFormat.setOutputPath(job, new Path(HDFS_OUTPUTPAH));
+        } else {
+            FileInputFormat.setInputPaths(job, HDFS_INPUTPATH2);
+            FileOutputFormat.setOutputPath(job, new Path(HDFS_OUTPUTPAH2));
+        }
+        job.setJobName(jobName);
+        this.resultFileName = resultFile;
+        this.expectedFileName = expectedFile;
+        giraphJobGens = new JobGen[4];
+        giraphJobGens[0] = new JobGenOuterJoin(job);
+        waitawhile();
+        giraphJobGens[1] = new JobGenInnerJoin(job);
+        waitawhile();
+        giraphJobGens[2] = new JobGenOuterJoinSort(job);
+        waitawhile();
+        giraphJobGens[3] = new JobGenOuterJoinSingleSort(job);
+    }
+
+    private void waitawhile() throws InterruptedException {
+        synchronized (this) {
+            this.wait(20);
+        }
+    }
+
+    @Test
+    public void test() throws Exception {
+        setUp();
+        for (JobGen jobGen : giraphJobGens) {
+            FileSystem dfs = FileSystem.get(job.getConfiguration());
+            dfs.delete(new Path(HDFS_OUTPUTPAH), true);
+            runCreate(jobGen);
+            runDataLoad(jobGen);
+            int i = 1;
+            boolean terminate = false;
+            do {
+                runLoopBodyIteration(jobGen, i);
+                terminate = IterationUtils.readTerminationState(job.getConfiguration(), jobGen.getJobId());
+                i++;
+            } while (!terminate);
+            runIndexScan(jobGen);
+            runHDFSWRite(jobGen);
+            runCleanup(jobGen);
+            compareResults();
+        }
+        tearDown();
+        waitawhile();
+    }
+
+    private void runCreate(JobGen jobGen) throws Exception {
+        try {
+            JobSpecification treeCreateJobSpec = jobGen.generateCreatingJob();
+            PregelixHyracksIntegrationUtil.runJob(treeCreateJobSpec, HYRACKS_APP_NAME);
+        } catch (Exception e) {
+            throw e;
+        }
+    }
+
+    private void runDataLoad(JobGen jobGen) throws Exception {
+        try {
+            JobSpecification bulkLoadJobSpec = jobGen.generateLoadingJob();
+            PregelixHyracksIntegrationUtil.runJob(bulkLoadJobSpec, HYRACKS_APP_NAME);
+        } catch (Exception e) {
+            throw e;
+        }
+    }
+
+    private void runLoopBodyIteration(JobGen jobGen, int iteration) throws Exception {
+        try {
+            JobSpecification loopBody = jobGen.generateJob(iteration);
+            PregelixHyracksIntegrationUtil.runJob(loopBody, HYRACKS_APP_NAME);
+        } catch (Exception e) {
+            throw e;
+        }
+    }
+
+    private void runIndexScan(JobGen jobGen) throws Exception {
+        try {
+            JobSpecification scanSortPrintJobSpec = jobGen.scanIndexPrintGraph(NC1, resultFileName);
+            PregelixHyracksIntegrationUtil.runJob(scanSortPrintJobSpec, HYRACKS_APP_NAME);
+        } catch (Exception e) {
+            throw e;
+        }
+    }
+
+    private void runHDFSWRite(JobGen jobGen) throws Exception {
+        try {
+            JobSpecification scanSortPrintJobSpec = jobGen.scanIndexWriteGraph();
+            PregelixHyracksIntegrationUtil.runJob(scanSortPrintJobSpec, HYRACKS_APP_NAME);
+        } catch (Exception e) {
+            throw e;
+        }
+    }
+
+    private void runCleanup(JobGen jobGen) throws Exception {
+        try {
+            JobSpecification[] cleanups = jobGen.generateCleanup();
+            runJobArray(cleanups);
+        } catch (Exception e) {
+            throw e;
+        }
+    }
+
+    private void runJobArray(JobSpecification[] jobs) throws Exception {
+        for (JobSpecification job : jobs) {
+            PregelixHyracksIntegrationUtil.runJob(job, HYRACKS_APP_NAME);
+        }
+    }
+
+    private void compareResults() throws Exception {
+        TestUtils.compareWithResult(new File(resultFileName), new File(expectedFileName));
+    }
+
+    public String toString() {
+        return jobFile;
+    }
+}
diff --git a/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/jobrun/RunJobTestSuite.java b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/jobrun/RunJobTestSuite.java
new file mode 100644
index 0000000..d44eb69
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/jobrun/RunJobTestSuite.java
@@ -0,0 +1,198 @@
+/*
+ * Copyright 2009-2010 by The Regents of the University of California
+ * Licensed 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 from
+ *
+ *     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 edu.uci.ics.pregelix.example.jobrun;
+
+import java.io.BufferedReader;
+import java.io.DataOutputStream;
+import java.io.File;
+import java.io.FileNotFoundException;
+import java.io.FileOutputStream;
+import java.io.FileReader;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.logging.Logger;
+
+import junit.framework.Test;
+import junit.framework.TestResult;
+import junit.framework.TestSuite;
+
+import org.apache.commons.io.FileUtils;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hdfs.MiniDFSCluster;
+import org.apache.hadoop.mapred.JobConf;
+
+import edu.uci.ics.pregelix.core.jobgen.clusterconfig.ClusterConfig;
+import edu.uci.ics.pregelix.core.util.PregelixHyracksIntegrationUtil;
+
+@SuppressWarnings("deprecation")
+public class RunJobTestSuite extends TestSuite {
+    private static final Logger LOGGER = Logger.getLogger(RunJobTestSuite.class.getName());
+
+    private static final String ACTUAL_RESULT_DIR = "actual";
+    private static final String EXPECTED_RESULT_DIR = "src/test/resources/expected";
+    private static final String PATH_TO_HADOOP_CONF = "src/test/resources/hadoop/conf";
+    private static final String PATH_TO_CLUSTER_STORE = "src/test/resources/cluster/data.properties";
+    private static final String PATH_TO_JOBS = "src/test/resources/jobs/";
+    private static final String PATH_TO_IGNORE = "src/test/resources/ignore.txt";
+    private static final String PATH_TO_ONLY = "src/test/resources/only.txt";
+    private static final String FILE_EXTENSION_OF_RESULTS = "result";
+
+    private static final String DATA_PATH = "data/webmap/webmap_link.txt";
+    private static final String HDFS_PATH = "/webmap/";
+
+    private static final String DATA_PATH2 = "data/webmapcomplex/webmap_link.txt";
+    private static final String HDFS_PATH2 = "/webmapcomplex/";
+
+    private static final String HYRACKS_APP_NAME = "giraph";
+    private static final String HADOOP_CONF_PATH = ACTUAL_RESULT_DIR + File.separator + "conf.xml";
+    private MiniDFSCluster dfsCluster;
+
+    private JobConf conf = new JobConf();
+    private int numberOfNC = 2;
+
+    public void setUp() throws Exception {
+        ClusterConfig.setStorePath(PATH_TO_CLUSTER_STORE);
+        cleanupStores();
+        PregelixHyracksIntegrationUtil.init();
+        PregelixHyracksIntegrationUtil.createApp(HYRACKS_APP_NAME);
+        LOGGER.info("Hyracks mini-cluster started");
+        FileUtils.forceMkdir(new File(ACTUAL_RESULT_DIR));
+        FileUtils.cleanDirectory(new File(ACTUAL_RESULT_DIR));
+        startHDFS();
+    }
+
+    private void cleanupStores() throws IOException {
+        FileUtils.forceMkdir(new File("teststore"));
+        FileUtils.forceMkdir(new File("build"));
+        FileUtils.cleanDirectory(new File("teststore"));
+        FileUtils.cleanDirectory(new File("build"));
+    }
+
+    private void startHDFS() throws IOException {
+        conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/core-site.xml"));
+        conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/mapred-site.xml"));
+        conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/hdfs-site.xml"));
+        FileSystem lfs = FileSystem.getLocal(new Configuration());
+        lfs.delete(new Path("build"), true);
+        System.setProperty("hadoop.log.dir", "logs");
+        dfsCluster = new MiniDFSCluster(conf, numberOfNC, true, null);
+        FileSystem dfs = FileSystem.get(conf);
+        Path src = new Path(DATA_PATH);
+        Path dest = new Path(HDFS_PATH);
+        dfs.mkdirs(dest);
+        dfs.copyFromLocalFile(src, dest);
+
+        src = new Path(DATA_PATH2);
+        dest = new Path(HDFS_PATH2);
+        dfs.mkdirs(dest);
+        dfs.copyFromLocalFile(src, dest);
+
+        DataOutputStream confOutput = new DataOutputStream(new FileOutputStream(new File(HADOOP_CONF_PATH)));
+        conf.writeXml(confOutput);
+        confOutput.flush();
+        confOutput.close();
+    }
+
+    /**
+     * cleanup hdfs cluster
+     */
+    private void cleanupHDFS() throws Exception {
+        dfsCluster.shutdown();
+    }
+
+    public void tearDown() throws Exception {
+        PregelixHyracksIntegrationUtil.destroyApp(HYRACKS_APP_NAME);
+        PregelixHyracksIntegrationUtil.deinit();
+        LOGGER.info("Hyracks mini-cluster shut down");
+        cleanupHDFS();
+    }
+
+    public static Test suite() throws Exception {
+        List<String> ignores = getFileList(PATH_TO_IGNORE);
+        List<String> onlys = getFileList(PATH_TO_ONLY);
+        File testData = new File(PATH_TO_JOBS);
+        File[] queries = testData.listFiles();
+        RunJobTestSuite testSuite = new RunJobTestSuite();
+        testSuite.setUp();
+        boolean onlyEnabled = false;
+
+        if (onlys.size() > 0) {
+            onlyEnabled = true;
+        }
+        for (File qFile : queries) {
+            if (isInList(ignores, qFile.getName()))
+                continue;
+
+            if (qFile.isFile()) {
+                if (onlyEnabled && !isInList(onlys, qFile.getName())) {
+                    continue;
+                } else {
+                    String resultFileName = ACTUAL_RESULT_DIR + File.separator + jobExtToResExt(qFile.getName());
+                    String expectedFileName = EXPECTED_RESULT_DIR + File.separator + jobExtToResExt(qFile.getName());
+                    testSuite.addTest(new RunJobTestCase(HADOOP_CONF_PATH, qFile.getName(), qFile.getAbsolutePath()
+                            .toString(), resultFileName, expectedFileName));
+                }
+            }
+        }
+        return testSuite;
+    }
+
+    /**
+     * Runs the tests and collects their result in a TestResult.
