mirror of
https://github.com/rubenhensen/k8scd.git
synced 2026-11-15 22:29:09 +01:00
Compare commits
98
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
6cba1a9363 | ||
|
|
acfce6645e | ||
|
|
a15a4f7c75 | ||
|
|
b072099cc1 | ||
|
|
e10ca337f1 | ||
|
|
c72b08867f | ||
|
|
d85362ce3b | ||
|
|
018f528fb3 | ||
|
|
714712b862 | ||
|
|
7dc13466cb | ||
|
|
9b77596bcb | ||
|
|
fbf2cb2d92 | ||
|
|
122873ca5c | ||
|
|
71449dd185 | ||
|
|
297d2dffa5 | ||
|
|
46117ee658 | ||
|
|
2a5bbc7f44 | ||
|
|
d7b0372f1a | ||
|
|
0ad6ca816c | ||
|
|
3e252799a4 | ||
|
|
bfd5619e9e | ||
|
|
0b38d8dec8 | ||
|
|
083353fb9d | ||
|
|
23f9c5c60a | ||
|
|
a8bf3d5b64 | ||
|
|
618954ae2c | ||
|
|
44dc85d306 | ||
|
|
b60735f6b0 | ||
|
|
3a57e5be48 | ||
|
|
1611f5d1ef | ||
|
|
5bb1422594 | ||
|
|
68b692a112 | ||
|
|
72f49bed51 | ||
|
|
f4b42757cd | ||
|
|
f529bd99ee | ||
|
|
74dec430b8 | ||
|
|
6fe0acc061 | ||
|
|
bb34b601d9 | ||
|
|
e98668d5fa | ||
|
|
389f911823 | ||
|
|
8f1c6a5b6e | ||
|
|
770631fdc0 | ||
|
|
855317b84d | ||
|
|
d69f2638d1 | ||
|
|
90e552c9f5 | ||
|
|
ad14995ba0 | ||
|
|
c359384ade | ||
|
|
a4fc386ee8 | ||
|
|
0dc0bc4322 | ||
|
|
d843f31d86 | ||
|
|
da23357946 | ||
|
|
b9d88f41b9 | ||
|
|
3c4a8cc8db | ||
|
|
d17e78130d | ||
|
|
22c5a325d6 | ||
|
|
6b2f5855d7 | ||
|
|
ef07307f93 | ||
|
|
aa940134ea | ||
|
|
f86ed09cd8 | ||
|
|
6d2bc379ba | ||
|
|
c25b8883da | ||
|
|
18f9e2efe6 | ||
|
|
5f5f5b01f0 | ||
|
|
6206ab5a74 | ||
|
|
075b3686c3 | ||
|
|
67c21c30d8 | ||
|
|
0c52d8a467 | ||
|
|
f2e4c5aff6 | ||
|
|
d836e4608c | ||
|
|
1f56e67e8b | ||
|
|
cadac4cebf | ||
|
|
bc71061db7 | ||
|
|
7d3a64e5c8 | ||
|
|
e137e79b75 | ||
|
|
67dc4f0783 | ||
|
|
684f536f2f | ||
|
|
1439466af4 | ||
|
|
57514c3c14 | ||
|
|
57851bf43a | ||
|
|
ada909ee02 | ||
|
|
345de16552 | ||
|
|
7396cc3ed6 | ||
|
|
26ca83457c | ||
|
|
4709194483 | ||
|
|
ad2d6fbae5 | ||
|
|
077711472e | ||
|
|
43f741141d | ||
|
|
cbee4955d3 | ||
|
|
a70dff6fdd | ||
|
|
ab0a09a356 | ||
|
|
b2649a682c | ||
|
|
ce3846bcd3 | ||
|
|
96c13c63f7 | ||
|
|
70151b0ef4 | ||
|
|
f5e8b1e633 | ||
|
|
ae2e5ad9fa | ||
|
|
8cf87483d6 | ||
|
|
45d1ea0d93 |
No files matched your search
@@ -0,0 +1,56 @@
|
||||
# Renders every Argo CD app the way Argo CD does and validates the result
|
||||
# (tools/ci/validate.py), so a broken manifest or a Renovate bump that no
|
||||
# longer renders shows up on the PR instead of in a failed sync.
|
||||
name: validate
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
push:
|
||||
branches: [main]
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
concurrency:
|
||||
group: validate-${{ github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
validate:
|
||||
runs-on: ubuntu-24.04
|
||||
timeout-minutes: 20
|
||||
steps:
|
||||
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Install helm, kustomize and kubeconform
|
||||
env:
|
||||
# Helm 4.2, like Argo CD 3.5.
|
||||
# renovate: datasource=github-releases depName=helm/helm
|
||||
HELM_VERSION: v4.2.1
|
||||
# renovate: datasource=github-releases depName=kubernetes-sigs/kustomize extractVersion=^kustomize/(?<version>.+)$
|
||||
KUSTOMIZE_VERSION: v5.8.3
|
||||
# renovate: datasource=github-releases depName=yannh/kubeconform
|
||||
KUBECONFORM_VERSION: v0.8.0
|
||||
run: |
|
||||
set -euo pipefail
|
||||
cd "$RUNNER_TEMP"
|
||||
curl -sSfLO "https://get.helm.sh/helm-${HELM_VERSION}-linux-amd64.tar.gz"
|
||||
curl -sSfL "https://get.helm.sh/helm-${HELM_VERSION}-linux-amd64.tar.gz.sha256sum" | sha256sum -c -
|
||||
k="https://github.com/kubernetes-sigs/kustomize/releases/download/kustomize%2F${KUSTOMIZE_VERSION}"
|
||||
curl -sSfLO "$k/kustomize_${KUSTOMIZE_VERSION}_linux_amd64.tar.gz"
|
||||
curl -sSfL "$k/checksums.txt" | grep " kustomize_${KUSTOMIZE_VERSION}_linux_amd64.tar.gz$" | sha256sum -c -
|
||||
c="https://github.com/yannh/kubeconform/releases/download/${KUBECONFORM_VERSION}"
|
||||
curl -sSfLO "$c/kubeconform-linux-amd64.tar.gz"
|
||||
curl -sSfL "$c/CHECKSUMS" | grep " kubeconform-linux-amd64.tar.gz$" | sha256sum -c -
|
||||
mkdir -p bin
|
||||
tar xzf "helm-${HELM_VERSION}-linux-amd64.tar.gz" -C bin --strip-components=1 linux-amd64/helm
|
||||
tar xzf "kustomize_${KUSTOMIZE_VERSION}_linux_amd64.tar.gz" -C bin kustomize
|
||||
tar xzf kubeconform-linux-amd64.tar.gz -C bin kubeconform
|
||||
echo "$RUNNER_TEMP/bin" >> "$GITHUB_PATH"
