{
  "slug": "failure-domain",
  "term": "Failure domain",
  "aliases": [
    "fault domain"
  ],
  "definition": "A failure domain is a group of components that can be affected by the same failure event because they share a dependency or physical location.",
  "note": "Hosts, racks, power supplies and network paths can define different failure domains. [ford-domains] Placing redundant data on separate hosts does not necessarily separate it across racks or power sources. [ceph-crush] Domain boundaries describe the failures a placement policy is intended to isolate; they do not prove statistical independence between components in different domains.",
  "related": [
    "crush-placement",
    "placement-group",
    "mirroring",
    "erasure-coding"
  ],
  "citations": [
    {
      "id": "ford-domains",
      "title": "Ford et al., Availability in Globally Distributed Storage Systems, OSDI 2010, section 4: failure domains",
      "url": "https://www.usenix.org/legacy/event/osdi10/tech/full_papers/Ford.pdf",
      "accessed": "2026-10-13"
    },
    {
      "id": "ceph-crush",
      "title": "Ceph Squid documentation: CRUSH Maps, hierarchy and placement rules",
      "url": "https://docs.ceph.com/en/squid/rados/operations/crush-map/",
      "accessed": "2026-10-13"
    },
    {
      "id": "hesela-availability",
      "title": "Storage availability and correlated failures: placement boundaries",
      "url": "https://hesela.com/analyses/storage-availability-correlated-failures/",
      "accessed": "2026-10-13"
    }
  ],
  "status": "shipping",
  "advantages": [],
  "limitations": [],
  "supersedes": [],
  "supersededBy": [],
  "firstSeen": null,
  "lastSeen": null,
  "updated": "2026-10-13"
}