本文整理汇总了Java中org.apache.hadoop.mapred.JobConf.setPartitionerClass方法的典型用法代码示例。如果您正苦于以下问题:Java JobConf.setPartitionerClass方法的具体用法?Java JobConf.setPartitionerClass怎么用?Java JobConf.setPartitionerClass使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类org.apache.hadoop.mapred.JobConf
的用法示例。
在下文中一共展示了JobConf.setPartitionerClass方法的3个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Java代码示例。
示例1: getJob
import org.apache.hadoop.mapred.JobConf; //导入方法依赖的package包/类
/**
* Sets up a job conf for the given job using the given config object. Ensures
* that the correct input format is set, the mapper and and reducer class and
* the input and output keys and value classes along with any other job
* configuration.
*
* @param config
* @return JobConf representing the job to be ran
* @throws IOException
*/
private JobConf getJob(ConfigExtractor config) throws IOException {
JobConf job = new JobConf(config.getConfig(), SliveTest.class);
job.setInputFormat(DummyInputFormat.class);
FileOutputFormat.setOutputPath(job, config.getOutputPath());
job.setMapperClass(SliveMapper.class);
job.setPartitionerClass(SlivePartitioner.class);
job.setReducerClass(SliveReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setOutputFormat(TextOutputFormat.class);
TextOutputFormat.setCompressOutput(job, false);
job.setNumReduceTasks(config.getReducerAmount());
job.setNumMapTasks(config.getMapAmount());
return job;
}
示例2: initTableReduceJob
import org.apache.hadoop.mapred.JobConf; //导入方法依赖的package包/类
/**
* Use this before submitting a TableReduce job. It will
* appropriately set up the JobConf.
*
* @param table The output table.
* @param reducer The reducer class to use.
* @param job The current job configuration to adjust.
* @param partitioner Partitioner to use. Pass <code>null</code> to use
* default partitioner.
* @param addDependencyJars upload HBase jars and jars for any of the configured
* job classes via the distributed cache (tmpjars).
* @throws IOException When determining the region count fails.
*/
public static void initTableReduceJob(String table,
Class<? extends TableReduce> reducer, JobConf job, Class partitioner,
boolean addDependencyJars) throws IOException {
job.setOutputFormat(TableOutputFormat.class);
job.setReducerClass(reducer);
job.set(TableOutputFormat.OUTPUT_TABLE, table);
job.setOutputKeyClass(ImmutableBytesWritable.class);
job.setOutputValueClass(Put.class);
job.setStrings("io.serializations", job.get("io.serializations"),
MutationSerialization.class.getName(), ResultSerialization.class.getName());
if (partitioner == HRegionPartitioner.class) {
job.setPartitionerClass(HRegionPartitioner.class);
int regions =
MetaTableAccessor.getRegionCount(HBaseConfiguration.create(job), TableName.valueOf(table));
if (job.getNumReduceTasks() > regions) {
job.setNumReduceTasks(regions);
}
} else if (partitioner != null) {
job.setPartitionerClass(partitioner);
}
if (addDependencyJars) {
addDependencyJars(job);
}
initCredentials(job);
}
示例3: setupPipesJob
import org.apache.hadoop.mapred.JobConf; //导入方法依赖的package包/类
private static void setupPipesJob(JobConf conf) throws IOException {
// default map output types to Text
if (!getIsJavaMapper(conf)) {
conf.setMapRunnerClass(PipesMapRunner.class);
// Save the user's partitioner and hook in our's.
setJavaPartitioner(conf, conf.getPartitionerClass());
conf.setPartitionerClass(PipesPartitioner.class);
}
if (!getIsJavaReducer(conf)) {
conf.setReducerClass(PipesReducer.class);
if (!getIsJavaRecordWriter(conf)) {
conf.setOutputFormat(NullOutputFormat.class);
}
}
String textClassname = Text.class.getName();
setIfUnset(conf, MRJobConfig.MAP_OUTPUT_KEY_CLASS, textClassname);
setIfUnset(conf, MRJobConfig.MAP_OUTPUT_VALUE_CLASS, textClassname);
setIfUnset(conf, MRJobConfig.OUTPUT_KEY_CLASS, textClassname);
setIfUnset(conf, MRJobConfig.OUTPUT_VALUE_CLASS, textClassname);
// Use PipesNonJavaInputFormat if necessary to handle progress reporting
// from C++ RecordReaders ...
if (!getIsJavaRecordReader(conf) && !getIsJavaMapper(conf)) {
conf.setClass(Submitter.INPUT_FORMAT,
conf.getInputFormat().getClass(), InputFormat.class);
conf.setInputFormat(PipesNonJavaInputFormat.class);
}
String exec = getExecutable(conf);
if (exec == null) {
throw new IllegalArgumentException("No application program defined.");
}
// add default debug script only when executable is expressed as
// <path>#<executable>
if (exec.contains("#")) {
// set default gdb commands for map and reduce task
String defScript = "$HADOOP_PREFIX/src/c++/pipes/debug/pipes-default-script";
setIfUnset(conf, MRJobConfig.MAP_DEBUG_SCRIPT,defScript);
setIfUnset(conf, MRJobConfig.REDUCE_DEBUG_SCRIPT,defScript);
}
URI[] fileCache = DistributedCache.getCacheFiles(conf);
if (fileCache == null) {
fileCache = new URI[1];
} else {
URI[] tmp = new URI[fileCache.length+1];
System.arraycopy(fileCache, 0, tmp, 1, fileCache.length);
fileCache = tmp;
}
try {
fileCache[0] = new URI(exec);
} catch (URISyntaxException e) {
IOException ie = new IOException("Problem parsing execable URI " + exec);
ie.initCause(e);
throw ie;
}
DistributedCache.setCacheFiles(fileCache, conf);
}