Several major changes in hyracks:
-- reduced CC/NC communications for reporting partition request and availability; partition request/availability are only reported for the case of send-side materialized (without pipelining) policies in case of task re-attempt.
-- changed buffer cache to dynamically allocate memory based on needs instead of pre-allocating
-- changed each network channel to lazily allocate memory based on needs, and changed materialized connectors to lazily allocate files based on needs
-- changed several major CCNCCFunctions to use non-java serde
-- added a sort-based group-by operator which pushes group-by aggregations into an external sort
-- make external sort a stable sort
1,3,and 4 is to reduce the job overhead.
2 is to reduce the unecessary NC resource consumptions such as memory and files.
5 and 6 are improvements to runtime operators.
One change in algebricks:
-- implemented a rule to push group-by aggregation into sort, i.e., using the sort-based gby operator
Several important changes in pregelix:
-- remove static states in vertex
-- direct check halt bit without deserialization
-- optimize the sort algorithm by packing yet-another 2-byte normalized key into the tPointers array
Change-Id: Id696f9a9f1647b4a025b8b33d20b3a89127c60d6
Reviewed-on: http://fulliautomatix.ics.uci.edu:8443/35
Tested-by: Jenkins <jenkins@fulliautomatix.ics.uci.edu>
Reviewed-by: Till Westmann <westmann@gmail.com>
diff --git a/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/FailureInjectionIterationCompleteHook.java b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/FailureInjectionIterationCompleteHook.java
new file mode 100644
index 0000000..c59e3ed
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/FailureInjectionIterationCompleteHook.java
@@ -0,0 +1,38 @@
+/*
+ * Copyright 2009-2013 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 edu.uci.ics.hyracks.api.exceptions.HyracksDataException;
+import edu.uci.ics.pregelix.api.job.IIterationCompleteReporterHook;
+import edu.uci.ics.pregelix.api.job.PregelixJob;
+import edu.uci.ics.pregelix.core.util.PregelixHyracksIntegrationUtil;
+
+/**
+ * @author yingyib
+ */
+public class FailureInjectionIterationCompleteHook implements IIterationCompleteReporterHook {
+
+ @Override
+ public void completeIteration(int superstep, PregelixJob job) throws HyracksDataException {
+ try {
+ if (superstep == 3) {
+ PregelixHyracksIntegrationUtil.shutdownNC1();
+ }
+ } catch (Exception e) {
+ throw new HyracksDataException(e);
+ }
+ }
+
+}
diff --git a/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/FailureRecoveryConnectedComponentsTest.java b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/FailureRecoveryConnectedComponentsTest.java
index efc7bcc..7c4ccce 100644
--- a/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/FailureRecoveryConnectedComponentsTest.java
+++ b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/FailureRecoveryConnectedComponentsTest.java
@@ -21,7 +21,6 @@
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.junit.Test;
-import edu.uci.ics.pregelix.api.graph.Vertex;
import edu.uci.ics.pregelix.api.job.PregelixJob;
import edu.uci.ics.pregelix.api.util.ConservativeCheckpointHook;
import edu.uci.ics.pregelix.api.util.DefaultVertexPartitioner;
@@ -58,26 +57,10 @@
FileOutputFormat.setOutputPath(job, new Path(OUTPUTPAH));
job.getConfiguration().setLong(PregelixJob.NUM_VERTICE, 23);
job.setCheckpointHook(ConservativeCheckpointHook.class);
+ job.setIterationCompleteReporterHook(FailureInjectionIterationCompleteHook.class);
testCluster.setUp();
Driver driver = new Driver(PageRankVertex.class);
- Thread thread = new Thread(new Runnable() {
-
- @Override
- public void run() {
- try {
- synchronized (this) {
- while (Vertex.getSuperstep() <= 5) {
- this.wait(200);
- }
- PregelixHyracksIntegrationUtil.shutdownNC1();
- }
- } catch (Exception e) {
- throw new IllegalStateException(e);
- }
- }
- });
- thread.start();
driver.runJob(job, "127.0.0.1", PregelixHyracksIntegrationUtil.TEST_HYRACKS_CC_CLIENT_PORT);
TestUtils.compareWithResultDir(new File(EXPECTEDPATH), new File(OUTPUTPAH));
diff --git a/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/FailureRecoveryInnerJoinTest.java b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/FailureRecoveryInnerJoinTest.java
index 421f2f5..886fb58 100644
--- a/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/FailureRecoveryInnerJoinTest.java
+++ b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/FailureRecoveryInnerJoinTest.java
@@ -21,7 +21,6 @@
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.junit.Test;
-import edu.uci.ics.pregelix.api.graph.Vertex;
import edu.uci.ics.pregelix.api.job.PregelixJob;
import edu.uci.ics.pregelix.api.util.ConservativeCheckpointHook;
import edu.uci.ics.pregelix.core.base.IDriver.Plan;
@@ -56,27 +55,11 @@
FileOutputFormat.setOutputPath(job, new Path(OUTPUTPAH));
job.getConfiguration().setLong(PregelixJob.NUM_VERTICE, 20);
job.setCheckpointHook(ConservativeCheckpointHook.class);
- job.setFixedVertexValueSize(true);
+ job.setIterationCompleteReporterHook(FailureInjectionIterationCompleteHook.class);
testCluster.setUp();
Driver driver = new Driver(PageRankVertex.class);
- Thread thread = new Thread(new Runnable() {
-
- @Override
- public void run() {
- try {
- synchronized (this) {
- while (Vertex.getSuperstep() <= 5) {
- this.wait(200);
- }
- PregelixHyracksIntegrationUtil.shutdownNC1();
- }
- } catch (Exception e) {
- throw new IllegalStateException(e);
- }
- }
- });
- thread.start();
+
driver.runJob(job, Plan.INNER_JOIN, "127.0.0.1",
PregelixHyracksIntegrationUtil.TEST_HYRACKS_CC_CLIENT_PORT, false);
diff --git a/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/FailureRecoveryTest.java b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/FailureRecoveryTest.java
index b3ad112..c6e85cb 100644
--- a/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/FailureRecoveryTest.java
+++ b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/FailureRecoveryTest.java
@@ -21,7 +21,6 @@
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.junit.Test;
-import edu.uci.ics.pregelix.api.graph.Vertex;
import edu.uci.ics.pregelix.api.job.PregelixJob;
import edu.uci.ics.pregelix.api.util.ConservativeCheckpointHook;
import edu.uci.ics.pregelix.core.driver.Driver;
@@ -56,26 +55,10 @@
job.getConfiguration().setLong(PregelixJob.NUM_VERTICE, 20);
job.setCheckpointHook(ConservativeCheckpointHook.class);
job.setFixedVertexValueSize(true);
+ job.setIterationCompleteReporterHook(FailureInjectionIterationCompleteHook.class);
testCluster.setUp();
Driver driver = new Driver(PageRankVertex.class);
- Thread thread = new Thread(new Runnable() {
-
- @Override
- public void run() {
- try {
- synchronized (this) {
- while (Vertex.getSuperstep() <= 5) {
- this.wait(200);
- }
- PregelixHyracksIntegrationUtil.shutdownNC1();
- }
- } catch (Exception e) {
- throw new IllegalStateException(e);
- }
- }
- });
- thread.start();
driver.runJob(job, "127.0.0.1", PregelixHyracksIntegrationUtil.TEST_HYRACKS_CC_CLIENT_PORT);
TestUtils.compareWithResultDir(new File(EXPECTEDPATH), new File(OUTPUTPAH));
diff --git a/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/FailureRecoveryWithoutCheckpointTest.java b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/FailureRecoveryWithoutCheckpointTest.java
index 9a2ef2c..83b896c 100644
--- a/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/FailureRecoveryWithoutCheckpointTest.java
+++ b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/FailureRecoveryWithoutCheckpointTest.java
@@ -21,7 +21,6 @@
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.junit.Test;
-import edu.uci.ics.pregelix.api.graph.Vertex;
import edu.uci.ics.pregelix.api.job.PregelixJob;
