SigNoz Observability Hexagonal Architecture

SigNoz Hexagonal Observability

SigNoz Observability Hexagonal Architecture OpenTelemetry Traces Metrics Logs ClickHouse APM Dashboard Alerts Production

OpenTelemetry Setup

# === OpenTelemetry + SigNoz Setup ===

# Install SigNoz (Docker Compose)
# git clone https://github.com/SigNoz/signoz.git
# cd signoz/deploy
# docker compose -f docker/clickhouse-setup/docker-compose.yaml up -d
#
# Access Dashboard: http://localhost:3301
#
# Install OpenTelemetry SDK (Python)
# pip install opentelemetry-api opentelemetry-sdk
# pip install opentelemetry-exporter-otlp
# pip install opentelemetry-instrumentation-flask
# pip install opentelemetry-instrumentation-requests
# pip install opentelemetry-instrumentation-sqlalchemy

from dataclasses import dataclass

@dataclass
class OTelComponent:
    component: str
    hex_layer: str
    what_it_captures: str
    signoz_feature: str

components = [
    OTelComponent("Tracer (Spans)",
        "All Layers",
        "Request Flow ข้าม Service + Duration + Status",
        "Distributed Tracing → Trace Explorer"),
    OTelComponent("Meter (Metrics)",
        "All Layers",
        "Counter Histogram Gauge (Rate Error Duration)",
        "Metrics → Dashboard + Alerts"),
    OTelComponent("Logger (Logs)",
        "All Layers",
        "Structured Log + trace_id Correlation",
        "Logs → Log Explorer (Correlated with Traces)"),
    OTelComponent("Propagator (Context)",
        "Infrastructure (HTTP/gRPC)",
        "Trace Context ข้าม Service (W3C TraceContext)",
        "Service Map → Dependency Graph"),
    OTelComponent("Auto-instrumentation",
        "Infrastructure",
        "Flask Express Spring DB HTTP Client อัตโนมัติ",
        "Traces + Metrics โดยไม่ต้องเขียน Code"),
]

print("=== OpenTelemetry Components ===")
for c in components:
    print(f"  [{c.component}] Layer: {c.hex_layer}")
    print(f"    Captures: {c.what_it_captures}")
    print(f"    SigNoz: {c.signoz_feature}")

Hexagonal Instrumentation

# === Instrumentation per Hexagonal Layer ===

# Domain Layer (Business Logic)
# @tracer.start_as_current_span("domain.process_order")
# def process_order(order: Order) -> OrderResult:
#     span = trace.get_current_span()
#     span.set_attribute("order.id", order.id)
#     span.set_attribute("order.amount", order.total)
#     orders_counter.add(1, {"status": "processing"})
#     # Business logic...
#     return result
#
# Application Layer (Use Cases)
# @tracer.start_as_current_span("usecase.create_order")
# async def create_order(request: CreateOrderRequest) -> CreateOrderResponse:
#     span = trace.get_current_span()
#     span.set_attribute("user.id", request.user_id)
#     with usecase_duration.record({"usecase": "create_order"}):
#         order = Order.create(request)
#         result = process_order(order)
#         await notify_customer(result)
#     return response
#
# Infrastructure Layer (Adapters)
# Auto-instrumented by OpenTelemetry:
# - HTTP (Flask/FastAPI): Request Duration Status Code
# - Database (SQLAlchemy): Query Duration Statement
# - HTTP Client (requests): External Call Duration

@dataclass
class InstrumentationGuide:
    layer: str
    span_name: str
    attributes: str
    metrics: str
    logs: str

guides = [
    InstrumentationGuide("Domain",
        "domain.{service}.{method}",
        "order.id order.amount user.id product.id",
        "orders_total revenue_total conversion_rate",
        "OrderCreated PaymentProcessed InventoryUpdated"),
    InstrumentationGuide("Application",
        "usecase.{name}",
        "user.id request.type session.id",
        "usecase_duration usecase_errors auth_attempts",
        "UseCaseStarted UseCaseCompleted AuthFailed"),
    InstrumentationGuide("Infrastructure (DB)",
        "db.{operation} (Auto-instrumented)",
        "db.system db.statement db.operation",
        "db_query_duration db_connections_active",
        "SlowQuery ConnectionPoolExhausted"),
    InstrumentationGuide("Infrastructure (HTTP)",
        "http.{method} (Auto-instrumented)",
        "http.method http.url http.status_code",
        "http_request_duration http_requests_total",
        "HTTPError TimeoutError RateLimited"),
    InstrumentationGuide("Infrastructure (Queue)",
        "queue.{operation}",
        "messaging.system messaging.destination",
        "queue_messages_produced queue_lag",
        "MessagePublished MessageConsumed ConsumerError"),
]

print("=== Instrumentation Guide ===")
for g in guides:
    print(f"\n  [{g.layer}] Span: {g.span_name}")
    print(f"    Attributes: {g.attributes}")
    print(f"    Metrics: {g.metrics}")
    print(f"    Logs: {g.logs}")

Production Dashboard

# === SigNoz Production Setup ===

@dataclass
class DashboardPanel:
    panel: str
    query: str
    target: str
    alert: str

panels = [
    DashboardPanel("Request Rate (RPM)",
        "rate(http_requests_total[5m]) * 60",
        "Baseline ±20%",
        "Drop > 50% → P1 Service Down"),
    DashboardPanel("Error Rate (%)",
        "rate(http_requests_total{status=~'5..'}[5m]) / rate(http_requests_total[5m])",
        "< 1%",
        "> 1% → P2 | > 5% → P1"),
    DashboardPanel("P99 Latency (ms)",
        "histogram_quantile(0.99, rate(http_request_duration_bucket[5m]))",
        "< 500ms",
        "> 1000ms → P2 | > 3000ms → P1"),
    DashboardPanel("Business: Orders/min",
        "rate(orders_total[5m]) * 60",
        "Baseline ±20%",
        "Drop > 30% → P2 Check Conversion"),
    DashboardPanel("DB Query Duration P95",
        "histogram_quantile(0.95, rate(db_query_duration_bucket[5m]))",
        "< 100ms",
        "> 500ms → P2 Slow Query"),
    DashboardPanel("ClickHouse Storage",
        "signoz_storage_bytes",
        "< 80% Disk",
        "> 90% → P2 Increase Retention/Sampling"),
]

print("=== Dashboard Panels ===")
for p in panels:
    print(f"  [{p.panel}]")
    print(f"    Query: {p.query}")
    print(f"    Target: {p.target}")
    print(f"    Alert: {p.alert}")

เคล็ดลับ

• OpenTelemetry: ใช้ OpenTelemetry Standard ไม่ Lock-in Vendor
• Sampling: ใช้ Tail-based Sampling เก็บเฉพาะ Error/Slow Traces
• Correlation: ใส่ trace_id ใน Log ทุกบรรทัด Correlate Trace+Log
• Business Metrics: สร้าง Business KPI Dashboard (Orders Revenue)
• ClickHouse: ClickHouse เร็วมาก Query Trace/Metric มหาศาลได้

SigNoz คืออะไร

Open Source APM Observability Traces Metrics Logs OpenTelemetry ClickHouse Dashboard Alerts ทดแทน Datadog New Relic ถูกกว่า

สรุป

SigNoz Observability Hexagonal Architecture OpenTelemetry Traces Metrics Logs ClickHouse Domain Application Infrastructure Dashboard Production