From 6c77b8e7f8e7558b7edd06c063a4a5939c6c2125 Mon Sep 17 00:00:00 2001 From: Brad Stein Date: Fri, 12 Dec 2025 00:50:02 -0300 Subject: [PATCH] restore docs after gitignore change --- clusters/oceanus/README.md | 5 +++++ hosts/styx/README.md | 2 ++ services/keycloak/README.md | 27 +++++++++++++++++++++++++++ services/monitoring/README.md | 28 ++++++++++++++++++++++++++++ 4 files changed, 62 insertions(+) create mode 100644 clusters/oceanus/README.md create mode 100644 hosts/styx/README.md create mode 100644 services/keycloak/README.md create mode 100644 services/monitoring/README.md diff --git a/clusters/oceanus/README.md b/clusters/oceanus/README.md new file mode 100644 index 0000000..d91b52f --- /dev/null +++ b/clusters/oceanus/README.md @@ -0,0 +1,5 @@ +# Oceanus Cluster Scaffold + +This directory prepares the Flux and Kustomize layout for a future Oceanus-managed cluster. +Populate `flux-system/` with `gotk-components.yaml` and related manifests after running `flux bootstrap`. +Define node-specific resources under `infrastructure/modules/profiles/oceanus-validator/` and reference workloads in `applications/` as they come online. diff --git a/hosts/styx/README.md b/hosts/styx/README.md new file mode 100644 index 0000000..992bac5 --- /dev/null +++ b/hosts/styx/README.md @@ -0,0 +1,2 @@ +# hosts/styx/README.md +Styx is air-gapped; provisioning scripts live under `scripts/`. diff --git a/services/keycloak/README.md b/services/keycloak/README.md new file mode 100644 index 0000000..bf7c21b --- /dev/null +++ b/services/keycloak/README.md @@ -0,0 +1,27 @@ +# services/keycloak + +Keycloak is deployed via raw manifests and backed by the shared Postgres (`postgres-service.postgres.svc.cluster.local:5432`). Create these secrets before applying: + +```bash +# DB creds (per-service DB/user in shared Postgres) +kubectl -n sso create secret generic keycloak-db \ + --from-literal=username=keycloak \ + --from-literal=password='' \ + --from-literal=database=keycloak + +# Admin console creds (maps to KC admin user) +kubectl -n sso create secret generic keycloak-admin \ + --from-literal=username=brad@bstein.dev \ + --from-literal=password='' +``` + +Apply: + +```bash +kubectl apply -k services/keycloak +``` + +Notes +- Service: `keycloak.sso.svc:80` (Ingress `sso.bstein.dev`, TLS via cert-manager). +- Uses Postgres schema `public`; DB/user should be provisioned in the shared Postgres instance. +- Health endpoints on :9000 are wired for probes. diff --git a/services/monitoring/README.md b/services/monitoring/README.md new file mode 100644 index 0000000..835ae1d --- /dev/null +++ b/services/monitoring/README.md @@ -0,0 +1,28 @@ +# services/monitoring + +## Grafana admin secret + +The Grafana Helm release expects a pre-existing secret named `grafana-admin` +in the `monitoring` namespace. Create or rotate it with: + +```bash +kubectl create secret generic grafana-admin \ + --namespace monitoring \ + --from-literal=admin-user=admin \ + --from-literal=admin-password='REPLACE_ME' +``` + +Update the password whenever you rotate credentials. + +## DCGM exporter image + +The NVIDIA GPU metrics DaemonSet expects `registry.bstein.dev/monitoring/dcgm-exporter:4.4.2-4.7.0-ubuntu22.04`, mirrored from `docker.io/nvidia/dcgm-exporter:4.4.2-4.7.0-ubuntu22.04`. Refresh it in Zot when bumping versions: + +```bash +skopeo copy \ + --all \ + docker://docker.io/nvidia/dcgm-exporter:4.4.2-4.7.0-ubuntu22.04 \ + docker://registry.bstein.dev/monitoring/dcgm-exporter:4.4.2-4.7.0-ubuntu22.04 +``` + +When finished mirroring from the control-plane, you can remove temporary tooling with `sudo apt-get purge -y skopeo && sudo apt-get autoremove -y` and clear `~/.config/containers/auth.json`.