聊聊storm trident spout的_maxTransactionActive
阿新 • • 發佈：2018-11-22
序
本文主要研究一下storm trident spout的_maxTransactionActive
MasterBatchCoordinator
storm-core-1.2.2-sources.jar!/org/apache/storm/trident/topology/MasterBatchCoordinator.java
TreeMap<Long, TransactionStatus> _activeTx = new TreeMap<Long, TransactionStatus>();
public void open(Map conf, TopologyContext context, SpoutOutputCollector collector) {
_throttler = new WindowedTimeThrottler((Number)conf.get(Config.TOPOLOGY_TRIDENT_BATCH_EMIT_INTERVAL_MILLIS), 1);
for - MasterBatchCoordinator在open方法對_maxTransactionActive進行設定，從Config.TOPOLOGY_MAX_SPOUT_PENDING(
topology.max.spout.pending)，配置檔案預設為null，這裡在該值為null時設定_maxTransactionActive為1 - nextTuple這裡對同時處理的batches的數量進行了控制，只有_activeTx中的batches處理成功或失敗之後才能繼續下一個batch
- _activeTx是一個treeMap，它以transactionId為key，value是TransactionStatus，它裡頭包含了TransactionAttempt及AttemptStatus；AttemptStatus有三種狀態，分別是PROCESSING、PROCESSED、COMMITTING
TridentSpoutCoordinator
storm-core-1.2.2-sources.jar!/org/apache/storm/trident/spout/TridentSpoutCoordinator.java
RotatingTransactionalState _state;
public void prepare(Map conf, TopologyContext context) {
_coord = _spout.getCoordinator(_id, conf, context);
_underlyingState = TransactionalState.newCoordinatorState(conf, _id);
_state = new RotatingTransactionalState(_underlyingState, META_DIR);
}
public void execute(Tuple tuple, BasicOutputCollector collector) {
TransactionAttempt attempt = (TransactionAttempt) tuple.getValue(0);
if(tuple.getSourceStreamId().equals(MasterBatchCoordinator.SUCCESS_STREAM_ID)) {
_state.cleanupBefore(attempt.getTransactionId());
_coord.success(attempt.getTransactionId());
} else {
long txid = attempt.getTransactionId();
Object prevMeta = _state.getPreviousState(txid);
Object meta = _coord.initializeTransaction(txid, prevMeta, _state.getState(txid));
_state.overrideState(txid, meta);
collector.emit(MasterBatchCoordinator.BATCH_STREAM_ID, new Values(attempt, meta));
}
}
複製程式碼- TridentSpoutCoordinator的execute方法按txid來存取meta，之後往TridentBoltExecutor發射Values(attempt, meta)
TridentBoltExecutor
storm-core-1.2.2-sources.jar!/org/apache/storm/trident/topology/TridentBoltExecutor.java
RotatingMap<Object, TrackedBatch> _batches;
public void execute(Tuple tuple) {
if(TupleUtils.isTick(tuple)) {
long now = System.currentTimeMillis();
if(now - _lastRotate > _messageTimeoutMs) {
_batches.rotate();
_lastRotate = now;
}
return;
}
String batchGroup = _batchGroupIds.get(tuple.getSourceGlobalStreamId());
if(batchGroup==null) {
// this is so we can do things like have simple DRPC that doesn't need to use batch processing
_coordCollector.setCurrBatch(null);
_bolt.execute(null, tuple);
_collector.ack(tuple);
return;
}
IBatchID id = (IBatchID) tuple.getValue(0);
//get transaction id
//if it already exists and attempt id is greater than the attempt there
TrackedBatch tracked = (TrackedBatch) _batches.get(id.getId());
// if(_batches.size() > 10 && _context.getThisTaskIndex() == 0) {
// System.out.println("Received in " + _context.getThisComponentId() + " " + _context.getThisTaskIndex()
// + " (" + _batches.size() + ")" +
// "\ntuple: " + tuple +
// "\nwith tracked " + tracked +
// "\nwith id " + id +
// "\nwith group " + batchGroup
// + "\n");
//
// }
//System.out.println("Num tracked: " + _batches.size() + " " + _context.getThisComponentId() + " " + _context.getThisTaskIndex());
