深入浅出Zookeeper源码（六）：客户端的请求在服务器中经历了什么

|-- LeaderRequestProcessor
   \-- processRequest //检查会话是否失效
|-- PrepRequestProcessor
   \-- processRequest //参数校验和根据需求创建事务
|-- ProposalRequestProcessor
   \-- processRequest // 发起proposal
   \-- //事务型请求
       \-- SyncRequestProcessor
           \-- processRequest // 将请求记录到事务日志中，如果有需要的话则触发快照
       \-- AckRequestProcessor
           \-- processRequest // 确认事务日志收集完成，对于Proposal的投票器进行ack反馈
       \-- CommitProcessor 
           \-- processRequest // 等待集群内Proposal投票直到可被提交
       \-- ToBeAppliedRequestProcessor 
           \-- processRequest // 存储已经被CommitProcessor处理过的可提交的Proposal——直到FinalRequestProcessor处理完后，才会将其移除
       \-- FinalRequestProcessor
           \-- processRequest // 回复请求，并改变内存数据库的状态
   \-- //非事务型请求
       \-- CommitProcessor 
           \-- processRequest // skip，只处理非事务型请求
       \-- ToBeAppliedRequestProcessor 
           \-- processRequest // skip，配合CommitProcessor一起工作
       \-- FinalRequestProcessor
           \-- processRequest // 回复请求，并改变内存数据库的状态

//处理 client的请求
|-- FollowerRequestProcessor
     \-- processRequest //事务的话调用CommitProcessor，并发送给leader；不然直接到FinalProcessor
|-- CommitProcessor 
     \-- processRequest  // 等待集群内Proposal投票直到可被提交
|-- FinalProcessor  
     \-- processRequest // 回复请求，并改变内存数据库的状态

//专门用来处理 leader发起的proposal
|-- SyncRequestProcessor
|    \-- processRequest // 将请求记录到事务日志中，如果有需要的话则触发快照
|-- SendAckRequestProcessor
     \-- processRequest  // ack给proposal发起者，表示自身完成了日志的记录

//处理 client的请求
|-- ObserverRequestProcessor
     \-- processRequest //和FollowerRequestProcessor代码几乎一模一样：事务的话调用CommitProcessor，并发送给leader；不然直接到FinalProcessor
|-- CommitProcessor
     \-- processRequest  // 等待集群内Proposal投票直到可被提交
|-- FinalProcessor
     \-- processRequest // 回复请求，并改变内存数据库的状态

   @Override
    protected void setupRequestProcessors() {
        RequestProcessor finalProcessor = new FinalRequestProcessor(this);
        RequestProcessor toBeAppliedProcessor = new Leader.ToBeAppliedRequestProcessor(finalProcessor, getLeader());
        commitProcessor = new CommitProcessor(toBeAppliedProcessor,
                Long.toString(getServerId()), false,
                getZooKeeperServerListener());
        commitProcessor.start();
        ProposalRequestProcessor proposalProcessor = new ProposalRequestProcessor(this,
                commitProcessor);
        proposalProcessor.initialize();
        prepRequestProcessor = new PrepRequestProcessor(this, proposalProcessor);
        prepRequestProcessor.start();
        firstProcessor = new LeaderRequestProcessor(this, prepRequestProcessor);

        setupContainerManager();
    }

    @Override
    public void processRequest(Request request)
            throws RequestProcessorException {
        // Check if this is a local session and we are trying to create
        // an ephemeral node, in which case we upgrade the session
        Request upgradeRequest = null;
        try {
            upgradeRequest = lzks.checkUpgradeSession(request);
        } catch (KeeperException ke) {
            if (request.getHdr() != null) {
                LOG.debug("Updating header");
                request.getHdr().setType(OpCode.error);
                request.setTxn(new ErrorTxn(ke.code().intValue()));
            }
            request.setException(ke);
            LOG.info("Error creating upgrade request " + ke.getMessage());
        } catch (IOException ie) {
            LOG.error("Unexpected error in upgrade", ie);
        }
        if (upgradeRequest != null) {
            nextProcessor.processRequest(upgradeRequest);
        }

        nextProcessor.processRequest(request);
    }

          case OpCode.create2:
                CreateRequest create2Request = new CreateRequest();
                pRequest2Txn(request.type, zks.getNextZxid(), request, create2Request, true);
                break;

    protected void pRequest2Txn(int type, long zxid, Request request,
                                Record record, boolean deserialize)
        throws KeeperException, IOException, RequestProcessorException
    {
        request.setHdr(new TxnHeader(request.sessionId, request.cxid, zxid,
                Time.currentWallTime(), type));

