use of edu.iu.dsc.tws.examples.utils.RandomString in project twister2 by DSC-SPIDAL.
the class BasicMemoryManagerGatherCommunication method init.
@Override
public void init(Config cfg, int containerId, ResourcePlan plan) {
LOG.log(Level.INFO, "Starting the example with container id: " + plan.getThisId());
this.config = cfg;
this.resourcePlan = plan;
this.id = containerId;
this.noOfTasksPerExecutor = NO_OF_TASKS / plan.noOfContainers();
this.randomString = new RandomString(128000, new Random(), RandomString.ALPHANUM);
// lets create the task plan
TaskPlan taskPlan = Utils.createReduceTaskPlan(cfg, plan, NO_OF_TASKS);
// first get the communication config file
TWSNetwork network = new TWSNetwork(cfg, taskPlan);
TWSCommunication channel = network.getDataFlowTWSCommunication();
Set<Integer> sources = new HashSet<>();
for (int i = 0; i < NO_OF_TASKS; i++) {
sources.add(i);
}
int dest = NO_OF_TASKS;
Map<String, Object> newCfg = new HashMap<>();
LOG.info("Setting up gather MM dataflow operation");
try {
// this method calls the init method
// I think this is wrong
aggregate = channel.gather(newCfg, MessageType.INTEGER, 0, sources, dest, new GatherBatchFinalReceiver(new FinalGatherReceive()), new GatherBatchPartialReceiver(dest));
aggregate.setMemoryMapped(true);
for (int i = 0; i < noOfTasksPerExecutor; i++) {
// the map thread where data is produced
LOG.info(String.format("%d Starting %d", id, i + id * noOfTasksPerExecutor));
Thread mapThread = new Thread(new MapWorker(i + id * noOfTasksPerExecutor));
mapThread.start();
}
// we need to progress the communication
while (true) {
try {
// progress the channel
channel.progress();
// we should progress the communication directive
aggregate.progress();
Thread.yield();
} catch (Throwable t) {
t.printStackTrace();
}
}
} catch (Throwable t) {
t.printStackTrace();
}
}
use of edu.iu.dsc.tws.examples.utils.RandomString in project twister2 by DSC-SPIDAL.
the class BasicMemoryManagerKeyedGatherCommunication method init.
@Override
public void init(Config cfg, int containerId, ResourcePlan plan) {
LOG.log(Level.INFO, "Starting the example with container id: " + plan.getThisId());
this.config = cfg;
this.resourcePlan = plan;
this.id = containerId;
this.noOfTasksPerExecutor = NO_OF_TASKS / plan.noOfContainers();
this.randomString = new RandomString(128000, new Random(), RandomString.ALPHANUM);
// lets create the task plan
TaskPlan taskPlan = Utils.createReduceTaskPlan(cfg, plan, NO_OF_TASKS);
// first get the communication config file
TWSNetwork network = new TWSNetwork(cfg, taskPlan);
TWSCommunication channel = network.getDataFlowTWSCommunication();
Set<Integer> sources = new HashSet<>();
for (int i = 0; i < NO_OF_TASKS; i++) {
sources.add(i);
}
int dest = NO_OF_TASKS;
Map<String, Object> newCfg = new HashMap<>();
LOG.info("Setting up keyed gather MM dataflow operation");
try {
// this method calls the init method
// I think this is wrong
aggregate = channel.gather(newCfg, MessageType.INTEGER, MessageType.INTEGER, 0, sources, dest, new GatherBatchFinalReceiver(new FinalGatherReceive()), new GatherBatchPartialReceiver(dest));
aggregate.setMemoryMapped(true);
for (int i = 0; i < noOfTasksPerExecutor; i++) {
// the map thread where data is produced
LOG.info(String.format("%d Starting %d", id, i + id * noOfTasksPerExecutor));
Thread mapThread = new Thread(new MapWorker(i + id * noOfTasksPerExecutor));
mapThread.start();
}
// we need to progress the communication
while (true) {
try {
// progress the channel
channel.progress();
// we should progress the communication directive
aggregate.progress();
Thread.yield();
} catch (Throwable t) {
t.printStackTrace();
}
}
} catch (Throwable t) {
t.printStackTrace();
}
}
use of edu.iu.dsc.tws.examples.utils.RandomString in project twister2 by DSC-SPIDAL.
the class WordCount method execute.
@Override
public void execute(WorkerEnvironment workerEnvironment) {
StreamingEnvironment cEnv = TSetEnvironment.initStreaming(workerEnvironment);
// create source and aggregator
cEnv.createSource(new SourceFunc<String>() {
// sample words
private List<String> sampleWords = new ArrayList<>();
// the random used to pick he words
private Random random;
@Override
public void prepare(TSetContext context) {
this.random = new Random();
RandomString randomString = new RandomString(MAX_CHARS, random, RandomString.ALPHANUM);
for (int i = 0; i < NO_OF_SAMPLE_WORDS; i++) {
sampleWords.add(randomString.nextRandomSizeString());
}
}
@Override
public boolean hasNext() {
return true;
}
@Override
public String next() {
return sampleWords.get(random.nextInt(sampleWords.size()));
}
}, 4).partition(new HashingPartitioner<>()).sink(new SinkFunc<String>() {
// keep track of the counts
private Map<String, Integer> counts = new HashMap<>();
private TSetContext context;
@Override
public void prepare(TSetContext context) {
this.context = context;
}
@Override
public boolean add(String word) {
int count = 1;
if (counts.containsKey(word)) {
count = counts.get(word);
count++;
}
counts.put(word, count);
LOG.log(Level.INFO, String.format("%d Word %s count %s", context.getIndex(), word, count));
return true;
}
});
// start executing the streaming graph
cEnv.run();
}
Aggregations