{
  "slug": "non-preemptive-priority",
  "term": "Non-preemptive priority",
  "aliases": [
    "nonpreemptive priority scheduling"
  ],
  "definition": "Non-preemptive priority selects higher-priority pending work at scheduling boundaries without interrupting the operation already in progress.",
  "note": "A two-class node with strict aggregate service beta and maximum lower-priority packet work L gives the high class beta_H(t)=max(0,beta(t)-L). For beta(t)=R*max(0,t-T), the added latency is L/R. [netcal-priority]\n\nIn a hypothetical serial server delivering 1 MiB/ms, an 8 MiB low-priority command starts at time zero. A 1 MiB high-priority request arrives at 0.5 ms: it waits 7.5 ms and completes 8.5 ms after arrival. Four 2 MiB commands with priority reconsidered between them reduce those times to 1.5 and 2.5 ms. Splitting bytes without exposing a scheduling boundary does not produce that result. [priority-example]\n\nSeek, rotation and internal work can dominate payload transfer. Semi-preemptible I/O exposes command boundaries, and actual interruption can add positioning cost. [semi-preemptible-fast03]\n\nLinux I/O-priority support depends on the scheduler; its realtime class can starve other work. Selecting that class alone supplies neither a service curve nor an end-to-end deadline. [linux-ioprio]",
  "status": "shipping",
  "advantages": [],
  "limitations": [],
  "related": [
    "strict-service-curve",
    "rate-latency-service-curve",
    "semi-preemptible-io",
    "io-scheduler"
  ],
  "supersedes": [],
  "supersededBy": [],
  "firstSeen": null,
  "lastSeen": null,
  "updated": "2026-11-20",
  "citations": [
    {
      "id": "netcal-priority",
      "title": "Le Boudec and Thiran. Network Calculus, 2022 online edition, Corollary 6.2.1, p. 176.",
      "url": "https://leboudec.github.io/netcal/latex/netCalBook.pdf",
      "accessed": "2026-11-20"
    },
    {
      "id": "semi-preemptible-fast03",
      "title": "Dimitrijevic, Rangaswami and Chang. Design and Implementation of Semi-preemptible IO. FAST 2003, sections 1, 3 and 4.",
      "url": "https://www.usenix.org/legacy/events/fast03/tech/full_papers/dimitrijevic/dimitrijevic.pdf",
      "accessed": "2026-11-20"
    },
    {
      "id": "linux-ioprio",
      "title": "Linux 6.16 documentation: Block I/O priorities, introduction and scheduling classes.",
      "url": "https://docs.kernel.org/6.16/block/ioprio.html",
      "accessed": "2026-11-20"
    },
    {
      "id": "priority-example",
      "title": "Hesela: exact hypothetical non-preemptive priority traces and bounds.",
      "url": "https://hesela.dev/research/nonpreemptive-priority/results.json",
      "accessed": "2026-11-20"
    }
  ],
  "provenance": [
    "The service bound is a published theorem for a specified node, not an empirical SSD guarantee. The trace is exact invented arithmetic, not a reproduction of FAST 2003.",
    "FAST 2003 studied a historical SCSI disk prototype. Device parallelism, firmware queues and retries require their own work and scheduling contracts."
  ]
}