import edu.uci.ics.pregelix.core.driver.Driver;
import edu.uci.ics.pregelix.core.util.PregelixHyracksIntegrationUtil;
@@ -54,26 +53,10 @@
FileOutputFormat.setOutputPath(job, new Path(OUTPUTPAH));
job.getConfiguration().setLong(PregelixJob.NUM_VERTICE, 20);
job.setFixedVertexValueSize(true);
+ job.setIterationCompleteReporterHook(FailureInjectionIterationCompleteHook.class);
testCluster.setUp();
Driver driver = new Driver(PageRankVertex.class);
- Thread thread = new Thread(new Runnable() {
-
- @Override
- public void run() {
- try {
- synchronized (this) {
- while (Vertex.getSuperstep() <= 5) {
- this.wait(200);
- }
- PregelixHyracksIntegrationUtil.shutdownNC1();
- }
- } catch (Exception e) {
- throw new IllegalStateException(e);
- }
- }
- });
- thread.start();
driver.runJob(job, "127.0.0.1", PregelixHyracksIntegrationUtil.TEST_HYRACKS_CC_CLIENT_PORT);
TestUtils.compareWithResultDir(new File(EXPECTEDPATH), new File(OUTPUTPAH));
diff --git a/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/GraphSampleVertexTest.java b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/GraphSampleVertexTest.java
new file mode 100644
index 0000000..3afb417
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/GraphSampleVertexTest.java
@@ -0,0 +1,93 @@
+/*
+ * Copyright 2009-2013 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.BufferedReader;
+import java.io.File;
+import java.io.FileInputStream;
+import java.io.InputStreamReader;
+
+import junit.framework.Assert;
+
+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.pregelix.api.job.PregelixJob;
+import edu.uci.ics.pregelix.core.driver.Driver;
+import edu.uci.ics.pregelix.core.util.PregelixHyracksIntegrationUtil;
+import edu.uci.ics.pregelix.example.GraphSampleVertex.GraphSampleVertexOutputFormat;
+import edu.uci.ics.pregelix.example.data.VLongNormalizedKeyComputer;
+import edu.uci.ics.pregelix.example.inputformat.TextGraphSampleVertexInputFormat;
+import edu.uci.ics.pregelix.example.util.TestCluster;
+
+/**
+ * @author yingyib
+ */
+public class GraphSampleVertexTest {
+ private static String INPUTPATH = "data/webmapcomplex";
+ private static String OUTPUTPAH = "actual/result";
+
+ @Test
+ public void test() throws Exception {
+ TestCluster testCluster = new TestCluster();
+ try {
+ PregelixJob job = new PregelixJob(GraphSampleVertex.class.getName());
+ job.setVertexClass(GraphSampleVertex.class);
+ job.setVertexInputFormatClass(TextGraphSampleVertexInputFormat.class);
+ job.setVertexOutputFormatClass(GraphSampleVertexOutputFormat.class);
+ job.setMessageCombinerClass(GraphSampleVertex.SimpleSampleCombiner.class);
+ job.addGlobalAggregatorClass(GraphSampleVertex.GlobalSamplingAggregator.class);
+ job.setNoramlizedKeyComputerClass(VLongNormalizedKeyComputer.class);
+ job.setFixedVertexValueSize(true);
+ job.getConfiguration().set(GraphSampleVertex.GLOBAL_RATE, "0.5f");
+ FileInputFormat.setInputPaths(job, INPUTPATH);
+ FileOutputFormat.setOutputPath(job, new Path(OUTPUTPAH));
+
+ testCluster.setUp();
+ Driver driver = new Driver(GraphSampleVertex.class);
+ driver.runJob(job, "127.0.0.1", PregelixHyracksIntegrationUtil.TEST_HYRACKS_CC_CLIENT_PORT);
+ int sampledVertexNum = countVertex(OUTPUTPAH);
+ int totalVertexNum = countVertex(INPUTPATH);
+ float ratio = (float) sampledVertexNum / (float) totalVertexNum;
+ Assert.assertEquals(true, ratio >= 0.5f);
+ } finally {
+ PregelixHyracksIntegrationUtil.deinit();
+ testCluster.cleanupHDFS();
+ }
+ }
+
+ private int countVertex(String filePath) throws Exception {
+ File dir = new File(filePath);
+ int count = 0;
+ if (dir.isDirectory()) {
+ File[] files = dir.listFiles();
+ for (File file : files) {
+ if (file.isFile() && !file.getName().contains(".crc")) {
+ BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream(file)));
+ while (reader.readLine() != null) {
+ count++;
+ }
+ reader.close();
+ }
+ }
+ return count;
+ } else {
+ return count;
+ }
+ }
+
+}
diff --git a/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/MultiJobConnectedComponentsTest.java b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/MultiJobConnectedComponentsTest.java
index 65b9845..a5f793f 100644
--- a/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/MultiJobConnectedComponentsTest.java
+++ b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/MultiJobConnectedComponentsTest.java
@@ -68,6 +68,10 @@
@Override
public void run() {
try {
+ synchronized (this) {
+ this.wait(2000);
+ this.notifyAll();
+ }
Driver driver = new Driver(PageRankVertex.class);
PregelixJob job2 = new PregelixJob(ConnectedComponentsVertex.class.getName());
job2.setVertexClass(ConnectedComponentsVertex.class);
diff --git a/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/MultiJobPageRankTest.java b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/MultiJobPageRankTest.java
index cfd1b27..414fab7 100644
--- a/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/MultiJobPageRankTest.java
+++ b/pregelix/pregelix-example/src/test/java/edu/uci/ics/pregelix/example/MultiJobPageRankTest.java
@@ -65,6 +65,10 @@
@Override
public void run() {
try {
+ synchronized (this) {
+ this.wait(5000);
+ this.notifyAll();
+ }
Driver driver = new Driver(PageRankVertex.class);
PregelixJob job2 = new PregelixJob(PageRankVertex.class.getName());
job2.setVertexClass(PageRankVertex.class);
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
index 5855fd3..9191fad 100644
--- 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
@@ -72,6 +72,7 @@
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);
+ job.getConfiguration().set(PregelixJob.JOB_ID, "test_job");
}
public void setUp() throws Exception {
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
index c7eff1e..3bedb49 100644
--- 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
@@ -79,7 +79,9 @@
FileOutputFormat.setOutputPath(job, new Path(HDFS_OUTPUTPAH));
job.getConfiguration().setLong(PregelixJob.NUM_VERTICE, 20);
job.setCheckpointHook(ConservativeCheckpointHook.class);
- job.setEnableDynamicOptimization(true);
+ job.setGroupByAlgorithm(false);
+ job.setGroupByMemoryLimit(3);
+ job.setFrameSize(1024);
job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
}
@@ -92,11 +94,11 @@
job.setNoramlizedKeyComputerClass(VLongNormalizedKeyComputer.class);
job.setVertexPartitionerClass(DefaultVertexPartitioner.class);
job.setFixedVertexValueSize(true);
+ job.setSkipCombinerKey(true);
FileInputFormat.setInputPaths(job, HDFS_INPUTPATH2);
FileOutputFormat.setOutputPath(job, new Path(HDFS_OUTPUTPAH2));
job.getConfiguration().setLong(PregelixJob.NUM_VERTICE, 23);
job.setCheckpointHook(ConservativeCheckpointHook.class);
- job.setEnableDynamicOptimization(true);
job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
}
@@ -112,6 +114,7 @@
job.getConfiguration().setLong(PregelixJob.NUM_VERTICE, 20);
job.getConfiguration().setLong(ShortestPathsVertex.SOURCE_ID, 0);
job.setDynamicVertexValueSize(true);
+ job.setSkipCombinerKey(true);
job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
}
@@ -122,11 +125,11 @@
job.setVertexOutputFormatClass(SimplePageRankVertexOutputFormat.class);
job.setNoramlizedKeyComputerClass(VLongNormalizedKeyComputer.class);
job.setFixedVertexValueSize(true);
+ job.setSkipCombinerKey(true);
FileInputFormat.setInputPaths(job, HDFS_INPUTPATH);
FileOutputFormat.setOutputPath(job, new Path(HDFS_OUTPUTPAH));
job.getConfiguration().setLong(PregelixJob.NUM_VERTICE, 20);
job.setCheckpointHook(ConservativeCheckpointHook.class);
- job.setEnableDynamicOptimization(true);
job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
}
@@ -137,11 +140,10 @@
job.setVertexOutputFormatClass(SimpleConnectedComponentsVertexOutputFormat.class);
job.setMessageCombinerClass(ConnectedComponentsVertex.SimpleMinCombiner.class);
