序
本文主要研究一下PowerJob的ServerController
ServerController
tech/powerjob/server/web/controller/ServerController.java
@RestController
@RequestMapping("/server")
@RequiredArgsConstructor
public class ServerController implements ServerInfoAware {
private ServerInfo serverInfo;
private final TransportService transportService;
private final ServerElectionService serverElectionService;
private final AppInfoRepository appInfoRepository;
private final WorkerClusterQueryService workerClusterQueryService;
@GetMapping("/assert")
public ResultDTO<Long> assertAppName(String appName) {
Optional<AppInfoDO> appInfoOpt = appInfoRepository.findByAppName(appName);
return appInfoOpt.map(appInfoDO -> ResultDTO.success(appInfoDO.getId())).
orElseGet(() -> ResultDTO.failed(String.format("app(%s) is not registered! Please register the app in oms-console first.", appName)));
}
@GetMapping("/assertV2")
public ResultDTO<WorkerAppInfo> assertAppNameV2(String appName) {
Optional<AppInfoDO> appInfoOpt = appInfoRepository.findByAppName(appName);
return appInfoOpt.map(appInfoDO -> {
WorkerAppInfo workerAppInfo = new WorkerAppInfo().setAppId(appInfoDO.getId());
return ResultDTO.success(workerAppInfo);
}).
orElseGet(() -> ResultDTO.failed(String.format("app(%s) is not registered! Please register the app in oms-console first.", appName)));
}
@GetMapping("/acquire")
public ResultDTO<String> acquireServer(ServerDiscoveryRequest request) {
return ResultDTO.success(serverElectionService.elect(request));
}
@GetMapping("/hello")
public ResultDTO<JSONObject> ping(@RequestParam(required = false) boolean debug) {
JSONObject res = new JSONObject();
res.put("localHost", NetUtils.getLocalHost());
res.put("serverInfo", serverInfo);
res.put("serverTime", CommonUtils.formatTime(System.currentTimeMillis()));
res.put("serverTimeTs", System.currentTimeMillis());
res.put("serverTimeZone", TimeZone.getDefault().getDisplayName());
res.put("appIds", workerClusterQueryService.getAppId2ClusterStatus().keySet());
if (debug) {
res.put("appId2ClusterInfo", JSON.parseObject(JSON.toJSONString(workerClusterQueryService.getAppId2ClusterStatus())));
}
try {
res.put("defaultAddress", JSONObject.toJSON(transportService.defaultProtocol()));
} catch (Exception ignore) {
}
return ResultDTO.success(res);
}
@Override
public void setServerInfo(ServerInfo serverInfo) {
this.serverInfo = serverInfo;
}
}ServerController實現了ServerInfoAware介面，它提供了assert、assertV2、acquire、hello介面；其中assert介面用於判斷指定的appName是否存在，assertV2返回的是WorkerAppInfo；acquire委託給了serverElectionService.elect(request)；hello介面返回server端的localhost、serverInfo、serverTime等資訊
elect
tech/powerjob/server/remote/server/election/ServerElectionService.java
public String elect(ServerDiscoveryRequest request) {
if (!accurate()) {
final String currentServer = request.getCurrentServer();
// 如果是本機，就不需要查資料庫那麼複雜的操作了，直接返回成功
Optional<ProtocolInfo> localProtocolInfoOpt = Optional.ofNullable(transportService.allProtocols().get(request.getProtocol()));
if (localProtocolInfoOpt.isPresent()) {
if (localProtocolInfoOpt.get().getExternalAddress().equals(currentServer) || localProtocolInfoOpt.get().getAddress().equals(currentServer)) {
log.info("[ServerElection] this server[{}] is worker[appId={}]'s current server, skip check", currentServer, request.getAppId());
return currentServer;
}
}
}
return getServer0(request);
}
private boolean accurate() {
return ThreadLocalRandom.current().nextInt(100) < accurateSelectServerPercentage;
} ServerElectionService的elect方法接收ServerDiscoveryRequest，它先判斷是否accurate(判斷100以內的隨機數是否小於accurateSelectServerPercentage，預設50)，是則執行getServer0，否則則先判斷ProtocolInfo的address是否是currentServer，是則直接返回，否則還是走getServer0getServer0
private String getServer0(ServerDiscoveryRequest discoveryRequest) {
final Long appId = discoveryRequest.getAppId();
final String protocol = discoveryRequest.getProtocol();
Set<String> downServerCache = Sets.newHashSet();
