{
  "slug": "tail-latency",
  "term": "Tail latency",
  "aliases": [
    "latency tail"
  ],
  "definition": "Tail latency describes the high-latency part of an operation response-time distribution, usually summarized using specified high percentiles.",
  "note": "State the operation population, timing boundaries, percentile estimator and observation window. An hourly mean cannot reconstruct request p99, and a wait-for-all fan-out request follows the slowest required response rather than an average leaf. [dean] The linked synthetic examples isolate these measurement differences.",
  "related": [
    "latency-storage",
    "tail-hour",
    "coordinated-omission",
    "fail-slow"
  ],
  "citations": [
    {
      "id": "dean",
      "title": "Dean and Barroso, The Tail at Scale, CACM 56(2), 2013; DOI 10.1145/2408776.2408794",
      "url": "https://www.barroso.org/publications/TheTailAtScale.pdf",
      "accessed": "2026-10-15"
    },
    {
      "id": "hesela-tail",
      "title": "Hesela: Slow RAID hours are not request tail latency; source audit and reproducible counterexamples",
      "url": "https://hesela.com/analyses/storage-tail-slowdowns-raid-fanout/",
      "accessed": "2026-10-15"
    }
  ],
  "status": "research",
  "advantages": [],
  "limitations": [],
  "supersedes": [],
  "supersededBy": [],
  "firstSeen": null,
  "lastSeen": null,
  "updated": "2026-10-15"
}