sickn33/agentic-awesome-skills

distributed-tracing

Implement distributed tracing with Jaeger and Tempo for request flow visibility across microservices.

ソースを見る

使い方

  1. インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
  2. 必要なツール、認証情報、対応環境を原文で確認します。
  3. 入力と成果物を指定し、出力を資料と照合します。
npx skills add https://github.com/sickn33/agentic-awesome-skills --skill distributed-tracing

開始前の確認

  • 導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
  • スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。
リポジトリの原文

見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。

Distributed Tracing

When to Use

Trace a request across services, diagnose latency and error propagation, or add observable boundaries to a new integration.

Inputs and prerequisites

Record installed SDK and backend versions, permitted collector endpoints, the service graph and a staging request. Inspect the installed version's primary documentation before selecting exporter APIs or deployment configuration. This bundle does not install a tracing backend.

Procedure

  1. Read resources/implementation-playbook.md and identify one user journey.
  2. Configure the matching OpenTelemetry SDK and OTLP exporter before loading instrumented frameworks. Use references/instrumentation.md for propagation, shutdown and privacy checks.
  3. Configure Jaeger using references/jaeger-setup.md, or the existing Tempo/collector deployment's supported configuration. Review listeners, authentication, transport protection, storage and retention before any deployment.
  4. Propagate context over HTTP and asynchronous messages. Use stable operation names and allowlisted attributes. Do not log credentials, raw request bodies or sensitive query values.
  5. Send successful and failing staging requests and verify connected spans in the backend. Record service identity, parentage, duration units and exporter errors.
  6. Measure queue loss and overhead. Select sampling based on those observations; no fixed percentage guarantees coverage or performance.

Example

A checkout calls inventory and payment. Verify that the root request and both downstream operations share a trace, that a simulated payment timeout is recorded, and that no card data is present. Repeat with exporter connectivity unavailable: request handling must retain the application's defined behavior.

Verification

  • Actual trace evidence for each exercised boundary, including queue consumers.
  • Allowed fields only; bounded attribute cardinality.
  • Shutdown flush and exporter failure behavior observed.
  • Access, storage and retention checked independently from UI availability.

Limitations

Head sampling can discard errors before tail sampling sees them. In-memory demos do not prove durable storage. Context propagation and cross-service clocks need actual integration tests; this guide is not a runnable multi-service application.

Sources

タスクに関連する項目

同じリポジトリから

関連する Skills

すべての Skills