storm jar topology-jar-path class ...
storm kill topology-name [-w wait-time-secs]
storm activate topology-name
storm deactivate topology-name
storm rebalance topology-name [-w wait-time-secs] [-n new-num-workers] [-e component=parallelism]*
storm classpath
storm localconfvalue conf-name
storm remoteconfvalue conf-name
storm nimbus
storm supervisor
storm ui
storm get-errors topology-name
storm kill_workers
storm list
storm logviewer
storm set_log_level -l [logger name]=[log level][:optional timeout] -r [logger name] topology-name
storm version
storm help [command]

// Spout
collector.emit(new Values(content1), uniqueMessageId);

// Bold
collector.emit(tuple, new Values(content2));
collector.ack(tuple);

import org.apache.storm.Config;
import org.apache.storm.LocalCluster;
import org.apache.storm.StormSubmitter;
import org.apache.storm.generated.AlreadyAliveException;
import org.apache.storm.generated.AuthorizationException;
import org.apache.storm.generated.InvalidTopologyException;
import org.apache.storm.topology.TopologyBuilder;
import org.apache.storm.tuple.Fields;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

public class WordCountTopology {

    private static final Logger logger = LoggerFactory.getLogger(WordCountTopology.class);

    public static void main(String[] args) throws InterruptedException {
        final String inputFile = "/opt/app/apache-storm-1.1.0/LICENSE";
        final String outputDir = "/opt/workspace/wordcount";

        TopologyBuilder builder = new TopologyBuilder();
        builder.setSpout(FileReadSpout.class.getSimpleName(), new FileReadSpout(inputFile));
        builder.setBolt(LineSplitBolt.class.getSimpleName(), new LineSplitBolt())
                .shuffleGrouping(FileReadSpout.class.getSimpleName());
        // 最终生成4个文件
        builder.setBolt(WordCountBolt.class.getSimpleName(), new WordCountBolt(outputDir), 2)
                .setNumTasks(4)
                .fieldsGrouping(LineSplitBolt.class.getSimpleName(), new Fields("word"));

        Config conf = new Config();
        conf.setDebug(true);
        if (args != null && args.length > 0) {
            try {
                StormSubmitter.submitTopology(args[0], conf, builder.createTopology());
            } catch (AlreadyAliveException | InvalidTopologyException | AuthorizationException e) {
                logger.error("Failed to submit " + WordCountTopology.class.getName() + ".", e);
            }
        } else {
            conf.setDebug(true);
            LocalCluster cluster = new LocalCluster();
            cluster.submitTopology(WordCountTopology.class.getSimpleName(), conf, builder.createTopology());
            Thread.sleep(30 * 1000);
            cluster.shutdown();
        }
    }

}

import java.io.BufferedReader;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.IOException;
import java.util.Map;

import org.apache.storm.spout.SpoutOutputCollector;
import org.apache.storm.task.TopologyContext;
import org.apache.storm.topology.OutputFieldsDeclarer;
import org.apache.storm.topology.base.BaseRichSpout;
import org.apache.storm.tuple.Fields;
import org.apache.storm.tuple.Values;

public class FileReadSpout extends BaseRichSpout {

    private static final long serialVersionUID = 8543601286964250940L;

    private String inputFile;

    private BufferedReader reader;

    private SpoutOutputCollector collector;

    public FileReadSpout(String inputFile) {
        this.inputFile = inputFile;
    }

    @Override
    @SuppressWarnings("rawtypes")
    public void open(Map conf, TopologyContext context, SpoutOutputCollector collector) {
        try {
            reader = new BufferedReader(new FileReader(inputFile));
        } catch (FileNotFoundException e) {
            throw new RuntimeException("Cannot find file [" + inputFile + "].", e);
        }
        this.collector = collector;
    }

    @Override
    public void nextTuple() {
        try {
            String line = null;
            while ((line = reader.readLine()) != null) {
                collector.emit(new Values(line));
            }
        } catch (IOException e) {
            throw new RuntimeException("Encountered a file read error.", e);
        }
    }

    @Override
    public void declareOutputFields(OutputFieldsDeclarer declarer) {
        declarer.declare(new Fields("line"));
    }

    @Override
    public void close() {
        if (reader != null) {
            try {
                reader.close();
            } catch (IOException e) {
                // Ignore
            }
        }
        super.close();
    }

