十四：Dubbo集群容错策略（一） -- failover

INF/dubbo/internal/org.apache.dubbo.rpc.cluster.Cluster

mock=org.apache.dubbo.rpc.cluster.support.wrapper.MockClusterWrapper
failover=org.apache.dubbo.rpc.cluster.support.FailoverCluster
failfast=org.apache.dubbo.rpc.cluster.support.FailfastCluster
failsafe=org.apache.dubbo.rpc.cluster.support.FailsafeCluster
failback=org.apache.dubbo.rpc.cluster.support.FailbackCluster
forking=org.apache.dubbo.rpc.cluster.support.ForkingCluster
available=org.apache.dubbo.rpc.cluster.support.AvailableCluster
mergeable=org.apache.dubbo.rpc.cluster.support.MergeableCluster
broadcast=org.apache.dubbo.rpc.cluster.support.BroadcastCluster
zone-aware=org.apache.dubbo.rpc.cluster.support.registry.ZoneAwareCluster

FailfastCluster 快速失败

	//org.apache.dubbo.rpc.cluster.support.FailfastCluster#doJoin
	@Override
    public <T> AbstractClusterInvoker<T> doJoin(Directory<T> directory) throws RpcException {
        return new FailfastClusterInvoker<>(directory);
    }

    //org.apache.dubbo.rpc.cluster.support.FailfastClusterInvoker#doInvoke
    @Override
    public Result doInvoke(Invocation invocation, List<Invoker<T>> invokers, LoadBalance loadbalance) throws RpcException {
        checkInvokers(invokers, invocation);
        //进行负载均衡算法选择
        Invoker<T> invoker = select(loadbalance, invocation, invokers, null);
        try {
        	//选出后进行 调用
            return invokeWithContext(invoker, invocation);
        } catch (Throwable e) {
        	//FailfastCluster 主要体现在这里，如果出现错误，则直接进行异常抛出
            if (e instanceof RpcException && ((RpcException) e).isBiz()) { // biz exception.
                throw (RpcException) e;
            }
            throw new RpcException(e instanceof RpcException ? ((RpcException) e).getCode() : 0,
                    "Failfast invoke providers " + invoker.getUrl() + " " + loadbalance.getClass().getSimpleName()
                            + " select from all providers " + invokers + " for service " + getInterface().getName()
                            + " method " + invocation.getMethodName() + " on consumer " + NetUtils.getLocalHost()
                            + " use dubbo version " + Version.getVersion()
                            + ", but no luck to perform the invocation. Last error is: " + e.getMessage(),
                    e.getCause() != null ? e.getCause() : e);
        }
    }

FailsafeCluster 安全失败

	//org.apache.dubbo.rpc.cluster.support.FailsafeCluster#doJoin
    @Override
    public <T> AbstractClusterInvoker<T> doJoin(Directory<T> directory) throws RpcException {
        return new FailsafeClusterInvoker<>(directory);
    }

	//org.apache.dubbo.rpc.cluster.support.FailsafeClusterInvoker#doInvoke
    @Override
    public Result doInvoke(Invocation invocation, List<Invoker<T>> invokers, LoadBalance loadbalance) throws RpcException {
        try {
            checkInvokers(invokers, invocation);
            Invoker<T> invoker = select(loadbalance, invocation, invokers, null);
            return invokeWithContext(invoker, invocation);
        } catch (Throwable e) {
        	//只是打印异常，并不会抛出 直接正常返回，主要适用于忽略异常调用的场景
            logger.error("Failsafe ignore exception: " + e.getMessage(), e);
            return AsyncRpcResult.newDefaultAsyncResult(null, null, invocation); // ignore
        }
    }

FailbackCluster 失败后重试

    //org.apache.dubbo.rpc.cluster.support.FailbackCluster#doJoin
    @Override
    public <T> AbstractClusterInvoker<T> doJoin(Directory<T> directory) throws RpcException {
        //1、
        return new FailbackClusterInvoker<>(directory);
    }

	//org.apache.dubbo.rpc.cluster.support.FailbackClusterInvoker
	//构造方法
    public FailbackClusterInvoker(Directory<T> directory) {
        super(directory);
		
        int retriesConfig = getUrl().getParameter(RETRIES_KEY, DEFAULT_FAILBACK_TIMES);
        if (retriesConfig <= 0) {
            retriesConfig = DEFAULT_FAILBACK_TIMES;
        }
        int failbackTasksConfig = getUrl().getParameter(FAIL_BACK_TASKS_KEY, DEFAULT_FAILBACK_TASKS);
        if (failbackTasksConfig <= 0) {
            failbackTasksConfig = DEFAULT_FAILBACK_TASKS;
        }
        //2、
        //缓存配置的重试次数
        retries = retriesConfig;
        //最大等待超时时间
        failbackTasks = failbackTasksConfig;
    }

	@Override
    protected Result doInvoke(Invocation invocation, List<Invoker<T>> invokers, LoadBalance loadbalance) throws RpcException {
        Invoker<T> invoker = null;
        try {
            checkInvokers(invokers, invocation);
            invoker = select(loadbalance, invocation, invokers, null);
            return invokeWithContext(invoker, invocation);
        } catch (Throwable e) {
            logger.error("Failback to invoke method " + invocation.getMethodName() + ", wait for retry in background. Ignored exception: "
                    + e.getMessage() + ", ", e);
            //3、
            addFailed(loadbalance, invocation, invokers, invoker);
            return AsyncRpcResult.newDefaultAsyncResult(null, null, invocation); // ignore
        }
    }
    
    private void addFailed(LoadBalance loadbalance, Invocation invocation, List<Invoker<T>> invokers, Invoker<T> lastInvoker) {
        if (failTimer == null) {
            synchronized (this) {
                if (failTimer == null) {
                	//4、定义定时器 类似于 schedule
                    failTimer = new HashedWheelTimer(
                            new NamedThreadFactory("failback-cluster-timer", true),
                            1,
                            TimeUnit.SECONDS, 32, failbackTasks);
                }
            }
        }
        //创建一个定时任务，RETRY_FAILED_PERIOD = 5 （重试间隔时间：5s，不可配置）
        RetryTimerTask retryTimerTask = new RetryTimerTask(loadbalance, invocation, invokers, lastInvoker, retries, RETRY_FAILED_PERIOD);
        try {
        	//执行调用
            failTimer.newTimeout(retryTimerTask, RETRY_FAILED_PERIOD, TimeUnit.SECONDS);
        } catch (Throwable e) {
            logger.error("Failback background works error,invocation->" + invocation + ", exception: " + e.getMessage());
        }
    }