        switch (type) {
            case OpCode.create:
            case OpCode.create2:
            case OpCode.createTTL:
            case OpCode.createContainer: {
                pRequest2TxnCreate(type, request, record, deserialize);
                break;
            }
//....多余代码不再展示

    private void pRequest2TxnCreate(int type, Request request, Record record, boolean deserialize) throws IOException, KeeperException {
        if (deserialize) {
            ByteBufferInputStream.byteBuffer2Record(request.request, record);
        }

        int flags;
        String path;
        List<ACL> acl;
        byte[] data;
        long ttl;
        if (type == OpCode.createTTL) {
            CreateTTLRequest createTtlRequest = (CreateTTLRequest)record;
            flags = createTtlRequest.getFlags();
            path = createTtlRequest.getPath();
            acl = createTtlRequest.getAcl();
            data = createTtlRequest.getData();
            ttl = createTtlRequest.getTtl();
        } else {
            CreateRequest createRequest = (CreateRequest)record;
            flags = createRequest.getFlags();
            path = createRequest.getPath();
            acl = createRequest.getAcl();
            data = createRequest.getData();
            ttl = -1;
        }
        CreateMode createMode = CreateMode.fromFlag(flags);
        validateCreateRequest(path, createMode, request, ttl);
        String parentPath = validatePathForCreate(path, request.sessionId);

        List<ACL> listACL = fixupACL(path, request.authInfo, acl);
        ChangeRecord parentRecord = getRecordForPath(parentPath);

        checkACL(zks, parentRecord.acl, ZooDefs.Perms.CREATE, request.authInfo);
        int parentCVersion = parentRecord.stat.getCversion();
        if (createMode.isSequential()) {
            path = path + String.format(Locale.ENGLISH, "%010d", parentCVersion);
        }
        validatePath(path, request.sessionId);
        try {
            if (getRecordForPath(path) != null) {
                throw new KeeperException.NodeExistsException(path);
            }
        } catch (KeeperException.NoNodeException e) {
            // ignore this one
        }
        boolean ephemeralParent = EphemeralType.get(parentRecord.stat.getEphemeralOwner()) == EphemeralType.NORMAL;
        if (ephemeralParent) {
            throw new KeeperException.NoChildrenForEphemeralsException(path);
        }
        int newCversion = parentRecord.stat.getCversion()+1;
        if (type == OpCode.createContainer) {
            request.setTxn(new CreateContainerTxn(path, data, listACL, newCversion));
        } else if (type == OpCode.createTTL) {
            request.setTxn(new CreateTTLTxn(path, data, listACL, newCversion, ttl));
        } else {
            request.setTxn(new CreateTxn(path, data, listACL, createMode.isEphemeral(),
                    newCversion));
        }
        StatPersisted s = new StatPersisted();
        if (createMode.isEphemeral()) {
            s.setEphemeralOwner(request.sessionId);
        }
        parentRecord = parentRecord.duplicate(request.getHdr().getZxid());
        parentRecord.childCount++;
        parentRecord.stat.setCversion(newCversion);
        addChangeRecord(parentRecord);
        addChangeRecord(new ChangeRecord(request.getHdr().getZxid(), path, s, 0, listACL));
    }

          case OpCode.multi:
                MultiTransactionRecord multiRequest = new MultiTransactionRecord();
                try {
                    ByteBufferInputStream.byteBuffer2Record(request.request, multiRequest);
                } catch(IOException e) {
                    request.setHdr(new TxnHeader(request.sessionId, request.cxid, zks.getNextZxid(),
                            Time.currentWallTime(), OpCode.multi));
                    throw e;
                }
                List<Txn> txns = new ArrayList<Txn>();
                //Each op in a multi-op must have the same zxid!
                long zxid = zks.getNextZxid();
                KeeperException ke = null;

                //Store off current pending change records in case we need to rollback
                Map<String, ChangeRecord> pendingChanges = getPendingChanges(multiRequest);

                for(Op op: multiRequest) {
                    Record subrequest = op.toRequestRecord();
                    int type;
                    Record txn;

                    /* If we've already failed one of the ops, don't bother
                     * trying the rest as we know it's going to fail and it
                     * would be confusing in the logfiles.
                     */
                    if (ke != null) {
                        type = OpCode.error;
                        txn = new ErrorTxn(Code.RUNTIMEINCONSISTENCY.intValue());
                    }