+     */
+    @Override
+    public void run(TestResult result) {
+        try {
+            int testCount = countTestCases();
+            for (int i = 0; i < testCount; i++) {
+                // cleanupStores();
+                Test each = this.testAt(i);
+                if (result.shouldStop())
+                    break;
+                runTest(each, result);
+            }
+            tearDown();
+        } catch (Exception e) {
+            throw new IllegalStateException(e);
+        }
+    }
+
+    protected static List<String> getFileList(String ignorePath) throws FileNotFoundException, IOException {
+        BufferedReader reader = new BufferedReader(new FileReader(ignorePath));
+        String s = null;
+        List<String> ignores = new ArrayList<String>();
+        while ((s = reader.readLine()) != null) {
+            ignores.add(s);
+        }
+        reader.close();
+        return ignores;
+    }
+
+    private static String jobExtToResExt(String fname) {
+        int dot = fname.lastIndexOf('.');
+        return fname.substring(0, dot + 1) + FILE_EXTENSION_OF_RESULTS;
+    }
+
+    private static boolean isInList(List<String> onlys, String name) {
+        for (String only : onlys)
+            if (name.indexOf(only) >= 0)
+                return true;
+        return false;
+    }
+
+}
diff --git a/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/util/TestUtils.java b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/util/TestUtils.java
new file mode 100644
index 0000000..1b22b47
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/util/TestUtils.java
@@ -0,0 +1,92 @@
+/*
+ * Copyright 2009-2010 by The Regents of the University of California
+ * Licensed 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 from
+ *
+ *     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 edu.uci.ics.pregelix.example.util;
+
+import java.io.BufferedReader;
+import java.io.File;
+import java.io.FileReader;
+
+public class TestUtils {
+
+    public static void compareWithResult(File expectedFile, File actualFile) throws Exception {
+        BufferedReader readerExpected = new BufferedReader(new FileReader(expectedFile));
+        BufferedReader readerActual = new BufferedReader(new FileReader(actualFile));
+        String lineExpected, lineActual;
+        int num = 1;
+        try {
+            while ((lineExpected = readerExpected.readLine()) != null) {
+                lineActual = readerActual.readLine();
+                // Assert.assertEquals(lineExpected, lineActual);
+                if (lineActual == null) {
+                    throw new Exception("Actual result changed at line " + num + ":\n< " + lineExpected + "\n> ");
+                }
+                if (!equalStrings(lineExpected, lineActual)) {
+                    throw new Exception("Result for changed at line " + num + ":\n< " + lineExpected + "\n> "
+                            + lineActual);
+                }
+                ++num;
+            }
+            lineActual = readerActual.readLine();
+            if (lineActual != null) {
+                throw new Exception("Actual result changed at line " + num + ":\n< \n> " + lineActual);
+            }
+        } finally {
+            readerExpected.close();
+            readerActual.close();
+        }
+    }
+
+    private static boolean equalStrings(String s1, String s2) {
+        String[] rowsOne = s1.split("\n");
+        String[] rowsTwo = s2.split("\n");
+
+        if (rowsOne.length != rowsTwo.length)
+            return false;
+
+        for (int i = 0; i < rowsOne.length; i++) {
+            String row1 = rowsOne[i];
+            String row2 = rowsTwo[i];
+
+            if (row1.equals(row2))
+                continue;
+
+            String[] fields1 = row1.split(",");
+            String[] fields2 = row2.split(",");
+
+            for (int j = 0; j < fields1.length; j++) {
+                if (fields1[j].equals(fields2[j])) {
+                    continue;
+                } else if (fields1[j].indexOf('.') < 0) {
+                    return false;
+                } else {
+                    fields1[j] = fields1[j].split("=")[1];
+                    fields2[j] = fields2[j].split("=")[1];
+                    Double double1 = Double.parseDouble(fields1[j]);
+                    Double double2 = Double.parseDouble(fields2[j]);
+                    float float1 = (float) double1.doubleValue();
+                    float float2 = (float) double2.doubleValue();
+
+                    if (Math.abs(float1 - float2) == 0)
+                        continue;
+                    else {
+                        return false;
+                    }
+                }
+            }
+        }
+        return true;
+    }
+
+}
diff --git a/pregelix/pregelix-example/src/test/resources/cluster/data.properties b/pregelix/pregelix-example/src/test/resources/cluster/data.properties
new file mode 100644
index 0000000..daf881e
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/cluster/data.properties
@@ -0,0 +1 @@
+store=teststore
\ No newline at end of file
diff --git a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsReal.result b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsReal.result
new file mode 100644
index 0000000..b8efedc
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsReal.result
@@ -0,0 +1,20 @@
+0|Vertex(id=0,value=0, edges=(1,))
+1|Vertex(id=1,value=0, edges=(1,2,))
+2|Vertex(id=2,value=0, edges=(1,2,3,))
+3|Vertex(id=3,value=0, edges=(1,2,3,4,))
+4|Vertex(id=4,value=0, edges=(1,2,3,4,5,))
+5|Vertex(id=5,value=0, edges=(1,2,3,4,5,6,))
+6|Vertex(id=6,value=0, edges=(1,2,3,4,5,6,7,))
+7|Vertex(id=7,value=0, edges=(1,2,3,4,5,6,7,8,))
+8|Vertex(id=8,value=0, edges=(1,2,3,4,5,6,7,8,9,))
+9|Vertex(id=9,value=0, edges=(1,2,3,4,5,6,7,8,9,10,))
+10|Vertex(id=10,value=0, edges=(11,))
+11|Vertex(id=11,value=0, edges=(11,12,))
+12|Vertex(id=12,value=0, edges=(11,12,13,))
+13|Vertex(id=13,value=0, edges=(11,12,13,14,))
+14|Vertex(id=14,value=0, edges=(11,12,13,14,15,))
+15|Vertex(id=15,value=0, edges=(11,12,13,14,15,16,))
+16|Vertex(id=16,value=0, edges=(11,12,13,14,15,16,17,))
+17|Vertex(id=17,value=0, edges=(11,12,13,14,15,16,17,18,))
+18|Vertex(id=18,value=0, edges=(11,12,13,14,15,16,17,18,19,))
+19|Vertex(id=19,value=0, edges=(0,11,12,13,14,15,16,17,18,19,))
diff --git a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex.result b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex.result
new file mode 100644
index 0000000..ad448b2
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex.result
@@ -0,0 +1,23 @@
+0|Vertex(id=0,value=0, edges=(1,50,))
+1|Vertex(id=1,value=0, edges=(1,2,))
+2|Vertex(id=2,value=0, edges=(1,2,3,))
+3|Vertex(id=3,value=0, edges=(1,2,3,4,))
+4|Vertex(id=4,value=0, edges=(1,2,3,4,5,))
+5|Vertex(id=5,value=0, edges=(1,2,3,4,5,6,))
+6|Vertex(id=6,value=0, edges=(1,2,3,4,5,6,7,))
+7|Vertex(id=7,value=0, edges=(1,2,3,4,5,6,7,8,))
+8|Vertex(id=8,value=0, edges=(1,2,3,4,5,6,7,8,9,))
+9|Vertex(id=9,value=0, edges=(1,2,3,4,5,6,7,8,9,10,))
+10|Vertex(id=10,value=0, edges=(11,99,))
+11|Vertex(id=11,value=0, edges=(11,12,101,))
+12|Vertex(id=12,value=0, edges=(11,12,13,))
+13|Vertex(id=13,value=0, edges=(11,12,13,14,))
+14|Vertex(id=14,value=0, edges=(11,12,13,14,15,))
+15|Vertex(id=15,value=0, edges=(11,12,13,14,15,16,))
+16|Vertex(id=16,value=0, edges=(11,12,13,14,15,16,17,))
+17|Vertex(id=17,value=0, edges=(11,12,13,14,15,16,17,18,))
+18|Vertex(id=18,value=0, edges=(11,12,13,14,15,16,17,18,19,))
+19|Vertex(id=19,value=0, edges=(0,11,12,13,14,15,16,17,18,19,))
+21|Vertex(id=21,value=21, edges=(22,23,24,))
+25|Vertex(id=25,value=25, edges=())
+27|Vertex(id=27,value=27, edges=())
diff --git a/pregelix/pregelix-example/src/test/resources/expected/PageRank.result b/pregelix/pregelix-example/src/test/resources/expected/PageRank.result
new file mode 100644
index 0000000..f38e191
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/expected/PageRank.result
@@ -0,0 +1,20 @@
+0|Vertex(id=0,value=0.008290140026154316, edges=(1,))
+1|Vertex(id=1,value=0.1535152819247165, edges=(1,2,))
+2|Vertex(id=2,value=0.14646839195826475, edges=(1,2,3,))
+3|Vertex(id=3,value=0.08125113985998214, edges=(1,2,3,4,))
+4|Vertex(id=4,value=0.03976979906329426, edges=(1,2,3,4,5,))
+5|Vertex(id=5,value=0.0225041581462058, edges=(1,2,3,4,5,6,))
+6|Vertex(id=6,value=0.015736276824953852, edges=(1,2,3,4,5,6,7,))
+7|Vertex(id=7,value=0.012542224114863661, edges=(1,2,3,4,5,6,7,8,))
+8|Vertex(id=8,value=0.010628239626209894, edges=(1,2,3,4,5,6,7,8,9,))
+9|Vertex(id=9,value=0.009294348455354817, edges=(1,2,3,4,5,6,7,8,9,10,))
