let Pregelix support dynamic vertex value size
git-svn-id: https://hyracks.googlecode.com/svn/branches/fullstack_staging@2677 123451ca-8445-de46-9d55-352943316053
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 c0b4a10..2c580c4 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
@@ -157,13 +157,6 @@
job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
}
- private static void genPageRank() throws IOException {
- generatePageRankJob("PageRank", outputBase + "PageRank.xml");
- generatePageRankJobReal("PageRank", outputBase + "PageRankReal.xml");
- generatePageRankJobRealComplex("PageRank", outputBase + "PageRankRealComplex.xml");
- generatePageRankJobRealNoCombiner("PageRank", outputBase + "PageRankRealNoCombiner.xml");
- }
-
private static void generateShortestPathJob(String jobName, String outputPath) throws IOException {
PregelixJob job = new PregelixJob(jobName);
job.setVertexClass(ShortestPathsVertex.class);
@@ -177,6 +170,27 @@
job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
}
+ private static void generatePageRankJobRealDynamic(String jobName, String outputPath) throws IOException {
+ PregelixJob job = new PregelixJob(jobName);
+ job.setVertexClass(PageRankVertex.class);
+ job.setVertexInputFormatClass(TextPageRankInputFormat.class);
+ job.setVertexOutputFormatClass(SimplePageRankVertexOutputFormat.class);
+ job.setMessageCombinerClass(PageRankVertex.SimpleSumCombiner.class);
+ job.setDynamicVertexValueSize(true);
+ FileInputFormat.setInputPaths(job, HDFS_INPUTPATH);
+ FileOutputFormat.setOutputPath(job, new Path(HDFS_OUTPUTPAH));
+ job.getConfiguration().setLong(PregelixJob.NUM_VERTICE, 20);
+ job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+ }
+
+ private static void genPageRank() throws IOException {
+ generatePageRankJob("PageRank", outputBase + "PageRank.xml");
+ generatePageRankJobReal("PageRank", outputBase + "PageRankReal.xml");
+ generatePageRankJobRealDynamic("PageRank", outputBase + "PageRankRealDynamic.xml");
+ generatePageRankJobRealComplex("PageRank", outputBase + "PageRankRealComplex.xml");
+ generatePageRankJobRealNoCombiner("PageRank", outputBase + "PageRankRealNoCombiner.xml");
+ }
+
private static void genShortestPath() throws IOException {
generateShortestPathJob("ShortestPaths", outputBase + "ShortestPaths.xml");
generateShortestPathJobReal("ShortestPaths", outputBase + "ShortestPathsReal.xml");
diff --git a/pregelix/pregelix-example/src/test/resources/expected/PageRankRealDynamic.result b/pregelix/pregelix-example/src/test/resources/expected/PageRankRealDynamic.result
new file mode 100644
index 0000000..ab05d38
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/expected/PageRankRealDynamic.result
@@ -0,0 +1,20 @@
+0|Vertex(id=0,value=0.008290140026154316, edges=(1,))
+1|Vertex(id=1,value=0.1535152819247165, edges=(1,2,))
+2|Vertex(id=2,value=0.14646839195826475, edges=(1,2,3,))
+3|Vertex(id=3,value=0.08125113985998214, edges=(1,2,3,4,))
+4|Vertex(id=4,value=0.03976979906329426, edges=(1,2,3,4,5,))
+5|Vertex(id=5,value=0.0225041581462058, edges=(1,2,3,4,5,6,))
+6|Vertex(id=6,value=0.015736276824953852, edges=(1,2,3,4,5,6,7,))
+7|Vertex(id=7,value=0.012542224114863661, edges=(1,2,3,4,5,6,7,8,))
+8|Vertex(id=8,value=0.010628239626209894, edges=(1,2,3,4,5,6,7,8,9,))
+9|Vertex(id=9,value=0.009294348455354817, edges=(1,2,3,4,5,6,7,8,9,10,))
+10|Vertex(id=10,value=0.008290140026154316, edges=(11,))
+11|Vertex(id=11,value=0.15351528192471647, edges=(11,12,))
+12|Vertex(id=12,value=0.14646839195826472, edges=(11,12,13,))
+13|Vertex(id=13,value=0.08125113985998214, edges=(11,12,13,14,))
+14|Vertex(id=14,value=0.03976979906329426, edges=(11,12,13,14,15,))
+15|Vertex(id=15,value=0.0225041581462058, edges=(11,12,13,14,15,16,))
+16|Vertex(id=16,value=0.015736276824953852, edges=(11,12,13,14,15,16,17,))
+17|Vertex(id=17,value=0.012542224114863661, edges=(11,12,13,14,15,16,17,18,))
+18|Vertex(id=18,value=0.010628239626209894, edges=(11,12,13,14,15,16,17,18,19,))
+19|Vertex(id=19,value=0.009294348455354817, edges=(0,11,12,13,14,15,16,17,18,19,))
diff --git a/pregelix/pregelix-example/src/test/resources/jobs/PageRankRealDynamic.xml b/pregelix/pregelix-example/src/test/resources/jobs/PageRankRealDynamic.xml
new file mode 100644
index 0000000..c1a04ae
--- /dev/null
+++ b/pregelix/pregelix-example/src/test/resources/jobs/PageRankRealDynamic.xml
@@ -0,0 +1,143 @@
+<?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>PageRank</value></property>
+<property><name>local.cache.size</name><value>10737418240</value></property>
+<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
+<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
+<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
+<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
+<property><name>mapred.task.timeout</name><value>600000</value></property>
+<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
+<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
+<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
+<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
+<property><name>ipc.client.kill.max</name><value>10</value></property>
+<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
+<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
+<property><name>io.sort.record.percent</name><value>0.05</value></property>
+<property><name>hadoop.security.authorization</name><value>false</value></property>
+<property><name>mapred.max.tracker.failures</name><value>4</value></property>
+<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
+<property><name>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.PageRankVertex</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.PageRankVertex$SimpleSumCombiner</value></property>
+<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
+<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
+<property><name>mapred.temp.dir</name><value>${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.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.TextPageRankInputFormat</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>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