job.setNoramlizedKeyComputerClass(VLongNormalizedKeyComputer.class);
- job.setDynamicVertexValueSize(true);
+ job.setSkipCombinerKey(true);
FileInputFormat.setInputPaths(job, HDFS_INPUTPATH);
FileOutputFormat.setOutputPath(job, new Path(HDFS_OUTPUTPAH));
job.getConfiguration().setLong(PregelixJob.NUM_VERTICE, 20);
- job.setEnableDynamicOptimization(true);
job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
}
@@ -153,11 +155,10 @@
job.setMessageCombinerClass(ConnectedComponentsVertex.SimpleMinCombiner.class);
job.setNoramlizedKeyComputerClass(VLongNormalizedKeyComputer.class);
job.setVertexPartitionerClass(DefaultVertexPartitioner.class);
- job.setDynamicVertexValueSize(true);
+ job.setSkipCombinerKey(true);
FileInputFormat.setInputPaths(job, HDFS_INPUTPATH2);
FileOutputFormat.setOutputPath(job, new Path(HDFS_OUTPUTPAH2));
job.getConfiguration().setLong(PregelixJob.NUM_VERTICE, 23);
- job.setEnableDynamicOptimization(true);
job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
}
@@ -168,6 +169,8 @@
job.setVertexOutputFormatClass(SimpleReachibilityVertexOutputFormat.class);
job.setMessageCombinerClass(ReachabilityVertex.SimpleReachibilityCombiner.class);
job.setNoramlizedKeyComputerClass(VLongNormalizedKeyComputer.class);
+ job.setSkipCombinerKey(true);
+ job.setFixedVertexValueSize(true);
FileInputFormat.setInputPaths(job, HDFS_INPUTPATH2);
FileOutputFormat.setOutputPath(job, new Path(HDFS_OUTPUTPAH2));
job.getConfiguration().setLong(PregelixJob.NUM_VERTICE, 23);
@@ -232,7 +235,6 @@
FileInputFormat.setInputPaths(job, HDFS_INPUTPATH);
FileOutputFormat.setOutputPath(job, new Path(HDFS_OUTPUTPAH));
job.getConfiguration().setLong(PregelixJob.NUM_VERTICE, 20);
- job.setEnableDynamicOptimization(true);
job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
}
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
index f077053..12195e6 100644
--- 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
@@ -94,11 +94,16 @@
@Test
public void test() throws Exception {
setUp();
- Plan[] plans = new Plan[] { Plan.INNER_JOIN, Plan.OUTER_JOIN, Plan.OUTER_JOIN_SINGLE_SORT, Plan.OUTER_JOIN_SORT };
+ Plan[] plans = new Plan[] { Plan.OUTER_JOIN, Plan.INNER_JOIN };
for (Plan plan : plans) {
+ job.setMergeConnector(true);
driver.runJob(job, plan, PregelixHyracksIntegrationUtil.CC_HOST,
PregelixHyracksIntegrationUtil.TEST_HYRACKS_CC_CLIENT_PORT, false);
compareResults();
+ //job.setMergeConnector(false);
+ //driver.runJob(job, plan, PregelixHyracksIntegrationUtil.CC_HOST,
+ // PregelixHyracksIntegrationUtil.TEST_HYRACKS_CC_CLIENT_PORT, false);
+ //compareResults();
}
tearDown();
waitawhile();
diff --git a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsReal/part-0 b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsReal/part-0
index f1f1d9b..0c89090 100755
--- a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsReal/part-0
+++ b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsReal/part-0
@@ -1,5 +1,5 @@
-0 0
-4 0
-8 0
-12 0
-16 0
+1 1
+5 1
+9 1
+13 0
+17 0
diff --git a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsReal/part-1 b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsReal/part-1
index 0fa02c1..6d2b709 100755
--- a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsReal/part-1
+++ b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsReal/part-1
@@ -1,5 +1,5 @@
-1 0
-5 0
-9 0
-13 0
-17 0
+2 1
+6 1
+10 1
+14 0
+18 0
diff --git a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsReal/part-2 b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsReal/part-2
index 542ccae..f90bfe0 100755
--- a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsReal/part-2
+++ b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsReal/part-2
@@ -1,5 +1,5 @@
-2 0
-6 0
-10 0
-14 0
-18 0
+3 1
+7 1
+11 0
+15 0
+19 0
diff --git a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsReal/part-3 b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsReal/part-3
index 1d5d6d9..503200b 100755
--- a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsReal/part-3
+++ b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsReal/part-3
@@ -1,5 +1,5 @@
-3 0
-7 0
-11 0
-15 0
-19 0
+0 0
+4 1
+8 1
+12 0
+16 0
diff --git a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex/part-0 b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex/part-0
index f1f1d9b..503200b 100755
--- a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex/part-0
+++ b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex/part-0
@@ -1,5 +1,5 @@
0 0
-4 0
-8 0
+4 1
+8 1
12 0
16 0
diff --git a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex/part-1 b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex/part-1
index 4e7d87a..4d86486 100755
--- a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex/part-1
+++ b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex/part-1
@@ -1,6 +1,6 @@
-1 0
-5 0
-9 0
+1 1
+5 1
+9 1
13 0
17 0
21 21
diff --git a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex/part-2 b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex/part-2
index 542ccae..6d2b709 100755
--- a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex/part-2
+++ b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex/part-2
@@ -1,5 +1,5 @@
-2 0
-6 0
-10 0
+2 1
+6 1
+10 1
14 0
18 0
diff --git a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex/part-3 b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex/part-3
index 513f3ff..af3a604 100755
--- a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex/part-3
+++ b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex/part-3
@@ -1,5 +1,5 @@
-3 0
-7 0
+3 1
+7 1
11 0
15 0
19 0
diff --git a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex2/part-0 b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex2/part-0
index 2c975de..ca71d2e 100755
--- a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex2/part-0
+++ b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex2/part-0
@@ -1,9 +1,9 @@
0 0
-2 0
-4 0
-6 0
-8 0
-10 0
+2 1
+4 1
+6 1
+8 1
+10 1
12 0
14 0
16 0
diff --git a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex2/part-1 b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex2/part-1
index 6976bc1..fae4a35 100755
--- a/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex2/part-1
+++ b/pregelix/pregelix-example/src/test/resources/expected/ConnectedComponentsRealComplex2/part-1
@@ -1,8 +1,8 @@
-1 0
-3 0
-5 0
-7 0
-9 0
+1 1
+3 1
+5 1
+7 1
+9 1
11 0
13 0
15 0
diff --git a/pregelix/pregelix-example/src/test/resources/jobs/ConnectedComponentsReal.xml b/pregelix/pregelix-example/src/test/resources/jobs/ConnectedComponentsReal.xml
index 3091c83..1cef17a0 100644
--- a/pregelix/pregelix-example/src/test/resources/jobs/ConnectedComponentsReal.xml
+++ b/pregelix/pregelix-example/src/test/resources/jobs/ConnectedComponentsReal.xml
@@ -80,7 +80,6 @@
<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>pregelix.dynamicopt</name><value>true</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>
@@ -122,13 +121,13 @@
<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.pregelix.example.ConnectedComponentsVertex$SimpleConnectedComponentsVertexOutputFormat</value></property>
<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
+<property><name>pregelix.skipCombinerKey</name><value>true</value></property>
<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
<property><name>hadoop.logfile.size</name><value>10000000</value></property>
<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.pregelix.example.inputformat.TextConnectedComponentsInputFormat</value></property>
<property><name>mapred.job.queue.name</name><value>default</value></property>
<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