+10|Vertex(id=10,value=0.008290140026154316, edges=(11,))
+11|Vertex(id=11,value=0.15351528192471647, edges=(11,12,))
+12|Vertex(id=12,value=0.14646839195826472, edges=(11,12,13,))
+13|Vertex(id=13,value=0.08125113985998214, edges=(11,12,13,14,))
+14|Vertex(id=14,value=0.03976979906329425, edges=(11,12,13,14,15,))
+15|Vertex(id=15,value=0.0225041581462058, edges=(11,12,13,14,15,16,))
+16|Vertex(id=16,value=0.015736276824953852, edges=(11,12,13,14,15,16,17,))
+17|Vertex(id=17,value=0.012542224114863661, edges=(11,12,13,14,15,16,17,18,))
+18|Vertex(id=18,value=0.010628239626209894, edges=(11,12,13,14,15,16,17,18,19,))
+19|Vertex(id=19,value=0.009294348455354817, edges=(0,11,12,13,14,15,16,17,18,19,))
diff --git a/pregelix/pregelix-example/src/test/resources/expected/PageRankReal.result b/pregelix/pregelix-example/src/test/resources/expected/PageRankReal.result
new file mode 100644
index 0000000..ab05d38
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/expected/PageRankReal.result
@@ -0,0 +1,20 @@
+0|Vertex(id=0,value=0.008290140026154316, edges=(1,))
+1|Vertex(id=1,value=0.1535152819247165, edges=(1,2,))
+2|Vertex(id=2,value=0.14646839195826475, edges=(1,2,3,))
+3|Vertex(id=3,value=0.08125113985998214, edges=(1,2,3,4,))
+4|Vertex(id=4,value=0.03976979906329426, edges=(1,2,3,4,5,))
+5|Vertex(id=5,value=0.0225041581462058, edges=(1,2,3,4,5,6,))
+6|Vertex(id=6,value=0.015736276824953852, edges=(1,2,3,4,5,6,7,))
+7|Vertex(id=7,value=0.012542224114863661, edges=(1,2,3,4,5,6,7,8,))
+8|Vertex(id=8,value=0.010628239626209894, edges=(1,2,3,4,5,6,7,8,9,))
+9|Vertex(id=9,value=0.009294348455354817, edges=(1,2,3,4,5,6,7,8,9,10,))
+10|Vertex(id=10,value=0.008290140026154316, edges=(11,))
+11|Vertex(id=11,value=0.15351528192471647, edges=(11,12,))
+12|Vertex(id=12,value=0.14646839195826472, edges=(11,12,13,))
+13|Vertex(id=13,value=0.08125113985998214, edges=(11,12,13,14,))
+14|Vertex(id=14,value=0.03976979906329426, edges=(11,12,13,14,15,))
+15|Vertex(id=15,value=0.0225041581462058, edges=(11,12,13,14,15,16,))
+16|Vertex(id=16,value=0.015736276824953852, edges=(11,12,13,14,15,16,17,))
+17|Vertex(id=17,value=0.012542224114863661, edges=(11,12,13,14,15,16,17,18,))
+18|Vertex(id=18,value=0.010628239626209894, edges=(11,12,13,14,15,16,17,18,19,))
+19|Vertex(id=19,value=0.009294348455354817, edges=(0,11,12,13,14,15,16,17,18,19,))
diff --git a/pregelix/pregelix-example/src/test/resources/expected/PageRankRealComplex.result b/pregelix/pregelix-example/src/test/resources/expected/PageRankRealComplex.result
new file mode 100644
index 0000000..1fc108a
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/expected/PageRankRealComplex.result
@@ -0,0 +1,23 @@
+0|Vertex(id=0,value=0.0072088164890121405, edges=(1,50,))
+1|Vertex(id=1,value=0.12352056961948686, edges=(1,2,))
+2|Vertex(id=2,value=0.12045670441668178, edges=(1,2,3,))
+3|Vertex(id=3,value=0.06798545786459467, edges=(1,2,3,4,))
+4|Vertex(id=4,value=0.03387281259892814, edges=(1,2,3,4,5,))
+5|Vertex(id=5,value=0.01942600635480669, edges=(1,2,3,4,5,6,))
+6|Vertex(id=6,value=0.013661020012182747, edges=(1,2,3,4,5,6,7,))
+7|Vertex(id=7,value=0.0109034351563503, edges=(1,2,3,4,5,6,7,8,))
+8|Vertex(id=8,value=0.009241684574402657, edges=(1,2,3,4,5,6,7,8,9,))
+9|Vertex(id=9,value=0.008082028259564783, edges=(1,2,3,4,5,6,7,8,9,10,))
+10|Vertex(id=10,value=0.007208817414047232, edges=(11,99,))
+11|Vertex(id=11,value=0.07555839219845861, edges=(11,12,101,))
+12|Vertex(id=12,value=0.07249452699565352, edges=(11,12,13,))
+13|Vertex(id=13,value=0.05063539695954156, edges=(11,12,13,14,))
+14|Vertex(id=14,value=0.029644452692487822, edges=(11,12,13,14,15,))
+15|Vertex(id=15,value=0.018670183493927354, edges=(11,12,13,14,15,16,))
+16|Vertex(id=16,value=0.013558283213067561, edges=(11,12,13,14,15,16,17,))
+17|Vertex(id=17,value=0.010892790899883237, edges=(11,12,13,14,15,16,17,18,))
+18|Vertex(id=18,value=0.009240874593661061, edges=(11,12,13,14,15,16,17,18,19,))
+19|Vertex(id=19,value=0.008081987856433137, edges=(0,11,12,13,14,15,16,17,18,19,))
+21|Vertex(id=21,value=0.006521739130434782, edges=(22,23,24,))
+25|Vertex(id=25,value=0.006521739130434782, edges=())
+27|Vertex(id=27,value=0.006521739130434782, edges=())
diff --git a/pregelix/pregelix-example/src/test/resources/expected/ShortestPaths.result b/pregelix/pregelix-example/src/test/resources/expected/ShortestPaths.result
new file mode 100644
index 0000000..7bb0ca3
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/expected/ShortestPaths.result
@@ -0,0 +1,20 @@
+0|Vertex(id=0,value=0.0, edges=(1,))
+1|Vertex(id=1,value=0.0, edges=(1,2,))
+2|Vertex(id=2,value=100.0, edges=(1,2,3,))
+3|Vertex(id=3,value=300.0, edges=(1,2,3,4,))
+4|Vertex(id=4,value=600.0, edges=(1,2,3,4,5,))
+5|Vertex(id=5,value=1000.0, edges=(1,2,3,4,5,6,))
+6|Vertex(id=6,value=1500.0, edges=(1,2,3,4,5,6,7,))
+7|Vertex(id=7,value=2100.0, edges=(1,2,3,4,5,6,7,8,))
+8|Vertex(id=8,value=2800.0, edges=(1,2,3,4,5,6,7,8,9,))
+9|Vertex(id=9,value=3600.0, edges=(1,2,3,4,5,6,7,8,9,10,))
+10|Vertex(id=10,value=4500.0, edges=(11,))
+11|Vertex(id=11,value=5500.0, edges=(11,12,))
+12|Vertex(id=12,value=6600.0, edges=(11,12,13,))
+13|Vertex(id=13,value=7800.0, edges=(11,12,13,14,))
+14|Vertex(id=14,value=9100.0, edges=(11,12,13,14,15,))
+15|Vertex(id=15,value=10500.0, edges=(11,12,13,14,15,16,))
+16|Vertex(id=16,value=12000.0, edges=(11,12,13,14,15,16,17,))
+17|Vertex(id=17,value=13600.0, edges=(11,12,13,14,15,16,17,18,))
+18|Vertex(id=18,value=15300.0, edges=(11,12,13,14,15,16,17,18,19,))
+19|Vertex(id=19,value=17100.0, edges=(0,11,12,13,14,15,16,17,18,19,))
diff --git a/pregelix/pregelix-example/src/test/resources/expected/ShortestPathsReal.result b/pregelix/pregelix-example/src/test/resources/expected/ShortestPathsReal.result
new file mode 100644
index 0000000..f2c31a6
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/expected/ShortestPathsReal.result
@@ -0,0 +1,20 @@
+0|Vertex(id=0,value=0.0, edges=(1,))
+1|Vertex(id=1,value=1.0, edges=(1,2,))
+2|Vertex(id=2,value=2.0, edges=(1,2,3,))
+3|Vertex(id=3,value=3.0, edges=(1,2,3,4,))
+4|Vertex(id=4,value=4.0, edges=(1,2,3,4,5,))
+5|Vertex(id=5,value=5.0, edges=(1,2,3,4,5,6,))
+6|Vertex(id=6,value=6.0, edges=(1,2,3,4,5,6,7,))
+7|Vertex(id=7,value=7.0, edges=(1,2,3,4,5,6,7,8,))
+8|Vertex(id=8,value=8.0, edges=(1,2,3,4,5,6,7,8,9,))
+9|Vertex(id=9,value=9.0, edges=(1,2,3,4,5,6,7,8,9,10,))
+10|Vertex(id=10,value=10.0, edges=(11,))
+11|Vertex(id=11,value=11.0, edges=(11,12,))
+12|Vertex(id=12,value=12.0, edges=(11,12,13,))
+13|Vertex(id=13,value=13.0, edges=(11,12,13,14,))
+14|Vertex(id=14,value=14.0, edges=(11,12,13,14,15,))
+15|Vertex(id=15,value=15.0, edges=(11,12,13,14,15,16,))
+16|Vertex(id=16,value=16.0, edges=(11,12,13,14,15,16,17,))
+17|Vertex(id=17,value=17.0, edges=(11,12,13,14,15,16,17,18,))
+18|Vertex(id=18,value=18.0, edges=(11,12,13,14,15,16,17,18,19,))
+19|Vertex(id=19,value=19.0, edges=(0,11,12,13,14,15,16,17,18,19,))
diff --git a/pregelix/pregelix-example/src/test/resources/hadoop/conf/core-site.xml b/pregelix/pregelix-example/src/test/resources/hadoop/conf/core-site.xml
new file mode 100644
index 0000000..47dfac5
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/hadoop/conf/core-site.xml
@@ -0,0 +1,18 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+
+<!-- Put site-specific property overrides in this file. -->
+
+<configuration>
+
+<property>
+    <name>fs.default.name</name>
+    <value>hdfs://127.0.0.1:31888</value>
+</property>
+<property>
+    <name>hadoop.tmp.dir</name>
+    <value>/tmp/hadoop</value>
+</property>
+
+
+</configuration>
diff --git a/pregelix/pregelix-example/src/test/resources/hadoop/conf/hdfs-site.xml b/pregelix/pregelix-example/src/test/resources/hadoop/conf/hdfs-site.xml
new file mode 100644
index 0000000..8d29b1d
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/hadoop/conf/hdfs-site.xml
@@ -0,0 +1,18 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+
+<!-- Put site-specific property overrides in this file. -->
+
+<configuration>
+
+<property>
+   <name>dfs.replication</name>
+   <value>1</value>
+</property>
+
+<property>
+	<name>dfs.block.size</name>
+	<value>65536</value>
+</property>
+
+</configuration>
diff --git a/pregelix/pregelix-example/src/test/resources/hadoop/conf/log4j.properties b/pregelix/pregelix-example/src/test/resources/hadoop/conf/log4j.properties
new file mode 100755
index 0000000..d5e6004
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/hadoop/conf/log4j.properties
@@ -0,0 +1,94 @@
+# Define some default values that can be overridden by system properties
+hadoop.root.logger=FATAL,console
+hadoop.log.dir=.
