Examples of org.apache.hadoop.mapred.jobcontrol.Job

Package org.apache.hadoop.mapred.jobcontrol

Examples of org.apache.hadoop.mapred.jobcontrol.Job

org.apache.hadoop.mapred.jobcontrol.Job
This class encapsulates a MapReduce job and its dependency. It monitors the states of the depending jobs and updates the state of this job. A job starts in the WAITING state. If it does not have any depending jobs, or all of the depending jobs are in SUCCESS state, then the job state will become READY. If any depending jobs fail, the job will fail too. When in READY state, the job can be submitted to Hadoop for execution, with the state changing into RUNNING state. From RUNNING state, the job can get into SUCCESS or FAILED state, depending the status of the job execution.

            lp.set((String)entry.getKey(), (String)entry.getValue());
        }
        FileInputFormat.addInputPath(lp, new Path(inputDir + "/page_views"));
        FileOutputFormat.setOutputPath(lp, new Path(outputDir + "/L7out"));
        lp.setNumReduceTasks(Integer.parseInt(parallel));
        Job group = new Job(lp);


        JobControl jc = new JobControl("L7 join");
        jc.addJob(group);


        new Thread(jc).start();

View Full Code Here

            lp.set((String)entry.getKey(), (String)entry.getValue());
        }
        FileInputFormat.addInputPath(lp, new Path(inputDir + "/page_views"));
        FileOutputFormat.setOutputPath(lp, new Path(outputDir + "/L1out"));
        lp.setNumReduceTasks(Integer.parseInt(parallel));
        Job group = new Job(lp);


        JobControl jc = new JobControl("L1 join");
        jc.addJob(group);


        new Thread(jc).start();

View Full Code Here

            lp.set((String)entry.getKey(), (String)entry.getValue());
        }
        FileInputFormat.addInputPath(lp, new Path(inputDir + "/page_views"));
        FileOutputFormat.setOutputPath(lp, new Path(outputDir + "/indexed_pages_3"));
        lp.setNumReduceTasks(0);
        Job loadPages = new Job(lp);


        JobConf lu = new JobConf(L3.class);
        lu.setJobName("L3 Load Users");
        lu.setInputFormat(TextInputFormat.class);
        lu.setOutputKeyClass(Text.class);
        lu.setOutputValueClass(Text.class);
        lu.setMapperClass(ReadUsers.class);
        props = System.getProperties();
        for (Map.Entry<Object,Object> entry : props.entrySet()) {
            lu.set((String)entry.getKey(), (String)entry.getValue());
        }
        FileInputFormat.addInputPath(lu, new Path(inputDir + "/users"));
        FileOutputFormat.setOutputPath(lu, new Path(outputDir + "/indexed_users_3"));
        lu.setNumReduceTasks(0);
        Job loadUsers = new Job(lu);


        JobConf join = new JobConf(L3.class);
        join.setJobName("L3 Join Users and Pages");
        join.setInputFormat(KeyValueTextInputFormat.class);
        join.setOutputKeyClass(Text.class);
        join.setOutputValueClass(Text.class);
        join.setMapperClass(IdentityMapper.class);
        join.setReducerClass(Join.class);
        props = System.getProperties();
        for (Map.Entry<Object,Object> entry : props.entrySet()) {
            join.set((String)entry.getKey(), (String)entry.getValue());
        }
        FileInputFormat.addInputPath(join, new Path(outputDir + "/indexed_pages_3"));
        FileInputFormat.addInputPath(join, new Path(outputDir + "/indexed_users_3"));
        FileOutputFormat.setOutputPath(join, new Path(outputDir + "/L3out"));
        join.setNumReduceTasks(Integer.parseInt(parallel));
        Job joinJob = new Job(join);
        joinJob.addDependingJob(loadPages);
        joinJob.addDependingJob(loadUsers);