-<property><name>pregelix.incStateLength</name><value>true</value></property>
<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
<property><name>topology.script.number.args</name><value>100</value></property>
<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
diff --git a/pregelix/pregelix-example/src/test/resources/jobs/ConnectedComponentsRealComplex.xml b/pregelix/pregelix-example/src/test/resources/jobs/ConnectedComponentsRealComplex.xml
index b6af65c..7b043b8 100644
--- a/pregelix/pregelix-example/src/test/resources/jobs/ConnectedComponentsRealComplex.xml
+++ b/pregelix/pregelix-example/src/test/resources/jobs/ConnectedComponentsRealComplex.xml
@@ -1,146 +1,145 @@
<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
-<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
-<property><name>mapred.task.cache.levels</name><value>2</value></property>
-<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
-<property><name>hadoop.native.lib</name><value>true</value></property>
-<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
-<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
-<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
-<property><name>io.skip.checksum.errors</name><value>false</value></property>
-<property><name>fs.default.name</name><value>file:///</value></property>
-<property><name>mapred.child.tmp</name><value>./tmp</value></property>
-<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
-<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
-<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
-<property><name>io.sort.factor</name><value>10</value></property>
-<property><name>mapred.task.timeout</name><value>600000</value></property>
-<property><name>mapred.max.tracker.failures</name><value>4</value></property>
-<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
-<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
-<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
-<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
-<property><name>tasktracker.http.threads</name><value>40</value></property>
-<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
-<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
-<property><name>pregelix.combinerClass</name><value>edu.uci.ics.pregelix.example.ConnectedComponentsVertex$SimpleMinCombiner</value></property>
-<property><name>mapred.output.compress</name><value>false</value></property>
-<property><name>io.bytes.per.checksum</name><value>512</value></property>
-<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
-<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
-<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
-<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
-<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
-<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
-<property><name>job.end.retry.attempts</name><value>0</value></property>
-<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
-<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
-<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
-<property><name>topology.script.number.args</name><value>100</value></property>
-<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
-<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
-<property><name>pregelix.partitionerClass</name><value>edu.uci.ics.pregelix.api.util.DefaultVertexPartitioner</value></property>
-<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
-<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
-<property><name>pregelix.numVertices</name><value>23</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
-<property><name>hadoop.security.authorization</name><value>false</value></property>
-<property><name>local.cache.size</name><value>10737418240</value></property>
-<property><name>mapred.min.split.size</name><value>0</value></property>
-<property><name>mapred.map.tasks</name><value>2</value></property>
-<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
-<property><name>mapred.job.queue.name</name><value>default</value></property>
-<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
-<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
-<property><name>job.end.retry.interval</name><value>30000</value></property>
-<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
-<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
-<property><name>mapred.reduce.tasks</name><value>1</value></property>
-<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
-<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
-<property><name>webinterface.private.actions</name><value>false</value></property>
-<property><name>io.sort.spill.percent</name><value>0.80</value></property>
-<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
-<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
-<property><name>mapred.job.name</name><value>ConnectedComponents</value></property>
-<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
-<property><name>mapred.map.max.attempts</name><value>4</value></property>
-<property><name>pregelix.incStateLength</name><value>true</value></property>
-<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
-<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
-<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
-<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
-<property><name>keep.failed.task.files</name><value>false</value></property>
-<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
-<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
-<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>io.map.index.skip</name><value>0</value></property>
-<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
-<property><name>hadoop.logfile.size</name><value>10000000</value></property>
-<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
-<property><name>fs.checkpoint.period</name><value>3600</value></property>
-<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
-<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
-<property><name>pregelix.dynamicopt</name><value>true</value></property>
-<property><name>fs.s3.maxRetries</name><value>4</value></property>
-<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
-<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
-<property><name>fs.trash.interval</name><value>0</value></property>
-<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
-<property><name>mapred.submit.replication</name><value>10</value></property>
-<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
-<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
-<property><name>mapred.job.tracker</name><value>local</value></property>
-<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
-<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
-<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
-<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
-<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
-<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
-<property><name>io.sort.record.percent</name><value>0.05</value></property>
-<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
-<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
-<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
-<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
-<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
-<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
-<property><name>pregelix.nmkComputerClass</name><value>edu.uci.ics.pregelix.example.data.VLongNormalizedKeyComputer</value></property>
-<property><name>hadoop.logfile.count</name><value>10</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>io.seqfile.compress.blocksize</name><value>1000000</value></property>
-<property><name>fs.s3.block.size</name><value>67108864</value></property>
