乐趣区

聊聊nacos-RaftCore的signalPublish

本文主要研究一下 nacos RaftCore 的 signalPublish

RaftCore

nacos-1.1.3/naming/src/main/java/com/alibaba/nacos/naming/consistency/persistent/raft/RaftCore.java

@Component
public class RaftCore {

    public static final String API_VOTE = UtilsAndCommons.NACOS_NAMING_CONTEXT + "/raft/vote";

    public static final String API_BEAT = UtilsAndCommons.NACOS_NAMING_CONTEXT + "/raft/beat";

    public static final String API_PUB = UtilsAndCommons.NACOS_NAMING_CONTEXT + "/raft/datum";

    public static final String API_DEL = UtilsAndCommons.NACOS_NAMING_CONTEXT + "/raft/datum";

    public static final String API_GET = UtilsAndCommons.NACOS_NAMING_CONTEXT + "/raft/datum";

    public static final String API_ON_PUB = UtilsAndCommons.NACOS_NAMING_CONTEXT + "/raft/datum/commit";

    public static final String API_ON_DEL = UtilsAndCommons.NACOS_NAMING_CONTEXT + "/raft/datum/commit";

    public static final String API_GET_PEER = UtilsAndCommons.NACOS_NAMING_CONTEXT + "/raft/peer";

    private ScheduledExecutorService executor = new ScheduledThreadPoolExecutor(1, new ThreadFactory() {
        @Override
        public Thread newThread(Runnable r) {Thread t = new Thread(r);

            t.setDaemon(true);
            t.setName("com.alibaba.nacos.naming.raft.notifier");

            return t;
        }
    });

    public static final Lock OPERATE_LOCK = new ReentrantLock();

    public static final int PUBLISH_TERM_INCREASE_COUNT = 100;

    private volatile Map<String, List<RecordListener>> listeners = new ConcurrentHashMap<>();

    private volatile ConcurrentMap<String, Datum> datums = new ConcurrentHashMap<>();

    @Autowired
    private RaftPeerSet peers;

    @Autowired
    private SwitchDomain switchDomain;

    @Autowired
    private GlobalConfig globalConfig;

    @Autowired
    private RaftProxy raftProxy;

    @Autowired
    private RaftStore raftStore;

    public volatile Notifier notifier = new Notifier();

    private boolean initialized = false;

    @PostConstruct
    public void init() throws Exception {Loggers.RAFT.info("initializing Raft sub-system");

        executor.submit(notifier);

        long start = System.currentTimeMillis();

        raftStore.loadDatums(notifier, datums);

        setTerm(NumberUtils.toLong(raftStore.loadMeta().getProperty("term"), 0L));

        Loggers.RAFT.info("cache loaded, datum count: {}, current term: {}", datums.size(), peers.getTerm());

        while (true) {if (notifier.tasks.size() <= 0) {break;}
            Thread.sleep(1000L);
        }

        initialized = true;

        Loggers.RAFT.info("finish to load data from disk, cost: {} ms.", (System.currentTimeMillis() - start));

        GlobalExecutor.registerMasterElection(new MasterElection());
        GlobalExecutor.registerHeartbeat(new HeartBeat());

        Loggers.RAFT.info("timer started: leader timeout ms: {}, heart-beat timeout ms: {}",
            GlobalExecutor.LEADER_TIMEOUT_MS, GlobalExecutor.HEARTBEAT_INTERVAL_MS);
    }

    public Map<String, List<RecordListener>> getListeners() {return listeners;}

    public void signalPublish(String key, Record value) throws Exception {if (!isLeader()) {JSONObject params = new JSONObject();
            params.put("key", key);
            params.put("value", value);
            Map<String, String> parameters = new HashMap<>(1);
            parameters.put("key", key);

            raftProxy.proxyPostLarge(getLeader().ip, API_PUB, params.toJSONString(), parameters);
            return;
        }

        try {OPERATE_LOCK.lock();
            long start = System.currentTimeMillis();
            final Datum datum = new Datum();
            datum.key = key;
            datum.value = value;
            if (getDatum(key) == null) {datum.timestamp.set(1L);
            } else {datum.timestamp.set(getDatum(key).timestamp.incrementAndGet());
            }

            JSONObject json = new JSONObject();
            json.put("datum", datum);
            json.put("source", peers.local());

            onPublish(datum, peers.local());

            final String content = JSON.toJSONString(json);

            final CountDownLatch latch = new CountDownLatch(peers.majorityCount());
            for (final String server : peers.allServersIncludeMyself()) {if (isLeader(server)) {latch.countDown();
                    continue;
                }
                final String url = buildURL(server, API_ON_PUB);
                HttpClient.asyncHttpPostLarge(url, Arrays.asList("key=" + key), content, new AsyncCompletionHandler<Integer>() {
                    @Override
                    public Integer onCompleted(Response response) throws Exception {if (response.getStatusCode() != HttpURLConnection.HTTP_OK) {Loggers.RAFT.warn("[RAFT] failed to publish data to peer, datumId={}, peer={}, http code={}",
                                datum.key, server, response.getStatusCode());
                            return 1;
                        }
                        latch.countDown();
                        return 0;
                    }