|
||||
pip install --quiet pyyaml==6.0.3
|
||||
|
||||
- name: Render and validate
|
||||
run: python3 tools/ci/validate.py
|
||||
@@ -6,3 +6,4 @@ velero-credentials
|
||||
nix-infra-machine/ssh/
|
||||
nix-infra-machine/.env
|
||||
nix-infra-machine/nix/
|
||||
.DS_Store
|
||||
@@ -0,0 +1,57 @@
|
||||
# Actual faces the internet through Envoy, so its pods only reach each
|
||||
# other, DNS and the internet: not the LAN (NAS, router), the Kubernetes
|
||||
# API or other namespaces.
|
||||
# The OIDC login goes through authentik's public address.
|
||||
# Ingress comes from Envoy and the node itself (kubelet probes; 10.1.7.64
|
||||
# is the node's Calico VXLAN address, projectcalico.org/IPv4VXLANTunnelAddr).
|
||||
# Same layout as mbgwp/networkpolicy.yaml.
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: default
|
||||
spec:
|
||||
podSelector: {}
|
||||
policyTypes:
|
||||
- Ingress
|
||||
- Egress
|
||||
ingress:
|
||||
- from:
|
||||
- podSelector: {}
|
||||
- from:
|
||||
- ipBlock:
|
||||
cidr: 192.168.1.204/32
|
||||
- ipBlock:
|
||||
cidr: 10.1.7.64/32
|
||||
- from:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: envoy-gateway-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: envoy
|
||||
ports:
|
||||
- port: 5006
|
||||
egress:
|
||||
- to:
|
||||
- podSelector: {}
|
||||
- to:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: kube-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
k8s-app: kube-dns
|
||||
ports:
|
||||
- protocol: UDP
|
||||
port: 53
|
||||
- protocol: TCP
|
||||
port: 53
|
||||
- to:
|
||||
- ipBlock:
|
||||
cidr: 0.0.0.0/0
|
||||
except:
|
||||
- 10.0.0.0/8
|
||||
- 100.64.0.0/10
|
||||
- 169.254.0.0/16
|
||||
- 172.16.0.0/12
|
||||
- 192.168.0.0/16
|
||||
@@ -16,7 +16,7 @@ spec:
|
||||
sources:
|
||||
- chart: authentik
|
||||
repoURL: https://charts.goauthentik.io
|
||||
targetRevision: 2026.2.1
|
||||
targetRevision: 2026.8.5
|
||||
helm:
|
||||
values: |
|
||||
authentik:
|
||||
@@ -99,6 +99,10 @@ spec:
|
||||
- name: REQUESTS_CA_BUNDLE
|
||||
value: /etc/ssl/certs/ca-certificates.crt
|
||||
server:
|
||||
resources:
|
||||
requests:
|
||||
cpu: 70m
|
||||
memory: 560Mi
|
||||
volumes:
|
||||
- name: patched-ca-bundle
|
||||
configMap:
|
||||
@@ -184,6 +188,10 @@ spec:
|
||||
mountPath: /etc/ssl/certs
|
||||
readOnly: true
|
||||
worker:
|
||||
resources:
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 336Mi
|
||||
volumes:
|
||||
- name: patched-ca-bundle
|
||||
configMap:
|
||||
@@ -270,12 +278,6 @@ spec:
|
||||
readOnly: true
|
||||
postgresql:
|
||||
enabled: false
|
||||
redis:
|
||||
enabled: true
|
||||
master:
|
||||
persistence:
|
||||
storageClass: longhorn
|
||||
size: 2Gi
|
||||
- repoURL: https://github.com/rubenhensen/k8scd.git
|
||||
targetRevision: HEAD
|
||||
path: authentik
|
||||
|
||||
@@ -12,7 +12,7 @@ spec:
|
||||
project: default
|
||||
source:
|
||||
repoURL: https://charts.jetstack.io
|
||||
targetRevision: v1.21.2
|
||||
targetRevision: v1.21.3
|
||||
chart: cert-manager
|
||||
helm:
|
||||
parameters:
|
||||
@@ -34,6 +34,20 @@ spec:
|
||||
- name: patched-ca-bundle
|
||||
mountPath: /etc/ssl/certs
|
||||
readOnly: true
|
||||
resources:
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 48Mi
|
||||
cainjector:
|
||||
resources:
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 80Mi
|
||||
webhook:
|
||||
resources:
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 32Mi
|
||||
syncPolicy:
|
||||
syncOptions:
|
||||
- CreateNamespace=true
|
||||
|
||||
@@ -24,6 +24,10 @@ spec:
|
||||
additionalArgs:
|
||||
- --leader-lease-duration=60
|
||||
- --leader-renew-deadline=40
|
||||
resources:
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 48Mi
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: cnpg-system
|
||||
|
||||
@@ -17,7 +17,23 @@ spec:
|
||||
sources:
|
||||
- chart: external-secrets
|
||||
repoURL: https://charts.external-secrets.io
|
||||
targetRevision: 2.13.0
|
||||
targetRevision: 2.14.0
|
||||
helm:
|
||||
values: |
|
||||
resources:
|
||||
requests:
|
||||
cpu: 20m
|
||||
memory: 64Mi
|
||||
certController:
|
||||
resources:
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 64Mi
|
||||
webhook:
|
||||
resources:
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 32Mi
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: external-secrets
|
||||
@@ -12,7 +12,7 @@ spec:
|
||||
project: default
|
||||
source:
|
||||
repoURL: https://groundhog2k.github.io/helm-charts/
|
||||
targetRevision: 0.15.0
|
||||
targetRevision: 0.16.7
|
||||
chart: wordpress
|
||||
helm:
|
||||
values: |
|
||||
@@ -101,6 +101,23 @@ spec:
|
||||
timeoutSeconds: 5
|
||||
failureThreshold: 30
|
||||
|
||||
# apache2.conf includes ports.conf after mods-enabled/*.conf, so the
|
||||
# prefork settings here replace mpm_prefork.conf's MaxRequestWorkers
|
||||
# 150. A worker takes ~45-60 MB (PSS), so 150 never fit in 1Gi: a
|
||||
# crawler asking for 88 pages at once got the container OOMKilled on
|
||||
# 2026-10-25. With 12 workers a burst waits in the listen backlog
|
||||
# instead. Listen is the chart's default (containerPort).
|
||||
apachePortsConfig: |
|
||||
Listen 8000
|
||||
<IfModule mpm_prefork_module>
|
||||
StartServers 4
|
||||
MinSpareServers 2
|
||||
MaxSpareServers 6
|
||||
ServerLimit 12
|
||||
MaxRequestWorkers 12
|
||||
MaxConnectionsPerChild 1000
|
||||
</IfModule>
|
||||
|
||||
# Custom PHP configuration
|
||||
customPhpConfig: |
|
||||
upload_max_filesize = 64M
|
||||
|
||||
@@ -0,0 +1,34 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: metrics-server
|
||||
namespace: argocd
|
||||
finalizers:
|
||||
- resources-finalizer.argocd.argoproj.io
|
||||
spec:
|
||||
project: default
|
||||
source:
|
||||
chart: metrics-server
|
||||
repoURL: https://kubernetes-sigs.github.io/metrics-server/
|
||||
targetRevision: 3.14.0
|
||||
helm:
|
||||
values: |
|
||||
# Resource usage for kubectl top and for sizing requests and limits.
|
||||
# It keeps everything in memory, so it adds no writes to the SSD.
|
||||
args:
|
||||
# microk8s's kubelet serves a self-signed certificate; its own
|
||||
# metrics-server addon passes the same flag.
|
||||
- --kubelet-insecure-tls
|
||||
resources:
|
||||
requests:
|
||||
cpu: 20m
|
||||
memory: 64Mi
|
||||
limits:
|
||||
memory: 256Mi
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: kube-system
|
||||
syncPolicy:
|
||||
automated:
|
||||
prune: true
|
||||
selfHeal: true
|
||||
@@ -1,21 +0,0 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: secrets-folder
|
||||
namespace: argocd
|
||||
finalizers:
|
||||
- resources-finalizer.argocd.argoproj.io
|
||||
spec:
|
||||
project: default
|
||||
source:
|
||||
repoURL: https://github.com/rubenhensen/k8scd.git
|
||||
targetRevision: HEAD
|
||||
path: secrets
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: secrets
|
||||
syncPolicy:
|
||||
syncOptions:
|
||||
- CreateNamespace=true
|
||||
automated:
|
||||
selfHeal: true
|
||||
@@ -7,7 +7,7 @@ spec:
|
||||
project: default
|
||||
source:
|
||||
repoURL: https://github.com/kubernetes-csi/external-snapshotter.git
|
||||
targetRevision: v8.2.1
|
||||
targetRevision: v8.7.0
|
||||
path: deploy/kubernetes/snapshot-controller
|
||||
kustomize:
|
||||
patches:
|
||||
@@ -30,10 +30,8 @@ spec:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: kube-system
|
||||
syncPolicy:
|
||||
# Was listed twice, with and without prune; Argo CD kept the last one.
|
||||
automated:
|
||||
selfHeal: true
|
||||
prune: true
|
||||
syncOptions:
|
||||
- CreateNamespace=true
|
||||
automated:
|
||||
selfHeal: true
|
||||
@@ -21,4 +21,5 @@ patches:
|
||||
- path: overlays/argocd-cm.patch.yaml
|
||||
- path: overlays/argocd-rbac-cm.patch.yaml
|
||||
- path: overlays/argocd-cmd-params-cm.patch.yaml
|
||||
- path: overlays/patched-ca-bundle.patch.yaml
|
||||
- path: overlays/patched-ca-bundle.patch.yaml
|
||||
- path: overlays/resources.patch.yaml
|
||||
@@ -0,0 +1,100 @@
|
||||
# Requests from what the components used on 2026-10-25 (kubectl top every
|
||||
# 5 minutes; highest value plus 10%). No limits until there are daytime
|
||||
# numbers, see docs/roadmap.md.
|
||||
apiVersion: apps/v1
|
||||
kind: StatefulSet
|
||||
metadata:
|
||||
name: argocd-application-controller
|
||||
spec:
|
||||
template:
|
||||
spec:
|
||||
containers:
|
||||
- name: argocd-application-controller
|
||||
resources:
|
||||
requests:
|
||||
cpu: 150m
|
||||
memory: 704Mi
|
||||
---
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: argocd-repo-server
|
||||
spec:
|
||||
template:
|
||||
spec:
|
||||
containers:
|
||||
- name: argocd-repo-server
|
||||
resources:
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 128Mi
|
||||
---
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: argocd-server
|
||||
spec:
|
||||
template:
|
||||
spec:
|
||||
containers:
|
||||
- name: argocd-server
|
||||
resources:
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 64Mi
|
||||
---
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: argocd-redis
|
||||
spec:
|
||||
template:
|
||||
spec:
|
||||
containers:
|
||||
- name: redis
|
||||
resources:
|
||||
requests:
|
||||
cpu: 20m
|
||||
memory: 96Mi
|
||||
---
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: argocd-applicationset-controller
|
||||
spec:
|
||||
template:
|
||||
spec:
|
||||
containers:
|
||||
- name: argocd-applicationset-controller
|
||||
resources:
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 48Mi
|
||||
---
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: argocd-notifications-controller
|
||||
spec:
|
||||
template:
|
||||
spec:
|
||||
containers:
|
||||
- name: argocd-notifications-controller
|
||||
resources:
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 48Mi
|
||||
---
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: argocd-dex-server
|
||||
spec:
|
||||
template:
|
||||
spec:
|
||||
containers:
|
||||
- name: dex
|
||||
resources:
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 32Mi
|
||||
+26
-3
@@ -14,7 +14,11 @@ Authentik is deployed as the central identity provider, providing OIDC and LDAP
|
||||
- `blueprint-argocd-oidc.yaml` — OIDC provider for ArgoCD
|
||||
- `blueprint-freshrss-oidc.yaml` — OIDC provider for FreshRSS
|
||||
- `blueprint-actualbudget-proxy.yaml` — Proxy provider for Actual Budget
|
||||
- `blueprint-longhorn-oidc.yaml` — OIDC provider for Longhorn (Envoy Gateway SecurityPolicy)
|
||||
- `blueprint-scouting.yaml` — immich's login with Scouts Online, see docs/immich-scouts-online.md
|
||||
- `blueprint-session-duration.yaml` — Session lifetime of the default authentication flow
|
||||
- **NetworkPolicies** (`networkpolicy.yaml`) — the pods reach each other, DNS and the internet,
|
||||
not the LAN or other namespaces; the worker and the database also reach the API server
|
||||
|
||||
## Session lifetime
|
||||
|
||||
@@ -30,9 +34,23 @@ Apache mod_auth_openidc refreshes on every request.