}

import java.util.Map;

import org.apache.storm.task.OutputCollector;
import org.apache.storm.task.TopologyContext;
import org.apache.storm.topology.OutputFieldsDeclarer;
import org.apache.storm.topology.base.BaseRichBolt;
import org.apache.storm.tuple.Fields;
import org.apache.storm.tuple.Tuple;
import org.apache.storm.tuple.Values;

public class LineSplitBolt extends BaseRichBolt {

    private static final long serialVersionUID = -2045688041930588092L;

    private OutputCollector collector;

    @Override
    @SuppressWarnings("rawtypes")
    public void prepare(Map conf, TopologyContext context, OutputCollector collector) {
        this.collector = collector;
    }

    @Override
    public void execute(Tuple tuple) {
        String line = tuple.getStringByField("line");
        String[] words = line.split(" ");
        for (String word : words) {
            word = word.trim();
            if (!word.isEmpty()) {
                word = word.toLowerCase();
                collector.emit(new Values(word, 1));
            }
        }

        collector.ack(tuple);
    }

    @Override
    public void declareOutputFields(OutputFieldsDeclarer declarer) {
        declarer.declare(new Fields("word", "count"));
    }

    @Override
    public void cleanup() {
        super.cleanup();
    }

}

import java.io.IOException;
import java.io.RandomAccessFile;
import java.util.HashMap;
import java.util.Map;
import java.util.UUID;

import org.apache.storm.task.OutputCollector;
import org.apache.storm.task.TopologyContext;
import org.apache.storm.topology.OutputFieldsDeclarer;
import org.apache.storm.topology.base.BaseRichBolt;
import org.apache.storm.tuple.Tuple;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

public class WordCountBolt extends BaseRichBolt {

    private static final long serialVersionUID = 8239697869626573368L;

    private static final Logger logger = LoggerFactory.getLogger(WordCountBolt.class);

    private String outputDir;

    private OutputCollector collector;

    private Map<String, Integer> wordCounter;

    public WordCountBolt(String outputDir) {
        this.outputDir = outputDir;
    }

    @Override
    @SuppressWarnings("rawtypes")
    public void prepare(Map conf, TopologyContext context, OutputCollector collector) {
        this.collector = collector;
        wordCounter = new HashMap<>();
    }

    @Override
    public void execute(Tuple tuple) {
        String word = tuple.getStringByField("word");
        Integer count = tuple.getIntegerByField("count");
        Integer wordCount = wordCounter.get(word);
        if (wordCount == null) {
            wordCounter.put(word, count);
        } else {
            wordCounter.put(word, count + wordCount);
        }

        collector.ack(tuple);
    }

    @Override
    public void declareOutputFields(OutputFieldsDeclarer declarer) {
    }

    @Override
    public void cleanup() {
        if (wordCounter != null) {
            outputResult(wordCounter);
            wordCounter.clear();
        }
        super.cleanup();
    }

    private void outputResult(Map<String, Integer> wordCounter) {
        String filePath = outputDir + "/" + UUID.randomUUID().toString();
        RandomAccessFile randomAccessFile = null;
        try {
            randomAccessFile = new RandomAccessFile(filePath, "rw");
            for (Map.Entry<String, Integer> entry : wordCounter.entrySet()) {
                randomAccessFile.writeChars(entry.getKey());
                randomAccessFile.writeChar('\t');
                randomAccessFile.writeChars(String.valueOf(entry.getValue()));
                randomAccessFile.writeChar('\n');
            }
        } catch (IOException e) {
            logger.error("Failed to write file [" + filePath + "].", e);
        } finally {
            if (randomAccessFile != null) {
                try {
                    randomAccessFile.close();
                } catch (IOException e) {
                    logger.warn("Failed to close output stream.", e);
                }
            }
        }
    }

}

package org.apache.storm.topology;

import java.io.Serializable;
import java.util.Map;

/**
 * Common methods for all possible components in a topology. This interface is used
 * when defining topologies using the Java API.
 */
public interface IComponent extends Serializable {

    /**
     * Declare the output schema for all the streams of this topology.
     *
     * @param declarer this is used to declare output stream ids, output fields, and whether or not each output stream is a direct stream
     */
    void declareOutputFields(OutputFieldsDeclarer declarer);

    /**
     * Declare configuration specific to this component. Only a subset of the "topology.*" configs can
     * be overridden. The component configuration can be further overridden when constructing the
     * topology using {@link TopologyBuilder}
     *
     */
    Map<String, Object> getComponentConfiguration();

}

package org.apache.storm.spout;

import org.apache.storm.task.TopologyContext;
import java.util.Map;
import java.io.Serializable;

