static void configureIncrementalLoad(
Job job,
HTableDescriptor tableDescriptor,
RegionLocator regionLocator,
Class<? extends OutputFormat<?, ?>> cls)
throws IOException, UnsupportedEncodingException {
Configuration conf = job.getConfiguration();
job.setOutputKeyClass(ImmutableBytesWritable.class);
job.setOutputValueClass(KeyValue.class);
job.setOutputFormatClass(cls);
// Based on the configured map output class, set the correct reducer to properly
// sort the incoming values.
// TODO it would be nice to pick one or the other of these formats.
if (KeyValue.class.equals(job.getMapOutputValueClass())) {
job.setReducerClass(KeyValueSortReducer.class);
} else if (Put.class.equals(job.getMapOutputValueClass())) {
job.setReducerClass(PutSortReducer.class);
} else if (Text.class.equals(job.getMapOutputValueClass())) {
job.setReducerClass(TextSortReducer.class);
} else {
LOG.warn("Unknown map output value type:" + job.getMapOutputValueClass());
}
conf.setStrings(
"io.serializations",
conf.get("io.serializations"),
MutationSerialization.class.getName(),
ResultSerialization.class.getName(),
KeyValueSerialization.class.getName());
if (conf.getBoolean(LOCALITY_SENSITIVE_CONF_KEY, DEFAULT_LOCALITY_SENSITIVE)) {
// record this table name for creating writer by favored nodes
LOG.info("bulkload locality sensitive enabled");
conf.set(OUTPUT_TABLE_NAME_CONF_KEY, regionLocator.getName().getNameAsString());
}
// Use table's region boundaries for TOP split points.
LOG.info("Looking up current regions for table " + regionLocator.getName());
List<ImmutableBytesWritable> startKeys = getRegionStartKeys(regionLocator);
LOG.info(
"Configuring "
+ startKeys.size()
+ " reduce partitions "
+ "to match current region count");
job.setNumReduceTasks(startKeys.size());
configurePartitioner(job, startKeys);
// Set compression algorithms based on column families
configureCompression(conf, tableDescriptor);
configureBloomType(tableDescriptor, conf);
configureBlockSize(tableDescriptor, conf);
configureDataBlockEncoding(tableDescriptor, conf);
TableMapReduceUtil.addDependencyJars(job);
TableMapReduceUtil.initCredentials(job);
LOG.info("Incremental table " + regionLocator.getName() + " output configured.");
}