+hadoop.log.file=hadoop.log
+
+# Define the root logger to the system property "hadoop.root.logger".
+log4j.rootLogger=${hadoop.root.logger}, EventCounter
+
+# Logging Threshold
+log4j.threshhold=FATAL
+
+#
+# Daily Rolling File Appender
+#
+
+log4j.appender.DRFA=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.DRFA.File=${hadoop.log.dir}/${hadoop.log.file}
+
+# Rollver at midnight
+log4j.appender.DRFA.DatePattern=.yyyy-MM-dd
+
+# 30-day backup
+#log4j.appender.DRFA.MaxBackupIndex=30
+log4j.appender.DRFA.layout=org.apache.log4j.PatternLayout
+
+# Pattern format: Date LogLevel LoggerName LogMessage
+log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+# Debugging Pattern format
+#log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
+
+
+#
+# console
+# Add "console" to rootlogger above if you want to use this 
+#
+
+log4j.appender.console=org.apache.log4j.ConsoleAppender
+log4j.appender.console.target=System.err
+log4j.appender.console.layout=org.apache.log4j.PatternLayout
+log4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{2}: %m%n
+
+#
+# TaskLog Appender
+#
+
+#Default values
+hadoop.tasklog.taskid=null
+hadoop.tasklog.noKeepSplits=4
+hadoop.tasklog.totalLogFileSize=100
+hadoop.tasklog.purgeLogSplits=true
+hadoop.tasklog.logsRetainHours=12
+
+log4j.appender.TLA=org.apache.hadoop.mapred.TaskLogAppender
+log4j.appender.TLA.taskId=${hadoop.tasklog.taskid}
+log4j.appender.TLA.totalLogFileSize=${hadoop.tasklog.totalLogFileSize}
+
+log4j.appender.TLA.layout=org.apache.log4j.PatternLayout
+log4j.appender.TLA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+
+#
+# Rolling File Appender
+#
+
+#log4j.appender.RFA=org.apache.log4j.RollingFileAppender
+#log4j.appender.RFA.File=${hadoop.log.dir}/${hadoop.log.file}
+
+# Logfile size and and 30-day backups
+#log4j.appender.RFA.MaxFileSize=1MB
+#log4j.appender.RFA.MaxBackupIndex=30
+
+#log4j.appender.RFA.layout=org.apache.log4j.PatternLayout
+#log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} - %m%n
+#log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
+
+#
+# FSNamesystem Audit logging
+# All audit events are logged at INFO level
+#
+log4j.logger.org.apache.hadoop.fs.FSNamesystem.audit=WARN
+
+# Custom Logging levels
+
+#log4j.logger.org.apache.hadoop.mapred.JobTracker=DEBUG
+#log4j.logger.org.apache.hadoop.mapred.TaskTracker=DEBUG
+#log4j.logger.org.apache.hadoop.fs.FSNamesystem=DEBUG
+
+# Jets3t library
+log4j.logger.org.jets3t.service.impl.rest.httpclient.RestS3Service=ERROR
+
+#
+# Event Counter Appender
+# Sends counts of logging messages at different severity levels to Hadoop Metrics.
+#
+log4j.appender.EventCounter=org.apache.hadoop.metrics.jvm.EventCounter
diff --git a/pregelix/pregelix-example/src/test/resources/hadoop/conf/mapred-site.xml b/pregelix/pregelix-example/src/test/resources/hadoop/conf/mapred-site.xml
new file mode 100644
index 0000000..1b9a4d6
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/hadoop/conf/mapred-site.xml
@@ -0,0 +1,25 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+
+<!-- Put site-specific property overrides in this file. -->
+
+<configuration>
+
+  <property>
+    <name>mapred.job.tracker</name>
+    <value>localhost:29007</value>
+  </property>
+  <property>
+     <name>mapred.tasktracker.map.tasks.maximum</name>
+     <value>20</value>
+  </property>
+   <property>
+      <name>mapred.tasktracker.reduce.tasks.maximum</name>
+      <value>20</value>
+   </property>
+   <property>
+      <name>mapred.min.split.size</name>
+      <value>65536</value>
+   </property>
+
+</configuration>
diff --git a/pregelix/pregelix-example/src/test/resources/hyracks-deployment.properties b/pregelix/pregelix-example/src/test/resources/hyracks-deployment.properties
new file mode 100644
index 0000000..9c42b89
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/hyracks-deployment.properties
@@ -0,0 +1,2 @@
+#cc.bootstrap.class=edu.uci.ics.asterix.hyracks.bootstrap.CCBootstrapImpl
+nc.bootstrap.class=edu.uci.ics.pregelix.runtime.bootstrap.NCBootstrapImpl
diff --git a/pregelix/pregelix-example/src/test/resources/ignore.txt b/pregelix/pregelix-example/src/test/resources/ignore.txt
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/ignore.txt
diff --git a/pregelix/pregelix-example/src/test/resources/jobs/ConnectedComponentsReal.xml b/pregelix/pregelix-example/src/test/resources/jobs/ConnectedComponentsReal.xml
new file mode 100644
index 0000000..fc2ab0a
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/jobs/ConnectedComponentsReal.xml
@@ -0,0 +1,142 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
+<property><name>giraph.combinerClass</name><value>edu.uci.ics.pregelix.example.ConnectedComponentsVertex$SimpleMinCombiner</value></property>
+<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
+<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
+<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
+<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
+<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
+<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
+<property><name>mapred.input.dir</name><value>file:/webmap</value></property>
+<property><name>mapred.submit.replication</name><value>10</value></property>
+<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
+<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
+<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
+<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
+<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
+<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
+<property><name>keep.failed.task.files</name><value>false</value></property>
+<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
+<property><name>io.bytes.per.checksum</name><value>512</value></property>
+<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
+<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
+<property><name>giraph.numVertices</name><value>20</value></property>
+<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
+<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
+<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
+<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
+<property><name>fs.checkpoint.period</name><value>3600</value></property>
+<property><name>mapred.child.tmp</name><value>./tmp</value></property>
+<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
+<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
+<property><name>hadoop.logfile.count</name><value>10</value></property>
+<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
+<property><name>mapred.output.dir</name><value>/result</value></property>
+<property><name>giraph.vertexClass</name><value>edu.uci.ics.pregelix.example.ConnectedComponentsVertex</value></property>
+<property><name>io.map.index.skip</name><value>0</value></property>
+<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
+<property><name>mapred.output.compress</name><value>false</value></property>
+<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
+<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
+<property><name>fs.checkpoint.size</name><value>67108864</value></property>
+<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
+<property><name>mapred.job.name</name><value>ConnectedComponents</value></property>
+<property><name>local.cache.size</name><value>10737418240</value></property>
+<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
+<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
+<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
+<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
+<property><name>mapred.task.timeout</name><value>600000</value></property>
+<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
+<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
+<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
+<property><name>ipc.client.kill.max</name><value>10</value></property>
+<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
+<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
+<property><name>io.sort.record.percent</name><value>0.05</value></property>
+<property><name>hadoop.security.authorization</name><value>false</value></property>
+<property><name>mapred.max.tracker.failures</name><value>4</value></property>
+<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
+<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
+<property><name>mapred.map.tasks</name><value>2</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
+<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
+<property><name>fs.default.name</name><value>file:///</value></property>
+<property><name>tasktracker.http.threads</name><value>40</value></property>
+<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
+<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
+<property><name>mapred.reduce.tasks</name><value>1</value></property>
+<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
+<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
+<property><name>io.file.buffer.size</name><value>4096</value></property>
+<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
+<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
+<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
+<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
+<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
+<property><name>hadoop.native.lib</name><value>true</value></property>
+<property><name>fs.s3.block.size</name><value>67108864</value></property>
+<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
+<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
+<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
+<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
+<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
+<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
+<property><name>mapred.queue.names</name><value>default</value></property>
+<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
+<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
+<property><name>mapred.job.tracker</name><value>local</value></property>
+<property><name>io.skip.checksum.errors</name><value>false</value></property>
+<property><name>giraph.vertexInputFormatClass</name><value>edu.uci.ics.pregelix.example.inputformat.TextConnectedComponentsInputFormat</value></property>
+<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
+<property><name>fs.s3.maxRetries</name><value>4</value></property>
+<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
+<property><name>fs.trash.interval</name><value>0</value></property>
+<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
+<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
+<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
+<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
+<property><name>io.sort.mb</name><value>100</value></property>
+<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
+<property><name>io.sort.factor</name><value>10</value></property>
+<property><name>mapred.task.profile</name><value>false</value></property>
+<property><name>job.end.retry.interval</name><value>30000</value></property>
+<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
+<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
+<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
+<property><name>webinterface.private.actions</name><value>false</value></property>
+<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
+<property><name>giraph.vertexOutputFormatClass</name><value>edu.uci.ics.pregelix.example.ConnectedComponentsVertex$SimpleConnectedComponentsVertexOutputFormat</value></property>
+<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
+<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
+<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
+<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.compress.map.output</name><value>false</value></property>
+<property><name>io.sort.spill.percent</name><value>0.80</value></property>
+<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
+<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
+<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
+<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
+<property><name>job.end.retry.attempts</name><value>0</value></property>
+<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
+<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
+<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
+<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
+<property><name>hadoop.logfile.size</name><value>10000000</value></property>
+<property><name>mapred.job.queue.name</name><value>default</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
+<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
+<property><name>topology.script.number.args</name><value>100</value></property>
+<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
+<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
+<property><name>mapred.task.cache.levels</name><value>2</value></property>
+<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
+<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
+<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
+<property><name>mapred.min.split.size</name><value>0</value></property>
+<property><name>mapred.map.max.attempts</name><value>4</value></property>
+<property><name>jobclient.output.filter</name><value>FAILED</value></property>
+<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
+<property><name>mapred.acls.enabled</name><value>false</value></property>
+</configuration>
\ No newline at end of file
diff --git a/pregelix/pregelix-example/src/test/resources/jobs/ConnectedComponentsRealComplex.xml b/pregelix/pregelix-example/src/test/resources/jobs/ConnectedComponentsRealComplex.xml
new file mode 100644
index 0000000..1a021c2
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/jobs/ConnectedComponentsRealComplex.xml
@@ -0,0 +1,142 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
+<property><name>giraph.combinerClass</name><value>edu.uci.ics.pregelix.example.ConnectedComponentsVertex$SimpleMinCombiner</value></property>
+<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
+<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
+<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
+<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
+<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
+<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
+<property><name>mapred.input.dir</name><value>file:/webmapcomplex</value></property>
+<property><name>mapred.submit.replication</name><value>10</value></property>
+<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
+<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
+<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
+<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
+<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
+<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
+<property><name>keep.failed.task.files</name><value>false</value></property>
+<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
+<property><name>io.bytes.per.checksum</name><value>512</value></property>
