Examples with DataPartition edu.iu.dsc.tws.api.dataset.DataPartition used on opensource projects

Example 1 with DataPartition

use of edu.iu.dsc.tws.api.dataset.DataPartition in project twister2 by DSC-SPIDAL.

the class TaskExecutor method distributeData.

/**
 * This method distributes collected {@link DataPartition}s to the
 * intended {@link Receptor}s
 */
public static void distributeData(ExecutionPlan executionPlan, Map<String, DataObject> dataMap) {
    Map<Integer, INodeInstance> nodes = executionPlan.getNodes();
    if (nodes != null) {
        nodes.forEach((id, node) -> {
            INode task = node.getNode();
            if (task instanceof Receptor) {
                Set<String> receivableNames = ((Receptor) task).getReceivableNames();
                for (String receivableName : receivableNames) {
                    DataObject dataObject = dataMap.get(receivableName);
                    if (dataObject == null) {
                        throw new Twister2RuntimeException("Couldn't find input data" + receivableName + " for task " + node.getId());
                    }
                    DataPartition partition = dataObject.getPartition(node.getIndex());
                    if (partition == null) {
                        throw new Twister2RuntimeException("Couldn't find input data" + receivableName + " for task index " + node.getIndex() + " of task" + node.getId());
                    }
                    ((Receptor) task).add(receivableName, dataObject);
                    ((Receptor) task).add(receivableName, partition);
                }
            }
        });
    }
}

Example 2 with DataPartition

use of edu.iu.dsc.tws.api.dataset.DataPartition in project twister2 by DSC-SPIDAL.

the class TaskExecutor method collectData.

/**
 * This method collects all the output from the provided {@link ExecutionPlan}.
 * The partition IDs will be assigned just before adding the partitions to the {@link DataObject}
 */
public static void collectData(Config cfg, ExecutionPlan executionPlan, Map<String, DataObject> dataMap) {
    Map<Integer, INodeInstance> nodes = executionPlan.getNodes();
    Map<String, DataObject> dataObjectMapForPlan = new HashMap<>();
    if (nodes != null) {
        nodes.forEach((taskId, node) -> {
            INode task = node.getNode();
            if (task instanceof Collector) {
                Set<String> collectibleNames = ((Collector) task).getCollectibleNames();
                collectibleNames.forEach(name -> {
                    DataPartition partition = ((Collector) task).get(name);
                    // if this task outs only one partition and user has implemented no arg get() method
                    if (collectibleNames.size() == 1 && partition == null) {
                        partition = ((Collector) task).get();
                    }
                    if (partition != null) {
                        partition.setId(node.getIndex());
                        dataObjectMapForPlan.computeIfAbsent(name, n -> new DataObjectImpl<>(cfg)).addPartition(partition);
                    } else {
                        LOG.warning(String.format("Task index %d  of task %d returned null for data %s", node.getIndex(), node.getId(), name));
                    }
                });
            }
        });
    }
    dataMap.putAll(dataObjectMapForPlan);
}

Example 3 with DataPartition

use of edu.iu.dsc.tws.api.dataset.DataPartition in project twister2 by DSC-SPIDAL.

the class IterativeJob method execute.

@Override
public void execute(WorkerEnvironment workerEnv) {
    ComputeEnvironment cEnv = ComputeEnvironment.init(workerEnv);
    TaskExecutor taskExecutor = cEnv.getTaskExecutor();
    int workerId = workerEnv.getWorkerId();
    Config config = workerEnv.getConfig();
    LOG.log(Level.INFO, "Task worker starting: " + workerId);
    IterativeSourceTask g = new IterativeSourceTask();
    PartitionTask r = new PartitionTask();
    ComputeGraphBuilder graphBuilder = ComputeGraphBuilder.newBuilder(config);
    graphBuilder.addSource("source", g, 4);
    ComputeConnection computeConnection = graphBuilder.addCompute("sink", r, 4);
    computeConnection.partition("source").viaEdge("partition").withDataType(MessageTypes.OBJECT);
    graphBuilder.setMode(OperationMode.BATCH);
    ComputeGraph graph = graphBuilder.build();
    ExecutionPlan plan = taskExecutor.plan(graph);
    IExecutor ex = taskExecutor.createExecution(graph, plan);
    for (int i = 0; i < 10; i++) {
        LOG.info("Starting iteration: " + i);
        taskExecutor.addInput(graph, plan, "source", "input", new DataObjectImpl<>(config));
        // this is a blocking call
        ex.execute();
        DataObject<Object> dataSet = taskExecutor.getOutput(graph, plan, "sink");
        DataPartition<Object>[] values = dataSet.getPartitions();
    }
    ex.closeExecution();
}