/**
 * ISpout is the core interface for implementing spouts. A Spout is responsible
 * for feeding messages into the topology for processing. For every tuple emitted by
 * a spout, Storm will track the (potentially very large) DAG of tuples generated
 * based on a tuple emitted by the spout. When Storm detects that every tuple in
 * that DAG has been successfully processed, it will send an ack message to the Spout.
 *
 * If a tuple fails to be fully processed within the configured timeout for the
 * topology (see {@link org.apache.storm.Config}), Storm will send a fail message to the spout
 * for the message.
 *
 * When a Spout emits a tuple, it can tag the tuple with a message id. The message id
 * can be any type. When Storm acks or fails a message, it will pass back to the
 * spout the same message id to identify which tuple it's referring to. If the spout leaves out
 * the message id, or sets it to null, then Storm will not track the message and the spout
 * will not receive any ack or fail callbacks for the message.
 *
 * Storm executes ack, fail, and nextTuple all on the same thread. This means that an implementor
 * of an ISpout does not need to worry about concurrency issues between those methods. However, it
 * also means that an implementor must ensure that nextTuple is non-blocking: otherwise
 * the method could block acks and fails that are pending to be processed.
 */
public interface ISpout extends Serializable {
    /**
     * Called when a task for this component is initialized within a worker on the cluster.
     * It provides the spout with the environment in which the spout executes.
     *
     * This includes the:
     *
     * @param conf The Storm configuration for this spout. This is the configuration provided to the topology merged in with cluster configuration on this machine.
     * @param context This object can be used to get information about this task's place within the topology, including the task id and component id of this task, input and output information, etc.
     * @param collector The collector is used to emit tuples from this spout. Tuples can be emitted at any time, including the open and close methods. The collector is thread-safe and should be saved as an instance variable of this spout object.
     */
    void open(Map conf, TopologyContext context, SpoutOutputCollector collector);

    /**
     * Called when an ISpout is going to be shutdown. There is no guarentee that close
     * will be called, because the supervisor kill -9's worker processes on the cluster.
     *
     * The one context where close is guaranteed to be called is a topology is
     * killed when running Storm in local mode.
     */
    void close();

    /**
     * Called when a spout has been activated out of a deactivated mode.
     * nextTuple will be called on this spout soon. A spout can become activated
     * after having been deactivated when the topology is manipulated using the
     * `storm` client.
     */
    void activate();

    /**
     * Called when a spout has been deactivated. nextTuple will not be called while
     * a spout is deactivated. The spout may or may not be reactivated in the future.
     */
    void deactivate();

    /**
     * When this method is called, Storm is requesting that the Spout emit tuples to the
     * output collector. This method should be non-blocking, so if the Spout has no tuples
     * to emit, this method should return. nextTuple, ack, and fail are all called in a tight
     * loop in a single thread in the spout task. When there are no tuples to emit, it is courteous
     * to have nextTuple sleep for a short amount of time (like a single millisecond)
     * so as not to waste too much CPU.
     */
    void nextTuple();

    /**
     * Storm has determined that the tuple emitted by this spout with the msgId identifier
     * has been fully processed. Typically, an implementation of this method will take that
     * message off the queue and prevent it from being replayed.
     */
    void ack(Object msgId);

    /**
     * The tuple emitted by this spout with the msgId identifier has failed to be
     * fully processed. Typically, an implementation of this method will put that
     * message back on the queue to be replayed at a later time.
     */
    void fail(Object msgId);
}

package org.apache.storm.task;

import org.apache.storm.tuple.Tuple;
import java.util.Map;
import java.io.Serializable;

/**
 * An IBolt represents a component that takes tuples as input and produces tuples
 * as output. An IBolt can do everything from filtering to joining to functions
 * to aggregations. It does not have to process a tuple immediately and may
 * hold onto tuples to process later.
 *
 * A bolt's lifecycle is as follows:
 *
 * IBolt object created on client machine. The IBolt is serialized into the topology
 * (using Java serialization) and submitted to the master machine of the cluster (Nimbus).
 * Nimbus then launches workers which deserialize the object, call prepare on it, and then
 * start processing tuples.
 *
 * If you want to parameterize an IBolt, you should set the parameters through its
 * constructor and save the parameterization state as instance variables (which will
 * then get serialized and shipped to every task executing this bolt across the cluster).
 *
 * When defining bolts in Java, you should use the IRichBolt interface which adds
 * necessary methods for using the Java TopologyBuilder API.
 */
public interface IBolt extends Serializable {
    /**
     * Called when a task for this component is initialized within a worker on the cluster.
     * It provides the bolt with the environment in which the bolt executes.
     *
     * This includes the:
     *
     * @param stormConf The Storm configuration for this bolt. This is the configuration provided to the topology merged in with cluster configuration on this machine.
     * @param context This object can be used to get information about this task's place within the topology, including the task id and component id of this task, input and output information, etc.
     * @param collector The collector is used to emit tuples from this bolt. Tuples can be emitted at any time, including the prepare and cleanup methods. The collector is thread-safe and should be saved as an instance variable of this bolt object.
     */
    void prepare(Map stormConf, TopologyContext context, OutputCollector collector);

