服務端用InstanceController#beat方法接收心跳請求。
InstanceController#beat
這裡會判斷是否已經有例項，如果沒有就建立例項，然後再開始檢查心跳。
public ObjectNode beat(HttpServletRequest request) throws Exception {
ObjectNode result = JacksonUtils.createEmptyJsonNode();
// 設定心跳時間，會直接改客戶端的心跳時間
result.put(SwitchEntry.CLIENT_BEAT_INTERVAL, switchDomain.getClientBeatInterval());
String beat = WebUtils.optional(request, "beat", StringUtils.EMPTY);
// 其他略
// 透過namespaceId, serviceName, clusterName, ip, port獲取Instance
Instance instance = serviceManager.getInstance(namespaceId, serviceName, clusterName, ip, port);
// 如果沒有，則註冊
if (instance == null) {
// 這個是透過beat判斷的，如果是第一次，則beat有資訊，就會建立clientBeat
// 如果不是第一次，正常instance不為空的，所以此時為空說明可能被移除了
if (clientBeat == null) {
result.put(CommonParams.CODE, NamingResponseCode.RESOURCE_NOT_FOUND);
return result;
}
// 其他略
// 註冊
serviceManager.registerInstance(namespaceId, serviceName, instance);
}
// 從serviceMap快取獲取Service
Service service = serviceManager.getService(namespaceId, serviceName);
if (service == null) {
throw new NacosException(NacosException.SERVER_ERROR,
"service not found: " + serviceName + "@" + namespaceId);
}
// 不是第一次，組裝clientBeat
if (clientBeat == null) {
clientBeat = new RsInfo();
clientBeat.setIp(ip);
clientBeat.setPort(port);
clientBeat.setCluster(clusterName);
}
// 處理心跳
service.processClientBeat(clientBeat);
result.put(CommonParams.CODE, NamingResponseCode.OK);
if (instance.containsMetadata(PreservedMetadataKeys.HEART_BEAT_INTERVAL)) {
result.put(SwitchEntry.CLIENT_BEAT_INTERVAL, instance.getInstanceHeartBeatInterval());
}
result.put(SwitchEntry.LIGHT_BEAT_ENABLED, switchDomain.isLightBeatEnabled());
return result;
}ServiceManager#getInstance
透過ip和埠獲取例項
public Instance getInstance(String namespaceId, String serviceName, String cluster, String ip, int port) {
// 從serviceMap快取獲取Service
Service service = getService(namespaceId, serviceName);
if (service == null) {
return null;
}
List<String> clusters = new ArrayList<>();
clusters.add(cluster);
// 從clusters叢集獲取Instance集合
List<Instance> ips = service.allIPs(clusters);
if (ips == null || ips.isEmpty()) {
return null;
}
// 透過ip和埠獲取例項
for (Instance instance : ips) {
if (instance.getIp().equals(ip) && instance.getPort() == port) {
return instance;
}
}
return null;
}Service#processClientBeat
封裝Runnable物件，放入執行緒池。
public void processClientBeat(final RsInfo rsInfo) {
// 建立ClientBeatProcessor物件，這個是Runnable，所以執行緒池會呼叫他的run方法
ClientBeatProcessor clientBeatProcessor = new ClientBeatProcessor();
clientBeatProcessor.setService(this);
clientBeatProcessor.setRsInfo(rsInfo);
HealthCheckReactor.scheduleNow(clientBeatProcessor);
}ClientBeatProcessor#run
找到對應的Instance，設定最後心跳時間，並設定為健康的，最後廣播訊息。
public void run() {
Service service = this.service;
if (Loggers.EVT_LOG.isDebugEnabled()) {
Loggers.EVT_LOG.debug("[CLIENT-BEAT] processing beat: {}", rsInfo.toString());
}
String ip = rsInfo.getIp();
String clusterName = rsInfo.getCluster();
int port = rsInfo.getPort();
Cluster cluster = service.getClusterMap().get(clusterName);
// 獲取所有Instance
List<Instance> instances = cluster.allIPs(true);
for (Instance instance : instances) {
// 透過ip和埠獲取Instance
if (instance.getIp().equals(ip) && instance.getPort() == port) {
if (Loggers.EVT_LOG.isDebugEnabled()) {
Loggers.EVT_LOG.debug("[CLIENT-BEAT] refresh beat: {}", rsInfo.toString());
}
// 設定最後心跳時間
instance.setLastBeat(System.currentTimeMillis());
// 沒有被標記且不不健康的，設定為健康
if (!instance.isMarked()) {
if (!instance.isHealthy()) {
instance.setHealthy(true);
Loggers.EVT_LOG
.info("service: {} {POS} {IP-ENABLED} valid: {}:{}@{}, region: {}, msg: client beat ok",
cluster.getService().getName(), ip, port, cluster.getName(),
UtilsAndCommons.LOCALHOST_SITE);
// 廣播訊息
getPushService().serviceChanged(service);
}
}
}
}
}PushService#onApplicationEvent
廣播訊息後，監聽ServiceChangeEvent型別的類會呼叫onApplicationEvent方法。這裡主要是封裝UDP資料併傳送。
public void onApplicationEvent(ServiceChangeEvent event) {
Service service = event.getService();
String serviceName = service.getName();
String namespaceId = service.getNamespaceId();
Future future = GlobalExecutor.scheduleUdpSender(() -> {
try {
Loggers.PUSH.info(serviceName + " is changed, add it to push queue.");
