Search in sources :

Example 1 with CoordSpec

use of org.apache.storm.trident.topology.TridentBoltExecutor.CoordSpec in project storm by apache.

the class TridentTopologyBuilder method buildTopology.

public StormTopology buildTopology(Map<String, Number> masterCoordResources) {
    TopologyBuilder builder = new TopologyBuilder();
    Map<GlobalStreamId, String> batchIdsForSpouts = fleshOutStreamBatchIds(false);
    Map<GlobalStreamId, String> batchIdsForBolts = fleshOutStreamBatchIds(true);
    Map<String, List<String>> batchesToCommitIds = new HashMap<>();
    Map<String, List<ITridentSpout>> batchesToSpouts = new HashMap<>();
    for (String id : _spouts.keySet()) {
        TransactionalSpoutComponent c = _spouts.get(id);
        if (c.spout instanceof IRichSpout) {
            //TODO: wrap this to set the stream name
            builder.setSpout(id, (IRichSpout) c.spout, c.parallelism);
        } else {
            String batchGroup = c.batchGroupId;
            if (!batchesToCommitIds.containsKey(batchGroup)) {
                batchesToCommitIds.put(batchGroup, new ArrayList<String>());
            }
            batchesToCommitIds.get(batchGroup).add(c.commitStateId);
            if (!batchesToSpouts.containsKey(batchGroup)) {
                batchesToSpouts.put(batchGroup, new ArrayList<ITridentSpout>());
            }
            batchesToSpouts.get(batchGroup).add((ITridentSpout) c.spout);
            BoltDeclarer scd = builder.setBolt(spoutCoordinator(id), new TridentSpoutCoordinator(c.commitStateId, (ITridentSpout) c.spout)).globalGrouping(masterCoordinator(c.batchGroupId), MasterBatchCoordinator.BATCH_STREAM_ID).globalGrouping(masterCoordinator(c.batchGroupId), MasterBatchCoordinator.SUCCESS_STREAM_ID);
            for (Map<String, Object> m : c.componentConfs) {
                scd.addConfigurations(m);
            }
            Map<String, TridentBoltExecutor.CoordSpec> specs = new HashMap();
            specs.put(c.batchGroupId, new CoordSpec());
            BoltDeclarer bd = builder.setBolt(id, new TridentBoltExecutor(new TridentSpoutExecutor(c.commitStateId, c.streamName, ((ITridentSpout) c.spout)), batchIdsForSpouts, specs), c.parallelism);
            bd.allGrouping(spoutCoordinator(id), MasterBatchCoordinator.BATCH_STREAM_ID);
            bd.allGrouping(masterCoordinator(batchGroup), MasterBatchCoordinator.SUCCESS_STREAM_ID);
            if (c.spout instanceof ICommitterTridentSpout) {
                bd.allGrouping(masterCoordinator(batchGroup), MasterBatchCoordinator.COMMIT_STREAM_ID);
            }
            for (Map<String, Object> m : c.componentConfs) {
                bd.addConfigurations(m);
            }
        }
    }
    for (String id : _batchPerTupleSpouts.keySet()) {
        SpoutComponent c = _batchPerTupleSpouts.get(id);
        SpoutDeclarer d = builder.setSpout(id, new RichSpoutBatchTriggerer((IRichSpout) c.spout, c.streamName, c.batchGroupId), c.parallelism);
        for (Map<String, Object> conf : c.componentConfs) {
            d.addConfigurations(conf);
        }
    }
    Number onHeap = masterCoordResources.get(Config.TOPOLOGY_COMPONENT_RESOURCES_ONHEAP_MEMORY_MB);
    Number offHeap = masterCoordResources.get(Config.TOPOLOGY_COMPONENT_RESOURCES_OFFHEAP_MEMORY_MB);
    Number cpuLoad = masterCoordResources.get(Config.TOPOLOGY_COMPONENT_CPU_PCORE_PERCENT);
    for (String batch : batchesToCommitIds.keySet()) {
        List<String> commitIds = batchesToCommitIds.get(batch);
        SpoutDeclarer masterCoord = builder.setSpout(masterCoordinator(batch), new MasterBatchCoordinator(commitIds, batchesToSpouts.get(batch)));
        if (onHeap != null) {
            if (offHeap != null) {
                masterCoord.setMemoryLoad(onHeap, offHeap);
            } else {
                masterCoord.setMemoryLoad(onHeap);
            }
        }
        if (cpuLoad != null) {
            masterCoord.setCPULoad(cpuLoad);
        }
    }
    for (String id : _bolts.keySet()) {
        Component c = _bolts.get(id);
        Map<String, CoordSpec> specs = new HashMap<>();
        for (GlobalStreamId s : getBoltSubscriptionStreams(id)) {
            String batch = batchIdsForBolts.get(s);
            if (!specs.containsKey(batch))
                specs.put(batch, new CoordSpec());
            CoordSpec spec = specs.get(batch);
            CoordType ct;
            if (_batchPerTupleSpouts.containsKey(s.get_componentId())) {
                ct = CoordType.single();
            } else {
                ct = CoordType.all();
            }
            spec.coords.put(s.get_componentId(), ct);
        }
        for (String b : c.committerBatches) {
            specs.get(b).commitStream = new GlobalStreamId(masterCoordinator(b), MasterBatchCoordinator.COMMIT_STREAM_ID);
        }
        BoltDeclarer d = builder.setBolt(id, new TridentBoltExecutor(c.bolt, batchIdsForBolts, specs), c.parallelism);
        for (Map<String, Object> conf : c.componentConfs) {
            d.addConfigurations(conf);
        }
        for (InputDeclaration inputDecl : c.declarations) {
            inputDecl.declare(d);
        }
        Map<String, Set<String>> batchToComponents = getBoltBatchToComponentSubscriptions(id);
        for (Map.Entry<String, Set<String>> entry : batchToComponents.entrySet()) {
            for (String comp : entry.getValue()) {
                d.directGrouping(comp, TridentBoltExecutor.COORD_STREAM(entry.getKey()));
            }
        }
        for (String b : c.committerBatches) {
            d.allGrouping(masterCoordinator(b), MasterBatchCoordinator.COMMIT_STREAM_ID);
        }
    }
    return builder.createTopology();
}
Also used : HashSet(java.util.HashSet) Set(java.util.Set) TopologyBuilder(org.apache.storm.topology.TopologyBuilder) HashMap(java.util.HashMap) ArrayList(java.util.ArrayList) List(java.util.List) TridentSpoutExecutor(org.apache.storm.trident.spout.TridentSpoutExecutor) CoordSpec(org.apache.storm.trident.topology.TridentBoltExecutor.CoordSpec) ICommitterTridentSpout(org.apache.storm.trident.spout.ICommitterTridentSpout) TridentSpoutCoordinator(org.apache.storm.trident.spout.TridentSpoutCoordinator) RichSpoutBatchTriggerer(org.apache.storm.trident.spout.RichSpoutBatchTriggerer) IRichSpout(org.apache.storm.topology.IRichSpout) BoltDeclarer(org.apache.storm.topology.BoltDeclarer) GlobalStreamId(org.apache.storm.generated.GlobalStreamId) SpoutDeclarer(org.apache.storm.topology.SpoutDeclarer) HashMap(java.util.HashMap) Map(java.util.Map) ITridentSpout(org.apache.storm.trident.spout.ITridentSpout) CoordType(org.apache.storm.trident.topology.TridentBoltExecutor.CoordType)

