Ben Vincent
8ce1b5f6bd
The internal intermediate CA re-key broke CA consumers because Reloader ignored Secrets and could not restart on the vault-ca-cert Secret. Enabling generic secret watching naively would restart every workload on each Vault/VSO secret rotation, so this scopes existing auto annotations to ConfigMaps and makes secret reload opt-in per Secret. - set reloader ignoreSecrets: false so Secrets are watched - convert every generic reloader.stakater.com/auto to the configmap-only configmap.reloader.stakater.com/auto form (22 annotations, 19 files) - add explicit secret.reloader.stakater.com/reload: "vault-ca-cert" to the CA consumers (artifactapi api, cephrgw-operator, puppetserver master+compiler, litellm, logarchiver) so CA rotation restarts them - add secret.reloader.stakater.com/reload: "kanidm-tls" so the cert-manager leaf renewal rolls kanidm - add docs/ca-rotation.md runbook and index it Closes #326 Claude-Session: https://claude.ai/code/session_01JUoARVdmhxKQHyyyp1pxeT
105 lines
3.5 KiB
YAML
105 lines
3.5 KiB
YAML
# Dedicated JetStream-enabled NATS cluster for the log bus. Deliberately NOT
|
|
# shared with app messaging (streamstack et al. run their own NATS in their own
|
|
# repo) — a separate cluster isolates logging blast-radius from app messaging
|
|
# and lets us size retention/storage purely for the log outage-buffer + replay
|
|
# use-case.
|
|
fullnameOverride: nats
|
|
|
|
config:
|
|
cluster:
|
|
enabled: true
|
|
replicas: 3
|
|
jetstream:
|
|
enabled: true
|
|
fileStore:
|
|
pvc:
|
|
# Sized for 3d retention: ~100 GiB/3d compressed (see
|
|
# nats-stream-limits ConfigMap) + file-store WAL/index/overhead, kept
|
|
# safely above the 130 GiB max_bytes cap. 3 replicas => ~0.5 TiB total
|
|
# provisioned on cephrbd-fast-delete. NB: this is the honest number for
|
|
# the assumed ~1500 events/s; higher real volume needs a bigger PVC +
|
|
# max_bytes together, else discard=old truncates retention below 3d.
|
|
size: 180Gi
|
|
storageClassName: cephrbd-fast-delete
|
|
# Per-user auth with publish/subscribe separation. Passwords are injected as
|
|
# env vars from the Vault-synced nats-auth Secret. The `<< $VAR >>` wrapping is
|
|
# REQUIRED by this chart: it renders the value UNQUOTED in nats.conf so the
|
|
# NATS server expands the env var. A plain `$VAR` is JSON-quoted ("$VAR") and
|
|
# NATS then treats it as a literal string — which broke auth for every client.
|
|
merge:
|
|
authorization:
|
|
users:
|
|
# Bootstrap Job (stream/consumer management) — full JetStream API.
|
|
- user: log-admin
|
|
password: << $NATS_ADMIN_PASSWORD >>
|
|
# Edge publishers (k8s DaemonSet + VM ingest) — publish only.
|
|
- user: log-producer
|
|
password: << $NATS_PRODUCER_PASSWORD >>
|
|
permissions:
|
|
publish:
|
|
allow:
|
|
- "logs.>"
|
|
subscribe:
|
|
allow:
|
|
- "_INBOX.>"
|
|
# Consumers (transform tier + archiver) — pull + ack only, no publish
|
|
# to log subjects.
|
|
- user: log-consumer
|
|
password: << $NATS_CONSUMER_PASSWORD >>
|
|
permissions:
|
|
publish:
|
|
allow:
|
|
- "$JS.API.CONSUMER.>"
|
|
- "$JS.API.STREAM.INFO.>"
|
|
- "$JS.ACK.LOGS.>"
|
|
subscribe:
|
|
allow:
|
|
- "_INBOX.>"
|
|
|
|
container:
|
|
# Pulled through the artifactapi dockerhub remote (upstream official nats;
|
|
# no DHI variant available for nats).
|
|
image:
|
|
repository: artifactapi.k8s.syd1.au.unkin.net/dockerhub/library/nats
|
|
tag: 2.14.2-alpine
|
|
env:
|
|
NATS_ADMIN_PASSWORD:
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: nats-auth
|
|
key: admin_password
|
|
NATS_PRODUCER_PASSWORD:
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: nats-auth
|
|
key: producer_password
|
|
NATS_CONSUMER_PASSWORD:
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: nats-auth
|
|
key: consumer_password
|
|
resources:
|
|
requests:
|
|
cpu: 250m
|
|
memory: 512Mi
|
|
limits:
|
|
cpu: "2"
|
|
memory: 4Gi
|
|
|
|
# Roll the StatefulSet on config changes only; nats-auth is Vault-rotated (VSO)
|
|
# so it is deliberately not watched here (no restart on routine key rotation).
|
|
podTemplate:
|
|
merge:
|
|
metadata:
|
|
annotations:
|
|
configmap.reloader.stakater.com/auto: "true"
|
|
|
|
# Config-reloader sidecar image, also through artifactapi.
|
|
reloader:
|
|
image:
|
|
repository: artifactapi.k8s.syd1.au.unkin.net/dockerhub/natsio/nats-server-config-reloader
|
|
tag: "0.23.0"
|
|
|
|
natsBox:
|
|
enabled: false
|