|
||||
|
||||
## LDAP Outpost
|
||||
|
||||
The LDAP outpost exposes Authentik's user directory over LDAP. It is used by:
|
||||
- **SOGo-mail** (in-cluster) — connects via `ak-outpost-ldap-outpost.authentik.svc.cluster.local:3389`
|
||||
- **Stalwart** (NixOS, external) — connects via `ldap.rubenhensen.nl:389`
|
||||
The LDAP outpost exposes Authentik's user directory over LDAP. It is used by
|
||||
**Stalwart** (NixOS on node001), which connects via `ldap.rubenhensen.nl:389`.
|
||||
The outpost itself talks to the server through `https://authentik.rubenhensen.nl/`.
|
||||
|
||||
Authentik's worker deploys the outpost and keeps its version equal to the
|
||||
server's. After the upgrades to 2026.5 and 2026.8 it didn't follow on its
|
||||
own; this rolls it over:
|
||||
|
||||
```bash
|
||||
kubectl -n authentik exec deploy/authentik-worker -- ak shell -c '
|
||||
from authentik.outposts.models import Outpost
|
||||
from authentik.outposts.tasks import outpost_controller
|
||||
outpost_controller.send(Outpost.objects.get(name="LDAP outpost").pk)'
|
||||
```
|
||||
|
||||
Upgrades go one release at a time (2026.2 → 2026.5 → 2026.8); since 2026.8
|
||||
authentik refuses to skip one.
|
||||
|
||||
### NodePort Service
|
||||
|
||||
@@ -87,3 +105,8 @@ microk8s config > ~/.kube/config
|
||||
```
|
||||
|
||||
**Note:** This must be re-applied after MicroK8s upgrades or cert rotations, as MicroK8s may regenerate the CA without the extension. The fix needs to run on every node in the cluster.
|
||||
|
||||
Checked 2026-10-25: the CA from this fix (`CN=microk8s-ca`, 2026-03-21, valid
|
||||
until 2036) still has the extension after the refreshes to 1.34, 1.35 and
|
||||
1.36. Check with
|
||||
`openssl x509 -in /var/snap/microk8s/current/certs/ca.crt -noout -ext keyUsage`.
|
||||
@@ -94,6 +94,16 @@ data:
|
||||
target: !KeyOf immich-app
|
||||
attrs:
|
||||
group: !KeyOf mbg-leden
|
||||
# auth.scoutingmbg.nl: straight to Scouts Online, then on to the
|
||||
# photos. Other domains keep the default brand.
|
||||
- model: authentik_brands.brand
|
||||
state: present
|
||||
identifiers:
|
||||
domain: auth.scoutingmbg.nl
|
||||
attrs:
|
||||
branding_title: Scouting MBG
|
||||
flow_authentication: !Find [authentik_flows.flow, [slug, scouts-online-login]]
|
||||
default_application: !KeyOf immich-app
|
||||
- model: authentik_policies.policybinding
|
||||
state: present
|
||||
identifiers:
|
||||
@@ -220,7 +230,8 @@ data:
|
||||
policy: !KeyOf sso-only
|
||||
# SOL only lets in members of the organisations picked in its
|
||||
# connection, and only sends roles within them. The callback URL is
|
||||
# https://authentik.rubenhensen.nl/source/oauth/callback/scouts-online/
|
||||
# https://auth.scoutingmbg.nl/source/oauth/callback/scouts-online/ (and
|
||||
# authentik.rubenhensen.nl, from before auth.scoutingmbg.nl existed)
|
||||
- model: authentik_sources_oauth.oauthsource
|
||||
id: source
|
||||
state: present
|
||||
|
||||
@@ -14,3 +14,20 @@ spec:
|
||||
usages:
|
||||
- digital signature
|
||||
- key encipherment
|
||||
---
|
||||
# The login of the Scouting MBG photos (immich), see blueprint-scouting.yaml.
|
||||
apiVersion: cert-manager.io/v1
|
||||
kind: Certificate
|
||||
metadata:
|
||||
name: auth-scoutingmbg-tls
|
||||
spec:
|
||||
secretName: auth-scoutingmbg-tls
|
||||
dnsNames:
|
||||
- auth.scoutingmbg.nl
|
||||
issuerRef:
|
||||
group: cert-manager.io
|
||||
kind: ClusterIssuer
|
||||
name: prod-cluster-issuer
|
||||
usages:
|
||||
- digital signature
|
||||
- key encipherment
|
||||
@@ -7,8 +7,12 @@ spec:
|
||||
- name: homelab
|
||||
namespace: envoy-gateway-system
|
||||
sectionName: https-authentik
|
||||
- name: homelab
|
||||
namespace: envoy-gateway-system
|
||||
sectionName: https-auth-scoutingmbg
|
||||
hostnames:
|
||||
- authentik.rubenhensen.nl
|
||||
- auth.scoutingmbg.nl
|
||||
rules:
|
||||
- backendRefs:
|
||||
- name: authentik-server
|
||||
@@ -32,3 +36,6 @@ spec:
|
||||
- group: ""
|
||||
kind: Secret
|
||||
name: authentik-tls
|
||||
- group: ""
|
||||
kind: Secret
|
||||
name: auth-scoutingmbg-tls
|
||||
@@ -0,0 +1,137 @@
|
||||
# authentik faces the internet (the login for every member of the group),
|
||||
# so its pods only reach each other, DNS and the internet: not the LAN
|
||||
# (NAS, router) or other namespaces. Scouts Online, the apps' OIDC calls
|
||||
# and the LDAP outpost's connection to the server all use public
|
||||
# addresses. The worker and the CNPG instance manager also reach the API
|
||||
# server (the node, port 16443). Ingress comes from Envoy, the CNPG
|
||||
# operator, the node itself (kubelet probes; 10.1.7.64 is the node's
|
||||
# Calico VXLAN address, projectcalico.org/IPv4VXLANTunnelAddr), and for
|
||||
# the LDAP outpost from anywhere: Stalwart on node001 comes in through the
|
||||
# router and the ldap-outpost-external NodePort.
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: default
|
||||
spec:
|
||||
podSelector: {}
|
||||
policyTypes:
|
||||
- Ingress
|
||||
- Egress
|
||||
ingress:
|
||||
- from:
|
||||
- podSelector: {}
|
||||
- from:
|
||||
- ipBlock:
|
||||
cidr: 192.168.1.204/32
|
||||
- ipBlock:
|
||||
cidr: 10.1.7.64/32
|
||||
egress:
|
||||
- to:
|
||||
- podSelector: {}
|
||||
- to:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: kube-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
k8s-app: kube-dns
|
||||
ports:
|
||||
- protocol: UDP
|
||||
port: 53
|
||||
- protocol: TCP
|
||||
port: 53
|
||||
- to:
|
||||
- ipBlock:
|
||||
cidr: 0.0.0.0/0
|
||||
except:
|
||||
- 10.0.0.0/8
|
||||
- 100.64.0.0/10
|
||||
- 169.254.0.0/16
|
||||
- 172.16.0.0/12
|
||||
- 192.168.0.0/16
|
||||
---
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: server-from-envoy
|
||||
spec:
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: authentik
|
||||
app.kubernetes.io/component: server
|
||||
policyTypes:
|
||||
- Ingress
|
||||
ingress:
|
||||
- from:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: envoy-gateway-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: envoy
|
||||
ports:
|
||||
- port: 9000
|
||||
---
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: ldap-outpost
|
||||
spec:
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: authentik-outpost-ldap
|
||||
policyTypes:
|
||||
- Ingress
|
||||
ingress:
|
||||
- ports:
|
||||
- port: 3389
|
||||
- port: 6636
|
||||
---
|
||||
# The outpost controller deploys and updates the LDAP outpost.
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: worker-to-api
|
||||
spec:
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: authentik
|
||||
app.kubernetes.io/component: worker
|
||||
policyTypes:
|
||||
- Egress
|
||||
egress:
|
||||
- to:
|
||||
- ipBlock:
|
||||
cidr: 192.168.1.204/32
|
||||
ports:
|
||||
- port: 16443
|
||||
---
|
||||
# The CNPG operator checks each instance on its status port and connects to
|
||||
# PostgreSQL; the instance manager inside each pod watches its Cluster
|
||||
# through the API server.
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: postgres-cnpg
|
||||
spec:
|
||||
podSelector:
|
||||
matchExpressions:
|
||||
- key: cnpg.io/cluster
|
||||
operator: Exists
|
||||
policyTypes:
|
||||
- Ingress
|
||||
- Egress
|
||||
ingress:
|
||||
- from:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: cnpg-system
|
||||
ports:
|
||||
- port: 8000
|
||||
- port: 5432
|
||||
egress:
|
||||
- to:
|
||||
- ipBlock:
|
||||
cidr: 192.168.1.204/32
|
||||
ports:
|
||||
- port: 16443
|
||||
@@ -8,6 +8,10 @@ spec:
|
||||
# start an in-place major upgrade. CNPG filled this in at creation.
|
||||
imageName: ghcr.io/cloudnative-pg/postgresql:17.4
|
||||
primaryUpdateStrategy: unsupervised
|
||||
resources:
|
||||
requests:
|
||||
cpu: 50m
|
||||
memory: 256Mi
|
||||
bootstrap:
|
||||
initdb:
|
||||
database: authentik
|
||||
|
||||
@@ -1,5 +1,19 @@
|
||||
# Velero Backup Testing Guide
|
||||
|
||||
**Use `restore-test.sh`.** It restores a few namespaces from a real backup
|
||||
into a throwaway k3s in Docker, from a read-only copy of the bucket, and
|
||||
checks that every volume comes back with the bytes it was backed up with:
|
||||
|
||||
```bash
|
||||
backup-testing/restore-test.sh # newest daily backup; ntfy, freshrss, actual-budget
|
||||
backup-testing/restore-test.sh <backup> <namespace>... # something else
|
||||
```
|
||||
|
||||
How it works and why it copies instead of pointing Velero at the NAS is at
|
||||
the top of the script. The rest of this README describes the older k3d
|
||||
scripts, which predate Envoy Gateway and still expect `*.hensen.io` and
|
||||
sol-auth.