// this code here ensures that only one attempt is ever tracked for a batch, so when
// failures happen you don't get an explosion in memory usage in the tasks
if(tracked!=null) {
if(id.getAttemptId() > tracked.attemptId) {
_batches.remove(id.getId());
tracked = null;
} else if(id.getAttemptId() < tracked.attemptId) {
// no reason to try to execute a previous attempt than we've already seen
return;
}
}
if(tracked==null) {
tracked = new TrackedBatch(new BatchInfo(batchGroup, id, _bolt.initBatchState(batchGroup, id)), _coordConditions.get(batchGroup), id.getAttemptId());
_batches.put(id.getId(), tracked);
}
_coordCollector.setCurrBatch(tracked);
//System.out.println("TRACKED: " + tracked + " " + tuple);
TupleType t = getTupleType(tuple, tracked);
if(t==TupleType.COMMIT) {
tracked.receivedCommit = true;
checkFinish(tracked, tuple, t);
} else if(t==TupleType.COORD) {
int count = tuple.getInteger(1);
tracked.reportedTasks++;
tracked.expectedTupleCount+=count;
checkFinish(tracked, tuple, t);
} else {
tracked.receivedTuples++;
boolean success = true;
try {
_bolt.execute(tracked.info, tuple);
if(tracked.condition.expectedTaskReports==0) {
success = finishBatch(tracked, tuple);
}
} catch(FailedException e) {
failBatch(tracked, e);
}
if(success) {
_collector.ack(tuple);
} else {
_collector.fail(tuple);
}
}
_coordCollector.setCurrBatch(null);
}
public static class TrackedBatch {
int attemptId;
BatchInfo info;
CoordCondition condition;
int reportedTasks = 0;
int expectedTupleCount = 0;
int receivedTuples = 0;
Map<Integer, Integer> taskEmittedTuples = new HashMap<>();
boolean failed = false;
boolean receivedCommit;
Tuple delayedAck = null;
public TrackedBatch(BatchInfo info, CoordCondition condition, int attemptId) {
this.info = info;
this.condition = condition;
this.attemptId = attemptId;
receivedCommit = condition.commitStream == null;
}
@Override
public String toString() {
return ToStringBuilder.reflectionToString(this);
}
}
private void checkFinish(TrackedBatch tracked, Tuple tuple, TupleType type) {
if(tracked.failed) {
failBatch(tracked);
_collector.fail(tuple);
return;
}
CoordCondition cond = tracked.condition;
boolean delayed = tracked.delayedAck==null &&
(cond.commitStream!=null && type==TupleType.COMMIT
|| cond.commitStream==null);
if(delayed) {
tracked.delayedAck = tuple;
}
boolean failed = false;
if(tracked.receivedCommit && tracked.reportedTasks == cond.expectedTaskReports) {
if(tracked.receivedTuples == tracked.expectedTupleCount) {
finishBatch(tracked, tuple);
} else {
//TODO: add logging that not all tuples were received
failBatch(tracked);
_collector.fail(tuple);
failed = true;
}
}
if(!delayed && !failed) {
_collector.ack(tuple);
}
}
private boolean finishBatch(TrackedBatch tracked, Tuple finishTuple) {
boolean success = true;
try {
_bolt.finishBatch(tracked.info);
String stream = COORD_STREAM(tracked.info.batchGroup);
for(Integer task: tracked.condition.targetTasks) {
_collector.emitDirect(task, stream, finishTuple, new Values(tracked.info.batchId, Utils.get(tracked.taskEmittedTuples, task, 0)));
}
if(tracked.delayedAck!=null) {
_collector.ack(tracked.delayedAck);
tracked.delayedAck = null;
}
} catch(FailedException e) {
failBatch(tracked, e);
success = false;
}
_batches.remove(tracked.info.batchId.getId());
return success;
}
private void failBatch(TrackedBatch tracked, FailedException e) {
if(e!=null && e instanceof ReportedFailedException) {
