zookeeper3.6源码解析（一）

 

先看集群启动类QuorumPeerMain，读取zoo.cfg配置，解析各种配置，接着判断是否进行数据清理，最后判断何种模式启动zookeeper，集群模式还是单机模式。

protected void initializeAndRun(String[] args) throws ConfigException, IOException, AdminServerException {
        QuorumPeerConfig config = new QuorumPeerConfig();
        if (args.length == 1) {
            config.parse(args[0]); //配置类，读取的参数为zoo.cfg地址
        }

        // Start and schedule the the purge task
        DatadirCleanupManager purgeMgr = new DatadirCleanupManager(
            config.getDataDir(),
            config.getDataLogDir(),
            config.getSnapRetainCount(),
            config.getPurgeInterval());
        purgeMgr.start(); //根据zoo.cfg解析的参数purgeInterval判断是否启动定时清理snapshot（数据）和log文件，清理的条件为zxid

        if (args.length == 1 && config.isDistributed()) { //判断是何种模式，集群模式还是单机模式，判断的标准为zoo.cfg.dynamic中选举者数量，超过一个为集群模式
            runFromConfig(config);
        } else {
            LOG.warn("Either no config or no quorum defined in config, running in standalone mode");
            // there is only server in the quorum -- run as standalone
            ZooKeeperServerMain.main(args); //可用选举这只有一个，则使用单机模式，standalone
        }
    }

 先看单机模式如何启动，单机模式相较于集群模式少了选举等功能，适合先入手。

单机模式启动类ZooKeeperServerMain。

 protected void initializeAndRun(String[] args) throws ConfigException, IOException, AdminServerException {
        try {
            ManagedUtil.registerLog4jMBeans(); //注册log4j jmx 中的mbean
        } catch (JMException e) {
            LOG.warn("Unable to register log4j JMX control", e);
        }

        ServerConfig config = new ServerConfig();
        if (args.length == 1) {
            config.parse(args[0]); //解析配置，Config为栈内变量，进行了重复读取，都是初始化QuorumPeerConfig进行解析
        } else {
            config.parse(args);
        }

        runFromConfig(config); //和集群模式区别的函数，属于不同的启动类
    }

单机的启动函数

/**
     * Run from a ServerConfig.
     * @param config ServerConfig to use.
     * @throws IOException
     * @throws AdminServerException
     */
    public void runFromConfig(ServerConfig config) throws IOException, AdminServerException {
        LOG.info("Starting server");
        FileTxnSnapLog txnLog = null;
        try {
            try {
                metricsProvider = MetricsProviderBootstrap.startMetricsProvider( //指标记录类
                    config.getMetricsProviderClassName(),
                    config.getMetricsProviderConfiguration());
            } catch (MetricsProviderLifeCycleException error) {
                throw new IOException("Cannot boot MetricsProvider " + config.getMetricsProviderClassName(), error);
            }
            ServerMetrics.metricsProviderInitialized(metricsProvider);
            // Note that this thread isn't going to be doing anything else,
            // so rather than spawning another thread, we will just call
            // run() in this thread.
            // create a file logger url from the command line args
            txnLog = new FileTxnSnapLog(config.dataLogDir, config.dataDir); //创建数据和日志文件类
            JvmPauseMonitor jvmPauseMonitor = null;
            if (config.jvmPauseMonitorToRun) {
                jvmPauseMonitor = new JvmPauseMonitor(config); //jvm暂停进程监控，默认不开启
            }
            //初始化配置，为zkserver相关线程做相关准备
            final ZooKeeperServer zkServer = new ZooKeeperServer(jvmPauseMonitor, txnLog, config.tickTime, config.minSessionTimeout, config.maxSessionTimeout, config.listenBacklog, null, config.initialConfig);
            txnLog.setServerStats(zkServer.serverStats());

            // Registers shutdown handler which will be used to know the
            // server error or shutdown state changes.
            final CountDownLatch shutdownLatch = new CountDownLatch(1);
            zkServer.registerServerShutdownHandler(new ZooKeeperServerShutdownHandler(shutdownLatch));