for (int i = 0; i < RETRY_TIMES; i++) {
// 無鎖獲取當前資料庫中的Server
Optional<AppInfoDO> appInfoOpt = appInfoRepository.findById(appId);
if (!appInfoOpt.isPresent()) {
throw new PowerJobException(appId + " is not registered!");
}
String appName = appInfoOpt.get().getAppName();
String originServer = appInfoOpt.get().getCurrentServer();
String activeAddress = activeAddress(originServer, downServerCache, protocol);
if (StringUtils.isNotEmpty(activeAddress)) {
return activeAddress;
}
// 無可用Server，重新進行Server選舉，需要加鎖
String lockName = String.format(SERVER_ELECT_LOCK, appId);
boolean lockStatus = lockService.tryLock(lockName, 30000);
if (!lockStatus) {
try {
Thread.sleep(500);
}catch (Exception ignore) {
}
continue;
}
try {
// 可能上一臺機器已經完成了Server選舉，需要再次判斷
AppInfoDO appInfo = appInfoRepository.findById(appId).orElseThrow(() -> new RuntimeException("impossible, unless we just lost our database."));
String address = activeAddress(appInfo.getCurrentServer(), downServerCache, protocol);
if (StringUtils.isNotEmpty(address)) {
return address;
}
// 篡位，如果本機存在協議，則作為Server排程該 worker
final ProtocolInfo targetProtocolInfo = transportService.allProtocols().get(protocol);
if (targetProtocolInfo != null) {
// 注意，寫入 AppInfoDO#currentServer 的永遠是 default 的繫結地址，僅在返回的時候特殊處理為協議地址
appInfo.setCurrentServer(transportService.defaultProtocol().getAddress());
appInfo.setGmtModified(new Date());
appInfoRepository.saveAndFlush(appInfo);
log.info("[ServerElection] this server({}) become the new server for app(appId={}).", appInfo.getCurrentServer(), appId);
return targetProtocolInfo.getExternalAddress();
}
}catch (Exception e) {
log.error("[ServerElection] write new server to db failed for app {}.", appName, e);
} finally {
lockService.unlock(lockName);
}
}
throw new PowerJobException("server elect failed for app " + appId);
}getServer0執行一個迴圈(最大10次)，它先根據appId獲取AppInfoDO，然後透過activeAddress判斷server是否存活，是則返回，否則重新進行server選舉
activeAddress
private String activeAddress(String serverAddress, Set<String> downServerCache, String protocol) {
if (downServerCache.contains(serverAddress)) {
return null;
}
if (StringUtils.isEmpty(serverAddress)) {
return null;
}
Ping ping = new Ping();
ping.setCurrentTime(System.currentTimeMillis());
URL targetUrl = ServerURLFactory.ping2Friend(serverAddress);
try {
AskResponse response = transportService.ask(Protocol.HTTP.name(), targetUrl, ping, AskResponse.class)
.toCompletableFuture()
.get(PING_TIMEOUT_MS, TimeUnit.MILLISECONDS);
if (response.isSuccess()) {
// 檢測透過的是遠端 server 的暴露地址，需要返回 worker 需要的協議地址
final JSONObject protocolInfo = JsonUtils.parseObject(response.getData(), JSONObject.class).getJSONObject(protocol);
if (protocolInfo != null) {
downServerCache.remove(serverAddress);
ProtocolInfo remoteProtocol = protocolInfo.toJavaObject(ProtocolInfo.class);
log.info("[ServerElection] server[{}] is active, it will be the master, final protocol={}", serverAddress, remoteProtocol);
// 4.3.3 升級 4.3.4 過程中，未升級的 server 還不存在 externalAddress，需要使用 address 相容
return Optional.ofNullable(remoteProtocol.getExternalAddress()).orElse(remoteProtocol.getAddress());
} else {
log.warn("[ServerElection] server[{}] is active but don't have target protocol", serverAddress);
}
}
} catch (TimeoutException te) {
log.warn("[ServerElection] server[{}] was down due to ping timeout!", serverAddress);
} catch (Exception e) {
log.warn("[ServerElection] server[{}] was down with unknown case!", serverAddress, e);
}
downServerCache.add(serverAddress);
return null;
}activeAddress透過transportService.ask請求ping介面，1s超時，若成功則從downServerCache移除，返回remoteProtocol.getAddress()，若失敗則將該serverAddress加入downServerCache
小結
ServerController實現了ServerInfoAware介面，它提供了assert、assertV2、acquire、hello介面；其中assert介面用於判斷指定的appName是否存在，assertV2返回的是WorkerAppInfo；acquire委託給了serverElectionService.elect(request)；hello介面返回server端的localhost、serverInfo、serverTime等資訊。