# In progress — iteration 22: db-bench, the measurement backbone

> **Status: 🔄 in progress** (spec + plan approved 2026-08-21) — second
> slice of the concurrency chain **✅ stage 3 → 22 → 31 → 24 → 23 → 32**.
> Board: [../stories/00-status.md](../stories/00-status.md).
>
> One marker doc per active slice; deleted when the slice lands.

## What

Execute [`superpowers/plans/2026-08-21-db-bench.md`](../superpowers/plans/2026-08-21-db-bench.md)
(spec: [`2026-08-21-db-bench-design.md`](../superpowers/specs/2026-08-21-db-bench-design.md),
approved): the `time.ticks` µs builtin, the `docs/examples/db-bench`
sample (seed/read/query/write/mix/msgrate/verify), the campaign driver
with relative gates vs `bench/baseline.json`, the restart proof and
kill -9 battery at both shard counts, and the first committed baseline.

## Why now

Nothing performance-shaped is sourced until this runs — and the arc owes
its before/after. One campaign now covers single- AND multi-shard
honestly (stage 3 landed), prices the RPC, and produces the mutex-inbox
number stage-2's deviation waits on.

## Story

- [22 — durability, throughput, scale](../stories/language-runtime-database/in-progress/22-durability-throughput-scale.md)

## Definition of done

- Plan Tasks 1–6 checked; `just db-bench` exit 0 twice in a row;
  gate-bites smoke proven (doctored results FAIL); baseline committed
  with rationale; arc delta + msgrate copied into story 8; full battery
  green.
- Story 22 → done/; board standup written from the actual numbers; this
  file deleted. Next slice: iteration 31 (actor lifecycle).