Redisson 分布式锁实战与 watch dog 机制解读

private void scheduleExpirationRenewal(long threadId) {
    ExpirationEntry entry = new ExpirationEntry();
    //将线程放入缓存中
    ExpirationEntry oldEntry = EXPIRATION_RENEWAL_MAP.putIfAbsent(getEntryName(), entry);
    //第二次获得锁后 不会进行延期操作
    if (oldEntry != null) {
        oldEntry.addThreadId(threadId);
    } else {
        entry.addThreadId(threadId);
        
        // 第一次获得锁 延期操作
        renewExpiration();
    }
}

// 进入 renewExpiration()
private void renewExpiration() {
    ExpirationEntry ee = EXPIRATION_RENEWAL_MAP.get(getEntryName());
    //如果缓存不存在，那不再锁续期
    if (ee == null) {
        return;
    }
    
    Timeout task = commandExecutor.getConnectionManager().newTimeout(new TimerTask() {
        @Override
        public void run(Timeout timeout) throws Exception {
            ExpirationEntry ent = EXPIRATION_RENEWAL_MAP.get(getEntryName());
            if (ent == null) {
                return;
            }
            Long threadId = ent.getFirstThreadId();
            if (threadId == null) {
                return;
            }
            
            //执行lua 进行续期
            RFuture<Boolean> future = renewExpirationAsync(threadId);
            future.onComplete((res, e) -> {
                if (e != null) {
                    log.error("Can't update lock " + getName() + " expiration", e);
                    return;
                }
                
                if (res) {
                    //延期成功，继续循环操作
                    renewExpiration();
                }
            });
        }
        //每隔internalLockLeaseTime/3=10秒检查一次
    }, internalLockLeaseTime / 3, TimeUnit.MILLISECONDS);
    
    ee.setTimeout(task);
}

//lua脚本 执行包装好的lua脚本进行key续期
protected RFuture<Boolean> renewExpirationAsync(long threadId) {
    return evalWriteAsync(getName(), LongCodec.INSTANCE, RedisCommands.EVAL_BOOLEAN,
            "if (redis.call('hexists', KEYS[1], ARGV[2]) == 1) then " +
                    "redis.call('pexpire', KEYS[1], ARGV[1]); " +
                    "return 1; " +
                    "end; " +
                    "return 0;",
            Collections.singletonList(getName()),
            internalLockLeaseTime, getLockName(threadId));
}

关键结论

上述源码读过来我们可以记住几个关键情报：

1. watch dog 在当前节点存活时每10s给分布式锁的key续期 30s；
2. watch dog 机制启动，且代码中没有释放锁操作时，watch dog 会不断的给锁续期；
3. 从可2得出，如果程序释放锁操作时因为异常没有被执行，那么锁无法被释放，所以释放锁操作一定要放到 finally {} 中；

看到3的时候，可能会有人有疑问，如果释放锁操作本身异常了，watch dog 还会不停的续期吗？下面看一下释放锁的源码，找找答案。

// 锁释放
public void unlock() {
    try {
        get(unlockAsync(Thread.currentThread().getId()));
    } catch (RedisException e) {
        if (e.getCause() instanceof IllegalMonitorStateException) {
            throw (IllegalMonitorStateException) e.getCause();
        } else {
            throw e;
        }
    }
}

// 进入 unlockAsync(Thread.currentThread().getId()) 方法 入参是当前线程的id
public RFuture<Void> unlockAsync(long threadId) {
    RPromise<Void> result = new RedissonPromise<Void>();
    //执行lua脚本 删除key
    RFuture<Boolean> future = unlockInnerAsync(threadId);

    future.onComplete((opStatus, e) -> {
        // 无论执行lua脚本是否成功 执行cancelExpirationRenewal(threadId) 方法来
        cancelExpirationRenewal(threadId);

        if (e != null) {
            result.tryFailure(e);
            return;
        }

        if (opStatus == null) {
            IllegalMonitorStateException cause = new IllegalMonitorStateException("attempt to unlock lock, not locked by current thread by node id: "
                    + id + " thread-id: " + threadId);
            result.tryFailure(cause);
            return;
        }

        result.trySuccess(null);
    });

    return result;
}

// 此方法会停止 watch dog 机制
void cancelExpirationRenewal(Long threadId) {
    ExpirationEntry task = EXPIRATION_RENEWAL_MAP.get(getEntryName());
    if (task == null) {
        return;
    }
    
    if (threadId != null) {
        task.removeThreadId(threadId);
    }

    if (threadId == null || task.hasNoThreads()) {
        Timeout timeout = task.getTimeout();
        if (timeout != null) {
            timeout.cancel();
        }
        EXPIRATION_RENEWAL_MAP.remove(getEntryName());
    }
}

EXPIRATION_RENEWAL_MAP.get(getEntryName());
if (ent == null) {
    return;
}