+<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
+<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
+<property><name>giraph.numVertices</name><value>23</value></property>
+<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
+<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
+<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
+<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
+<property><name>fs.checkpoint.period</name><value>3600</value></property>
+<property><name>mapred.child.tmp</name><value>./tmp</value></property>
+<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
+<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
+<property><name>hadoop.logfile.count</name><value>10</value></property>
+<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
+<property><name>mapred.output.dir</name><value>/resultcomplex</value></property>
+<property><name>giraph.vertexClass</name><value>edu.uci.ics.pregelix.example.ConnectedComponentsVertex</value></property>
+<property><name>io.map.index.skip</name><value>0</value></property>
+<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
+<property><name>mapred.output.compress</name><value>false</value></property>
+<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
+<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
+<property><name>fs.checkpoint.size</name><value>67108864</value></property>
+<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
+<property><name>mapred.job.name</name><value>ConnectedComponents</value></property>
+<property><name>local.cache.size</name><value>10737418240</value></property>
+<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
+<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
+<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
+<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
+<property><name>mapred.task.timeout</name><value>600000</value></property>
+<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
+<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
+<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
+<property><name>ipc.client.kill.max</name><value>10</value></property>
+<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
+<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
+<property><name>io.sort.record.percent</name><value>0.05</value></property>
+<property><name>hadoop.security.authorization</name><value>false</value></property>
+<property><name>mapred.max.tracker.failures</name><value>4</value></property>
+<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
+<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
+<property><name>mapred.map.tasks</name><value>2</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
+<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
+<property><name>fs.default.name</name><value>file:///</value></property>
+<property><name>tasktracker.http.threads</name><value>40</value></property>
+<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
+<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
+<property><name>mapred.reduce.tasks</name><value>1</value></property>
+<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
+<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
+<property><name>io.file.buffer.size</name><value>4096</value></property>
+<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
+<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
+<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
+<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
+<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
+<property><name>hadoop.native.lib</name><value>true</value></property>
+<property><name>fs.s3.block.size</name><value>67108864</value></property>
+<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
+<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
+<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
+<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
+<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
+<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
+<property><name>mapred.queue.names</name><value>default</value></property>
+<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
+<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
+<property><name>mapred.job.tracker</name><value>local</value></property>
+<property><name>io.skip.checksum.errors</name><value>false</value></property>
+<property><name>giraph.vertexInputFormatClass</name><value>edu.uci.ics.pregelix.example.inputformat.TextConnectedComponentsInputFormat</value></property>
+<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
+<property><name>fs.s3.maxRetries</name><value>4</value></property>
+<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
+<property><name>fs.trash.interval</name><value>0</value></property>
+<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
+<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
+<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
+<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
+<property><name>io.sort.mb</name><value>100</value></property>
+<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
+<property><name>io.sort.factor</name><value>10</value></property>
+<property><name>mapred.task.profile</name><value>false</value></property>
+<property><name>job.end.retry.interval</name><value>30000</value></property>
+<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
+<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
+<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
+<property><name>webinterface.private.actions</name><value>false</value></property>
+<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
+<property><name>giraph.vertexOutputFormatClass</name><value>edu.uci.ics.pregelix.example.ConnectedComponentsVertex$SimpleConnectedComponentsVertexOutputFormat</value></property>
+<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
+<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
+<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
+<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.compress.map.output</name><value>false</value></property>
+<property><name>io.sort.spill.percent</name><value>0.80</value></property>
+<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
+<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
+<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
+<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
+<property><name>job.end.retry.attempts</name><value>0</value></property>
+<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
+<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
+<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
+<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
+<property><name>hadoop.logfile.size</name><value>10000000</value></property>
+<property><name>mapred.job.queue.name</name><value>default</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
+<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
+<property><name>topology.script.number.args</name><value>100</value></property>
+<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
+<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
+<property><name>mapred.task.cache.levels</name><value>2</value></property>
+<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
+<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
+<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
+<property><name>mapred.min.split.size</name><value>0</value></property>
+<property><name>mapred.map.max.attempts</name><value>4</value></property>
+<property><name>jobclient.output.filter</name><value>FAILED</value></property>
+<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
+<property><name>mapred.acls.enabled</name><value>false</value></property>
+</configuration>
\ No newline at end of file
diff --git a/pregelix/pregelix-example/src/test/resources/jobs/PageRank.xml b/pregelix/pregelix-example/src/test/resources/jobs/PageRank.xml
new file mode 100644
index 0000000..e5294b7
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/jobs/PageRank.xml
@@ -0,0 +1,142 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
+<property><name>giraph.combinerClass</name><value>edu.uci.ics.pregelix.example.PageRankVertex$SimpleSumCombiner</value></property>
+<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
+<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
+<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
+<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
+<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
+<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
+<property><name>mapred.input.dir</name><value>file:/webmap</value></property>
+<property><name>mapred.submit.replication</name><value>10</value></property>
+<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
+<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
+<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
+<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
+<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
+<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
+<property><name>keep.failed.task.files</name><value>false</value></property>
+<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
+<property><name>io.bytes.per.checksum</name><value>512</value></property>
+<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
+<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
+<property><name>giraph.numVertices</name><value>20</value></property>
+<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
+<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
+<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
+<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
+<property><name>fs.checkpoint.period</name><value>3600</value></property>
+<property><name>mapred.child.tmp</name><value>./tmp</value></property>
+<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
+<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
+<property><name>hadoop.logfile.count</name><value>10</value></property>
+<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
+<property><name>mapred.output.dir</name><value>/result</value></property>
+<property><name>giraph.vertexClass</name><value>edu.uci.ics.pregelix.example.PageRankVertex</value></property>
+<property><name>io.map.index.skip</name><value>0</value></property>
+<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
+<property><name>mapred.output.compress</name><value>false</value></property>
+<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
+<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
+<property><name>fs.checkpoint.size</name><value>67108864</value></property>
+<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
+<property><name>mapred.job.name</name><value>PageRank</value></property>
+<property><name>local.cache.size</name><value>10737418240</value></property>
+<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
+<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
+<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
+<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
+<property><name>mapred.task.timeout</name><value>600000</value></property>
+<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
+<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
+<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
+<property><name>ipc.client.kill.max</name><value>10</value></property>
+<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
+<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
+<property><name>io.sort.record.percent</name><value>0.05</value></property>
+<property><name>hadoop.security.authorization</name><value>false</value></property>
+<property><name>mapred.max.tracker.failures</name><value>4</value></property>
+<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
+<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
+<property><name>mapred.map.tasks</name><value>2</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
+<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
+<property><name>fs.default.name</name><value>file:///</value></property>
+<property><name>tasktracker.http.threads</name><value>40</value></property>
+<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
+<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
+<property><name>mapred.reduce.tasks</name><value>1</value></property>
+<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
+<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
+<property><name>io.file.buffer.size</name><value>4096</value></property>
+<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
+<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
+<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
+<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
+<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
+<property><name>hadoop.native.lib</name><value>true</value></property>
+<property><name>fs.s3.block.size</name><value>67108864</value></property>
+<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
+<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
+<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
+<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
+<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
+<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
+<property><name>mapred.queue.names</name><value>default</value></property>
+<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
+<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
+<property><name>mapred.job.tracker</name><value>local</value></property>
+<property><name>io.skip.checksum.errors</name><value>false</value></property>
+<property><name>giraph.vertexInputFormatClass</name><value>edu.uci.ics.pregelix.example.PageRankVertex$SimplePageRankVertexInputFormat</value></property>
+<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
+<property><name>fs.s3.maxRetries</name><value>4</value></property>
+<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
+<property><name>fs.trash.interval</name><value>0</value></property>
+<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
+<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
+<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
+<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
+<property><name>io.sort.mb</name><value>100</value></property>
+<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
+<property><name>io.sort.factor</name><value>10</value></property>
+<property><name>mapred.task.profile</name><value>false</value></property>
+<property><name>job.end.retry.interval</name><value>30000</value></property>
+<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
+<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
+<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
+<property><name>webinterface.private.actions</name><value>false</value></property>
+<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
+<property><name>giraph.vertexOutputFormatClass</name><value>edu.uci.ics.pregelix.example.PageRankVertex$SimplePageRankVertexOutputFormat</value></property>
