Apache SkyWalking 修复TTL timer 失效bug详解

core:
  selector: ${SW_CORE:default}
  default:
    # Mixed: Receive agent data, Level 1 aggregate, Level 2 aggregate
    # Receiver: Receive agent data, Level 1 aggregate
    # Aggregator: Level 2 aggregate
    role: ${SW_CORE_ROLE:Mixed} # Mixed/Receiver/Aggregator
    restHost: ${SW_CORE_REST_HOST:0.0.0.0}
    restPort: ${SW_CORE_REST_PORT:12800}
# 省略部分配置...  

cluster:
  selector: ${SW_CLUSTER:standalone}
  standalone:
  # Please check your ZooKeeper is 3.5+, However, it is also compatible with ZooKeeper 3.4.x. Replace the ZooKeeper 3.5+
  # library the oap-libs folder with your ZooKeeper 3.4.x library.
  zookeeper:
    namespace: ${SW_NAMESPACE:""}
    hostPort: ${SW_CLUSTER_ZK_HOST_PORT:localhost:2181}
    # Retry Policy
    baseSleepTimeMs: ${SW_CLUSTER_ZK_SLEEP_TIME:1000} # initial amount of time to wait between retries
    maxRetries: ${SW_CLUSTER_ZK_MAX_RETRIES:3} # max number of times to retry
    # Enable ACL
    enableACL: ${SW_ZK_ENABLE_ACL:false} # disable ACL in default
    schema: ${SW_ZK_SCHEMA:digest} # only support digest schema
    expression: ${SW_ZK_EXPRESSION:skywalking:skywalking}
    internalComHost: ${SW_CLUSTER_INTERNAL_COM_HOST:""}
    internalComPort: ${SW_CLUSTER_INTERNAL_COM_PORT:-1}
  kubernetes:
    namespace: ${SW_CLUSTER_K8S_NAMESPACE:default}
  # 省略部分配置...

core:
  selector: ${SW_CORE:default}
  default:
    # Mixed: Receive agent data, Level 1 aggregate, Level 2 aggregate
    # Receiver: Receive agent data, Level 1 aggregate
    # Aggregator: Level 2 aggregate
    role: ${SW_CORE_ROLE:Mixed} # Mixed/Receiver/Aggregator
    restHost: ${SW_CORE_REST_HOST:0.0.0.0}
    restPort: ${SW_CORE_REST_PORT:12800}
    # 省略部分配置...
    # Set a timeout on metrics data. After the timeout has expired, the metrics data will automatically be deleted.
    enableDataKeeperExecutor: ${SW_CORE_ENABLE_DATA_KEEPER_EXECUTOR:true} # Turn it off then automatically metrics data delete will be close.
    dataKeeperExecutePeriod: ${SW_CORE_DATA_KEEPER_EXECUTE_PERIOD:5} # How often the data keeper executor runs periodically, unit is minute
    recordDataTTL: ${SW_CORE_RECORD_DATA_TTL:3} # Unit is day
    metricsDataTTL: ${SW_CORE_METRICS_DATA_TTL:7} # Unit is day
    # 省略部分配置...

/**
 * TTL = Time To Live
 *
 * DataTTLKeeperTimer is an internal timer, it drives the {@link IHistoryDeleteDAO} to remove the expired data. TTL
 * configurations are provided in {@link CoreModuleConfig}, some storage implementations, such as ES6/ES7, provides an
 * override TTL, which could be more suitable for the implementation. No matter which TTL configurations are set, they
 * are all driven by this timer.
 */
@Slf4j
public enum DataTTLKeeperTimer {
    INSTANCE;
    private ModuleManager moduleManager;
    private ClusterNodesQuery clusterNodesQuery;
    private CoreModuleConfig moduleConfig;
    public void start(ModuleManager moduleManager, CoreModuleConfig moduleConfig) {
        this.moduleManager = moduleManager;
        this.clusterNodesQuery = moduleManager.find(ClusterModule.NAME).provider().getService(ClusterNodesQuery.class);
        this.moduleConfig = moduleConfig;
        // 创建定时任务
        Executors.newSingleThreadScheduledExecutor()
                 .scheduleAtFixedRate(
                     new RunnableWithExceptionProtection(
                         this::delete, // 删除过期的数据
                         t -> log.error("Remove data in background failure.", t)
                     ), moduleConfig
                         .getDataKeeperExecutePeriod(), moduleConfig.getDataKeeperExecutePeriod(), TimeUnit.MINUTES);
    }
    /**
     * DataTTLKeeperTimer starts in every OAP node, but the deletion only work when it is as the first node in the OAP
     * node list from {@link ClusterNodesQuery}.
     */
    private void delete() {
        IModelManager modelGetter = moduleManager.find(CoreModule.NAME).provider().getService(IModelManager.class);
        List<Model> models = modelGetter.allModels();
        try {
            // 查询服务节点
            List<RemoteInstance> remoteInstances = clusterNodesQuery.queryRemoteNodes();
            if (CollectionUtils.isNotEmpty(remoteInstances) && !remoteInstances.get(0).getAddress().isSelf()) {
                log.info(
                    "The selected first getAddress is {}. The remove stage is skipped.",
                    remoteInstances.get(0).toString()
                );
                return;
            }
            // 返回的第一个节点是自己，则执行删除操作
            log.info("Beginning to remove expired metrics from the storage.");
            models.forEach(this::execute);
        } finally {
            log.info("Beginning to inspect data boundaries.");
            this.inspect(models);
        }
    }
    private void execute(Model model) {
        try {
            if (!model.isTimeSeries()) {
                return;
            }
            if (log.isDebugEnabled()) {
                log.debug(
                    "Is record? {}. RecordDataTTL {}, MetricsDataTTL {}",
                    model.isRecord(),
                    moduleConfig.getRecordDataTTL(),
                    moduleConfig.getMetricsDataTTL());
            }
            // 获取 IHistoryDeleteDAO 接口的具体实现
            moduleManager.find(StorageModule.NAME)
                         .provider()
                         .getService(IHistoryDeleteDAO.class)
                         .deleteHistory(model, Metrics.TIME_BUCKET,
                                        model.isRecord() ? moduleConfig.getRecordDataTTL() : moduleConfig.getMetricsDataTTL()
                         );
        } catch (IOException e) {
            log.warn("History of {} delete failure", model.getName());
            log.error(e.getMessage(), e);
        }
    }
    private void inspect(List<Model> models) {
        try {
            moduleManager.find(StorageModule.NAME)
                         .provider()
                         .getService(IHistoryDeleteDAO.class)
                         .inspect(models, Metrics.TIME_BUCKET);
        } catch (IOException e) {
            log.error(e.getMessage(), e);
        }
    }
}