        JobControl jc = new JobControl("L3 join");
        jc.addJob(loadPages);
        jc.addJob(loadUsers);
        jc.addJob(joinJob);

View Full Code Here

            lp.set((String)entry.getKey(), (String)entry.getValue());
        }
        FileInputFormat.addInputPath(lp, new Path(inputDir + "/page_views"));
        FileOutputFormat.setOutputPath(lp, new Path(outputDir + "/L6out"));
        lp.setNumReduceTasks(Integer.parseInt(parallel));
        Job group = new Job(lp);


        JobControl jc = new JobControl("L6 join");
        jc.addJob(group);


        new Thread(jc).start();

View Full Code Here

            lp.set((String)entry.getKey(), (String)entry.getValue());
        }
        FileInputFormat.addInputPath(lp, new Path(inputDir + "/page_views"));
        FileOutputFormat.setOutputPath(lp, new Path(outputDir + "/highest_value_page_per_user"));
        lp.setNumReduceTasks(Integer.parseInt(parallel));
        Job loadPages = new Job(lp);


        JobConf lu = new JobConf(L12.class);
        lu.setJobName("L12 Find Total Timespent per Term");
        lu.setInputFormat(TextInputFormat.class);
        lu.setOutputKeyClass(Text.class);
        lu.setOutputValueClass(LongWritable.class);
        lu.setMapperClass(TotalTimespentPerTerm.class);
        lu.setCombinerClass(TotalTimespentPerTerm.class);
        lu.setReducerClass(TotalTimespentPerTerm.class);
        props = System.getProperties();
        for (Map.Entry<Object,Object> entry : props.entrySet()) {
            lu.set((String)entry.getKey(), (String)entry.getValue());
        }
        FileInputFormat.addInputPath(lu, new Path(inputDir + "/page_views"));
        FileOutputFormat.setOutputPath(lu, new Path(outputDir + "/total_timespent_per_term"));
        lu.setNumReduceTasks(Integer.parseInt(parallel));
        Job loadUsers = new Job(lu);


        JobConf join = new JobConf(L12.class);
        join.setJobName("L12 Find Queries Per Action");
        join.setInputFormat(TextInputFormat.class);
        join.setOutputKeyClass(Text.class);
        join.setOutputValueClass(LongWritable.class);
        join.setMapperClass(QueriesPerAction.class);
        join.setCombinerClass(QueriesPerAction.class);
        join.setReducerClass(QueriesPerAction.class);
        props = System.getProperties();
        for (Map.Entry<Object,Object> entry : props.entrySet()) {
            join.set((String)entry.getKey(), (String)entry.getValue());
        }
        FileInputFormat.addInputPath(join, new Path(inputDir + "/page_views"));
        FileOutputFormat.setOutputPath(join, new Path(outputDir + "/queries_per_action"));
        join.setNumReduceTasks(Integer.parseInt(parallel));
        Job joinJob = new Job(join);


        JobControl jc = new JobControl("L12 join");
        jc.addJob(loadPages);
        jc.addJob(loadUsers);
        jc.addJob(joinJob);

View Full Code Here

        }
        FileInputFormat.addInputPath(lp, new Path(inputDir + "/page_views"));
        FileOutputFormat.setOutputPath(lp, new Path(outputDir + "/L9out"));
        // Hardcode the parallel to 40 since MyPartitioner assumes it
        lp.setNumReduceTasks(40);
        Job group = new Job(lp);


        JobControl jc = new JobControl("L9 join");
        jc.addJob(group);


        new Thread(jc).start();

View Full Code Here

            lp.set((String)entry.getKey(), (String)entry.getValue());
        }
        FileInputFormat.addInputPath(lp, new Path(inputDir + "/page_views"));
        FileOutputFormat.setOutputPath(lp, new Path(outputDir + "/L15out"));
        lp.setNumReduceTasks(Integer.parseInt(parallel));
        Job group = new Job(lp);


