{
  "slug": "microbenchmark",
  "term": "Microbenchmark",
  "aliases": [
    "Micro-benchmark"
  ],
  "definition": "A microbenchmark measures a small set of operations to isolate a specific performance cost or behavior.",
  "note": "Use focused tests to explain a mechanism, then use a representative application workload or trace to assess its wider effect. Record cache state, request sizes, concurrency and timing boundaries; a macrobenchmark is not automatically realistic either. [traeger]\n\nFor example, sg_read at sg3_utils v1.48 can issue zero-block SCSI READ(10), READ(12) or READ(16) commands to time command overhead. READ(6) does not share that zero-block meaning. A command rate from this test does not establish data-transfer bandwidth or application IOPS. [sg-read]\n\nIn Slowfs, researchers delayed ext2 operations through CPU-side execution, not added device I/O service time. CPU-bound compile workloads could conceal that overhead. The injected mechanism matters: a slowdown factor alone cannot predict the response to a physically slower disk. [traeger]",
  "status": "unknown",
  "advantages": [],
  "limitations": [
    {
      "text": "An isolated cost can change when other operations contend for shared resources; combine narrow measurements with tests of the intended workload.",
      "citationIds": [
        "traeger"
      ]
    }
  ],
  "related": [
    "iops",
    "latency-storage",
    "fault-injection"
  ],
  "supersedes": [],
  "supersededBy": [],
  "firstSeen": null,
  "lastSeen": null,
  "citations": [
    {
      "id": "traeger",
      "title": "Traeger et al., A Nine Year Study of File System and Storage Benchmarking, FSL-07-01, sections 3.1-3.2 and 12.1-12.2",
      "url": "https://www.fsl.cs.stonybrook.edu/docs/fsbench/fsbench-tr.html",
      "accessed": "2026-11-10"
    },
    {
      "id": "sg-read",
      "title": "sg3_utils v1.48: sg_read(8), description and zero-block SCSI READ timing",
      "url": "https://raw.githubusercontent.com/hreinecke/sg3_utils/v1.48/doc/sg_read.8",
      "accessed": "2026-11-10"
    },
    {
      "id": "hesela-scsi",
      "title": "Hesela: SCSI command handling, transfer counts and benchmark scope",
      "url": "https://hesela.com/tech/scsi/",
      "accessed": "2026-11-10"
    }
  ],
  "updated": "2026-11-10",
  "provenance": [
    "Source synthesis, not a new hardware measurement or reproduction of the historical Slowfs experiment."
  ]
}