railiance-cluster/docs/cluster-resource-evidence.md
codex b36ac28b49
All checks were successful
CI Smoke / host-smoke (push) Successful in 0s
CI Smoke / container-smoke (push) Successful in 2s
Publish pending unscheduled pods in cluster observations.
RAIL-BS-WP-0014: residual millicores count scheduled pods only.
state_hub_preflight_observation matches the STATE-WP-0091 fixture shape.

Assistant: grok
Assistant-Session: 01a09dc1-b21e-77e1-919e-fcad2f82b267
2026-09-14 10:34:27 +02:00

18 lines
952 B
Markdown

# Cluster resource evidence
`make cluster-observe` captures a non-secret, timestamped observation for
`resource:railiance:reef-railiance:k3s`. It separates allocatable capacity,
requests, limits, optional observed usage, PVC demand, storage-class behavior,
and measurement gaps. It never reads Secret objects or pod environments.
The allocation section publishes raw numerators, denominators, residual
capacity, and `cluster-raw-drivers-v1`. Residual millicores exclude
pending unscheduled pods; those pods are listed under
`allocation.pending_unscheduled` and projected as
`state_hub_preflight_observation` for STATE-WP-0091. Residual capacity is
**not** a kube-scheduler guarantee. It does not select a financial
allocation formula or write booked cost; those decisions remain with
resource-control.
Current failure-domain evidence remains explicit: one Ready node on
`railiance01` with local storage. ThreePhoenix is a target, not live capacity.