|
||||
|
||||
This guide explains how to test your Velero backups using a temporary K3d cluster.
|
||||
|
||||
## Features
|
||||
|
||||
Executable
+222
@@ -0,0 +1,222 @@
|
||||
#!/bin/bash
|
||||
# Restore a few namespaces from the real Velero backups into a throwaway
|
||||
# k3s in Docker, to prove the backups can be restored. Nothing on the NAS
|
||||
# changes:
|
||||
# - one backup (backups/<name>/) and the kopia repositories of the chosen
|
||||
# namespaces (kopia/<namespace>/) are copied read-only from MinIO with
|
||||
# rclone into a Docker volume. A second Velero on the real bucket could
|
||||
# run kopia maintenance on the same repositories as the cluster's own
|
||||
# - `rclone serve s3` serves that copy to a Velero 1.18.2 in k3s, with a
|
||||
# ReadOnly backup storage location
|
||||
# - storage class longhorn becomes local-path; only core workload
|
||||
# resources are restored (no routes, certificates, ExternalSecrets or
|
||||
# NetworkPolicies)
|
||||
# - every pod volume restore has to complete with as many bytes as its
|
||||
# backup had, and the restored deployments have to become available
|
||||
#
|
||||
# Usage (on a machine with docker, kubectl and jq):
|
||||
# backup-testing/restore-test.sh [backup] [namespace ...]
|
||||
# Defaults: the newest Completed daily-backup, and ntfy freshrss
|
||||
# actual-budget. Not gatus: a restored Gatus would start sending alerts.
|
||||
#
|
||||
# It reads Velero's MinIO key from the cluster (velero/cloud-credentials)
|
||||
# into a temporary directory, and the copied backup holds every Secret of
|
||||
# the cluster; all of it is deleted at the end. KEEP=1 keeps the test
|
||||
# cluster (kubeconfig in the printed directory) until you run it with
|
||||
# CLEANUP=1. FROM_VOLUME=<docker volume> takes the bucket from a volume
|
||||
# instead of the NAS (for rehearsals; laid out as <bucket>/backups/...).
|
||||
#
|
||||
# Rehearsed on 2026-10-25 against a backup made in the test cluster itself,
|
||||
# which is how two pitfalls showed up: Velero skips hostPath volumes, and
|
||||
# k3s only provisions local PVs (which it can back up and restore) for a
|
||||
# storage class with the annotation defaultVolumeType: local.
|
||||
set -euo pipefail
|
||||
|
||||
PROD_KUBECONFIG=${PROD_KUBECONFIG:-$HOME/.kube/homelab-config}
|
||||
PORT=${PORT:-16443}
|
||||
K3S=rancher/k3s:v1.34.9-k3s1
|
||||
RCLONE=rclone/rclone:1.75.1
|
||||
HELM=alpine/helm:3.19.0
|
||||
VELERO_CHART=12.2.1
|
||||
AWS_PLUGIN=velero/velero-plugin-for-aws:v1.14.4
|
||||
NET=restore-test VOL=restore-test-s3
|
||||
|
||||
cleanup() {
|
||||
docker rm -f -v restore-k3s restore-s3 >/dev/null 2>&1 || true
|
||||
docker volume rm "$VOL" >/dev/null 2>&1 || true
|
||||
docker network rm "$NET" >/dev/null 2>&1 || true
|
||||
[[ -n ${WORK:-} ]] && rm -rf "$WORK"
|
||||
}
|
||||
if [[ ${CLEANUP:-} == 1 ]]; then
|
||||
cleanup; rm -rf "${TMPDIR:-/tmp}"/restore-test.*; echo "cleaned up"; exit 0
|
||||
fi
|
||||
if docker ps -a --format '{{.Names}}' | grep -qx restore-k3s; then
|
||||
echo "A test cluster from an earlier run exists; run with CLEANUP=1 first." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
WORK=$(mktemp -d "${TMPDIR:-/tmp}/restore-test.XXXXXX")
|
||||
chmod 700 "$WORK"
|
||||
[[ ${KEEP:-} == 1 ]] || trap cleanup EXIT
|
||||
|
||||
pk() { kubectl --kubeconfig "$PROD_KUBECONFIG" "$@"; }
|
||||
tk() { kubectl --kubeconfig "$WORK/kubeconfig" "$@"; }
|
||||
# wait_for <seconds> <what> <command...>
|
||||
wait_for() {
|
||||
local limit=$1 what=$2; shift 2
|
||||
local end=$((SECONDS + limit))
|
||||
until "$@" >/dev/null 2>&1; do
|
||||
if ((SECONDS > end)); then echo "timed out waiting for $what" >&2; exit 1; fi
|
||||
sleep 5
|
||||
done
|
||||
}
|
||||
|
||||
# Endpoint, region and bucket as Velero itself uses them. MinIO answers a
|
||||
# request signed for the wrong region (rclone defaults to us-east-1) with a
|
||||
# bare 400 on HEAD.
|
||||
if [[ -n ${FROM_VOLUME:-} ]]; then
|
||||
BUCKET=${BUCKET:-velero-backups}
|
||||
else
|
||||
bsl=$(pk -n velero get backupstoragelocations default -o json)
|
||||
MINIO=${MINIO:-$(jq -r '.spec.config.s3Url' <<<"$bsl")}
|
||||
REGION=${REGION:-$(jq -r '.spec.config.region // "us-east-1"' <<<"$bsl")}
|
||||
BUCKET=${BUCKET:-$(jq -r '.spec.objectStorage.bucket' <<<"$bsl")}
|
||||
fi
|
||||
|
||||
backup=${1:-}
|
||||
shift || true
|
||||
namespaces=("$@")
|
||||
[[ ${#namespaces[@]} -gt 0 ]] || namespaces=(ntfy freshrss actual-budget)
|
||||
if [[ -z $backup ]]; then
|
||||
backup=$(pk -n velero get backups.velero.io -o json | jq -r '[.items[]
|
||||
| select(.metadata.labels["velero.io/schedule-name"] == "daily-backup" and .status.phase == "Completed")]
|
||||
| max_by(.status.startTimestamp).metadata.name')
|
||||
fi
|
||||
echo "== backup $backup, namespaces: ${namespaces[*]}"
|
||||
|
||||
docker network create "$NET" >/dev/null
|
||||
docker volume create "$VOL" >/dev/null
|
||||
if [[ -n ${FROM_VOLUME:-} ]]; then
|
||||
echo "== copy from the volume $FROM_VOLUME"
|
||||
docker run --rm -v "$FROM_VOLUME:/from:ro" -v "$VOL:/data" alpine:3.22 cp -a /from/. /data/
|
||||
else
|
||||
echo "== copy from the NAS (read-only)"
|
||||
(umask 077; pk -n velero get secret cloud-credentials -o jsonpath='{.data.cloud}' | base64 -d |
|
||||
awk -F' *= *' '/aws_access_key_id/ {print "RCLONE_CONFIG_NAS_ACCESS_KEY_ID="$2}
|
||||
/aws_secret_access_key/ {print "RCLONE_CONFIG_NAS_SECRET_ACCESS_KEY="$2}' > "$WORK/nas.env"
|
||||
printf 'RCLONE_CONFIG_NAS_TYPE=s3\nRCLONE_CONFIG_NAS_PROVIDER=Minio\nRCLONE_CONFIG_NAS_ENDPOINT=%s\nRCLONE_CONFIG_NAS_REGION=%s\n' "$MINIO" "$REGION" >> "$WORK/nas.env")
|
||||
copy() { docker run --rm --env-file "$WORK/nas.env" -v "$VOL:/data" "$RCLONE" copy --stats-one-line "nas:$BUCKET/$1" "/data/$BUCKET/$1"; }
|
||||
copy "backups/$backup"
|
||||
for ns in "${namespaces[@]}"; do copy "kopia/$ns"; done
|
||||
rm -f "$WORK/nas.env"
|
||||
fi
|
||||
|
||||
echo "== local S3 and k3s"
|
||||
docker run -d --name restore-s3 --network "$NET" -v "$VOL:/data" "$RCLONE" \
|
||||
serve s3 /data --addr :8080 --auth-key test,restore-test-secret >/dev/null
|
||||
s3ip=$(docker inspect -f "{{(index .NetworkSettings.Networks \"$NET\").IPAddress}}" restore-s3)
|
||||
docker run -d --name restore-k3s --privileged --network "$NET" -p "127.0.0.1:$PORT:6443" "$K3S" \
|
||||
server --disable traefik --disable metrics-server --tls-san 127.0.0.1 --tls-san restore-k3s >/dev/null
|
||||
node_ready() { docker exec restore-k3s kubectl get nodes 2>/dev/null | grep -q ' Ready'; }
|
||||
wait_for 180 "k3s" node_ready
|
||||
docker exec restore-k3s cat /etc/rancher/k3s/k3s.yaml | sed "s#https://127.0.0.1:6443#https://127.0.0.1:$PORT#" > "$WORK/kubeconfig"
|
||||
docker exec restore-k3s cat /etc/rancher/k3s/k3s.yaml | sed 's#https://127.0.0.1:6443#https://restore-k3s:6443#' > "$WORK/kubeconfig-net"
|
||||
|
||||
echo "== Velero"
|
||||
cat > "$WORK/values.yaml" <<EOF
|
||||
configuration:
|
||||
backupStorageLocation:
|
||||
- name: default
|
||||
provider: aws
|
||||