    /**
     * Process a single tuple of input. The Tuple object contains metadata on it
     * about which component/stream/task it came from. The values of the Tuple can
     * be accessed using Tuple#getValue. The IBolt does not have to process the Tuple
     * immediately. It is perfectly fine to hang onto a tuple and process it later
     * (for instance, to do an aggregation or join).
     *
     * Tuples should be emitted using the OutputCollector provided through the prepare method.
     * It is required that all input tuples are acked or failed at some point using the OutputCollector.
     * Otherwise, Storm will be unable to determine when tuples coming off the spouts
     * have been completed.
     *
     * For the common case of acking an input tuple at the end of the execute method,
     * see IBasicBolt which automates this.
     *
     * @param input The input tuple to be processed.
     */
    void execute(Tuple input);

    /**
     * Called when an IBolt is going to be shutdown. There is no guarentee that cleanup
     * will be called, because the supervisor kill -9's worker processes on the cluster.
     *
     * The one context where cleanup is guaranteed to be called is when a topology
     * is killed when running Storm in local mode.
     */
    void cleanup();
}

package org.apache.storm.topology;

import org.apache.storm.spout.ISpout;

/**
 * When writing topologies using Java, {@link IRichBolt} and {@link IRichSpout} are the main interfaces
 * to use to implement components of the topology.
 *
 */
public interface IRichSpout extends ISpout, IComponent {

}

package org.apache.storm.topology;

import org.apache.storm.task.IBolt;

/**
 * When writing topologies using Java, {@link IRichBolt} and {@link IRichSpout} are the main interfaces
 * to use to implement components of the topology.
 *
 */
public interface IRichBolt extends IBolt, IComponent {

}

package org.apache.storm.topology;

import org.apache.storm.task.TopologyContext;
import org.apache.storm.tuple.Tuple;
import java.util.Map;

public interface IBasicBolt extends IComponent {
    void prepare(Map stormConf, TopologyContext context);
    /**
     * Process the input tuple and optionally emit new tuples based on the input tuple.
     *
     * All acking is managed for you. Throw a FailedException if you want to fail the tuple.
     */
    void execute(Tuple input, BasicOutputCollector collector);
    void cleanup();
}

package org.apache.storm.state;

import org.apache.storm.task.TopologyContext;
import java.io.Serializable;
import java.util.Map;

public interface IStateSpout extends Serializable {
    void open(Map conf, TopologyContext context);
    void close();
    void nextTuple(StateSpoutOutputCollector collector);
    void synchronize(SynchronizeOutputCollector collector);
}

package org.apache.storm.topology;

import org.apache.storm.state.IStateSpout;

public interface IRichStateSpout extends IStateSpout, IComponent {

}

package org.apache.storm.topology.base;

import org.apache.storm.topology.IComponent;
import java.util.Map;

public abstract class BaseComponent implements IComponent {
    @Override
    public Map<String, Object> getComponentConfiguration() {
        return null;
    }
}

package org.apache.storm.topology.base;

import org.apache.storm.topology.IRichSpout;

public abstract class BaseRichSpout extends BaseComponent implements IRichSpout {
    @Override
    public void close() {
    }

    @Override
    public void activate() {
    }

    @Override
    public void deactivate() {
    }

    @Override
    public void ack(Object msgId) {
    }

    @Override
    public void fail(Object msgId) {
    }
}

package org.apache.storm.topology.base;

import org.apache.storm.topology.IRichBolt;

public abstract class BaseRichBolt extends BaseComponent implements IRichBolt {
    @Override
    public void cleanup() {
    }
}

package org.apache.storm.topology.base;

import org.apache.storm.task.TopologyContext;
import org.apache.storm.topology.IBasicBolt;
import java.util.Map;

public abstract class BaseBasicBolt extends BaseComponent implements IBasicBolt {

    @Override
    public void prepare(Map stormConf, TopologyContext context) {
    }