            // Start Admin server
            adminServer = AdminServerFactory.createAdminServer();
            adminServer.setZooKeeperServer(zkServer);
            adminServer.start();

            boolean needStartZKServer = true;
            if (config.getClientPortAddress() != null) {
                cnxnFactory = ServerCnxnFactory.createFactory();
                cnxnFactory.configure(config.getClientPortAddress(), config.getMaxClientCnxns(), config.getClientPortListenBacklog(), false);
                cnxnFactory.startup(zkServer);
                // zkServer has been started. So we don't need to start it again in secureCnxnFactory.
                needStartZKServer = false;
            }
            if (config.getSecureClientPortAddress() != null) {
                secureCnxnFactory = ServerCnxnFactory.createFactory();
                secureCnxnFactory.configure(config.getSecureClientPortAddress(), config.getMaxClientCnxns(), config.getClientPortListenBacklog(), true);
                secureCnxnFactory.startup(zkServer, needStartZKServer);
            }

            containerManager = new ContainerManager(
                zkServer.getZKDatabase(),
                zkServer.firstProcessor,
                Integer.getInteger("znode.container.checkIntervalMs", (int) TimeUnit.MINUTES.toMillis(1)),
                Integer.getInteger("znode.container.maxPerMinute", 10000),
                Long.getLong("znode.container.maxNeverUsedIntervalMs", 0)
            );
            containerManager.start();
            ZKAuditProvider.addZKStartStopAuditLog();

            // Watch status of ZooKeeper server. It will do a graceful shutdown
            // if the server is not running or hits an internal error.
            shutdownLatch.await();

            shutdown();

            if (cnxnFactory != null) {
                cnxnFactory.join();
            }
            if (secureCnxnFactory != null) {
                secureCnxnFactory.join();
            }
            if (zkServer.canShutdown()) {
                zkServer.shutdown(true);
            }
        } catch (InterruptedException e) {
            // warn, but generally this is ok
            LOG.warn("Server interrupted", e);
        } finally {
            if (txnLog != null) {
                txnLog.close();
            }
            if (metricsProvider != null) {
                try {
                    metricsProvider.stop();
                } catch (Throwable error) {
                    LOG.warn("Error while stopping metrics", error);
                }
            }
        }
    }

zookeeperserver类初始化

public ZooKeeperServer(FileTxnSnapLog txnLogFactory, int tickTime, int minSessionTimeout, int maxSessionTimeout, int clientPortListenBacklog, ZKDatabase zkDb, String initialConfig, boolean reconfigEnabled) {
        serverStats = new ServerStats(this); //保存sever自身状态
        this.txnLogFactory = txnLogFactory;
        this.txnLogFactory.setServerStats(this.serverStats); //数据文件保存server状态
        this.zkDb = zkDb;
        this.tickTime = tickTime; //每次tick的单次计量单位，莫问2000ms
        setMinSessionTimeout(minSessionTimeout); //session time todo:
        setMaxSessionTimeout(maxSessionTimeout);
        this.listenBacklog = clientPortListenBacklog;
        this.reconfigEnabled = reconfigEnabled;

        listener = new ZooKeeperServerListenerImpl(this); //保存server，用来通知server关键线程停止

        readResponseCache = new ResponseCache(Integer.getInteger(
            GET_DATA_RESPONSE_CACHE_SIZE,
            ResponseCache.DEFAULT_RESPONSE_CACHE_SIZE)); //LRUCache 结构的缓存，底层是linkedhashmap 维护顺序性，和缓存淘汰

        getChildrenResponseCache = new ResponseCache(Integer.getInteger(
            GET_CHILDREN_RESPONSE_CACHE_SIZE,
            ResponseCache.DEFAULT_RESPONSE_CACHE_SIZE));

        this.initialConfig = initialConfig;

        this.requestPathMetricsCollector = new RequestPathMetricsCollector(); //请求相关指标收集

        this.initLargeRequestThrottlingSettings();

        LOG.info(
            "Created server with"
                + " tickTime {}"
                + " minSessionTimeout {}"
                + " maxSessionTimeout {}"
                + " clientPortListenBacklog {}"
                + " datadir {}"
                + " snapdir {}",
            tickTime,
            getMinSessionTimeout(),
            getMaxSessionTimeout(),
            getClientPortListenBacklog(),
            txnLogFactory.getDataDir(),
            txnLogFactory.getSnapDir());
    }