+<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
+<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
+<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
+<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.compress.map.output</name><value>false</value></property>
+<property><name>io.sort.spill.percent</name><value>0.80</value></property>
+<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
+<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
+<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
+<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
+<property><name>job.end.retry.attempts</name><value>0</value></property>
+<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
+<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
+<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
+<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
+<property><name>hadoop.logfile.size</name><value>10000000</value></property>
+<property><name>mapred.job.queue.name</name><value>default</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
+<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
+<property><name>topology.script.number.args</name><value>100</value></property>
+<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
+<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
+<property><name>mapred.task.cache.levels</name><value>2</value></property>
+<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
+<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
+<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
+<property><name>mapred.min.split.size</name><value>0</value></property>
+<property><name>mapred.map.max.attempts</name><value>4</value></property>
+<property><name>jobclient.output.filter</name><value>FAILED</value></property>
+<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
+<property><name>mapred.acls.enabled</name><value>false</value></property>
+</configuration>
\ No newline at end of file
diff --git a/pregelix/pregelix-example/src/test/resources/jobs/PageRankReal.xml b/pregelix/pregelix-example/src/test/resources/jobs/PageRankReal.xml
new file mode 100644
index 0000000..a3d0551
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/jobs/PageRankReal.xml
@@ -0,0 +1,142 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
+<property><name>giraph.combinerClass</name><value>edu.uci.ics.pregelix.example.PageRankVertex$SimpleSumCombiner</value></property>
+<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
+<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
+<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
+<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
+<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
+<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
+<property><name>mapred.input.dir</name><value>file:/webmap</value></property>
+<property><name>mapred.submit.replication</name><value>10</value></property>
+<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
+<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
+<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
+<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
+<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
+<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
+<property><name>keep.failed.task.files</name><value>false</value></property>
+<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
+<property><name>io.bytes.per.checksum</name><value>512</value></property>
+<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
+<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
+<property><name>giraph.numVertices</name><value>20</value></property>
+<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
+<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
+<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
+<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
+<property><name>fs.checkpoint.period</name><value>3600</value></property>
+<property><name>mapred.child.tmp</name><value>./tmp</value></property>
+<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
+<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
+<property><name>hadoop.logfile.count</name><value>10</value></property>
+<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
+<property><name>mapred.output.dir</name><value>/result</value></property>
+<property><name>giraph.vertexClass</name><value>edu.uci.ics.pregelix.example.PageRankVertex</value></property>
+<property><name>io.map.index.skip</name><value>0</value></property>
+<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
+<property><name>mapred.output.compress</name><value>false</value></property>
+<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
+<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
+<property><name>fs.checkpoint.size</name><value>67108864</value></property>
+<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
+<property><name>mapred.job.name</name><value>PageRank</value></property>
+<property><name>local.cache.size</name><value>10737418240</value></property>
+<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
+<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
+<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
+<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
+<property><name>mapred.task.timeout</name><value>600000</value></property>
+<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
+<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
+<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
+<property><name>ipc.client.kill.max</name><value>10</value></property>
+<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
+<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
+<property><name>io.sort.record.percent</name><value>0.05</value></property>
+<property><name>hadoop.security.authorization</name><value>false</value></property>
+<property><name>mapred.max.tracker.failures</name><value>4</value></property>
+<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
+<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
+<property><name>mapred.map.tasks</name><value>2</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
+<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
+<property><name>fs.default.name</name><value>file:///</value></property>
+<property><name>tasktracker.http.threads</name><value>40</value></property>
+<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
+<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
+<property><name>mapred.reduce.tasks</name><value>1</value></property>
+<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
+<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
+<property><name>io.file.buffer.size</name><value>4096</value></property>
+<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
+<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
+<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
+<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
+<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
+<property><name>hadoop.native.lib</name><value>true</value></property>
+<property><name>fs.s3.block.size</name><value>67108864</value></property>
+<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
+<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
+<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
+<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
+<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
+<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
+<property><name>mapred.queue.names</name><value>default</value></property>
+<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
+<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
+<property><name>mapred.job.tracker</name><value>local</value></property>
+<property><name>io.skip.checksum.errors</name><value>false</value></property>
+<property><name>giraph.vertexInputFormatClass</name><value>edu.uci.ics.pregelix.example.inputformat.TextPageRankInputFormat</value></property>
+<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
+<property><name>fs.s3.maxRetries</name><value>4</value></property>
+<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
+<property><name>fs.trash.interval</name><value>0</value></property>
+<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
+<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
+<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
+<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
+<property><name>io.sort.mb</name><value>100</value></property>
+<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
+<property><name>io.sort.factor</name><value>10</value></property>
+<property><name>mapred.task.profile</name><value>false</value></property>
+<property><name>job.end.retry.interval</name><value>30000</value></property>
+<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
+<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
+<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
+<property><name>webinterface.private.actions</name><value>false</value></property>
+<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
+<property><name>giraph.vertexOutputFormatClass</name><value>edu.uci.ics.pregelix.example.PageRankVertex$SimplePageRankVertexOutputFormat</value></property>
+<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
+<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
+<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
+<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.compress.map.output</name><value>false</value></property>
+<property><name>io.sort.spill.percent</name><value>0.80</value></property>
+<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
+<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
+<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
+<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
+<property><name>job.end.retry.attempts</name><value>0</value></property>
+<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
+<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
+<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
+<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
+<property><name>hadoop.logfile.size</name><value>10000000</value></property>
+<property><name>mapred.job.queue.name</name><value>default</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
+<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
+<property><name>topology.script.number.args</name><value>100</value></property>
+<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
+<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
+<property><name>mapred.task.cache.levels</name><value>2</value></property>
+<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
+<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
+<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
+<property><name>mapred.min.split.size</name><value>0</value></property>
+<property><name>mapred.map.max.attempts</name><value>4</value></property>
+<property><name>jobclient.output.filter</name><value>FAILED</value></property>
+<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
+<property><name>mapred.acls.enabled</name><value>false</value></property>
+</configuration>
\ No newline at end of file
diff --git a/pregelix/pregelix-example/src/test/resources/jobs/PageRankRealComplex.xml b/pregelix/pregelix-example/src/test/resources/jobs/PageRankRealComplex.xml
new file mode 100644
index 0000000..0aa829b
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/jobs/PageRankRealComplex.xml
@@ -0,0 +1,142 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
+<property><name>giraph.combinerClass</name><value>edu.uci.ics.pregelix.example.PageRankVertex$SimpleSumCombiner</value></property>
+<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
+<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
+<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
+<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
+<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
+<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
+<property><name>mapred.input.dir</name><value>file:/webmapcomplex</value></property>
+<property><name>mapred.submit.replication</name><value>10</value></property>
+<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
+<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
+<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
+<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
+<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
+<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
+<property><name>keep.failed.task.files</name><value>false</value></property>
+<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
+<property><name>io.bytes.per.checksum</name><value>512</value></property>
+<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
+<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
+<property><name>giraph.numVertices</name><value>23</value></property>
+<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
+<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
+<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
+<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
+<property><name>fs.checkpoint.period</name><value>3600</value></property>
+<property><name>mapred.child.tmp</name><value>./tmp</value></property>
+<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
+<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
+<property><name>hadoop.logfile.count</name><value>10</value></property>
+<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
+<property><name>mapred.output.dir</name><value>/resultcomplex</value></property>
+<property><name>giraph.vertexClass</name><value>edu.uci.ics.pregelix.example.PageRankVertex</value></property>
+<property><name>io.map.index.skip</name><value>0</value></property>
+<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
+<property><name>mapred.output.compress</name><value>false</value></property>
+<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
+<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
+<property><name>fs.checkpoint.size</name><value>67108864</value></property>
+<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
+<property><name>mapred.job.name</name><value>PageRank</value></property>
+<property><name>local.cache.size</name><value>10737418240</value></property>
+<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
+<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
+<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
+<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
+<property><name>mapred.task.timeout</name><value>600000</value></property>
+<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
+<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
+<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
+<property><name>ipc.client.kill.max</name><value>10</value></property>
+<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
+<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
+<property><name>io.sort.record.percent</name><value>0.05</value></property>