        JobControl jc = new JobControl("L15 join");
        jc.addJob(group);


        new Thread(jc).start();

View Full Code Here

            lp.set((String)entry.getKey(), (String)entry.getValue());
        }
        FileInputFormat.addInputPath(lp, new Path(inputDir + "/page_views"));
        FileOutputFormat.setOutputPath(lp, new Path(outputDir + "/indexed_pages_5"));
        lp.setNumReduceTasks(0);
        Job loadPages = new Job(lp);


        JobConf lu = new JobConf(L5.class);
        lu.setJobName("L5 Load Users");
        lu.setInputFormat(TextInputFormat.class);
        lu.setOutputKeyClass(Text.class);
        lu.setOutputValueClass(Text.class);
        lu.setMapperClass(ReadUsers.class);
        props = System.getProperties();
        for (Map.Entry<Object,Object> entry : props.entrySet()) {
            lu.set((String)entry.getKey(), (String)entry.getValue());
        }
        FileInputFormat.addInputPath(lu, new Path(inputDir + "/users"));
        FileOutputFormat.setOutputPath(lu, new Path(outputDir + "/indexed_users_5"));
        lu.setNumReduceTasks(0);
        Job loadUsers = new Job(lu);


        JobConf join = new JobConf(L5.class);
        join.setJobName("L5 Join Users and Pages");
        join.setInputFormat(KeyValueTextInputFormat.class);
        join.setOutputKeyClass(Text.class);
        join.setOutputValueClass(Text.class);
        join.setMapperClass(IdentityMapper.class);
        join.setReducerClass(Join.class);
        props = System.getProperties();
        for (Map.Entry<Object,Object> entry : props.entrySet()) {
            join.set((String)entry.getKey(), (String)entry.getValue());
        }
        FileInputFormat.addInputPath(join, new Path(outputDir + "/indexed_pages_5"));
        FileInputFormat.addInputPath(join, new Path(outputDir + "/indexed_users_5"));
        FileOutputFormat.setOutputPath(join, new Path(outputDir + "/L5out"));
        join.setNumReduceTasks(Integer.parseInt(parallel));
        Job joinJob = new Job(join);
        joinJob.addDependingJob(loadPages);
        joinJob.addDependingJob(loadUsers);


        JobControl jc = new JobControl("L5 join");
        jc.addJob(loadPages);
        jc.addJob(loadUsers);
        jc.addJob(joinJob);

View Full Code Here

        DistributedCache.addCacheFile(
            new URI(inputDir + "/power_users"), lp);
        FileInputFormat.addInputPath(lp, new Path(inputDir + "/page_views"));
        FileOutputFormat.setOutputPath(lp, new Path(outputDir + "/L2out"));
        lp.setNumReduceTasks(0);
        Job loadPages = new Job(lp);


        JobControl jc = new JobControl("L2 join");
        jc.addJob(loadPages);


        new Thread(jc).start();

View Full Code Here

        }
        FileInputFormat.addInputPath(lp, new Path(inputDir + "/page_views"));
        FileOutputFormat.setOutputPath(lp, new Path(outputDir + "/L10out"));
        // Hardcode the parallel to 40 since MyPartitioner assumes it
        lp.setNumReduceTasks(40);
        Job group = new Job(lp);


        JobControl jc = new JobControl("L10 join");
        jc.addJob(group);


        new Thread(jc).start();

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.hadoop.mapred.jobcontrol.Job

com.ebay.erl.mobius.core.MobiusJob

fm.last.hadoop.programs.labs.trackstats.TrackStatisticsProgram

org.apache.hadoop.abacus.ValueAggregatorJob

org.apache.hadoop.fs.FileSystem

org.apache.hadoop.fs.Path

org.apache.hadoop.mapred.JobClient

org.apache.hadoop.mapred.JobConf

org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorJob

org.apache.hadoop.mapred.RunningJob

org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.JobControlCompiler

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.