_collector.reportError(e);
}
tracked.failed = true;
if(tracked.delayedAck!=null) {
_collector.fail(tracked.delayedAck);
tracked.delayedAck = null;
}
}
複製程式碼- TridentBoltExecutor使用RotatingMap(
_batches)來存放batch的資訊，key為txid，而valute為TrackedBatch - 在呼叫_bolt.execute(tracked.info, tuple)方法時，傳遞了BatchInfo，它裡頭的state值為_bolt.initBatchState(batchGroup, id)，通過_bolt的initBatchState得來的，這是在第一次_batches裡頭沒有該txid資訊的時候，第一次建立的時候呼叫
- 這裡的checkFinish也是根據batch對應的TrackedBatch資訊來進行判斷的；finishBatch的時候會呼叫_bolt.finishBatch(tracked.info)，傳遞batchInfo過去；failBatch也是對batch對應的TrackedBatch進行操作
BatchInfo
storm-core-1.2.2-sources.jar!/org/apache/storm/trident/topology/BatchInfo.java
public class BatchInfo {
public IBatchID batchId;
public Object state;
public String batchGroup;
public BatchInfo(String batchGroup, IBatchID batchId, Object state) {
this.batchGroup = batchGroup;
this.batchId = batchId;
this.state = state;
}
}
複製程式碼- BatchInfo裡頭包含了batchId，state以及batchGroup資訊
TridentSpoutExecutor
storm-core-1.2.2-sources.jar!/org/apache/storm/trident/spout/TridentSpoutExecutor.java
public Object initBatchState(String batchGroup, Object batchId) {
return null;
}
public void execute(BatchInfo info, Tuple input) {
// there won't be a BatchInfo for the success stream
TransactionAttempt attempt = (TransactionAttempt) input.getValue(0);
if(input.getSourceStreamId().equals(MasterBatchCoordinator.COMMIT_STREAM_ID)) {
if(attempt.equals(_activeBatches.get(attempt.getTransactionId()))) {
((ICommitterTridentSpout.Emitter) _emitter).commit(attempt);
_activeBatches.remove(attempt.getTransactionId());
} else {
throw new FailedException("Received commit for different transaction attempt");
}
} else if(input.getSourceStreamId().equals(MasterBatchCoordinator.SUCCESS_STREAM_ID)) {
// valid to delete before what's been committed since
// those batches will never be accessed again
_activeBatches.headMap(attempt.getTransactionId()).clear();
_emitter.success(attempt);
} else {
_collector.setBatch(info.batchId);
_emitter.emitBatch(attempt, input.getValue(1), _collector);
_activeBatches.put(attempt.getTransactionId(), attempt);
}
}
public void finishBatch(BatchInfo batchInfo) {
}
複製程式碼- TridentSpoutExecutor的execute方法，也是根據txid來區分各自batch的資訊
SubtopologyBolt
storm-core-1.2.2-sources.jar!/org/apache/storm/trident/planner/SubtopologyBolt.java
public Object initBatchState(String batchGroup, Object batchId) {
ProcessorContext ret = new ProcessorContext(batchId, new Object[_nodes.size()]);
for(TridentProcessor p: _myTopologicallyOrdered.get(batchGroup)) {
p.startBatch(ret);
}
return ret;
}
public void execute(BatchInfo batchInfo, Tuple tuple) {
String sourceStream = tuple.getSourceStreamId();
InitialReceiver ir = _roots.get(sourceStream);
if(ir==null) {
throw new RuntimeException("Received unexpected tuple " + tuple.toString());
}
ir.receive((ProcessorContext) batchInfo.state, tuple);
}
public void finishBatch(BatchInfo batchInfo) {
for(TridentProcessor p: _myTopologicallyOrdered.get(batchInfo.batchGroup)) {
p.finishBatch((ProcessorContext) batchInfo.state);
}
}
protected static class InitialReceiver {
List<TridentProcessor> _receivers = new ArrayList<>();
RootFactory _factory;
ProjectionFactory _project;
String _stream;
public InitialReceiver(String stream, Fields allFields) {
// TODO: don't want to project for non-batch bolts...???
// how to distinguish "batch" streams from non-batch streams?
