{
    "api": "YAML JSON TOON Database",
    "version": "1.0.0",
    "format": "json",
    "dataset": {
        "id": 2894,
        "slug": "site-reliability-practices",
        "title": "Site Reliability Practices",
        "description": "Key concepts from site reliability engineering.",
        "summary": "The vocabulary of site reliability engineering: service-level indicators, objectives and agreements, error budgets, incident response and chaos engineering, with the metrics and routines around them such as MTTR, toil, postmortems, runbooks and the four golden signals.",
        "use_when": [
            "You are setting reliability targets or writing an incident process.",
            "You need precise definitions that teams can share."
        ],
        "caveats": [
            "The terms come from large-scale operations; scale them down for small teams rather than copying them whole.",
            "Metrics such as MTTR are averages and can hide long-tail incidents."
        ],
        "related": [
            "monitoring-logging-tools",
            "cicd-pipeline-stages",
            "version-control-workflows"
        ],
        "entry_count": 16,
        "fields": [
            {
                "section": "data",
                "field": "term",
                "type": "string",
                "example": "SLI"
            },
            {
                "section": "data",
                "field": "description",
                "type": "string",
                "example": "Service Level Indicator: a measurable aspect of\u2026"
            }
        ],
        "category": "DevOps",
        "category_slug": "devops",
        "tags": "devops,sre,reliability",
        "view_count": 50,
        "created_at": 1793403093,
        "updated_at": 1793403093
    },
    "data": [
        {
            "term": "SLI",
            "description": "Service Level Indicator: a measurable aspect of service level."
        },
        {
            "term": "SLO",
            "description": "Service Level Objective: target value for an SLI over time."
        },
        {
            "term": "SLA",
            "description": "Service Level Agreement: contractual consequences for missing SLOs."
        },
        {
            "term": "Error Budget",
            "description": "Allowed amount of unreliability derived from the SLO."
        },
        {
            "term": "Incident Response",
            "description": "Process for responding to and resolving service disruptions."
        },
        {
            "term": "Chaos Engineering",
            "description": "Intentionally injecting failures to validate resilience."
        },
        {
            "term": "MTTR",
            "description": "Mean time to recovery: the average time to restore service after a failure."
        },
        {
            "term": "MTTD",
            "description": "Mean time to detect: the average time between a failure beginning and its detection."
        },
        {
            "term": "MTBF",
            "description": "Mean time between failures: the average operating time between failures of a system."
        },
        {
            "term": "Toil",
            "description": "Manual, repetitive, automatable operational work that scales with service size and adds no lasting value."
        },
        {
            "term": "Blameless Postmortem",
            "description": "A written review of an incident that records timeline, causes and follow-ups without assigning personal blame."
        },
        {
            "term": "Runbook",
            "description": "Documented steps for handling a known alert or operation so responders act consistently."
        },
        {
            "term": "Canary Release",
            "description": "Releasing a change to a small share of traffic first and expanding only if metrics stay healthy."
        },
        {
            "term": "Blue-Green Deployment",
            "description": "Running two identical environments and switching traffic from the old to the new, allowing instant rollback."
        },
        {
            "term": "Four Golden Signals",
            "description": "Latency, traffic, errors and saturation: the four metrics Google's SRE book recommends monitoring for any service."
        },
        {
            "term": "Capacity Planning",
            "description": "Forecasting demand and provisioning enough resources to meet objectives without large waste."
        }
    ]
}