-<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
-<property><name>mapred.acls.enabled</name><value>false</value></property>
-<property><name>mapred.queue.names</name><value>default</value></property>
<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
-<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
-<property><name>pregelix.vertexClass</name><value>edu.uci.ics.pregelix.example.ConnectedComponentsVertex</value></property>
-<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
-<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
-<property><name>mapred.output.dir</name><value>/resultcomplex</value></property>
-<property><name>io.sort.mb</name><value>100</value></property>
-<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
-<property><name>mapred.compress.map.output</name><value>false</value></property>
-<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
-<property><name>ipc.client.kill.max</name><value>10</value></property>
-<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
-<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
-<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
<property><name>mapred.input.dir</name><value>file:/webmapcomplex</value></property>
-<property><name>io.file.buffer.size</name><value>4096</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>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>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
-<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.pregelix.example.inputformat.TextConnectedComponentsInputFormat</value></property>
-<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
-<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.pregelix.example.ConnectedComponentsVertex$SimpleConnectedComponentsVertexOutputFormat</value></property>
-<property><name>mapred.task.profile</name><value>false</value></property>
-<property><name>jobclient.output.filter</name><value>FAILED</value></property>
-<property><name>mapred.tasktracker.map.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>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>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>pregelix.nmkComputerClass</name><value>edu.uci.ics.pregelix.example.data.VLongNormalizedKeyComputer</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>pregelix.numVertices</name><value>23</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>pregelix.vertexClass</name><value>edu.uci.ics.pregelix.example.ConnectedComponentsVertex</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>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>pregelix.combinerClass</name><value>edu.uci.ics.pregelix.example.ConnectedComponentsVertex$SimpleMinCombiner</value></property>
+<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
+<property><name>mapred.temp.dir</name><value>${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>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.pregelix.example.ConnectedComponentsVertex$SimpleConnectedComponentsVertexOutputFormat</value></property>
+<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
+<property><name>pregelix.skipCombinerKey</name><value>true</value></property>
+<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
+<property><name>pregelix.partitionerClass</name><value>edu.uci.ics.pregelix.api.util.DefaultVertexPartitioner</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>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.pregelix.example.inputformat.TextConnectedComponentsInputFormat</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
index 6fe04fb..857dc48 100644
--- a/pregelix/pregelix-example/src/test/resources/jobs/PageRankReal.xml
+++ b/pregelix/pregelix-example/src/test/resources/jobs/PageRankReal.xml
@@ -23,6 +23,7 @@
<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
+<property><name>pregelix.framesize</name><value>1024</value></property>
<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
<property><name>tasktracker.http.threads</name><value>40</value></property>
<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
@@ -45,6 +46,7 @@
<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
+<property><name>pregelix.groupmem</name><value>3</value></property>
<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
<property><name>pregelix.numVertices</name><value>20</value></property>
<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
@@ -85,7 +87,6 @@
<property><name>fs.checkpoint.period</name><value>3600</value></property>
<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
-<property><name>pregelix.dynamicopt</name><value>true</value></property>
<property><name>fs.s3.maxRetries</name><value>4</value></property>
<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
@@ -115,6 +116,7 @@
<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
<property><name>fs.s3.block.size</name><value>67108864</value></property>
<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
+<property><name>pregelix.groupalg</name><value>false</value></property>
<property><name>mapred.acls.enabled</name><value>false</value></property>
<property><name>mapred.queue.names</name><value>default</value></property>
<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
diff --git a/pregelix/pregelix-example/src/test/resources/jobs/PageRankRealComplex.xml b/pregelix/pregelix-example/src/test/resources/jobs/PageRankRealComplex.xml
index d0f9759..5e1fb16 100644
--- a/pregelix/pregelix-example/src/test/resources/jobs/PageRankRealComplex.xml
+++ b/pregelix/pregelix-example/src/test/resources/jobs/PageRankRealComplex.xml
@@ -81,12 +81,12 @@
<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
<property><name>io.map.index.skip</name><value>0</value></property>
<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
+<property><name>pregelix.skipCombinerKey</name><value>true</value></property>
<property><name>hadoop.logfile.size</name><value>10000000</value></property>
<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
<property><name>fs.checkpoint.period</name><value>3600</value></property>
<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
-<property><name>pregelix.dynamicopt</name><value>true</value></property>
<property><name>fs.s3.maxRetries</name><value>4</value></property>
<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
diff --git a/pregelix/pregelix-example/src/test/resources/jobs/PageRankRealDynamic.xml b/pregelix/pregelix-example/src/test/resources/jobs/PageRankRealDynamic.xml
index 0173390..c05a4da 100644
--- a/pregelix/pregelix-example/src/test/resources/jobs/PageRankRealDynamic.xml
+++ b/pregelix/pregelix-example/src/test/resources/jobs/PageRankRealDynamic.xml
@@ -80,7 +80,6 @@
<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>pregelix.dynamicopt</name><value>true</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>
diff --git a/pregelix/pregelix-example/src/test/resources/jobs/PageRankRealNoCombiner.xml b/pregelix/pregelix-example/src/test/resources/jobs/PageRankRealNoCombiner.xml
index a7a38e0..cd8ee02 100644
--- a/pregelix/pregelix-example/src/test/resources/jobs/PageRankRealNoCombiner.xml
+++ b/pregelix/pregelix-example/src/test/resources/jobs/PageRankRealNoCombiner.xml
@@ -80,7 +80,6 @@
<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>pregelix.dynamicopt</name><value>true</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>
@@ -122,6 +121,7 @@
<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.pregelix.example.PageRankVertex$SimplePageRankVertexOutputFormat</value></property>
<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
+<property><name>pregelix.skipCombinerKey</name><value>true</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>