bucket: $BUCKET
|
||||
accessMode: ReadOnly
|
||||
config:
|
||||
region: minio
|
||||
s3ForcePathStyle: "true"
|
||||
s3Url: http://$s3ip:8080
|
||||
volumeSnapshotLocation: []
|
||||
defaultRepoMaintainFrequency: 8760h
|
||||
credentials:
|
||||
secretContents:
|
||||
cloud: |
|
||||
[default]
|
||||
aws_access_key_id=test
|
||||
aws_secret_access_key=restore-test-secret
|
||||
initContainers:
|
||||
- name: velero-plugin-for-aws
|
||||
image: $AWS_PLUGIN
|
||||
volumeMounts:
|
||||
- mountPath: /target
|
||||
name: plugins
|
||||
deployNodeAgent: true
|
||||
snapshotsEnabled: false
|
||||
upgradeCRDs: false
|
||||
EOF
|
||||
docker run --rm --network "$NET" -e HOME=/tmp -e KC="$(base64 < "$WORK/kubeconfig-net")" \
|
||||
-e VALUES="$(base64 < "$WORK/values.yaml")" --entrypoint sh "$HELM" -c '
|
||||
echo "$KC" | base64 -d > /tmp/kc && echo "$VALUES" | base64 -d > /tmp/v.yaml &&
|
||||
helm --kubeconfig /tmp/kc install velero velero --repo https://vmware-tanzu.github.io/helm-charts \
|
||||
--version '"$VELERO_CHART"' -n velero --create-namespace -f /tmp/v.yaml >/dev/null'
|
||||
tk apply -f - >/dev/null <<EOF
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: change-storage-class
|
||||
namespace: velero
|
||||
labels:
|
||||
velero.io/plugin-config: ""
|
||||
velero.io/change-storage-class: RestoreItemAction
|
||||
data:
|
||||
longhorn: local-path
|
||||
EOF
|
||||
wait_for 300 "Velero to sync $backup" tk -n velero get backups.velero.io "$backup"
|
||||
echo " Velero sees $backup"
|
||||
|
||||
echo "== restore"
|
||||
tk apply -f - >/dev/null <<EOF
|
||||
apiVersion: velero.io/v1
|
||||
kind: Restore
|
||||
metadata:
|
||||
name: restore-test
|
||||
namespace: velero
|
||||
spec:
|
||||
backupName: $backup
|
||||
includedNamespaces: [$(IFS=,; echo "${namespaces[*]}")]
|
||||
# PersistentVolumes have to be included: only then does Velero clear the
|
||||
# PVC's volumeName. It doesn't restore a PV whose data comes from kopia;
|
||||
# k3s provisions a new one.
|
||||
includedResources: [namespaces, persistentvolumeclaims, persistentvolumes, pods, deployments,
|
||||
replicasets, statefulsets, services, configmaps, secrets, serviceaccounts]
|
||||
restorePVs: true
|
||||
EOF
|
||||
restore_done() { [[ $(tk -n velero get restore restore-test -o jsonpath='{.status.phase}') =~ ^(Completed|PartiallyFailed|Failed|FailedValidation)$ ]]; }
|
||||
wait_for 1800 "the restore" restore_done
|
||||
phase=$(tk -n velero get restore restore-test -o jsonpath='{.status.phase}')
|
||||
echo " restore: $phase"
|
||||
|
||||
echo "== check"
|
||||
failed=0
|
||||
expected=$(docker run --rm -v "$VOL:/data" alpine:3.22 zcat "/data/$BUCKET/backups/$backup/$backup-podvolumebackups.json.gz" |
|
||||
jq -r --arg ns "$(IFS=,; echo "${namespaces[*]}")" '.[] | select(.spec.pod.namespace as $p | $ns | split(",") | index($p))
|
||||
| "\(.spec.pod.namespace)/\(.spec.volume) \(.status.progress.totalBytes // 0)"' | sort -u)
|
||||
restored=$(tk -n velero get podvolumerestores.velero.io -o json |
|
||||
jq -r '.items[] | "\(.spec.pod.namespace)/\(.spec.volume) \(.status.progress.totalBytes // 0) \(.status.phase)"' | sort -u)
|
||||
while read -r vol bytes; do
|
||||
[[ -z $vol ]] && continue
|
||||
got=$(awk -v v="$vol" '$1 == v {print $2, $3}' <<<"$restored")
|
||||
if [[ $got == "$bytes Completed" ]]; then
|
||||
echo " ok $vol ($bytes bytes)"
|
||||
else
|
||||
echo " FAILED $vol: backed up $bytes bytes, restore: ${got:-none}"; failed=1
|
||||
fi
|
||||
done <<<"$expected"
|
||||
for ns in "${namespaces[@]}"; do
|
||||
if tk -n "$ns" wait --for=condition=Available deployment --all --timeout=300s >/dev/null 2>&1; then
|
||||
echo " ok $ns: deployments available"
|
||||
else
|
||||
echo " FAILED $ns: deployments not available"; tk -n "$ns" get pods; failed=1
|
||||
fi
|
||||
done
|
||||
[[ $phase == Completed ]] || failed=1
|
||||
[[ ${KEEP:-} == 1 ]] && echo "Kept; kubeconfig: $WORK/kubeconfig. Remove with CLEANUP=1 $0"
|
||||
if [[ $failed == 0 ]]; then echo "== restore test passed"; else echo "== restore test FAILED"; exit 1; fi
|
||||
@@ -1,381 +0,0 @@
|
||||
#!/bin/bash
|
||||
# test-velero-backup.sh - Automated script to test Velero backups
|
||||
|
||||
set -e
|
||||
|
||||
# Configuration - customize these variables
|
||||
BACKUP_NAME="" # Will list backups if empty
|
||||
S3_BUCKET="velero-backups"
|
||||
S3_REGION="minio"
|
||||
S3_URL="http://192.168.1.99:9000" # Your NAS MinIO server
|
||||
S3_ACCESS_KEY="" # Will be filled from credentials
|
||||
S3_SECRET_KEY="" # Will be filled from credentials
|
||||
ORIGINAL_NAMESPACE="" # Namespace in the original backup
|
||||
TEST_NAMESPACE="default"
|
||||
DEBUG=false # Set to true for verbose debugging
|
||||
|
||||
# Parse command line arguments
|
||||
while [[ $# -gt 0 ]]; do
|
||||
case $1 in
|
||||
--backup-name)
|
||||
BACKUP_NAME="$2"
|
||||
shift 2
|
||||
;;
|
||||
--s3-access-key)
|
||||
S3_ACCESS_KEY="$2"
|
||||
shift 2
|
||||
;;
|
||||
--s3-secret-key)
|
||||
S3_SECRET_KEY="$2"
|
||||
shift 2
|
||||
;;
|
||||
--s3-bucket)
|
||||
S3_BUCKET="$2"
|
||||
shift 2
|
||||
;;
|
||||
--s3-region)
|
||||
S3_REGION="$2"
|
||||
shift 2
|
||||
;;
|
||||
--s3-url)
|
||||
S3_URL="$2"
|
||||
shift 2
|
||||
;;
|
||||
--original-namespace)
|
||||
ORIGINAL_NAMESPACE="$2"
|
||||
shift 2
|
||||
;;
|
||||
--test-namespace)
|
||||
TEST_NAMESPACE="$2"
|
||||
shift 2
|
||||
;;
|
||||
--debug)
|
||||
DEBUG=true
|
||||
shift
|
||||
;;
|
||||
--help)
|
||||
echo "Usage: $0 [options]"
|
||||
echo "Options:"
|
||||
echo " --backup-name NAME Name of the Velero backup to restore"
|
||||
echo " --s3-bucket BUCKET S3 bucket containing backups"
|
||||
echo " --s3-region REGION S3 region"
|
||||
echo " --s3-url URL S3 endpoint URL"
|
||||
echo " --s3-access-key KEY S3 access key"
|
||||
echo " --s3-secret-key KEY S3 secret key"
|
||||
echo " --original-namespace NS Namespace in the original backup"
|
||||
echo " --test-namespace NS Namespace for restoration (default: default)"
|
||||
echo " --debug Enable debug output"
|
||||
echo " --help Show this help message"
|
||||
exit 0
|
||||
;;
|
||||
*)
|
||||
echo "Unknown option: $1"
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
done
|
||||
|
||||
# Verify required variables
|
||||
if [[ -z "$S3_BUCKET" || -z "$S3_REGION" || -z "$S3_ACCESS_KEY" || -z "$S3_SECRET_KEY" || -z "$ORIGINAL_NAMESPACE" || -z "$TEST_NAMESPACE" ]]; then
|
||||
echo "Error: S3 configuration is incomplete"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Function to clean up resources
|
||||
cleanup() {
|
||||
echo "Cleaning up resources..."
|
||||
k3d cluster delete backup-test || true
|
||||
echo "Cleanup complete"
|
||||
}
|
||||
|
||||
# Function for debugging output
|
||||
debug() {
|
||||
if [[ "$DEBUG" == "true" ]]; then
|
||||
echo "[DEBUG] $*"
|
||||
fi
|
||||
}
|
||||
|
||||
# Register cleanup function to run on exit (ctrl+c, etc.)
|
||||
trap cleanup EXIT
|
||||
|
||||
echo "=== Starting Velero backup test process ==="
|
||||
|
||||
# 1. Create K3d cluster
|
||||
echo "Creating K3d cluster..."
