mirror of
https://github.com/OneUptime/oneuptime.git
synced 2026-01-11 19:56:44 +00:00
- Add Telemetry service entrypoint - Telemetry/Index.ts: app bootstrap, routes mounting, infrastructure init and Telemetry SDK init. - Unified queue + worker - Telemetry/Jobs/TelemetryIngest/ProcessTelemetry.ts: single worker that dispatches queued jobs to specific processors (logs, traces, metrics, syslog, fluent logs). - Telemetry/Services/Queue/TelemetryQueueService.ts: central queue API and job payload types. - Per-type Queue wrappers (LogsQueueService, MetricsQueueService, TracesQueueService, FluentLogsQueueService, SyslogQueueService). - OpenTelemetry ingestion middleware and proto support - Telemetry/Middleware/OtelRequestMiddleware.ts: detect OTLP endpoint (logs/traces/metrics), decode protobuf bodies using protobufjs and set product type. - Telemetry/ProtoFiles/OTel/v1/*.proto: include common.proto, logs.proto, metrics.proto, resource.proto, traces.proto for OTLP v1 messages. - Ingest services - Telemetry/Services/OtelLogsIngestService.ts: parse incoming OTLP logs, map attributes, convert timestamps, batch insert logs. - Telemetry/Services/OtelTracesIngestService.ts: parse OTLP traces, build span rows, extract exceptions, batch insert spans and exceptions, save telemetry exception summary. - Telemetry/Services/OtelMetricsIngestService.ts: parse OTLP metrics, normalize datapoints, batch insert metrics and index metric name -> service map. - Telemetry/Services/SyslogIngestService.ts: syslog ingestion endpoints, parser integration, map syslog fields to attributes and logs. - Telemetry/Services/FluentLogsIngestService.ts: ingest Fluentd style logs, normalize entries and insert into log backend. - Telemetry/Services/OtelIngestBaseService.ts: helpers to resolve service name from attributes/headers. - Syslog parser and utilities - Telemetry/Utils/SyslogParser.ts: robust RFC5424 and RFC3164 parser, structured data extraction and sanitization. - Telemetry/Tests/Utils/SyslogParser.test.ts: unit tests for parser behavior. - Telemetry exception utilities - Telemetry/Utils/Exception.ts: generate exception fingerprint and upsert telemetry exception status (saveOrUpdateTelemetryException). - Queue & job integration - New integration with Common/Server/Infrastructure/Queue and QueueWorker, job id generation and telemetry job types. - Telemetry services add ingestion jobs instead of processing synchronously. - Config, build and dev tooling - Add Telemetry/package.json, package-lock.json, tsconfig.json, nodemon.json, jest config. - New script configs and dependencies (protobufjs, ts-node, jest, nodemon, etc). - Docker / environment updates - docker-compose.base.yml, docker-compose.dev.yml, docker-compose.yml: rename service from open-telemetry-ingest -> telemetry and wire TELEMETRY_* envs. - config.example.env: rename and consolidate environment variables (OPEN_TELEMETRY_* -> TELEMETRY_*, update hostnames and ports). - Tests/Scripts/status-check.sh: update ready-check target to telemetry/status/ready. - Other - Telemetry/Services/Queue/*: export helpers and legacy-compatible job interface shims. - Memory cleanup and batching safeguards across ingest services. - Logging and capture spans added to key code paths. BREAKING CHANGES / MIGRATION NOTES: - Environment variables and docker service names changed: - Replace OPEN_TELEMETRY_... vars with TELEMETRY_... (PORT, HOSTNAME, CONCURRENCY, DISABLE_TELEMETRY, etc). - docker-compose entries moved from "open-telemetry-ingest" to "telemetry" and image name changed to oneuptime/telemetry. - Update any deployment automation and monitoring checks referencing the old service name or endpoints. - Consumers: OTLP endpoints and behavior remain supported, but ingestion is now queued and processed asynchronously. Testing / Running: - Install deps in Telemetry/ (npm install) after syncing Common workspace. - Run dev: npx nodemon (nodemon.json) or build & start using provided scripts. - Run tests with jest (Telemetry test suite includes SyslogParser unit tests). Files added/modified (high level): - Added many files under Telemetry/: Index, Jobs, Middleware, ProtoFiles, Services, Utils, Tests, package and config artifacts. - Modified docker-compose.* and config.example.env and status check script to use new TELEMETRY service/vars.