Aggregations

ArrayList (java.util.ArrayList)1 HashMap (java.util.HashMap)1 HashSet (java.util.HashSet)1 List (java.util.List)1 Map (java.util.Map)1 Set (java.util.Set)1 GlobalStreamId (org.apache.storm.generated.GlobalStreamId)1 BoltDeclarer (org.apache.storm.topology.BoltDeclarer)1 IRichSpout (org.apache.storm.topology.IRichSpout)1 SpoutDeclarer (org.apache.storm.topology.SpoutDeclarer)1 TopologyBuilder (org.apache.storm.topology.TopologyBuilder)1 ICommitterTridentSpout (org.apache.storm.trident.spout.ICommitterTridentSpout)1 ITridentSpout (org.apache.storm.trident.spout.ITridentSpout)1 RichSpoutBatchTriggerer (org.apache.storm.trident.spout.RichSpoutBatchTriggerer)1 TridentSpoutCoordinator (org.apache.storm.trident.spout.TridentSpoutCoordinator)1 TridentSpoutExecutor (org.apache.storm.trident.spout.TridentSpoutExecutor)1 CoordSpec (org.apache.storm.trident.topology.TridentBoltExecutor.CoordSpec)1 CoordType (org.apache.storm.trident.topology.TridentBoltExecutor.CoordType)1