Reject the cluster that runs fast but cannot recover — conditional result
Not accepted: 1,050 tokens/s passes; recovery takes 150 s against a 120 s limit (30 s over). Retest the full release after repair.derived
| Value kind | derived — Derived values are guide calculations; their result is only as fixed as the stated inputs, scope, and method. |
|---|---|
| Scope | Hypothetical acceptance case; inputs and arithmetic are in the chapter's worked example. Not a measured result. |
| As of | 2026-09 |
| Source | Guide derivation from a worked example with hypothetical inputs, Chapter 7.14, 2026-09-08 |
| Derivation | Useful throughput = 3,780,000 tokens / 3,600 s = 1,050 tokens/s, which clears the 1,000 tokens/s, 89.0% quality and 50 ms p99 gates. Recovery overrun = 150 − 120 = 30 s, so the cluster is not accepted. Reversing it requires recovery within 120 s, the same performance, quality and defect gates, and passing inventory, authorized-update, failed-update-recovery and rollback checks on the restored manifest. |
| Review | checking…review by 2027-03-08 · standard cadence |
| Recorded changes | last 2026-10-19 · 2 revisions tracked |
| Claim id | guide2-t29-7-14-result |
Where the guide uses it
← Full numbers register — every date-stamped figure in the guide, with revision history.