diff --git a/pregelix/pregelix-example/src/test/resources/jobs/ReachibilityRealComplex.xml b/pregelix/pregelix-example/src/test/resources/jobs/ReachibilityRealComplex.xml
index 225429a..8aa6a23 100644
--- a/pregelix/pregelix-example/src/test/resources/jobs/ReachibilityRealComplex.xml
+++ b/pregelix/pregelix-example/src/test/resources/jobs/ReachibilityRealComplex.xml
@@ -1,145 +1,147 @@
<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
-<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>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>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>Reachibility</value></property>
-<property><name>pregelix.nmkComputerClass</name><value>edu.uci.ics.pregelix.example.data.VLongNormalizedKeyComputer</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>pregelix.numVertices</name><value>23</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>pregelix.vertexClass</name><value>edu.uci.ics.pregelix.example.ReachabilityVertex</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>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>ReachibilityVertex.destId</name><value>10</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>pregelix.combinerClass</name><value>edu.uci.ics.pregelix.example.ReachabilityVertex$SimpleReachibilityCombiner</value></property>
-<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
-<property><name>mapred.temp.dir</name><value>${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>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.pregelix.example.ReachabilityVertex$SimpleReachibilityVertexOutputFormat</value></property>
-<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
-<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
-<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
-<property><name>hadoop.logfile.size</name><value>10000000</value></property>
-<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.pregelix.example.inputformat.TextReachibilityVertexInputFormat</value></property>
-<property><name>mapred.job.queue.name</name><value>default</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
-<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
-<property><name>ReachibilityVertex.sourceId</name><value>1</value></property>
-<property><name>topology.script.number.args</name><value>100</value></property>
-<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
-<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
<property><name>mapred.task.cache.levels</name><value>2</value></property>
-<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
-<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
-<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
+<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
+<property><name>hadoop.native.lib</name><value>true</value></property>
+<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
+<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
+<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
+<property><name>io.skip.checksum.errors</name><value>false</value></property>
+<property><name>fs.default.name</name><value>file:///</value></property>
+<property><name>mapred.child.tmp</name><value>./tmp</value></property>
+<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
+<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
+<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
+<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
+<property><name>io.sort.factor</name><value>10</value></property>
+<property><name>mapred.task.timeout</name><value>600000</value></property>
+<property><name>mapred.max.tracker.failures</name><value>4</value></property>
+<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
+<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
+<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
+<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
+<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
+<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
+<property><name>tasktracker.http.threads</name><value>40</value></property>
+<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
+<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
+<property><name>pregelix.combinerClass</name><value>edu.uci.ics.pregelix.example.ReachabilityVertex$SimpleReachibilityCombiner</value></property>
+<property><name>mapred.output.compress</name><value>false</value></property>
+<property><name>io.bytes.per.checksum</name><value>512</value></property>
+<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
+<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
+<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
+<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
+<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
+<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
+<property><name>job.end.retry.attempts</name><value>0</value></property>
+<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
+<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
+<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
+<property><name>topology.script.number.args</name><value>100</value></property>
+<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
+<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
+<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
+<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
+<property><name>pregelix.numVertices</name><value>23</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
+<property><name>hadoop.security.authorization</name><value>false</value></property>
+<property><name>local.cache.size</name><value>10737418240</value></property>
<property><name>mapred.min.split.size</name><value>0</value></property>
+<property><name>mapred.map.tasks</name><value>2</value></property>
+<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
+<property><name>mapred.job.queue.name</name><value>default</value></property>
+<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
+<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
+<property><name>job.end.retry.interval</name><value>30000</value></property>
+<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
+<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
+<property><name>mapred.reduce.tasks</name><value>1</value></property>
+<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
+<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
+<property><name>webinterface.private.actions</name><value>false</value></property>
+<property><name>io.sort.spill.percent</name><value>0.80</value></property>
+<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
+<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
+<property><name>mapred.job.name</name><value>Reachibility</value></property>
+<property><name>hadoop.util.hash.type</name><value>murmur</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>pregelix.incStateLength</name><value>false</value></property>
+<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
+<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
+<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
+<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
+<property><name>keep.failed.task.files</name><value>false</value></property>
<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
+<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
+<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>io.map.index.skip</name><value>0</value></property>
+<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
+<property><name>pregelix.skipCombinerKey</name><value>true</value></property>
+<property><name>hadoop.logfile.size</name><value>10000000</value></property>
+<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
+<property><name>fs.checkpoint.period</name><value>3600</value></property>
