{
    "api": "YAML JSON TOON Database",
    "version": "1.0.0",
    "format": "json",
    "dataset": {
        "id": 1633,
        "slug": "observability-signals",
        "title": "Observability Signals and Alert Design",
        "description": "Operational signals, useful questions, and failure modes for service monitoring and incident diagnosis.",
        "summary": "Operational signals, useful questions, and failure modes for service monitoring and incident diagnosis. Each row includes a practical application and a failure to check before using it.",
        "use_when": [
            "Add useful diagnostics to a small API.",
            "Choose alerts tied to a real user-visible failure."
        ],
        "caveats": [
            "Names and conventions vary by instrumentation stack.",
            "Collecting telemetry does not by itself provide an actionable alert."
        ],
        "related": [
            "site-reliability-practices",
            "reliable-background-jobs"
        ],
        "reviewed_at": "2026-10-12",
        "sources": [
            {
                "title": "OpenTelemetry signals",
                "url": "https:\/\/opentelemetry.io\/docs\/concepts\/signals\/"
            },
            {
                "title": "Google SRE monitoring guidance",
                "url": "https:\/\/sre.google\/sre-book\/monitoring-distributed-systems\/"
            }
        ],
        "reading": [
            "logs-metrics-and-traces-for-a-small-api"
        ],
        "provenance": "Original editorial reference notes by YJTOON, informed by the linked primary documentation. External specifications retain their own licenses.",
        "entry_count": 10,
        "fields": [
            {
                "section": "data",
                "field": "signal",
                "type": "string",
                "example": "Metric"
            },
            {
                "section": "data",
                "field": "question",
                "type": "string",
                "example": "How much or how often?"
            },
            {
                "section": "data",
                "field": "example",
                "type": "string",
                "example": "Request count per service and status class."
            },
            {
                "section": "data",
                "field": "pitfall",
                "type": "string",
                "example": "Unbounded labels create excessive cardinality."
            }
        ],
        "category": "DevOps",
        "category_slug": "devops",
        "tags": "devops,observability signals,reference,engineering",
        "view_count": 1,
        "created_at": 1791798640,
        "updated_at": 1791798640
    },
    "data": [
        {
            "signal": "Metric",
            "question": "How much or how often?",
            "example": "Request count per service and status class.",
            "pitfall": "Unbounded labels create excessive cardinality."
        },
        {
            "signal": "Log",
            "question": "What happened at this event?",
            "example": "A structured failure record with an operation ID.",
            "pitfall": "Logging credentials or full private payloads."
        },
        {
            "signal": "Trace",
            "question": "Where did a request spend time?",
            "example": "Spans covering a request and its database query.",
            "pitfall": "Missing propagation breaks the end-to-end path."
        },
        {
            "signal": "Latency histogram",
            "question": "What does the duration distribution look like?",
            "example": "Bucket counts for request duration.",
            "pitfall": "A mean hides slow-tail behavior."
        },
        {
            "signal": "Error ratio",
            "question": "What fraction of eligible requests failed?",
            "example": "Failed requests divided by all eligible requests.",
            "pitfall": "A raw error count changes with traffic."
        },
        {
            "signal": "Saturation",
            "question": "How close is a resource to its capacity?",
            "example": "Queue depth relative to workers.",
            "pitfall": "A high utilization number alone may not indicate user harm."
        },
        {
            "signal": "SLI",
            "question": "What measured behavior represents service quality?",
            "example": "Fraction of requests completed within the latency target.",
            "pitfall": "The denominator must match user-relevant work."
        },
        {
            "signal": "SLO",
            "question": "What reliability target do we intend to meet?",
            "example": "A target success fraction over a defined window.",
            "pitfall": "A target without a window is underspecified."
        },
        {
            "signal": "Burn rate",
            "question": "How quickly is the error budget being consumed?",
            "example": "Observed error fraction divided by the allowed fraction.",
            "pitfall": "Short windows can be noisy at low volume."
        },
        {
            "signal": "Correlation ID",
            "question": "Which records describe one operation?",
            "example": "A stable request or job identifier across signals.",
            "pitfall": "It is not a user identity and should not contain secrets."
        }
    ]
}