+<property><name>hadoop.security.authorization</name><value>false</value></property>
+<property><name>mapred.max.tracker.failures</name><value>4</value></property>
+<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
+<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
+<property><name>mapred.map.tasks</name><value>2</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
+<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
+<property><name>fs.default.name</name><value>file:///</value></property>
+<property><name>tasktracker.http.threads</name><value>40</value></property>
+<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
+<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
+<property><name>mapred.reduce.tasks</name><value>1</value></property>
+<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
+<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
+<property><name>io.file.buffer.size</name><value>4096</value></property>
+<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
+<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
+<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
+<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
+<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
+<property><name>hadoop.native.lib</name><value>true</value></property>
+<property><name>fs.s3.block.size</name><value>67108864</value></property>
+<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
+<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
+<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
+<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
+<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
+<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
+<property><name>mapred.queue.names</name><value>default</value></property>
+<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
+<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
+<property><name>mapred.job.tracker</name><value>local</value></property>
+<property><name>io.skip.checksum.errors</name><value>false</value></property>
+<property><name>giraph.vertexInputFormatClass</name><value>edu.uci.ics.pregelix.example.inputformat.TextPageRankInputFormat</value></property>
+<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
+<property><name>fs.s3.maxRetries</name><value>4</value></property>
+<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
+<property><name>fs.trash.interval</name><value>0</value></property>
+<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
+<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
+<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
+<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
+<property><name>io.sort.mb</name><value>100</value></property>
+<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
+<property><name>io.sort.factor</name><value>10</value></property>
+<property><name>mapred.task.profile</name><value>false</value></property>
+<property><name>job.end.retry.interval</name><value>30000</value></property>
+<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
+<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
+<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
+<property><name>webinterface.private.actions</name><value>false</value></property>
+<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
+<property><name>giraph.vertexOutputFormatClass</name><value>edu.uci.ics.pregelix.example.PageRankVertex$SimplePageRankVertexOutputFormat</value></property>
+<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
+<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
+<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
+<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.compress.map.output</name><value>false</value></property>
+<property><name>io.sort.spill.percent</name><value>0.80</value></property>
+<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
+<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
+<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
+<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
+<property><name>job.end.retry.attempts</name><value>0</value></property>
+<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
+<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
+<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
+<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
+<property><name>hadoop.logfile.size</name><value>10000000</value></property>
+<property><name>mapred.job.queue.name</name><value>default</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
+<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
+<property><name>topology.script.number.args</name><value>100</value></property>
+<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
+<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
+<property><name>mapred.task.cache.levels</name><value>2</value></property>
+<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
+<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
+<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
+<property><name>mapred.min.split.size</name><value>0</value></property>
+<property><name>mapred.map.max.attempts</name><value>4</value></property>
+<property><name>jobclient.output.filter</name><value>FAILED</value></property>
+<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
+<property><name>mapred.acls.enabled</name><value>false</value></property>
+</configuration>
\ No newline at end of file
diff --git a/pregelix/pregelix-example/src/test/resources/jobs/ShortestPaths.xml b/pregelix/pregelix-example/src/test/resources/jobs/ShortestPaths.xml
new file mode 100644
index 0000000..bae8cec
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/jobs/ShortestPaths.xml
@@ -0,0 +1,143 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
+<property><name>giraph.combinerClass</name><value>edu.uci.ics.pregelix.example.ShortestPathsVertex$SimpleMinCombiner</value></property>
+<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
+<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
+<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
+<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
+<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
+<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
+<property><name>mapred.input.dir</name><value>file:/webmap</value></property>
+<property><name>mapred.submit.replication</name><value>10</value></property>
+<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
+<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
+<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
+<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
+<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
+<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
+<property><name>keep.failed.task.files</name><value>false</value></property>
+<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
+<property><name>io.bytes.per.checksum</name><value>512</value></property>
+<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
+<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
+<property><name>giraph.numVertices</name><value>20</value></property>
+<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
+<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
+<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
+<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
+<property><name>fs.checkpoint.period</name><value>3600</value></property>
+<property><name>mapred.child.tmp</name><value>./tmp</value></property>
+<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
+<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
+<property><name>hadoop.logfile.count</name><value>10</value></property>
+<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
+<property><name>mapred.output.dir</name><value>/result</value></property>
+<property><name>giraph.vertexClass</name><value>edu.uci.ics.pregelix.example.ShortestPathsVertex</value></property>
+<property><name>io.map.index.skip</name><value>0</value></property>
+<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
+<property><name>mapred.output.compress</name><value>false</value></property>
+<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
+<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
+<property><name>fs.checkpoint.size</name><value>67108864</value></property>
+<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
+<property><name>mapred.job.name</name><value>ShortestPaths</value></property>
+<property><name>local.cache.size</name><value>10737418240</value></property>
+<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
+<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
+<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
+<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
+<property><name>mapred.task.timeout</name><value>600000</value></property>
+<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
+<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
+<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
+<property><name>ipc.client.kill.max</name><value>10</value></property>
+<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
+<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
+<property><name>io.sort.record.percent</name><value>0.05</value></property>
+<property><name>hadoop.security.authorization</name><value>false</value></property>
+<property><name>mapred.max.tracker.failures</name><value>4</value></property>
+<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
+<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
+<property><name>mapred.map.tasks</name><value>2</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
+<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
+<property><name>fs.default.name</name><value>file:///</value></property>
+<property><name>tasktracker.http.threads</name><value>40</value></property>
+<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
+<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
+<property><name>mapred.reduce.tasks</name><value>1</value></property>
+<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
+<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
+<property><name>io.file.buffer.size</name><value>4096</value></property>
+<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
+<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
+<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
+<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
+<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
+<property><name>hadoop.native.lib</name><value>true</value></property>
+<property><name>fs.s3.block.size</name><value>67108864</value></property>
+<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
+<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
+<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
+<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
+<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
+<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
+<property><name>mapred.queue.names</name><value>default</value></property>
+<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
+<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
+<property><name>mapred.job.tracker</name><value>local</value></property>
+<property><name>io.skip.checksum.errors</name><value>false</value></property>
+<property><name>giraph.vertexInputFormatClass</name><value>edu.uci.ics.pregelix.example.PageRankVertex$SimplePageRankVertexInputFormat</value></property>
+<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
+<property><name>fs.s3.maxRetries</name><value>4</value></property>
+<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
+<property><name>fs.trash.interval</name><value>0</value></property>
+<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
+<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
+<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
+<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
+<property><name>io.sort.mb</name><value>100</value></property>
+<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
+<property><name>io.sort.factor</name><value>10</value></property>
+<property><name>mapred.task.profile</name><value>false</value></property>
+<property><name>job.end.retry.interval</name><value>30000</value></property>
+<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
+<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
+<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
+<property><name>webinterface.private.actions</name><value>false</value></property>
+<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
+<property><name>giraph.vertexOutputFormatClass</name><value>edu.uci.ics.pregelix.example.PageRankVertex$SimplePageRankVertexOutputFormat</value></property>
+<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
+<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
+<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
+<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.compress.map.output</name><value>false</value></property>
+<property><name>io.sort.spill.percent</name><value>0.80</value></property>
+<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
+<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
+<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
+<property><name>SimpleShortestPathsVertex.sourceId</name><value>0</value></property>
+<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
+<property><name>job.end.retry.attempts</name><value>0</value></property>
+<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
+<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
+<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
+<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
+<property><name>hadoop.logfile.size</name><value>10000000</value></property>
+<property><name>mapred.job.queue.name</name><value>default</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
+<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
+<property><name>topology.script.number.args</name><value>100</value></property>
+<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
+<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
+<property><name>mapred.task.cache.levels</name><value>2</value></property>
+<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
+<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
+<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
+<property><name>mapred.min.split.size</name><value>0</value></property>
+<property><name>mapred.map.max.attempts</name><value>4</value></property>
+<property><name>jobclient.output.filter</name><value>FAILED</value></property>
+<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
+<property><name>mapred.acls.enabled</name><value>false</value></property>
+</configuration>
\ No newline at end of file
diff --git a/pregelix/pregelix-example/src/test/resources/jobs/ShortestPathsReal.xml b/pregelix/pregelix-example/src/test/resources/jobs/ShortestPathsReal.xml
new file mode 100644
index 0000000..954f50e
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/jobs/ShortestPathsReal.xml
@@ -0,0 +1,143 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
