{
  "slug": "hedged-request",
  "term": "Hedged request",
  "aliases": [
    "hedged read",
    "request hedging"
  ],
  "definition": "A hedged request is a redundant copy dispatched after an initial request remains unfinished for a chosen delay, allowing an eligible response to complete the operation.",
  "note": "The client cancels outstanding copies after receiving a result. [dean]\n\nA dispatch fraction is not a resource-utilization fraction. Shared slow states and delayed cancellation change the benefit and cost; preserve the read's consistency contract when deciding which response is acceptable. [hesela]",
  "related": [
    "tied-request",
    "adaptive-replica-selection",
    "tail-latency",
    "linearizability"
  ],
  "citations": [
    {
      "id": "dean",
      "title": "Dean and Barroso. The Tail at Scale. CACM 56(2), 2013, pp. 77-78. DOI: 10.1145/2408776.2408794.",
      "url": "https://www.barroso.org/publications/TheTailAtScale.pdf",
      "accessed": "2026-10-17"
    },
    {
      "id": "hesela",
      "title": "Hesela. Hedged reads: replica dependence and cancellation work, with exact synthetic examples.",
      "url": "https://hesela.com/analyses/storage-tail-slowdowns-raid-fanout/#hedged-reads",
      "accessed": "2026-10-17"
    }
  ],
  "status": "research",
  "advantages": [],
  "limitations": [],
  "supersedes": [],
  "supersededBy": [],
  "firstSeen": null,
  "lastSeen": null,
  "updated": "2026-10-17"
}