|
||||
k3d cluster create backup-test \
|
||||
--api-port 6443 \
|
||||
--port "80:80@loadbalancer" \
|
||||
--port "443:443@loadbalancer" \
|
||||
--agents 0 \
|
||||
--k3s-arg "--disable=traefik@server:0" \
|
||||
--wait
|
||||
# -v /mnt/longhorn:/var/lib/longhorn:shared@all \
|
||||
# -i hebury/k3s:v1.32.2-k3s1 \
|
||||
# --wait
|
||||
|
||||
# Verify cluster is running
|
||||
kubectl config use-context k3d-backup-test
|
||||
kubectl get nodes
|
||||
|
||||
# 2. Install Longhorn
|
||||
# echo "Installing Longhorn..."
|
||||
# kubectl create namespace longhorn-system
|
||||
|
||||
# helm repo add longhorn https://charts.longhorn.io
|
||||
# helm repo update
|
||||
|
||||
# helm install longhorn longhorn/longhorn \
|
||||
# --namespace longhorn-system \
|
||||
# --set persistence.defaultClassReplicaCount=1 \
|
||||
# --set defaultSettings.backupTarget="" \
|
||||
# --set defaultSettings.defaultReplicaCount=1
|
||||
|
||||
# echo "Waiting for Longhorn to be ready..."
|
||||
# kubectl -n longhorn-system rollout status deployment/longhorn-ui
|
||||
# kubectl -n longhorn-system rollout status deployment/longhorn-driver-deployer
|
||||
# kubectl -n longhorn-system rollout status daemonset/longhorn-manager
|
||||
|
||||
# 3. Install Velero with S3 provider
|
||||
echo "Installing Velero..."
|
||||
cat > velero-credentials <<EOF
|
||||
[default]
|
||||
aws_access_key_id=$S3_ACCESS_KEY
|
||||
aws_secret_access_key=$S3_SECRET_KEY
|
||||
EOF
|
||||
|
||||
helm repo add vmware-tanzu https://vmware-tanzu.github.io/helm-charts
|
||||
helm repo update
|
||||
|
||||
debug "Installing Velero with S3 configuration:"
|
||||
debug " Bucket: $S3_BUCKET"
|
||||
debug " Region: $S3_REGION"
|
||||
debug " URL: $S3_URL"
|
||||
|
||||
helm install velero vmware-tanzu/velero \
|
||||
--namespace velero \
|
||||
--create-namespace \
|
||||
--set-file credentials.secretContents.cloud=velero-credentials \
|
||||
--set configuration.backupStorageLocation[0].provider=aws \
|
||||
--set configuration.backupStorageLocation[0].name=default \
|
||||
--set configuration.backupStorageLocation[0].bucket=$S3_BUCKET \
|
||||
--set configuration.backupStorageLocation[0].config.region=$S3_REGION \
|
||||
--set configuration.backupStorageLocation[0].config.s3ForcePathStyle=true \
|
||||
--set configuration.backupStorageLocation[0].config.s3Url=$S3_URL \
|
||||
--set configuration.volumeSnapshotLocation[0].name=default \
|
||||
--set configuration.volumeSnapshotLocation[0].provider=aws \
|
||||
--set configuration.volumeSnapshotLocation[0].config.region=$S3_REGION \
|
||||
--set configuration.features=EnableCSI \
|
||||
--set initContainers[0].name=velero-plugin-for-aws \
|
||||
--set initContainers[0].image=velero/velero-plugin-for-aws:v1.11.1 \
|
||||
--set initContainers[0].volumeMounts[0].mountPath=/target \
|
||||
--set initContainers[0].volumeMounts[0].name=plugins \
|
||||
--set deployNodeAgent=true \
|
||||
--set nodeAgent.containerSecurityContext.privileged=true \
|
||||
--wait
|
||||
|
||||
rm velero-credentials
|
||||
|
||||
# Wait for Velero to be ready
|
||||
echo "Waiting for Velero to be fully ready..."
|
||||
kubectl -n velero rollout status deployment/velero --timeout=120s
|
||||
|
||||
echo "Install change-storage-class.yaml"
|
||||
kubectl apply -f change-storage-class.yaml
|
||||
|
||||
# Check if velero CLI is installed and functioning
|
||||
if ! command -v velero &> /dev/null; then
|
||||
echo "Error: Velero CLI is not installed or not in PATH"
|
||||
echo "Please install the Velero CLI by following instructions at: https://velero.io/docs/main/basic-install/"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Verify Velero is connected to the storage location
|
||||
echo "Checking Velero backup storage location..."
|
||||
kubectl -n velero get backupstoragelocation default -o jsonpath='{.status.phase}' | grep -q "Available" || {
|
||||
echo "Warning: Backup storage location is not available, it may take a few minutes to initialize"
|
||||
echo "Storage location status:"
|
||||
kubectl -n velero get backupstoragelocation default -o yaml
|
||||
|
||||
# Wait a bit longer for the location to become available
|
||||
echo "Waiting 30 seconds for backup storage location to become available..."
|
||||
sleep 30
|
||||
}
|
||||
|
||||
# 4. List backups
|
||||
echo "Checking for available backups..."
|
||||
if ! velero_output=$(velero backup get 2>&1); then
|
||||
echo "Error listing backups: $velero_output"
|
||||
|
||||
# Try to verify S3 connectivity
|
||||
echo "Checking S3 connectivity..."
|
||||
|
||||
# Install AWS CLI if needed
|
||||
if ! command -v aws &> /dev/null; then
|
||||
echo "AWS CLI not found, skipping S3 connectivity test"
|
||||
else
|
||||
# Create temporary AWS profile
|
||||
mkdir -p ~/.aws
|
||||
cat > ~/.aws/credentials <<EOF
|
||||
[velero-test]
|
||||
aws_access_key_id=$S3_ACCESS_KEY
|
||||
aws_secret_access_key=$S3_SECRET_KEY
|
||||
EOF
|
||||
|
||||
cat > ~/.aws/config <<EOF
|
||||
[profile velero-test]
|
||||
region=$S3_REGION
|
||||
output=json
|
||||
EOF
|
||||
|
||||
# Try to list bucket contents
|
||||
echo "Testing S3 connection to bucket $S3_BUCKET..."
|
||||
if aws --profile velero-test --endpoint-url $S3_URL s3 ls s3://$S3_BUCKET/; then
|
||||
echo "S3 connection successful, but Velero couldn't list backups."
|
||||
echo "This might indicate that there are no backups in the bucket or the backups are in a different format than expected."
|
||||
else
|
||||
echo "Error connecting to S3. Please check your credentials and connectivity to $S3_URL"
|
||||
fi
|
||||
|
||||
# Cleanup AWS files
|
||||
rm ~/.aws/credentials ~/.aws/config
|
||||
fi
|
||||
|
||||
if [[ -z "$BACKUP_NAME" ]]; then
|
||||
echo "No backup name specified and no backups found. Exiting."
|
||||
exit 1
|
||||
fi
|
||||
else
|
||||
echo "Available backups:"
|
||||
echo "$velero_output"
|
||||
|
||||
if [[ -z "$BACKUP_NAME" ]]; then
|
||||
echo "Specify a backup name using --backup-name and run again."
|
||||
exit 0
|
||||
fi
|
||||
fi
|
||||
|
||||
# 5. Create test namespace if needed
|
||||
if [[ "$TEST_NAMESPACE" != "default" ]]; then
|
||||
kubectl create namespace $TEST_NAMESPACE || true
|
||||
fi
|
||||
|
||||
# 6. Restore backup
|
||||
echo "Restoring backup: $BACKUP_NAME"
|
||||
if [[ -z "$ORIGINAL_NAMESPACE" ]]; then
|
||||
# If no namespace specified, restore everything
|
||||
velero restore create --from-backup $BACKUP_NAME \
|
||||
--wait
|
||||
else
|
||||
# Restore specific namespace with mapping
|
||||
velero restore create --from-backup $BACKUP_NAME \
|
||||
--namespace-mappings $ORIGINAL_NAMESPACE:$TEST_NAMESPACE \
|
||||
--include-namespaces $ORIGINAL_NAMESPACE \
|
||||
--exclude-namespaces kube-system,kube-public,kube-node-lease,velero \
|
||||
--exclude-resources certificates.cert-manager.io \
|
||||
--wait
|
||||
fi
|
||||
|
||||
# 7. Check restore status
|
||||
echo "Checking restore status:"
|
||||
velero restore get
|
||||
|
||||
# Wait for pods to be ready
|
||||
echo "Waiting for pods to be ready..."