+<property><name>giraph.combinerClass</name><value>edu.uci.ics.pregelix.example.ShortestPathsVertex$SimpleMinCombiner</value></property>
+<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
+<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
+<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
+<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
+<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
+<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
+<property><name>mapred.input.dir</name><value>file:/webmap</value></property>
+<property><name>mapred.submit.replication</name><value>10</value></property>
+<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
+<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
+<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
+<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
+<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
+<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
+<property><name>keep.failed.task.files</name><value>false</value></property>
+<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
+<property><name>io.bytes.per.checksum</name><value>512</value></property>
+<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
+<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
+<property><name>giraph.numVertices</name><value>20</value></property>
+<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
+<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
+<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
+<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
+<property><name>fs.checkpoint.period</name><value>3600</value></property>
+<property><name>mapred.child.tmp</name><value>./tmp</value></property>
+<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
+<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
+<property><name>hadoop.logfile.count</name><value>10</value></property>
+<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
+<property><name>mapred.output.dir</name><value>/result</value></property>
+<property><name>giraph.vertexClass</name><value>edu.uci.ics.pregelix.example.ShortestPathsVertex</value></property>
+<property><name>io.map.index.skip</name><value>0</value></property>
+<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
+<property><name>mapred.output.compress</name><value>false</value></property>
+<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
+<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
+<property><name>fs.checkpoint.size</name><value>67108864</value></property>
+<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
+<property><name>mapred.job.name</name><value>ShortestPaths</value></property>
+<property><name>local.cache.size</name><value>10737418240</value></property>
+<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
+<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
+<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
+<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
+<property><name>mapred.task.timeout</name><value>600000</value></property>
+<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
+<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
+<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
+<property><name>ipc.client.kill.max</name><value>10</value></property>
+<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
+<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
+<property><name>io.sort.record.percent</name><value>0.05</value></property>
+<property><name>hadoop.security.authorization</name><value>false</value></property>
+<property><name>mapred.max.tracker.failures</name><value>4</value></property>
+<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
+<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
+<property><name>mapred.map.tasks</name><value>2</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
+<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
+<property><name>fs.default.name</name><value>file:///</value></property>
+<property><name>tasktracker.http.threads</name><value>40</value></property>
+<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
+<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
+<property><name>mapred.reduce.tasks</name><value>1</value></property>
+<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
+<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
+<property><name>io.file.buffer.size</name><value>4096</value></property>
+<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
+<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
+<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
+<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
+<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
+<property><name>hadoop.native.lib</name><value>true</value></property>
+<property><name>fs.s3.block.size</name><value>67108864</value></property>
+<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
+<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
+<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
+<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
+<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
+<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
+<property><name>mapred.queue.names</name><value>default</value></property>
+<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
+<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
+<property><name>mapred.job.tracker</name><value>local</value></property>
+<property><name>io.skip.checksum.errors</name><value>false</value></property>
+<property><name>giraph.vertexInputFormatClass</name><value>edu.uci.ics.pregelix.example.inputformat.TextShortestPathsInputFormat</value></property>
+<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
+<property><name>fs.s3.maxRetries</name><value>4</value></property>
+<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
+<property><name>fs.trash.interval</name><value>0</value></property>
+<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
+<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
+<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
+<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
+<property><name>io.sort.mb</name><value>100</value></property>
+<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
+<property><name>io.sort.factor</name><value>10</value></property>
+<property><name>mapred.task.profile</name><value>false</value></property>
+<property><name>job.end.retry.interval</name><value>30000</value></property>
+<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
+<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
+<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
+<property><name>webinterface.private.actions</name><value>false</value></property>
+<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
+<property><name>giraph.vertexOutputFormatClass</name><value>edu.uci.ics.pregelix.example.PageRankVertex$SimplePageRankVertexOutputFormat</value></property>
+<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
+<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
+<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
+<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.compress.map.output</name><value>false</value></property>
+<property><name>io.sort.spill.percent</name><value>0.80</value></property>
+<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
+<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
+<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
+<property><name>SimpleShortestPathsVertex.sourceId</name><value>0</value></property>
+<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
+<property><name>job.end.retry.attempts</name><value>0</value></property>
+<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
+<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
+<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
+<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
+<property><name>hadoop.logfile.size</name><value>10000000</value></property>
+<property><name>mapred.job.queue.name</name><value>default</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
+<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
+<property><name>topology.script.number.args</name><value>100</value></property>
+<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
+<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
+<property><name>mapred.task.cache.levels</name><value>2</value></property>
+<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
+<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
+<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
+<property><name>mapred.min.split.size</name><value>0</value></property>
+<property><name>mapred.map.max.attempts</name><value>4</value></property>
+<property><name>jobclient.output.filter</name><value>FAILED</value></property>
+<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
+<property><name>mapred.acls.enabled</name><value>false</value></property>
+</configuration>
\ No newline at end of file
diff --git a/pregelix/pregelix-example/src/test/resources/log4j.properties b/pregelix/pregelix-example/src/test/resources/log4j.properties
new file mode 100755
index 0000000..d5e6004
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/log4j.properties
@@ -0,0 +1,94 @@
+# Define some default values that can be overridden by system properties
+hadoop.root.logger=FATAL,console
+hadoop.log.dir=.
+hadoop.log.file=hadoop.log
+
+# Define the root logger to the system property "hadoop.root.logger".
+log4j.rootLogger=${hadoop.root.logger}, EventCounter
+
+# Logging Threshold
+log4j.threshhold=FATAL
+
+#
+# Daily Rolling File Appender
+#
+
+log4j.appender.DRFA=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.DRFA.File=${hadoop.log.dir}/${hadoop.log.file}
+
+# Rollver at midnight
+log4j.appender.DRFA.DatePattern=.yyyy-MM-dd
+
+# 30-day backup
+#log4j.appender.DRFA.MaxBackupIndex=30
+log4j.appender.DRFA.layout=org.apache.log4j.PatternLayout
+
+# Pattern format: Date LogLevel LoggerName LogMessage
+log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+# Debugging Pattern format
+#log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
+
+
+#
+# console
+# Add "console" to rootlogger above if you want to use this 
+#
+
+log4j.appender.console=org.apache.log4j.ConsoleAppender
+log4j.appender.console.target=System.err
+log4j.appender.console.layout=org.apache.log4j.PatternLayout
+log4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{2}: %m%n
+
+#
+# TaskLog Appender
+#
+
+#Default values
+hadoop.tasklog.taskid=null
+hadoop.tasklog.noKeepSplits=4
+hadoop.tasklog.totalLogFileSize=100
+hadoop.tasklog.purgeLogSplits=true
+hadoop.tasklog.logsRetainHours=12
+
+log4j.appender.TLA=org.apache.hadoop.mapred.TaskLogAppender
+log4j.appender.TLA.taskId=${hadoop.tasklog.taskid}
+log4j.appender.TLA.totalLogFileSize=${hadoop.tasklog.totalLogFileSize}
+
+log4j.appender.TLA.layout=org.apache.log4j.PatternLayout
+log4j.appender.TLA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+
+#
+# Rolling File Appender
+#
+
+#log4j.appender.RFA=org.apache.log4j.RollingFileAppender
+#log4j.appender.RFA.File=${hadoop.log.dir}/${hadoop.log.file}
+
+# Logfile size and and 30-day backups
+#log4j.appender.RFA.MaxFileSize=1MB
+#log4j.appender.RFA.MaxBackupIndex=30
+
+#log4j.appender.RFA.layout=org.apache.log4j.PatternLayout
+#log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} - %m%n
+#log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
+
+#
+# FSNamesystem Audit logging
+# All audit events are logged at INFO level
+#
+log4j.logger.org.apache.hadoop.fs.FSNamesystem.audit=WARN
+
+# Custom Logging levels
+
+#log4j.logger.org.apache.hadoop.mapred.JobTracker=DEBUG
+#log4j.logger.org.apache.hadoop.mapred.TaskTracker=DEBUG
+#log4j.logger.org.apache.hadoop.fs.FSNamesystem=DEBUG
+
+# Jets3t library
+log4j.logger.org.jets3t.service.impl.rest.httpclient.RestS3Service=ERROR
+
+#
+# Event Counter Appender
+# Sends counts of logging messages at different severity levels to Hadoop Metrics.
+#
+log4j.appender.EventCounter=org.apache.hadoop.metrics.jvm.EventCounter
diff --git a/pregelix/pregelix-example/src/test/resources/logging.properties b/pregelix/pregelix-example/src/test/resources/logging.properties
new file mode 100644
index 0000000..b8f2be9
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/logging.properties
@@ -0,0 +1,66 @@
+############################################################
+#  	Default Logging Configuration File
+#
+# You can use a different file by specifying a filename
+# with the java.util.logging.config.file system property.  
+# For example java -Djava.util.logging.config.file=myfile
+############################################################
+
+############################################################
+#  	Global properties
+############################################################
+
+# "handlers" specifies a comma separated list of log Handler 
+# classes.  These handlers will be installed during VM startup.
+# Note that these classes must be on the system classpath.
+# By default we only configure a ConsoleHandler, which will only
+# show messages at the INFO and above levels.
+
+handlers= java.util.logging.ConsoleHandler
+
+# To also add the FileHandler, use the following line instead.
+
+# handlers= java.util.logging.FileHandler, java.util.logging.ConsoleHandler
+
+# Default global logging level.
+# This specifies which kinds of events are logged across
+# all loggers.  For any given facility this global level
+# can be overriden by a facility specific level
+# Note that the ConsoleHandler also has a separate level
+# setting to limit messages printed to the console.
+
+.level= SEVERE
+# .level= INFO
+# .level= FINE
+# .level = FINEST
+
+############################################################
+# Handler specific properties.
+# Describes specific configuration info for Handlers.
+############################################################
+
+# default file output is in user's home directory.
+
+# java.util.logging.FileHandler.pattern = %h/java%u.log
+# java.util.logging.FileHandler.limit = 50000
+# java.util.logging.FileHandler.count = 1
+# java.util.logging.FileHandler.formatter = java.util.logging.XMLFormatter
+
+# Limit the message that are printed on the console to FINE and above.
+
+java.util.logging.ConsoleHandler.level = FINEST
+java.util.logging.ConsoleHandler.formatter = java.util.logging.SimpleFormatter
+
+
+############################################################
+# Facility specific properties.
+# Provides extra control for each logger.
+############################################################
+
+# For example, set the com.xyz.foo logger to only log SEVERE
+# messages:
+
+#edu.uci.ics.asterix.level = FINE
+#edu.uci.ics.algebricks.level = FINE
+edu.uci.ics.hyracks.level = SEVERE
+#edu.uci.ics.hyracks.control.nc.net.level = FINE
\ No newline at end of file
diff --git a/pregelix/pregelix-example/src/test/resources/only.txt b/pregelix/pregelix-example/src/test/resources/only.txt
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/only.txt