                    /* Prep the request and convert to a Txn */
                    else {
                        try {
                            pRequest2Txn(op.getType(), zxid, request, subrequest, false);
                            type = request.getHdr().getType();
                            txn = request.getTxn();
                        } catch (KeeperException e) {
                            ke = e;
                            type = OpCode.error;
                            txn = new ErrorTxn(e.code().intValue());

                            if (e.code().intValue() > Code.APIERROR.intValue()) {
                                LOG.info("Got user-level KeeperException when processing {} aborting" +
                                        " remaining multi ops. Error Path:{} Error:{}",
                                        request.toString(), e.getPath(), e.getMessage());
                            }

                            request.setException(e);

                            /* Rollback change records from failed multi-op */
                            rollbackPendingChanges(zxid, pendingChanges);
                        }
                    }

                    //FIXME: I don't want to have to serialize it here and then
                    //       immediately deserialize in next processor. But I'm
                    //       not sure how else to get the txn stored into our list.
                    ByteArrayOutputStream baos = new ByteArrayOutputStream();
                    BinaryOutputArchive boa = BinaryOutputArchive.getArchive(baos);
                    txn.serialize(boa, "request") ;
                    ByteBuffer bb = ByteBuffer.wrap(baos.toByteArray());

                    txns.add(new Txn(type, bb.array()));
                }

                request.setHdr(new TxnHeader(request.sessionId, request.cxid, zxid,
                        Time.currentWallTime(), request.type));
                request.setTxn(new MultiTxn(txns));

                break;

//All the rest don't need to create a Txn - just verify session
            case OpCode.sync:
                zks.sessionTracker.checkSession(request.sessionId,
                        request.getOwner());
                break;

  public void processRequest(Request request) throws RequestProcessorException {
        // LOG.warn("Ack>>> cxid = " + request.cxid + " type = " +
        // request.type + " id = " + request.sessionId);
        // request.addRQRec(">prop");


        /* In the following IF-THEN-ELSE block, we process syncs on the leader.
         * If the sync is coming from a follower, then the follower
         * handler adds it to syncHandler. Otherwise, if it is a client of
         * the leader that issued the sync command, then syncHandler won't
         * contain the handler. In this case, we add it to syncHandler, and
         * call processRequest on the next processor.
         */

        if (request instanceof LearnerSyncRequest){
            zks.getLeader().processSync((LearnerSyncRequest)request);
        } else {
            nextProcessor.processRequest(request);
            if (request.getHdr() != null) {
                // We need to sync and get consensus on any transactions
                try {
                    zks.getLeader().propose(request);
                } catch (XidRolloverException e) {
                    throw new RequestProcessorException(e.getMessage(), e);
                }
                syncProcessor.processRequest(request);
            }
        }
    }

  /**
     * create a proposal and send it out to all the members
     *
     * @param request
     * @return the proposal that is queued to send to all the members
     */
    public Proposal propose(Request request) throws XidRolloverException {
        /**
         * Address the rollover issue. All lower 32bits set indicate a new leader
         * election. Force a re-election instead. See ZOOKEEPER-1277
         */
        if ((request.zxid & 0xffffffffL) == 0xffffffffL) {
            String msg =
                    "zxid lower 32 bits have rolled over, forcing re-election, and therefore new epoch start";
            shutdown(msg);
            throw new XidRolloverException(msg);
        }

        byte[] data = SerializeUtils.serializeRequest(request);
        proposalStats.setLastBufferSize(data.length);
        QuorumPacket pp = new QuorumPacket(Leader.PROPOSAL, request.zxid, data, null);

        Proposal p = new Proposal();
        p.packet = pp;
        p.request = request;                
        
        synchronized(this) {
           p.addQuorumVerifier(self.getQuorumVerifier());
                   
           if (request.getHdr().getType() == OpCode.reconfig){
               self.setLastSeenQuorumVerifier(request.qv, true);                       
           }
           
           if (self.getQuorumVerifier().getVersion()<self.getLastSeenQuorumVerifier().getVersion()) {
               p.addQuorumVerifier(self.getLastSeenQuorumVerifier());
           }
                   
            if (LOG.isDebugEnabled()) {
                LOG.debug("Proposing:: " + request);
            }

            lastProposed = p.packet.getZxid();
            outstandingProposals.put(lastProposed, p);
            sendPacket(pp);
        }
        return p;
    }

    /**
     * This message type is sent by a leader to propose a mutation.
     */
    public final static int PROPOSAL = 2;

   public void processRequest(Request request) {
        // request.addRQRec(">sync");
        queuedRequests.add(request);
    }

   //线程的核心方法，会对queuedRequests这个队列进行操作
    @Override
    public void run() {
        try {
            int logCount = 0;