                    @Override
                    public STATE onContentWriteCompleted() {return STATE.CONTINUE;}
                });

            }

            if (!latch.await(UtilsAndCommons.RAFT_PUBLISH_TIMEOUT, TimeUnit.MILLISECONDS)) {
                // only majority servers return success can we consider this update success
                Loggers.RAFT.error("data publish failed, caused failed to notify majority, key={}", key);
                throw new IllegalStateException("data publish failed, caused failed to notify majority, key=" + key);
            }

            long end = System.currentTimeMillis();
            Loggers.RAFT.info("signalPublish cost {} ms, key: {}", (end - start), key);
        } finally {OPERATE_LOCK.unlock();
        }
    }

    //......
}
  • signalPublish 方法判断当前节点是否是 leader,如果不是则转发 publish 到 leader 节点的 /v1/ns/raft/datum 接口
  • 如果是 leader 则构造 datum 以及 peers.majorityCount()大小的 CountDownLatch,然后遍历 peers.allServersIncludeMyself(),对于 leader 节点直接 latch.countDown(),对于非 leader 节点则发送异步请求,请求 /v1/ns/raft/datum/commit 接口,在 onCompleted 的时候,如果请求成功执行 latch.countDown()
  • 最后对于 CountDownLatch 未能在 RAFT_PUBLISH_TIMEOUT 返回的,抛出 IllegalStateException

RaftController

nacos-1.1.3/naming/src/main/java/com/alibaba/nacos/naming/controllers/RaftController.java

@RestController
@RequestMapping({UtilsAndCommons.NACOS_NAMING_CONTEXT + "/raft",
    UtilsAndCommons.NACOS_SERVER_CONTEXT + UtilsAndCommons.NACOS_NAMING_CONTEXT + "/raft"})
public class RaftController {

    @Autowired
    private RaftConsistencyServiceImpl raftConsistencyService;

    @Autowired
    private ServiceManager serviceManager;

    @Autowired
    private RaftCore raftCore;

    //......

    @NeedAuth
    @RequestMapping(value = "/datum/commit", method = RequestMethod.POST)
    public String onPublish(HttpServletRequest request, HttpServletResponse response) throws Exception {response.setHeader("Content-Type", "application/json; charset=" + getAcceptEncoding(request));
        response.setHeader("Cache-Control", "no-cache");
        response.setHeader("Content-Encode", "gzip");

        String entity = IOUtils.toString(request.getInputStream(), "UTF-8");
        String value = URLDecoder.decode(entity, "UTF-8");
        JSONObject jsonObject = JSON.parseObject(value);
        String key = "key";

        RaftPeer source = JSON.parseObject(jsonObject.getString("source"), RaftPeer.class);
        JSONObject datumJson = jsonObject.getJSONObject("datum");

        Datum datum = null;
        if (KeyBuilder.matchInstanceListKey(datumJson.getString(key))) {datum = JSON.parseObject(jsonObject.getString("datum"), new TypeReference<Datum<Instances>>() {});
        } else if (KeyBuilder.matchSwitchKey(datumJson.getString(key))) {datum = JSON.parseObject(jsonObject.getString("datum"), new TypeReference<Datum<SwitchDomain>>() {});
        } else if (KeyBuilder.matchServiceMetaKey(datumJson.getString(key))) {datum = JSON.parseObject(jsonObject.getString("datum"), new TypeReference<Datum<Service>>() {});
        }

        raftConsistencyService.onPut(datum, source);
        return "ok";
    }

    //......
}
  • onPublish 方法主要是执行 raftConsistencyService.onPut(datum, source)

RaftConsistencyServiceImpl

nacos-1.1.3/naming/src/main/java/com/alibaba/nacos/naming/consistency/persistent/raft/RaftConsistencyServiceImpl.java

@Service
public class RaftConsistencyServiceImpl implements PersistentConsistencyService {

    @Autowired
    private RaftCore raftCore;

    @Autowired
    private RaftPeerSet peers;

    @Autowired
    private SwitchDomain switchDomain;

    //......

    public void onPut(Datum datum, RaftPeer source) throws NacosException {
        try {raftCore.onPublish(datum, source);
        } catch (Exception e) {Loggers.RAFT.error("Raft onPut failed.", e);
            throw new NacosException(NacosException.SERVER_ERROR, "Raft onPut failed, datum:" + datum + ", source:" + source, e);
        }
    }

    //......
}
  • onPut 方法执行的是 raftCore.onPublish(datum, source)

RaftCore

nacos-1.1.3/naming/src/main/java/com/alibaba/nacos/naming/consistency/persistent/raft/RaftCore.java