    @Override
    public void cleanup() {
    }
}

builder.setBolt("join", new Joiner(), parallelism)
        .fieldGrouping("1", new Field("1-joinfield1", "1-joinfield2"))
        .fieldGrouping("2", new Field("2-joinfield1", "2-joinfield2"))
        .fieldGrouping("3", new Field("3-joinfield1", "3-joinfield2"));

builder.setBolt("rank", new RankBolt(), parallelism)
        .fieldGrouping("spout", new Fields("count"));
builder.setBolt("merge_rank", new MergeRank())
        .globalGrouping("rank");

<dependency>
    <groupId>...</groupId>
    <artifactId>...</artifactId>
    <version>...</version>
    <exclusions>
        <exclusion>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
        </exclusion>
        <exclusion>
            <groupId>log4j</groupId>
            <artifactId>log4j</artifactId>
        </exclusion>
    </exclusions>
</dependency>

Config conf = new Config();
conf.setNumWorkers(2); // use two worker processes
topologyBuilder.setSpout("blue-spout", new BlueSpout(), 2);
topologyBuilder.setBolt("green-bolt", new GreenBolt(), 2)
               .setNumTasks(4)
               .shuffleGrouping("blue-spout");
topologyBuilder.setBolt("yellow-bolt", new YellowBolt(), 6)
               .shuffleGrouping("green-bolt");
StormSubmitter.submitTopology(
        "mytopology",
        conf,
        topologyBuilder.createTopology()
    );

storm rebalance mytopology -n 5 -e blue-spout=3 -e yellow-bolt=10

import java.io.IOException;
import java.io.RandomAccessFile;
import java.util.HashMap;
import java.util.Map;
import java.util.UUID;

import org.apache.storm.Config;
import org.apache.storm.task.OutputCollector;
import org.apache.storm.task.TopologyContext;
import org.apache.storm.topology.OutputFieldsDeclarer;
import org.apache.storm.topology.base.BaseRichBolt;
import org.apache.storm.tuple.Tuple;
import org.apache.storm.utils.TupleUtils;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

public class WordCountBolt extends BaseRichBolt {

    private static final long serialVersionUID = 8239697869626573368L;

    private static final Logger logger = LoggerFactory.getLogger(WordCountBolt.class);

    private String outputDir;

    private OutputCollector collector;

    private Map<String, Integer> wordCounter;

    public WordCountBolt(String outputDir) {
        this.outputDir = outputDir;
    }

    @Override
    @SuppressWarnings("rawtypes")
    public void prepare(Map conf, TopologyContext context, OutputCollector collector) {
        this.collector = collector;
        wordCounter = new HashMap<>();
    }

    @Override
    public void execute(Tuple tuple) {
        if (TupleUtils.isTick(tuple)) { // tick tuple
            outputResult(wordCounter);
            wordCounter.clear();
        } else {    // 正常tuple
            String word = tuple.getStringByField("word");
            Integer count = tuple.getIntegerByField("count");
            Integer wordCount = wordCounter.get(word);
            if (wordCount == null) {
                wordCounter.put(word, count);
            } else {
                wordCounter.put(word, count + wordCount);
            }
        }

        collector.ack(tuple);
    }

    @Override
    public void declareOutputFields(OutputFieldsDeclarer declarer) {
    }

    @Override
    public void cleanup() {
        if (wordCounter != null) {
            wordCounter.clear();
        }
        super.cleanup();
    }

    @Override
    public Map<String, Object> getComponentConfiguration() {
        Config conf = new Config();
        // 5秒定时
        conf.put(Config.TOPOLOGY_TICK_TUPLE_FREQ_SECS, 5);
        return conf;
    }

    private void outputResult(Map<String, Integer> wordCounter) {
        String filePath = outputDir + "/" + UUID.randomUUID().toString();
        RandomAccessFile randomAccessFile = null;
        try {
            randomAccessFile = new RandomAccessFile(filePath, "rw");
            for (Map.Entry<String, Integer> entry : wordCounter.entrySet()) {
                randomAccessFile.writeChars(entry.getKey());
                randomAccessFile.writeChar('\t');
                randomAccessFile.writeChars(String.valueOf(entry.getValue()));
                randomAccessFile.writeChar('\n');
            }
        } catch (IOException e) {
            logger.error("Failed to write file [" + filePath + "].", e);
        } finally {
            if (randomAccessFile != null) {
                try {
                    randomAccessFile.close();
                } catch (IOException e) {
                    logger.warn("Failed to close output stream.", e);
                }
            }
        }
    }

}

work.childopts: "-Xms2g -Xmx2g"