jakman85andClaude Opus 5.5
9a69f6906a
hostRoot was /run/cilium/cgroupv2 with autoMount disabled, but nothing mounts cgroup2 there. The agent mounted one from inside its own private cgroup namespace, so socket-LB attached to the agent's own cgroup and host processes got no Service/LB translation. k3s-prod-1 (Gateway L2 lease holder + kube-vip VIP) therefore could not reach the Gateway VIP, and its apiserver's OIDC authenticator has failed since 2026-09-12. Co-Authored-By: Claude Opus 5.5 <[email protected]>
66 lines
3.3 KiB
YAML
66 lines
3.3 KiB
YAML
# Cilium Helm values — REFERENCE COPY of the parity set (docs/02 Cilium-ownership contract).
|
|
#
|
|
# The AUTHORITATIVE values that Flux reconciles are inlined in helmrelease.yaml. This file is a
|
|
# readable, un-nested mirror of that value set so WS-NET can diff it against the live cluster and
|
|
# the Ansible bootstrap render at a glance. Keep the two in sync.
|
|
#
|
|
# SOURCE OF TRUTH (all [parity] fields MUST equal these):
|
|
# infra/ansible/roles/cilium/templates/cilium-values.yaml.j2
|
|
# infra/ansible/roles/cilium/defaults/main.yml (cilium_version: 1.20.1)
|
|
# infra/ansible/inventory/group_vars/all.yml (k3s_apiserver_endpoint = the kube-vip VIP,
|
|
# k3s_api_port) — NOT k3s_api_host, which is the
|
|
# founder's own address and bootstrap-only
|
|
#
|
|
# chart version (helmrelease.yaml chart.spec.version): 1.20.1 # [parity] = cilium_version
|
|
|
|
# [parity] k3s kube-proxy disabled → Cilium replaces it (ADR-0001/0002)
|
|
kubeProxyReplacement: true
|
|
# [parity] = the k3s API endpoint + port. THE CONTROL-PLANE VIP (kube-vip), not the primary node —
|
|
# changed 2026-09-06; the Ansible half is k3s_apiserver_endpoint, NOT k3s_api_host.
|
|
# Mirrors the HelmRelease's ${K3S_API_HOST} cluster-vars token (R-ENV-02). This file is NOT a
|
|
# kustomize resource, so nothing substitutes it — the token is shown with its dev value beside it.
|
|
k8sServiceHost: "${K3S_API_HOST}" # the CONTROL-PLANE VIP — dev: 192.168.1.49 | prod: 192.168.2.9
|
|
k8sServicePort: 6443
|
|
# [parity] ingress via Gateway API, no Traefik (docs/09)
|
|
gatewayAPI:
|
|
enabled: true
|
|
# [parity] egress-class steering (ADR-0002; VPN model ADR-0013)
|
|
egressGateway:
|
|
enabled: true
|
|
# [parity] Egress Gateway REQUIRES masquerade; ipv4 + eBPF is the Phase-1 crash fix — keep BOTH
|
|
enableIPv4Masquerade: true
|
|
bpf:
|
|
masquerade: true
|
|
# [parity] flow observability / isolation audit
|
|
hubble:
|
|
enabled: true
|
|
relay:
|
|
enabled: true
|
|
ui:
|
|
enabled: true
|
|
# [parity] ingress VIP announcement on the flat LAN (docs/09, OQ-1)
|
|
l2announcements:
|
|
enabled: true
|
|
# [parity] the host's cgroup2 root is /sys/fs/cgroup (systemd mounts it); do not auto-mount.
|
|
# NOT /run/cilium/cgroupv2: nothing mounts cgroup2 there, so socket-LB attached to the agent's own
|
|
# cgroup and host processes lost Service/LB translation (2026-10-03 — see helmrelease.yaml).
|
|
cgroup:
|
|
autoMount:
|
|
enabled: false
|
|
hostRoot: /sys/fs/cgroup
|
|
# [parity] roll the agent DaemonSet ONE node at a time. Overrides the cilium 1.20.1 chart
|
|
# default of 2, which on 3 nodes lets a single bad render break 2/3 agents at once — as the
|
|
# 2026-09-01 incident did (k8sServiceHost: "" → the `config` init container fell back to the
|
|
# ClusterIP 10.43.0.1:443, translatable only by the very agent being replaced). A CNI upgrade
|
|
# has no healthy-peer fallback, least of all on a cold prod bootstrap; maxUnavailable: 1 stops
|
|
# the rollout at the first unready pod. Cost: serialised, slower upgrades (fine at 3 nodes).
|
|
updateStrategy:
|
|
type: RollingUpdate
|
|
rollingUpdate:
|
|
maxUnavailable: 1
|
|
# NON-parity (Flux/prod may differ; dev sets 1 to save RAM) — omitted from the HelmRelease:
|
|
# operator.replicas
|
|
#
|
|
# TODO (Phase 2, WS-NET): ipam / ipv4NativeRoutingCIDR pinned to cluster CIDRs; east-west
|
|
# encryption (wireguard/ipsec) decision (WS-SEC/WS-NET).
|