ConcurrentMap<String, PushClient> clients = clientMap
.get(UtilsAndCommons.assembleFullServiceName(namespaceId, serviceName));
if (MapUtils.isEmpty(clients)) {
return;
}
Map<String, Object> cache = new HashMap<>(16);
long lastRefTime = System.nanoTime();
// 遍歷PushClient集合
for (PushClient client : clients.values()) {
// 過期了就算了
if (client.zombie()) {
Loggers.PUSH.debug("client is zombie: " + client.toString());
clients.remove(client.toString());
Loggers.PUSH.debug("client is zombie: " + client.toString());
continue;
}
Receiver.AckEntry ackEntry;
Loggers.PUSH.debug("push serviceName: {} to client: {}", serviceName, client.toString());
String key = getPushCacheKey(serviceName, client.getIp(), client.getAgent());
byte[] compressData = null;
Map<String, Object> data = null;
if (switchDomain.getDefaultPushCacheMillis() >= 20000 && cache.containsKey(key)) {
org.javatuples.Pair pair = (org.javatuples.Pair) cache.get(key);
compressData = (byte[]) (pair.getValue0());
data = (Map<String, Object>) pair.getValue1();
Loggers.PUSH.debug("[PUSH-CACHE] cache hit: {}:{}", serviceName, client.getAddrStr());
}
// 封裝UDP資料，如果資料大於1kb則壓縮，compressIfNecessary這個方法判斷
if (compressData != null) {
ackEntry = prepareAckEntry(client, compressData, data, lastRefTime);
} else {
ackEntry = prepareAckEntry(client, prepareHostsData(client), lastRefTime);
if (ackEntry != null) {
cache.put(key, new org.javatuples.Pair<>(ackEntry.origin.getData(), ackEntry.data));
}
}
Loggers.PUSH.info("serviceName: {} changed, schedule push for: {}, agent: {}, key: {}",
client.getServiceName(), client.getAddrStr(), client.getAgent(),
(ackEntry == null ? null : ackEntry.key));
// 傳送udp資料
udpPush(ackEntry);
}
} catch (Exception e) {
Loggers.PUSH.error("[NACOS-PUSH] failed to push serviceName: {} to client, error: {}", serviceName, e);
} finally {
futureMap.remove(UtilsAndCommons.assembleFullServiceName(namespaceId, serviceName));
}
}, 1000, TimeUnit.MILLISECONDS);
futureMap.put(UtilsAndCommons.assembleFullServiceName(namespaceId, serviceName), future);
}PushService#udpPush
傳送UDP資料，會重試10次。每10秒檢查一次。
private static Receiver.AckEntry udpPush(Receiver.AckEntry ackEntry) {
if (ackEntry == null) {
Loggers.PUSH.error("[NACOS-PUSH] ackEntry is null.");
return null;
}
// 重試最大次數還沒成功，就刪除ackMap和udpSendTimeMap的內容
if (ackEntry.getRetryTimes() > MAX_RETRY_TIMES) {
Loggers.PUSH.warn("max re-push times reached, retry times {}, key: {}", ackEntry.retryTimes, ackEntry.key);
ackMap.remove(ackEntry.key);
udpSendTimeMap.remove(ackEntry.key);
failedPush += 1;
return ackEntry;
}
try {
if (!ackMap.containsKey(ackEntry.key)) {
totalPush++;
}
ackMap.put(ackEntry.key, ackEntry);
udpSendTimeMap.put(ackEntry.key, System.currentTimeMillis());
Loggers.PUSH.info("send udp packet: " + ackEntry.key);
// udp傳送
udpSocket.send(ackEntry.origin);
ackEntry.increaseRetryTime();
// 10秒檢查一次
GlobalExecutor.scheduleRetransmitter(new Retransmitter(ackEntry),
TimeUnit.NANOSECONDS.toMillis(ACK_TIMEOUT_NANOS), TimeUnit.MILLISECONDS);
return ackEntry;
} catch (Exception e) {
Loggers.PUSH.error("[NACOS-PUSH] failed to push data: {} to client: {}, error: {}", ackEntry.data,
ackEntry.origin.getAddress().getHostAddress(), e);
ackMap.remove(ackEntry.key);
udpSendTimeMap.remove(ackEntry.key);
failedPush += 1;
return null;
}
}Retransmitter#run
每10秒檢查是否傳送成功，如果沒傳送成功，就繼續傳送，最多10次。
public void run() {
if (ackMap.containsKey(ackEntry.key)) {
Loggers.PUSH.info("retry to push data, key: " + ackEntry.key);
udpPush(ackEntry);
}
}Receiver#run
PushService建立的時候，會開啟Receiver的執行緒。
static {
// 其他略
Receiver receiver = new Receiver();
Thread inThread = new Thread(receiver);
inThread.setDaemon(true);
inThread.setName("com.alibaba.nacos.naming.push.receiver");
inThread.start();
// 其他略
}他這裡會有個while(true)，收到請求後移除ackMap對應的key。
public void run() {
while (true) {
// 其他略
String ackKey = getAckKey(ip, port, ackPacket.lastRefTime);
AckEntry ackEntry = ackMap.remove(ackKey);
// 其他略
}
}廣播總結
廣播的時候，會往ackMap存入值，廣播過程失敗就從ackMap移除對應的值。有時候UDP請求不成功，那這個值一直會在ackMap，這個時候，Retransmitter每隔10秒就會去ackMap看看有沒有成功，如果沒有成功，他就會去重試，直至到達重試最大次數。另外還有一個執行緒，會去監聽UDP響應，如果收到了響應，就會從ackMap移除對應的值。這個UDP是傳送給客戶端的，Nacos - HostReactor的建立提到了收到請求後的處理，讓客戶端自己去更新資訊。
心跳總結
主要是收到心跳請求後，更新心跳的時間、健康狀態以及廣播