railiance-platform/workplans/RAILIANCE-WP-0016-apps-pg-resource-evidence.md
codex ea2e9ec97d
All checks were successful
CI Smoke / host-smoke (push) Successful in 0s
CI Smoke / container-smoke (push) Successful in 1s
fix(workplans): adopt ADR-007 derived identifiers for unregistered records
These workplans exist only in the retired local hub. Their random pre-ADR-007
identifiers are refused by C-06 as stale references, so they cannot be
registered. Deriving from the canonical record id takes no identity from
anything: central does not hold them and the old ids die with the cache.

Records central already holds were deliberately left untouched.

Refs CUST-WP-0068-T06

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 2583210@bnt-lap001
Assistant-Session: f2bff2d5-e9b2-4338-92ca-10282a927006
2026-08-25 20:20:45 +02:00

89 lines
2.8 KiB
Markdown

---
id: RAILIANCE-WP-0016
type: workplan
title: "Publish apps-pg resource and recovery evidence"
domain: financials
repo: railiance-platform
status: finished
owner: codex
topic_slug: railiance
created: "2026-08-11"
updated: "2026-08-14"
state_hub_workstream_id: "857ca302-bb94-5d41-a649-1aa966368df4"
related:
- RAILIANCE-WP-0003
- RESOURCE-WP-0003
---
# RAILIANCE-WP-0016 — apps-pg resource evidence
## Goal
Provide platform-owned evidence for `resource:railiance:apps-pg`: demand,
utilization, recovery, operations labor, and consumer allocation. Origin:
`RESOURCE-WP-0003-T04` delegated evidence gap.
## T01 — Publish database capacity and utilization
```task
id: RAILIANCE-WP-0016-T01
status: done
priority: high
state_hub_task_id: "475b8930-1e75-580b-a5e4-ce14b038c0ce"
```
Record instance count, CPU/memory requests and observed use, provisioned and
used storage, database growth, connections, I/O or other available saturation
proxies, and consumer database attribution with timestamps and provenance.
Done when resource-control can forecast database capacity without reading
application data or credentials.
## T02 — Publish recovery and operational evidence
```task
id: RAILIANCE-WP-0016-T02
status: done
priority: high
state_hub_task_id: "a2ca2b69-f089-5ae4-8c97-bc031503f304"
```
Record backup coverage, restore-test results, recovery objectives, upgrade and
maintenance cadence, incidents, and setup/recurring operator labor. Keep
service procedures and execution in railiance-platform.
Done when the portfolio can distinguish verified recovery, unresolved local
storage risk, and platform labor cost.
## T03 — Define shared database allocation drivers
```task
id: RAILIANCE-WP-0016-T03
status: done
priority: medium
state_hub_task_id: "159eefae-d81c-57db-969f-0f9fcecdbc18"
```
Publish candidate consumer drivers such as database storage GB-month,
connections, transactions, or measured I/O. Include shared overhead,
unattributed residual, method version, and uncertainty.
Done when resource-control can allocate a referenced apps-pg cost without
making railiance-platform a financial ledger.
## Outcome
Published 2026-08-14. Observation
`docs/evidence/RAILIANCE-WP-0016-apps-pg-observation.json` and narrative
`docs/evidence/RAILIANCE-WP-0016-apps-pg-resource-evidence.md`.
- T01: 1/1 instance, 10Gi local-path, 590 MiB PGDATA, no CPU/memory
requests, two consumer catalogs (~16.6 MiB), `vergabe_db` unused.
- T02: no ScheduledBackup, not an Option A target, RPO unbounded, RTO
undefined — unresolved local-storage risk. Labor: ~6h setup, ~0.5h/month
recurring, high uncertainty, no EUR.
- T03: method `apps-pg-dbbytes-v1`, driver `database_gb`, residual
`platform:apps-pg-overhead` (94.8% of used volume is WAL/catalog).
Refresh: `make apps-pg-evidence`. resource-control can now replace the
illustrative `examples/control-cycle/apps-pg-*.json` fixtures.