+<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
+<property><name>ReachibilityVertex.sourceId</name><value>1</value></property>
+<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
+<property><name>fs.s3.maxRetries</name><value>4</value></property>
+<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
+<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
+<property><name>fs.trash.interval</name><value>0</value></property>
+<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
+<property><name>mapred.submit.replication</name><value>10</value></property>
+<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
+<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
+<property><name>mapred.job.tracker</name><value>local</value></property>
+<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
+<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
+<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
+<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
+<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
+<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
+<property><name>io.sort.record.percent</name><value>0.05</value></property>
+<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
+<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
+<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
+<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
+<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
+<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
+<property><name>pregelix.nmkComputerClass</name><value>edu.uci.ics.pregelix.example.data.VLongNormalizedKeyComputer</value></property>
+<property><name>hadoop.logfile.count</name><value>10</value></property>
+<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
+<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
+<property><name>fs.s3.block.size</name><value>67108864</value></property>
+<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
<property><name>mapred.acls.enabled</name><value>false</value></property>
+<property><name>mapred.queue.names</name><value>default</value></property>
+<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
+<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
+<property><name>pregelix.vertexClass</name><value>edu.uci.ics.pregelix.example.ReachabilityVertex</value></property>
+<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
+<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
+<property><name>mapred.output.dir</name><value>/resultcomplex</value></property>
+<property><name>ReachibilityVertex.destId</name><value>10</value></property>
+<property><name>io.sort.mb</name><value>100</value></property>
+<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
+<property><name>mapred.compress.map.output</name><value>false</value></property>
+<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
+<property><name>ipc.client.kill.max</name><value>10</value></property>
+<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
+<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
+<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
+<property><name>mapred.input.dir</name><value>file:/webmapcomplex</value></property>
+<property><name>io.file.buffer.size</name><value>4096</value></property>
+<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
+<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
+<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.pregelix.example.inputformat.TextReachibilityVertexInputFormat</value></property>
+<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
+<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.pregelix.example.ReachabilityVertex$SimpleReachibilityVertexOutputFormat</value></property>
+<property><name>mapred.task.profile</name><value>false</value></property>
+<property><name>jobclient.output.filter</name><value>FAILED</value></property>
+<property><name>mapred.tasktracker.map.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>fs.checkpoint.size</name><value>67108864</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
index b757514..41f7588 100644
--- a/pregelix/pregelix-example/src/test/resources/jobs/ShortestPathsReal.xml
+++ b/pregelix/pregelix-example/src/test/resources/jobs/ShortestPathsReal.xml
@@ -1,145 +1,146 @@
<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
-<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>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>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>pregelix.nmkComputerClass</name><value>edu.uci.ics.pregelix.example.data.VLongNormalizedKeyComputer</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>pregelix.numVertices</name><value>20</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>pregelix.vertexClass</name><value>edu.uci.ics.pregelix.example.ShortestPathsVertex</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>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>pregelix.combinerClass</name><value>edu.uci.ics.pregelix.example.ShortestPathsVertex$SimpleMinCombiner</value></property>
-<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
-<property><name>mapred.temp.dir</name><value>${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>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.pregelix.example.PageRankVertex$SimplePageRankVertexOutputFormat</value></property>
-<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
-<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
-<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
-<property><name>hadoop.logfile.size</name><value>10000000</value></property>
-<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.pregelix.example.inputformat.TextShortestPathsInputFormat</value></property>
-<property><name>mapred.job.queue.name</name><value>default</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
-<property><name>pregelix.incStateLength</name><value>true</value></property>
-<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
-<property><name>topology.script.number.args</name><value>100</value></property>
-<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
-<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
<property><name>mapred.task.cache.levels</name><value>2</value></property>
-<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
-<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
-<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
+<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
+<property><name>hadoop.native.lib</name><value>true</value></property>
+<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
+<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
+<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
+<property><name>io.skip.checksum.errors</name><value>false</value></property>
+<property><name>fs.default.name</name><value>file:///</value></property>
+<property><name>mapred.child.tmp</name><value>./tmp</value></property>
+<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
+<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
+<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
+<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
+<property><name>io.sort.factor</name><value>10</value></property>
+<property><name>mapred.task.timeout</name><value>600000</value></property>
+<property><name>mapred.max.tracker.failures</name><value>4</value></property>
+<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
+<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
+<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
+<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
+<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
+<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