_stream = stream;
_factory = new RootFactory(allFields);
List<String> projected = new ArrayList<>(allFields.toList());
projected.remove(0);
_project = new ProjectionFactory(_factory, new Fields(projected));
}
public void receive(ProcessorContext context, Tuple tuple) {
TridentTuple t = _project.create(_factory.create(tuple));
for(TridentProcessor r: _receivers) {
r.execute(context, _stream, t);
}
}
public void addReceiver(TridentProcessor p) {
_receivers.add(p);
}
public Factory getOutputFactory() {
return _project;
}
}
複製程式碼- SubtopologyBolt在initBatchState的時候，建立ProcessorContext的也是帶有batchId的標識，這樣子不同的batch並行的話，它們的ProcessorContext也是區分開來的
- execute方法使用的是各自batch的ProcessorContext(
batchInfo.state)，呼叫TridentProcessor的execute方法，使用的是各自batch的ProcessorContext - finishBatch方法也一樣，將(ProcessorContext) batchInfo.state傳遞給TridentProcessor.finishBatch
AggregateProcessor
storm-core-1.2.2-sources.jar!/org/apache/storm/trident/planner/processor/AggregateProcessor.java
public void startBatch(ProcessorContext processorContext) {
_collector.setContext(processorContext);
processorContext.state[_context.getStateIndex()] = _agg.init(processorContext.batchId, _collector);
}
public void execute(ProcessorContext processorContext, String streamId, TridentTuple tuple) {
_collector.setContext(processorContext);
_agg.aggregate(processorContext.state[_context.getStateIndex()], _projection.create(tuple), _collector);
}
public void finishBatch(ProcessorContext processorContext) {
_collector.setContext(processorContext);
_agg.complete(processorContext.state[_context.getStateIndex()], _collector);
}
複製程式碼- AggregateProcessor的startBatch、execute、finishBatch方法都使用了ProcessorContext的state，而該ProcessorContext從SubtopologyBolt傳遞過來的就是區分batch的
EachProcessor
storm-core-1.2.2-sources.jar!/org/apache/storm/trident/planner/processor/EachProcessor.java
public void prepare(Map conf, TopologyContext context, TridentContext tridentContext) {
List<Factory> parents = tridentContext.getParentTupleFactories();
if(parents.size()!=1) {
throw new RuntimeException("Each operation can only have one parent");
}
_context = tridentContext;
_collector = new AppendCollector(tridentContext);
_projection = new ProjectionFactory(parents.get(0), _inputFields);
_function.prepare(conf, new TridentOperationContext(context, _projection));
}
public void execute(ProcessorContext processorContext, String streamId, TridentTuple tuple) {
_collector.setContext(processorContext, tuple);
_function.execute(_projection.create(tuple), _collector);
}
public void startBatch(ProcessorContext processorContext) {
}
public void finishBatch(ProcessorContext processorContext) {
}
複製程式碼- EachProcessor則是將ProcessorContext設定到_collector，然後呼叫_function.execute的時候，將_collector傳遞過去；這裡的_collector為AppendCollector
AppendCollector
storm-core-1.2.2-sources.jar!/org/apache/storm/trident/planner/processor/AppendCollector.java
public class AppendCollector implements TridentCollector {
OperationOutputFactory _factory;
TridentContext _triContext;
TridentTuple tuple;
ProcessorContext context;
public AppendCollector(TridentContext context) {
_triContext = context;
_factory = new OperationOutputFactory(context.getParentTupleFactories().get(0), context.getSelfOutputFields());
}
public void setContext(ProcessorContext pc, TridentTuple t) {
this.context = pc;
this.tuple = t;
}
@Override
public void emit(List<Object> values) {
TridentTuple toEmit = _factory.create((TridentTupleView) tuple, values);
for(TupleReceiver r: _triContext.getReceivers()) {
r.execute(context, _triContext.getOutStreamId(), toEmit);
}
}
@Override
public void reportError(Throwable t) {
_triContext.getDelegateCollector().reportError(t);
}
public Factory getOutputFactory() {
return _factory;
}
}
複製程式碼- 當_function.execute使用AppendCollector進行emit的時候，AppendCollector會將這些tuple交給TupleReceiver去處理，而傳遞過去的context為EachProcessor設定的ProcessorContext，即每個batch自己的ProcessorContext；TupleReceiver的execute方法可能對ProcessorContext進行存取，這個也是batch維度的，比如AggregateProcessor將聚合結果存放到自己batch的processorContext.state中
小結
- storm的trident使用[id,count]資料來告訴下游的TridentBoltExecutor來結束一個batch；而TridentBoltExecutor在接收[id,count]資料的時候，會先判斷tracked.reportedTasks是否等於cond.expectedTaskReports(
這個在上游的TridentBoltExecutor的parallelism大於1的時候用來聚合這些task的資料)，相等之後再判斷tracked.receivedTuples是否等於tracked.expectedTupleCount，相等才能進行finishBatch - storm的trident spout的_maxTransactionActive引數根據Config.TOPOLOGY_MAX_SPOUT_PENDING(
topology.max.spout.pending)進行設定，配置檔案預設為null，在該值為null時_maxTransactionActive為1 - MasterBatchCoordinator對同時處理的batches的數量進行了控制，只有_activeTx中的batches處理成功或失敗之後才能繼續下一個batch；而當並行有多個_activeTx的時候，下游的TridentBoltExecutor也能夠區分batch來進行處理，不會造成混亂；比如SubtopologyBolt在initBatchState的時候，建立ProcessorContext的也是帶有batchId的標識，這樣子不同的batch並行的話，它們的ProcessorContext也是區分開來的；SubtopologyBolt裡頭呼叫的TridentProcessor有的會使用ProcessorContext來儲存結果，比如AggregateProcessor將聚合結果存放到自己batch的processorContext.state中