Package com.linkedin.whiteelephant.mapreduce.lib.job

Examples of com.linkedin.whiteelephant.mapreduce.lib.job.StagedOutputJob

124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
        List<String> inputPaths = new ArrayList<String>();
        inputPaths.add(task.inputPathFormat);
       
        String outputPath = task.outputPath;
       
        final StagedOutputJob job = StagedOutputJob.createStagedJob(
           _props,
           _name + "-parse-confs-" + task.id,
           inputPaths,
           "/tmp" + outputPath,
           outputPath,
           _log);
       
        job.getConfiguration().set("jobs.output.path", _confsOutputPathRoot);
        job.getConfiguration().set("logs.cluster.name", clusterName);
               
        job.setOutputKeyClass(BytesWritable.class);
        job.setOutputValueClass(NullWritable.class);
 
        job.setInputFormatClass(CombineDocumentFileFormat.class);
        job.setOutputFormatClass(AvroKeyOutputFormat.class);
 
        AvroJob.setOutputKeySchema(job, JobConf.SCHEMA$);
       
        job.setNumReduceTasks(0);
  
        job.setMapperClass(ParseJobConfs.TheMapper.class);
       
        executor.submit(job);
      }
     
      executor.waitForCompletion();
View Full Code Here
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
  {
    List<String> inputPaths = new ArrayList<String>();
   
    inputPaths.add(inputPattern);
   
    final StagedOutputJob job = StagedOutputJob.createStagedJob(
      _props,
      _name + "-" + "usage-per-hour-" + clusterName + "-" + year + "-" + day,
      inputPaths,
      "/tmp" + output,
      output,
      _log);
   
    final Configuration conf = job.getConfiguration();
   
    conf.set("cluster.name", clusterName);
               
    job.setOutputKeyClass(BytesWritable.class);
    job.setOutputValueClass(BytesWritable.class);
   
    job.setInputFormatClass(AvroKeyValueInputFormat.class);
    job.setOutputFormatClass(AvroKeyValueOutputFormat.class);
   
    AvroJob.setInputKeySchema(job, Schema.create(Type.STRING));
    AvroJob.setInputValueSchema(job, LogData.SCHEMA$);
   
    AvroJob.setMapOutputKeySchema(job, AttemptStatsKey.SCHEMA$);
    AvroJob.setMapOutputValueSchema(job, AttemptStatsValue.SCHEMA$);
   
    AvroJob.setOutputKeySchema(job, AttemptStatsKey.SCHEMA$);
    AvroJob.setOutputValueSchema(job, AttemptStatsValue.SCHEMA$);
   
    job.setNumReduceTasks(numReducers);
   
    job.setMapperClass(ComputeUsagePerHour.TheMapper.class);
    job.setReducerClass(ComputeUsagePerHour.TheReducer.class);
   
    executor.submit(job);
  }
View Full Code Here
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
        List<String> inputPaths = new ArrayList<String>();
        inputPaths.add(task.inputPathFormat);
       
        String outputPath = task.outputPath;
       
        final StagedOutputJob job = StagedOutputJob.createStagedJob(
           _props,
           _name + "-parse-jobs-" + task.id,
           inputPaths,
           "/tmp" + outputPath,
           outputPath,
           _log);
       
        job.getConfiguration().set("jobs.output.path", _jobsOutputPathRoot);
        job.getConfiguration().set("logs.cluster.name", clusterName);
               
        // 1 reducer per 12 GB of input data
        long numReduceTasks = (int)Math.ceil(((double)task.totalLength) / 1024 / 1024 / 1024 / 12);
               
        job.setOutputKeyClass(BytesWritable.class);
        job.setOutputValueClass(BytesWritable.class);
 
        job.setInputFormatClass(CombinedTextInputFormat.class);
        job.setOutputFormatClass(AvroKeyValueOutputFormat.class);
 
        AvroJob.setOutputKeySchema(job, Schema.create(Type.STRING));
        AvroJob.setOutputValueSchema(job, LogData.SCHEMA$);
       
        job.setNumReduceTasks((int)numReduceTasks);
  
        job.setMapperClass(ParseJobsFromLogs.TheMapper.class);
        job.setReducerClass(ParseJobsFromLogs.TheReducer.class);
        
        AvroJob.setMapOutputKeySchema(job, Schema.create(Type.STRING));
        AvroJob.setMapOutputValueSchema(job, LogData.SCHEMA$);
       
        MyAvroMultipleOutputs.addNamedOutput(job, "logs", AvroKeyValueOutputFormat.class, Schema.create(Type.STRING), LogData.SCHEMA$);
View Full Code Here
TOP

Related Classes of com.linkedin.whiteelephant.mapreduce.lib.job.StagedOutputJob

  • com.linkedin.whiteelephant.analysis.ComputeUsagePerHour
  • com.linkedin.whiteelephant.parsing.ParseJobConfs
  • com.linkedin.whiteelephant.parsing.ParseJobsFromLogs
  • org.apache.hadoop.conf.Configuration
  • org.apache.hadoop.fs.FileSystem
  • org.apache.hadoop.fs.Path
    • Copyright © 2018 www.massapicom. All rights reserved.
    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.