|
||||
kubectl wait --for=condition=ready pod --all -n $TEST_NAMESPACE --timeout=600s || true
|
||||
|
||||
# 8. Run validation script (create it first if it doesn't exist)
|
||||
# if [[ ! -f ./validate-restore.sh ]]; then
|
||||
# echo "Creating validation script..."
|
||||
# cat > validate-restore.sh <<'EOF'
|
||||
# #!/bin/bash
|
||||
# # validate-restore.sh - Script to validate Velero backup restoration
|
||||
|
||||
# set -e
|
||||
# echo "Starting validation of restored resources..."
|
||||
|
||||
# # Get namespace from command line or use default
|
||||
# NAMESPACE="${1:-default}"
|
||||
|
||||
# # Check all deployments
|
||||
# echo "Checking deployments..."
|
||||
# deployments=$(kubectl get deployment -n $NAMESPACE -o name)
|
||||
# if [[ -z "$deployments" ]]; then
|
||||
# echo "❌ No deployments found in namespace $NAMESPACE"
|
||||
# else
|
||||
# echo "Found deployments: $deployments"
|
||||
|
||||
# # Check if pods are running for each deployment
|
||||
# for deployment in $deployments; do
|
||||
# name=$(echo $deployment | cut -d'/' -f2)
|
||||
# echo -n "Checking deployment $name: "
|
||||
|
||||
# # Check if pods are running
|
||||
# ready_replicas=$(kubectl get deployment -n $NAMESPACE $name -o jsonpath='{.status.readyReplicas}')
|
||||
# if [[ -n "$ready_replicas" && "$ready_replicas" != "0" ]]; then
|
||||
# echo "✅ $ready_replicas pods ready"
|
||||
# else
|
||||
# echo "❌ No pods running"
|
||||
# fi
|
||||
# done
|
||||
# fi
|
||||
|
||||
# # Check all services
|
||||
# echo "Checking services..."
|
||||
# services=$(kubectl get service -n $NAMESPACE -o name | grep -v "kubernetes")
|
||||
# if [[ -z "$services" ]]; then
|
||||
# echo "❌ No services found in namespace $NAMESPACE"
|
||||
# else
|
||||
# echo "Found services: $services"
|
||||
|
||||
# # Check if services have endpoints
|
||||
# for service in $services; do
|
||||
# name=$(echo $service | cut -d'/' -f2)
|
||||
# echo -n "Checking service $name: "
|
||||
|
||||
# # Check if service has endpoints
|
||||
# endpoints=$(kubectl get endpoints -n $NAMESPACE $name -o jsonpath='{.subsets[*].addresses[*].ip}')
|
||||
# if [ -n "$endpoints" ]; then
|
||||
# echo "✅ Has endpoints"
|
||||
# else
|
||||
# echo "❌ No endpoints"
|
||||
# fi
|
||||
# done
|
||||
# fi
|
||||
|
||||
# # Check PVCs
|
||||
# echo "Checking PVCs..."
|
||||
# pvcs=$(kubectl get pvc -n $NAMESPACE -o name)
|
||||
# if [[ -z "$pvcs" ]]; then
|
||||
# echo "No PVCs found in namespace $NAMESPACE"
|
||||
# else
|
||||
# pvc_count=$(echo "$pvcs" | wc -l)
|
||||
# echo "Found $pvc_count PVCs"
|
||||
|
||||
# # Check if PVCs are bound
|
||||
# bound_count=$(kubectl get pvc -n $NAMESPACE -o jsonpath='{.items[?(@.status.phase=="Bound")].metadata.name}' | wc -w)
|
||||
# echo "$bound_count/$pvc_count PVCs are bound"
|
||||
|
||||
# if [ "$bound_count" -ne "$pvc_count" ]; then
|
||||
# echo "❌ Not all PVCs are bound"
|
||||
# else
|
||||
# echo "✅ All PVCs are bound"
|
||||
# fi
|
||||
# fi
|
||||
|
||||
# echo "Validation complete!"
|
||||
# exit 0
|
||||
# EOF
|
||||
# chmod +x validate-restore.sh
|
||||
# fi
|
||||
|
||||
echo "Running validation tests..."
|
||||
./validate-restore.sh $TEST_NAMESPACE
|
||||
|
||||
echo ""
|
||||
echo "=== Backup test process completed ==="
|
||||
echo "The cluster will be deleted when you close this terminal or press Ctrl+C"
|
||||
echo "To access the cluster manually, use: kubectl config use-context k3d-backup-test"
|
||||
echo ""
|
||||
|
||||
# Keep the script running until user terminates it
|
||||
read -p "Press Enter to clean up and exit..."
|
||||
@@ -0,0 +1,56 @@
|
||||
# Bolletjestrui faces the internet through Envoy, so its pods only reach each
|
||||
# other, DNS and the internet: not the LAN (NAS, router), the Kubernetes
|
||||
# API or other namespaces.
|
||||
# Ingress comes from Envoy and the node itself (kubelet probes; 10.1.7.64
|
||||
# is the node's Calico VXLAN address, projectcalico.org/IPv4VXLANTunnelAddr).
|
||||
# Same layout as mbgwp/networkpolicy.yaml.
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: default
|
||||
spec:
|
||||
podSelector: {}
|
||||
policyTypes:
|
||||
- Ingress
|
||||
- Egress
|
||||
ingress:
|
||||
- from:
|
||||
- podSelector: {}
|
||||
- from:
|
||||
- ipBlock:
|
||||
cidr: 192.168.1.204/32
|
||||
- ipBlock:
|
||||
cidr: 10.1.7.64/32
|
||||
- from:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: envoy-gateway-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: envoy
|
||||
ports:
|
||||
- port: 3000
|
||||
egress:
|
||||
- to:
|
||||
- podSelector: {}
|
||||
- to:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: kube-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
k8s-app: kube-dns
|
||||
ports:
|
||||
- protocol: UDP
|
||||
port: 53
|
||||
- protocol: TCP
|
||||
port: 53
|
||||
- to:
|
||||
- ipBlock:
|
||||
cidr: 0.0.0.0/0
|
||||
except:
|
||||
- 10.0.0.0/8
|
||||
- 100.64.0.0/10
|
||||
- 169.254.0.0/16
|
||||
- 172.16.0.0/12
|
||||
- 192.168.0.0/16
|
||||
@@ -31,8 +31,9 @@ view, and everything is shared with everyone automatically.
|
||||
|
||||
## Design
|
||||
|
||||
- **authentik** (authentik.rubenhensen.nl for now; auth.scoutingmbg.nl
|
||||
later, once the group's DNS has a record for it) brokers the login: a
|
||||
- **authentik** (on auth.scoutingmbg.nl, with a brand "Scouting MBG" that
|
||||
logs in through Scouts Online and then sends people to the photos)
|
||||
brokers the login: a
|
||||
Scouts Online source turns the roles into the groups `MBG leden` and
|
||||
`MBG kader` (active `Kaderlid` role) on every login, and the immich
|
||||
provider turns those into `immich_quota` and `immich_role`
|
||||
@@ -106,10 +107,29 @@ C. Switch
|
||||
- [x] Nobody uses `fotoupload@` anymore: its 9 (browser) sessions ended
|
||||
2026-10-24. Its API key stays for share-sync
|
||||
|
||||
D. auth.scoutingmbg.nl (2026-10-25)
|
||||
- [x] The group's DNS points scoutingmbg.nl, www, foto and auth at node001
|
||||
(rubenhensen.nl). node001 passes all four through to the home cluster
|
||||
(SNI on 443, a proxy on 80 for HTTP-01), like its other tunneled hosts,
|
||||
and gatus on s1 checks them
|
||||
- [x] Certificate, Gateway listener `https-auth-scoutingmbg`, the authentik
|
||||
route on both hostnames, the brand, and immich's issuer on
|
||||
https://auth.scoutingmbg.nl/application/o/immich/
|
||||
- [x] SOL connection: redirect URI
|
||||
`https://auth.scoutingmbg.nl/source/oauth/callback/scouts-online/`.
|
||||
Editing the connection left the authentik.rubenhensen.nl URI unusable
|
||||
(SOL answers `invalid_client` after the login when the redirect URI isn't
|
||||
registered), so logins failed for a few minutes until immich moved over
|
||||
|
||||
## Open points
|
||||
|
||||
- `foto.scoutingmbg.nl` is a CNAME to `mbg.hensen.io`; hensen.io is about
|
||||
to expire. Keep it until the group's DNS points foto at scoutingmbg.nl.
|
||||
- DNS (2026-10-24/25): the group's DNS host (ns1/ns2.webhosted.nl) pointed
|
||||
scoutingmbg.nl, www, foto and auth at node001 (rubenhensen.nl); those are
|
||||
all the records it moved, and node001 tunnels all four home. ns1 lagged
|
||||
behind ns2 (a zone serial from June) until 2026-10-24 16:50 UTC. Nothing
|
||||
uses mbg.hensen.io anymore, so hensen.io can expire. The SPF record's
|
||||
`a` now means node001, which is fine: the WordPress site sends no mail
|
||||
and the group's mail goes through Google (`mx`)
|
||||
- Public shared links become public for real once sol-auth is gone.
|
||||
- Photos leiding back up from their phones stay private until they add
|
||||
them to a shared album.
|
||||
@@ -38,13 +38,33 @@ between them live.
|
||||
|
||||
## Before: shrink what has to move
|
||||
|
||||
- [ ] Delete stale snapshots. 188 snapshots hold 334 GiB, 214 GiB of it in
|
||||
- [x] Delete stale snapshots. 188 snapshots hold 334 GiB, 214 GiB of it in
|
||||
snapshots from before October 2026, nearly all on immich-claim
|
||||
(pvc-75d269dd): a 72.5 GiB one from 2024-12-20, 71.3 GiB from
|
||||
2025-03-02, daily ones from 2025-03-13 to 03-20 (a recurring job that no
|
||||
longer exists), 56.6 GiB from 2026-01-20. The Longhorn backups on the NAS
|
||||
don't depend on them. Deleting a snapshot merges it into the next one,
|
||||
which writes a lot, so do this in a quiet hour, one volume at a time.
|
||||
Happened on 2026-10-24, from a Claude Code session at Ruben's request
|
||||
(the 45 snapshots from before October 2026, small volumes first): immich-claim's
|
||||
old snapshots were removed at 14:43 UTC and Longhorn merged them one
|
||||
after another, about 45 minutes each, until 23:15. For those 8.5 hours
|
||||
sda ran 250-440 writes/s and 200-400 reads/s at 6-20 ms per write on
|
||||
average, with "full" IO pressure at 45-75% (`~/iosample.log`); the
|
||||
instance manager wrote 2.3 TB and read 2.8 TB in 30 hours. What is left
|
||||
on immich-claim is one 233 GiB snapshot (`system-backup-0b7f8c6047294b36`,
|
||||
from the Longhorn system backup of 2026-10-22) that everything merged
|
||||
into; 148 snapshots hold 273 GiB across all volumes.
