fail-slow · unknown · also fail-slow failure, hardware performance fault

Fail-slow

Fail-slow describes a component that remains operational but performs more slowly than expected for its operating conditions.

Related Observatory article: Fail-slow on hesela.com

A slowdown is an observed performance symptom, not proof of a particular physical defect or imminent fail-stop event. Hardware, firmware and workload context must be separated. Gray failure additionally concerns a disagreement between application and system observations. [1] [2]

Relations

related

gray-failure, differential-observability, io-timeout

Citations

1. Gunawi et al., Fail-Slow at Scale, FAST 2018; hardware performance faults and study limits. (accessed 2026-10-13)
2. Huang et al., Gray Failure: The Achilles' Heel of Cloud-Scale Systems, HotOS 2017, section 3; DOI 10.1145/3102980.3103005. (accessed 2026-10-13)
3. Hesela: Fail-slow NVMe SSDs: what SMART and heartbeats miss (accessed 2026-10-13)

JSON: /data/terms/fail-slow.json