            // we do this in an attempt to ensure that not all of the servers
            // in the ensemble take a snapshot at the same time
            int randRoll = r.nextInt(snapCount/2);
            while (true) {
                Request si = null;
                if (toFlush.isEmpty()) {
                    si = queuedRequests.take();
                } else {
                    si = queuedRequests.poll();
                    if (si == null) {
                        flush(toFlush);
                        continue;
                    }
                }
                if (si == requestOfDeath) {
                    break;
                }
                if (si != null) {
                    // track the number of records written to the log
                    if (zks.getZKDatabase().append(si)) {
                        logCount++;
                        if (logCount > (snapCount / 2 + randRoll)) {
                            randRoll = r.nextInt(snapCount/2);
                            // roll the log
                            zks.getZKDatabase().rollLog();
                            // take a snapshot
                            if (snapInProcess != null && snapInProcess.isAlive()) {
                                LOG.warn("Too busy to snap, skipping");
                            } else {
                                snapInProcess = new ZooKeeperThread("Snapshot Thread") {
                                        public void run() {
                                            try {
                                                zks.takeSnapshot();
                                            } catch(Exception e) {
                                                LOG.warn("Unexpected exception", e);
                                            }
                                        }
                                    };
                                snapInProcess.start();
                            }
                            logCount = 0;
                        }
                    } else if (toFlush.isEmpty()) {
                        // optimization for read heavy workloads
                        // iff this is a read, and there are no pending
                        // flushes (writes), then just pass this to the next
                        // processor
                        if (nextProcessor != null) {
                            nextProcessor.processRequest(si);
                            if (nextProcessor instanceof Flushable) {
                                ((Flushable)nextProcessor).flush();
                            }
                        }
                        continue;
                    }
                    toFlush.add(si);
                    if (toFlush.size() > 1000) {
                        flush(toFlush);
                    }
                }
            }
        } catch (Throwable t) {
            handleException(this.getName(), t);
        } finally{
            running = false;
        }
        LOG.info("SyncRequestProcessor exited!");
    }

        /*
         * (non-Javadoc)
         *
         * @see org.apache.zookeeper.server.RequestProcessor#processRequest(org.apache.zookeeper.server.Request)
         */
        public void processRequest(Request request) throws RequestProcessorException {
            next.processRequest(request);

            // The only requests that should be on toBeApplied are write
            // requests, for which we will have a hdr. We can't simply use
            // request.zxid here because that is set on read requests to equal
            // the zxid of the last write op.
            if (request.getHdr() != null) {
                long zxid = request.getHdr().getZxid();
                Iterator<Proposal> iter = leader.toBeApplied.iterator();
                if (iter.hasNext()) {
                    Proposal p = iter.next();
                    if (p.request != null && p.request.zxid == zxid) {
                        iter.remove();
                        return;
                    }
                }
                LOG.error("Committed request not found on toBeApplied: "
                          + request);
            }
        }

    @Override
    protected void setupRequestProcessors() {
        RequestProcessor finalProcessor = new FinalRequestProcessor(this);
        commitProcessor = new CommitProcessor(finalProcessor,
                Long.toString(getServerId()), true, getZooKeeperServerListener());
        commitProcessor.start();
        firstProcessor = new FollowerRequestProcessor(this, commitProcessor);
        ((FollowerRequestProcessor) firstProcessor).start();
        syncProcessor = new SyncRequestProcessor(this,
                new SendAckRequestProcessor((Learner)getFollower()));
        syncProcessor.start();
    }

/**
 * This class is the superclass of two of the three main actors in a ZK
 * ensemble: Followers and Observers. Both Followers and Observers share 
 * a good deal of code which is moved into Peer to avoid duplication. 
 */
public class Learner {      

    @Override
    public void run() {
        try {
            while (!finished) {
                Request request = queuedRequests.take();
                if (LOG.isTraceEnabled()) {
                    ZooTrace.logRequest(LOG, ZooTrace.CLIENT_REQUEST_TRACE_MASK,
                            'F', request, "");
                }
                if (request == Request.requestOfDeath) {
                    break;
                }
                // We want to queue the request to be processed before we submit
                // the request to the leader so that we are ready to receive
                // the response
                nextProcessor.processRequest(request);

