{
  "slug": "content-defined-chunking",
  "term": "Content-defined chunking",
  "aliases": [
    "CDC"
  ],
  "definition": "Content-defined chunking divides a byte stream using content-dependent boundary rules rather than only fixed offsets.",
  "note": "The aim is to retain reusable chunks despite shifted offsets; minimum-size suppression and maximum-size forced cuts can disrupt resynchronization. Boundary selection is separate from checking whole-chunk identity. [lbfs]",
  "related": [
    "deduplication",
    "fastcdc",
    "rolling-hash",
    "chunk-fragmentation"
  ],
  "citations": [
    {
      "id": "lbfs",
      "title": "Athicha Muthitacharoen, Benjie Chen and David Mazieres. A Low-bandwidth Network File System. SOSP 2001, sections 3.1.1-3.1.3.",
      "url": "https://pdos.csail.mit.edu/papers/lbfs:sosp01/lbfs.pdf",
      "accessed": "2026-10-12"
    },
    {
      "id": "hesela-cdc",
      "title": "Content-defined chunking: boundaries are not identity",
      "url": "https://hesela.com/analyses/content-defined-chunking-boundaries/",
      "accessed": "2026-10-12"
    }
  ],
  "status": "shipping",
  "advantages": [],
  "limitations": [],
  "supersedes": [],
  "supersededBy": [],
  "firstSeen": null,
  "lastSeen": null,
  "updated": "2026-10-12"
}