85 lines
2.5 KiB
TypeScript
85 lines
2.5 KiB
TypeScript
import OTelIngestAPI from "./API/OTelIngest";
|
|
import MetricsAPI from "./API/Metrics";
|
|
import SyslogAPI from "./API/Syslog";
|
|
import FluentAPI from "./API/Fluent";
|
|
import { PromiseVoidFunction } from "Common/Types/FunctionTypes";
|
|
import { ClickhouseAppInstance } from "Common/Server/Infrastructure/ClickhouseDatabase";
|
|
import PostgresAppInstance from "Common/Server/Infrastructure/PostgresDatabase";
|
|
import Redis from "Common/Server/Infrastructure/Redis";
|
|
import InfrastructureStatus from "Common/Server/Infrastructure/Status";
|
|
import Express, { ExpressApplication } from "Common/Server/Utils/Express";
|
|
import logger from "Common/Server/Utils/Logger";
|
|
import Realtime from "Common/Server/Utils/Realtime";
|
|
import App from "Common/Server/Utils/StartServer";
|
|
import Telemetry from "Common/Server/Utils/Telemetry";
|
|
import "./Jobs/TelemetryIngest/ProcessTelemetry";
|
|
import { TELEMETRY_CONCURRENCY } from "./Config";
|
|
import type { StatusAPIOptions } from "Common/Server/API/StatusAPI";
|
|
import "ejs";
|
|
|
|
const app: ExpressApplication = Express.getExpressApp();
|
|
|
|
const APP_NAME: string = "telemetry";
|
|
const ROUTE_PREFIXES: Array<string> = [`/${APP_NAME}`, "/"];
|
|
|
|
app.use(ROUTE_PREFIXES, OTelIngestAPI);
|
|
app.use(ROUTE_PREFIXES, MetricsAPI);
|
|
app.use(ROUTE_PREFIXES, SyslogAPI);
|
|
app.use(ROUTE_PREFIXES, FluentAPI);
|
|
|
|
const init: PromiseVoidFunction = async (): Promise<void> => {
|
|
try {
|
|
const statusCheck: PromiseVoidFunction = async (): Promise<void> => {
|
|
return await InfrastructureStatus.checkStatusWithRetry({
|
|
checkClickhouseStatus: true,
|
|
checkPostgresStatus: true,
|
|
checkRedisStatus: true,
|
|
retryCount: 3,
|
|
});
|
|
};
|
|
|
|
// Initialize telemetry
|
|
Telemetry.init({
|
|
serviceName: APP_NAME,
|
|
});
|
|
|
|
logger.info(
|
|
`Telemetry Service - Queue concurrency: ${TELEMETRY_CONCURRENCY}`,
|
|
);
|
|
|
|
// init the app
|
|
const statusOptions: StatusAPIOptions = {
|
|
liveCheck: statusCheck,
|
|
readyCheck: statusCheck,
|
|
};
|
|
|
|
await App.init({
|
|
appName: APP_NAME,
|
|
statusOptions: statusOptions,
|
|
});
|
|
|
|
// connect to the database.
|
|
await PostgresAppInstance.connect();
|
|
|
|
// connect redis
|
|
await Redis.connect();
|
|
|
|
await ClickhouseAppInstance.connect(
|
|
ClickhouseAppInstance.getDatasourceOptions(),
|
|
);
|
|
|
|
await Realtime.init();
|
|
// add default routes
|
|
await App.addDefaultRoutes();
|
|
} catch (err) {
|
|
logger.error("App Init Failed:");
|
|
logger.error(err);
|
|
throw err;
|
|
}
|
|
};
|
|
|
|
init().catch((err: Error) => {
|
|
logger.error(err);
|
|
logger.error("Exiting node process");
|
|
process.exit(1);
|
|
});
|