+<property><name>tasktracker.http.threads</name><value>40</value></property>
+<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
+<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
+<property><name>pregelix.combinerClass</name><value>edu.uci.ics.pregelix.example.ShortestPathsVertex$SimpleMinCombiner</value></property>
+<property><name>mapred.output.compress</name><value>false</value></property>
+<property><name>io.bytes.per.checksum</name><value>512</value></property>
+<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
+<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
+<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
+<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
+<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
+<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
+<property><name>job.end.retry.attempts</name><value>0</value></property>
+<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
+<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
+<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
+<property><name>topology.script.number.args</name><value>100</value></property>
+<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
+<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
+<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
+<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
+<property><name>pregelix.numVertices</name><value>20</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
+<property><name>hadoop.security.authorization</name><value>false</value></property>
+<property><name>local.cache.size</name><value>10737418240</value></property>
<property><name>mapred.min.split.size</name><value>0</value></property>
+<property><name>mapred.map.tasks</name><value>2</value></property>
+<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
+<property><name>mapred.job.queue.name</name><value>default</value></property>
+<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
+<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
+<property><name>job.end.retry.interval</name><value>30000</value></property>
+<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
+<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
+<property><name>mapred.reduce.tasks</name><value>1</value></property>
+<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
+<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
+<property><name>webinterface.private.actions</name><value>false</value></property>
+<property><name>io.sort.spill.percent</name><value>0.80</value></property>
+<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
+<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
+<property><name>mapred.job.name</name><value>ShortestPaths</value></property>
+<property><name>hadoop.util.hash.type</name><value>murmur</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>pregelix.incStateLength</name><value>true</value></property>
+<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
+<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
+<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
+<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
+<property><name>keep.failed.task.files</name><value>false</value></property>
<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
+<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
+<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>io.map.index.skip</name><value>0</value></property>
+<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
+<property><name>pregelix.skipCombinerKey</name><value>true</value></property>
+<property><name>hadoop.logfile.size</name><value>10000000</value></property>
+<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
+<property><name>SimpleShortestPathsVertex.sourceId</name><value>0</value></property>
+<property><name>fs.checkpoint.period</name><value>3600</value></property>
+<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
+<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
+<property><name>fs.s3.maxRetries</name><value>4</value></property>
+<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
+<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
+<property><name>fs.trash.interval</name><value>0</value></property>
+<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
+<property><name>mapred.submit.replication</name><value>10</value></property>
+<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
+<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
+<property><name>mapred.job.tracker</name><value>local</value></property>
+<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
+<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
+<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
+<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
+<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
+<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
+<property><name>io.sort.record.percent</name><value>0.05</value></property>
+<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
+<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
+<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
+<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
+<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
+<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
+<property><name>pregelix.nmkComputerClass</name><value>edu.uci.ics.pregelix.example.data.VLongNormalizedKeyComputer</value></property>
+<property><name>hadoop.logfile.count</name><value>10</value></property>
+<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
+<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
+<property><name>fs.s3.block.size</name><value>67108864</value></property>
+<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
<property><name>mapred.acls.enabled</name><value>false</value></property>
+<property><name>mapred.queue.names</name><value>default</value></property>
+<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
+<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
+<property><name>pregelix.vertexClass</name><value>edu.uci.ics.pregelix.example.ShortestPathsVertex</value></property>
+<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
+<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
+<property><name>mapred.output.dir</name><value>/result</value></property>
+<property><name>io.sort.mb</name><value>100</value></property>
+<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
+<property><name>mapred.compress.map.output</name><value>false</value></property>
+<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
+<property><name>ipc.client.kill.max</name><value>10</value></property>
+<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
+<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
+<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
+<property><name>mapred.input.dir</name><value>file:/webmap</value></property>
+<property><name>io.file.buffer.size</name><value>4096</value></property>
+<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
+<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
+<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.pregelix.example.inputformat.TextShortestPathsInputFormat</value></property>
+<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
+<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.pregelix.example.PageRankVertex$SimplePageRankVertexOutputFormat</value></property>
+<property><name>mapred.task.profile</name><value>false</value></property>
+<property><name>jobclient.output.filter</name><value>FAILED</value></property>
+<property><name>mapred.tasktracker.map.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>fs.checkpoint.size</name><value>67108864</value></property>
</configuration>
\ No newline at end of file