railiance-platform/workplans/RPF-WP-0010-apps-pg-resource-evidence.md
codex e4af2a1d10
All checks were successful
CI Smoke / host-smoke (push) Successful in 0s
CI Smoke / container-smoke (push) Successful in 1s
fix(workplans): migrate active workplans off the retired RAILIANCE-WP prefix
RAILIANCE-WP is a family name, not a repository (ADR-007, and the prefix
registry already lists it retired). Three repositories independently used one
number space for unrelated work — RAILIANCE-WP-0012 was openbao extraction here,
a cnpg backup in railiance-apps and a deploy-verify in railiance-cluster. This
repository also carried two files both numbered 0016.

Active workplans move to the successor prefix and are renumbered from 0001 in
historical order. Archived workplans keep their historical identifiers.

Projection UUIDs are re-derived from the new canonical ids. Records already
registered under the old identifiers leave orphaned hub rows behind; that debt
is recorded in CUST-WP-0068 and clears when ADR-012's reset-from-forge lands.

Refs CUST-WP-0068-T03

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 2583210@bnt-lap001
Assistant-Session: f2bff2d5-e9b2-4338-92ca-10282a927006
2026-08-25 22:58:35 +02:00

2.8 KiB

id type title domain repo status owner topic_slug created updated state_hub_workstream_id related
RPF-WP-0010 workplan Publish apps-pg resource and recovery evidence financials railiance-platform finished codex railiance 2026-08-11 2026-08-14 ee4a867f-eae2-5e85-b0b1-9802a3f31f10
RAILIANCE-WP-0003
RESOURCE-WP-0003

RPF-WP-0010 — 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

id: RPF-WP-0010-T01
status: done
priority: high
state_hub_task_id: "4cba1304-9a5d-5a26-8706-fe1df7ca5d4e"

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

id: RPF-WP-0010-T02
status: done
priority: high
state_hub_task_id: "382751c3-b05c-51d1-9a9c-d64363978851"

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

id: RPF-WP-0010-T03
status: done
priority: medium
state_hub_task_id: "01148c0f-9d21-5c64-be99-cb5f42697274"

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/RPF-WP-0010-apps-pg-observation.json and narrative docs/evidence/RPF-WP-0010-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.