                // We now ship the request to the leader. As with all
                // other quorum operations, sync also follows this code
                // path, but different from others, we need to keep track
                // of the sync operations this follower has pending, so we
                // add it to pendingSyncs.
                switch (request.type) {
                case OpCode.sync:
                    zks.pendingSyncs.add(request);
                    zks.getFollower().request(request);
                    break;
                case OpCode.create:
                case OpCode.create2:
                case OpCode.createTTL:
                case OpCode.createContainer:
                case OpCode.delete:
                case OpCode.deleteContainer:
                case OpCode.setData:
                case OpCode.reconfig:
                case OpCode.setACL:
                case OpCode.multi:
                case OpCode.check:
                    zks.getFollower().request(request);
                    break;
                case OpCode.createSession:
                case OpCode.closeSession:
                    // Don't forward local sessions to the leader.
                    if (!request.isLocalSession()) {
                        zks.getFollower().request(request);
                    }
                    break;
                }
            }
        } catch (Exception e) {
            handleException(this.getName(), e);
        }
        LOG.info("FollowerRequestProcessor exited loop!");
    }

    public void processRequest(Request si) {
        if(si.type != OpCode.sync){
            QuorumPacket qp = new QuorumPacket(Leader.ACK, si.getHdr().getZxid(), null,
                null);
            try {
                learner.writePacket(qp, false);
            } catch (IOException e) {
                LOG.warn("Closing connection to leader, exception during packet send", e);
                try {
                    if (!learner.sock.isClosed()) {
                        learner.sock.close();
                    }
                } catch (IOException e1) {
                    // Nothing to do, we are shutting things down, so an exception here is irrelevant
                    LOG.debug("Ignoring error closing the connection", e1);
                }
            }
        }
    }

    /**
     * Set up the request processors for an Observer:
     * firstProcesor->commitProcessor->finalProcessor
     */
    @Override
    protected void setupRequestProcessors() {      
        // We might consider changing the processor behaviour of 
        // Observers to, for example, remove the disk sync requirements.
        // Currently, they behave almost exactly the same as followers.
        RequestProcessor finalProcessor = new FinalRequestProcessor(this);
        commitProcessor = new CommitProcessor(finalProcessor,
                Long.toString(getServerId()), true,
                getZooKeeperServerListener());
        commitProcessor.start();
        firstProcessor = new ObserverRequestProcessor(this, commitProcessor);
        ((ObserverRequestProcessor) firstProcessor).start();

        /*
         * Observer should write to disk, so that the it won't request
         * too old txn from the leader which may lead to getting an entire
         * snapshot.
         *
         * However, this may degrade performance as it has to write to disk
         * and do periodic snapshot which may double the memory requirements
         */
        if (syncRequestProcessorEnabled) {
            syncProcessor = new SyncRequestProcessor(this, null);
            syncProcessor.start();
        }
    }

    @Override
    public void run() {
        try {
            while (!finished) {
                Request request = queuedRequests.take();
                if (LOG.isTraceEnabled()) {
                    ZooTrace.logRequest(LOG, ZooTrace.CLIENT_REQUEST_TRACE_MASK,
                            'F', request, "");
                }
                if (request == Request.requestOfDeath) {
                    break;
                }
                // We want to queue the request to be processed before we submit
                // the request to the leader so that we are ready to receive
                // the response
                nextProcessor.processRequest(request);

                // We now ship the request to the leader. As with all
                // other quorum operations, sync also follows this code
                // path, but different from others, we need to keep track
                // of the sync operations this Observer has pending, so we
                // add it to pendingSyncs.
                switch (request.type) {
                case OpCode.sync:
                    zks.pendingSyncs.add(request);
                    zks.getObserver().request(request);
                    break;
                case OpCode.create:
                case OpCode.create2:
                case OpCode.createTTL:
                case OpCode.createContainer:
                case OpCode.delete:
                case OpCode.deleteContainer:
                case OpCode.setData:
                case OpCode.reconfig:
                case OpCode.setACL:
                case OpCode.multi:
                case OpCode.check:
                    zks.getObserver().request(request);
                    break;
                case OpCode.createSession:
                case OpCode.closeSession:
                    // Don't forward local sessions to the leader.
                    if (!request.isLocalSession()) {
                        zks.getObserver().request(request);
                    }
                    break;
                }
            }
        } catch (Exception e) {
            handleException(this.getName(), e);
        }
        LOG.info("ObserverRequestProcessor exited loop!");
    }

Consistency Guarantees
ZooKeeper is a high performance, scalable service. Both reads and write operations are designed to be fast, though reads are faster than writes. The reason for this is that in the case of reads, ZooKeeper can serve older data, which in turn is due to ZooKeeper's consistency guarantees:

Sequential Consistency
Updates from a client will be applied in the order that they were sent.
...........