@Component
public class RaftCore {

    public static final String API_VOTE = UtilsAndCommons.NACOS_NAMING_CONTEXT + "/raft/vote";

    public static final String API_BEAT = UtilsAndCommons.NACOS_NAMING_CONTEXT + "/raft/beat";

    public static final String API_PUB = UtilsAndCommons.NACOS_NAMING_CONTEXT + "/raft/datum";

    public static final String API_DEL = UtilsAndCommons.NACOS_NAMING_CONTEXT + "/raft/datum";

    public static final String API_GET = UtilsAndCommons.NACOS_NAMING_CONTEXT + "/raft/datum";

    public static final String API_ON_PUB = UtilsAndCommons.NACOS_NAMING_CONTEXT + "/raft/datum/commit";

    public static final String API_ON_DEL = UtilsAndCommons.NACOS_NAMING_CONTEXT + "/raft/datum/commit";

    public static final String API_GET_PEER = UtilsAndCommons.NACOS_NAMING_CONTEXT + "/raft/peer";

    private ScheduledExecutorService executor = new ScheduledThreadPoolExecutor(1, new ThreadFactory() {
        @Override
        public Thread newThread(Runnable r) {Thread t = new Thread(r);

            t.setDaemon(true);
            t.setName("com.alibaba.nacos.naming.raft.notifier");

            return t;
        }
    });

    public static final Lock OPERATE_LOCK = new ReentrantLock();

    public static final int PUBLISH_TERM_INCREASE_COUNT = 100;

    private volatile Map<String, List<RecordListener>> listeners = new ConcurrentHashMap<>();

    private volatile ConcurrentMap<String, Datum> datums = new ConcurrentHashMap<>();

    @Autowired
    private RaftPeerSet peers;

    @Autowired
    private SwitchDomain switchDomain;

    @Autowired
    private GlobalConfig globalConfig;

    @Autowired
    private RaftProxy raftProxy;

    @Autowired
    private RaftStore raftStore;

    public volatile Notifier notifier = new Notifier();

    private boolean initialized = false;

    //......

    public void onPublish(Datum datum, RaftPeer source) throws Exception {RaftPeer local = peers.local();
        if (datum.value == null) {Loggers.RAFT.warn("received empty datum");
            throw new IllegalStateException("received empty datum");
        }

        if (!peers.isLeader(source.ip)) {Loggers.RAFT.warn("peer {} tried to publish data but wasn't leader, leader: {}",
                JSON.toJSONString(source), JSON.toJSONString(getLeader()));
            throw new IllegalStateException("peer(" + source.ip + ") tried to publish" +
                "data but wasn't leader");
        }

        if (source.term.get() < local.term.get()) {Loggers.RAFT.warn("out of date publish, pub-term: {}, cur-term: {}",
                JSON.toJSONString(source), JSON.toJSONString(local));
            throw new IllegalStateException("out of date publish, pub-term:"
                + source.term.get() + ", cur-term:" + local.term.get());
        }

        local.resetLeaderDue();

        // if data should be persistent, usually this is always true:
        if (KeyBuilder.matchPersistentKey(datum.key)) {raftStore.write(datum);
        }

        datums.put(datum.key, datum);

        if (isLeader()) {local.term.addAndGet(PUBLISH_TERM_INCREASE_COUNT);
        } else {if (local.term.get() + PUBLISH_TERM_INCREASE_COUNT > source.term.get()) {
                //set leader term:
                getLeader().term.set(source.term.get());
                local.term.set(getLeader().term.get());
            } else {local.term.addAndGet(PUBLISH_TERM_INCREASE_COUNT);
            }
        }
        raftStore.updateTerm(local.term.get());

        notifier.addTask(datum.key, ApplyAction.CHANGE);

        Loggers.RAFT.info("data added/updated, key={}, term={}", datum.key, local.term);
    }

    //......
}
  • onPublish 方法首先判断请求的节点是否是 leader,不是则抛出 IllegalStateException;对于 source.term 小于 local.term 的抛出 IllegalStateException
  • 之后执行 local.resetLeaderDue(),以及 raftStore.write(datum),datums.put(datum.key, datum);对于 leader 节点执行 local.term.addAndGet(PUBLISH_TERM_INCREASE_COUNT),非 leader 节点则更新 leader term 以及 local.term
  • 最后执行 raftStore.updateTerm(local.term.get())以及 notifier.addTask(datum.key, ApplyAction.CHANGE)

小结

  • signalPublish 方法判断当前节点是否是 leader,如果不是则转发 publish 到 leader 节点的 /v1/ns/raft/datum 接口
  • 如果是 leader 则构造 datum 以及 peers.majorityCount()大小的 CountDownLatch,然后遍历 peers.allServersIncludeMyself(),对于 leader 节点直接 latch.countDown(),对于非 leader 节点则发送异步请求,请求 /v1/ns/raft/datum/commit 接口,在 onCompleted 的时候,如果请求成功执行 latch.countDown()
  • 最后对于 CountDownLatch 未能在 RAFT_PUBLISH_TIMEOUT 返回的,抛出 IllegalStateException

doc

  • RaftCore
退出移动版