|
||||
- [ ] Delete the snapshots the Longhorn system backups left behind: 116
|
||||
`system-backup-*` snapshots (one per volume for each system backup
|
||||
before an upgrade step on 2026-10-22 and 23) hold 258 GiB. The system
|
||||
backups on the NAS don't need them. The small volumes are cheap; on
|
||||
immich-claim the 233 GiB one is the base the rest merged into, so
|
||||
deleting it means hours of merging like on 2026-10-24: one night, or
|
||||
after the move to the NVMe drive. Then trim (next item); deleted files
|
||||
only free space once both are done. Next time, take system backups with
|
||||
the volume backup policy `disabled` when the nightly backups are fresh,
|
||||
so they create no snapshots
|
||||
- [ ] Trim immich-claim's filesystem (Longhorn UI, volume, "Trim Filesystem")
|
||||
so blocks of deleted files are released.
|
||||
- [ ] Fresh backups: let a nightly Longhorn and Velero backup run, plus a
|
||||
@@ -61,8 +81,10 @@ between them live.
|
||||
- [ ] Boot into the BIOS (F2): the NVMe drive shows up under storage, SATA
|
||||
operation stays AHCI, and the boot sequence still starts "ubuntu" from
|
||||
the SATA SSD.
|
||||
- [ ] Boot. `lsblk` shows `nvme0n1`; wait until everything is green again
|
||||
(gatus on s1 and s2).
|
||||
- [ ] Boot. `lsblk` shows `nvme0n1`.
|
||||
- [ ] Unseal Vault, which comes up sealed (until then ESO can't refresh
|
||||
secrets): `for p in vault-0 vault-1 vault-2; do kubectl -n vault exec -ti $p -- vault operator unseal; done`
|
||||
- [ ] Wait until everything is green again (gatus on s1 and s2).
|
||||
|
||||
## Prepare the disk (sudo on opti1)
|
||||
|
||||
|
||||
+487
@@ -0,0 +1,487 @@
|
||||
# Roadmap
|
||||
|
||||
Where the cluster stands and what is left, as of 2026-10-25. Takes over
|
||||
from wishlist.txt (January 2026, removed); its items are sorted in at the
|
||||
bottom.
|
||||
|
||||
## State
|
||||
|
||||
One node: opti1, an OptiPlex 5060 with an i5-8600T, 32 GB and one 1 TB
|
||||
SATA SSD that is 72% full. microk8s v1.36.5 from 1.36/edge, snap held.
|
||||
35 Argo CD apps (with metrics-server), all Synced/Healthy; every Longhorn
|
||||
volume has one replica. authentik 2026.8.5, Vault 2.2.1. Backups go to the
|
||||
NAS (192.168.1.99): Longhorn to NFS at 00:00 (7 kept), Velero to MinIO at
|
||||
01:00 (daily kept 30 days, weekly 90 days). Gatus on s1 (node001, Hetzner)
|
||||
and s2 (home) watch each other and alert through ntfy; s2 also gets an
|
||||
hourly report from inside the cluster on the backups, Vault's seal, the
|
||||
Argo CD apps and the CNPG clusters.
|
||||
Every app namespace has NetworkPolicies, and CI renders and validates all
|
||||
apps on every PR. node001 runs mail and tunnels the public hosts home.
|
||||
|
||||
## Follow-ups from this week
|
||||
|
||||
From docs/upgrade-k8s-1.33.md, docs/immich-scouts-online.md and
|
||||
docs/longhorn-second-ssd.md:
|
||||
|
||||
- [x] Read `~/iosample.log` on opti1: the worst stretch was not the
|
||||
backups but 8.5 hours of Longhorn merging immich-claim's deleted
|
||||
snapshots (2026-10-24 14:30-23:15), see docs/upgrade-k8s-1.33.md
|
||||
- [ ] From 2026-10-27, if immich runs without problems: delete
|
||||
`immich/postgresql-cluster.yaml` (the PG14 cluster still runs, 20 GiB),
|
||||
the Longhorn snapshots and backups `immich-pg14-pre-vchord` and
|
||||
`immich-pg17-pre-v3`, and both dumps in `~` on opti1. PostgreSQL 14
|
||||
reaches end of life on 2026-11-12
|
||||
- [ ] The upgrade's dqlite and backend copies in `/root/` on opti1
|
||||
(`backend-*.tar`, `dqlite-pre-*`)
|
||||
- [ ] Log in to immich as a jeugdlid (quota 0)
|
||||
- [ ] Back to 1.36/stable once it is at v1.36.5 or later (still v1.36.2 on
|
||||
2026-10-25). The snap is held, so microk8s gets no updates at all until
|
||||
someone refreshes it
|
||||
- [ ] Second SSD, docs/longhorn-second-ssd.md
|
||||
- [ ] Optional: `MACHINE_LEARNING_MODEL_REVISION=v2` for immich ML
|
||||
|
||||
## Next, in order
|
||||
|
||||
### 1. hensen.io expires
|
||||
|
||||
foto.scoutingmbg.nl was a CNAME to mbg.hensen.io. Since 2026-10-24 it is a
|
||||
CNAME to rubenhensen.nl (node001, which tunnels it home), but only on the
|
||||
group's ns2: ns1 is stuck on an old serial and still answers
|
||||
mbg.hensen.io (docs/immich-scouts-online.md).
|
||||
|
||||
- [x] Expiry date: 2027-01-09 (whois, 2026-10-25; registrar Key-Systems)
|
||||
- [x] ns1 caught up on 2026-10-24 16:50 UTC; both ns1 and ns2 answer
|
||||
`rubenhensen.nl` for foto (checked 2026-10-25), and nothing in the
|
||||
cluster uses hensen.io anymore. hensen.io can expire
|
||||
|
||||
### 2. Off-site backups
|
||||
|
||||
Both backup targets are on the same NAS, in the same house as opti1. A
|
||||
fire or burglary takes the cluster, the backups and 45,703 photos that
|
||||
belong to the group.
|
||||
|
||||
There is no off-site copy (2026-10-25). The plan: swap S3 buckets with a
|
||||
friend.
|
||||
|
||||
- [ ] Ours to his bucket: Hyper Backup on the Synology, destination "S3
|
||||
Storage" with his endpoint as a custom server. Client-side encryption
|
||||
on: the kopia repositories use Velero's default password
|
||||
(`static-passw0rd`), so without it he could read everything, the
|
||||
group's photos included. Keep the encryption key next to the Vault
|
||||
unseal key. Source: the shared folder with MinIO's `velero-backups`
|
||||
bucket (~150-200 GB). Daily after the Velero backup, Smart Recycle,
|
||||
mail on failure
|
||||
- [ ] Needed from him: endpoint, which S3 server he runs, space (~200 GB
|
||||
now, 500 GB to grow), and versioning or object lock on the bucket, so
|
||||
whoever takes over the NAS can't delete the off-site copy as well
|
||||
- [ ] His backups with us: Garage (not MinIO, see 5) in Container Manager
|
||||
on the Synology, in its own shared folder, with a bucket and key for him
|
||||
and a quota. Only the S3 API public, as `s3.rubenhensen.nl` through
|
||||
node001 and Envoy with a cert-manager certificate; the admin API stays
|
||||
on the LAN. The cluster side (DNS, node001 tunnel, Certificate,
|
||||
HTTPRoute) goes in git. Needed: how much space he wants, free space on
|
||||
the NAS
|
||||
- [ ] Decide which copy of the immich library goes off-site (see 5)
|
||||
- [ ] A restore test that runs on a schedule. `backup-testing/` predates
|
||||
Envoy Gateway and still rewrites `*.hensen.io` and bypasses sol-auth.
|
||||
Planned on 2026-10-25, not run: a second Velero on the real bucket is
|
||||
risky even with a ReadOnly location, because kopia could then run
|
||||
maintenance on the same repositories from two clusters. Instead: copy
|
||||
one backup (`backups/<name>/`) and the kopia repositories of a few small
|
||||
namespaces (`kopia/{gatus,ntfy,freshrss}/`) read-only from the NAS with
|
||||
rclone into a local folder, serve that with `rclone serve s3`, and
|
||||
restore into a throwaway k3s in Docker (Velero 1.18.2, node agent on,
|
||||
storage class longhorn mapped to local-path, without httproutes,
|
||||
certificates, referencegrants and networkpolicies). It needs the MinIO
|
||||
key outside the cluster, which wants your go-ahead; better still, a
|
||||
MinIO user with read-only access to `velero-backups`.
|
||||
Built as `backup-testing/restore-test.sh` (2026-10-25) and rehearsed
|
||||
end to end against a backup made inside the test cluster, with a
|
||||
ReadOnly location: data restored byte for byte (same sha256), deployment
|
||||
available, everything removed afterwards. Two pitfalls found on the way
|
||||
are in the script's header. Not yet run against the real backups:
|
||||
- [x] Ran `backup-testing/restore-test.sh` on 2026-10-25 against
|
||||
daily-backup-20261025010027 (ntfy, freshrss, actual-budget): every pod
|
||||
volume came back with its backed-up byte count (actual-budget 8.4 MB,
|
||||
freshrss 293 MB, ntfy 180 KB) and all deployments became available. The
|
||||
first run failed on a 400 from MinIO: rclone signed for us-east-1 while
|
||||
MinIO runs region `minio`; the script now reads endpoint, region and
|
||||
bucket from Velero's location. Copying freshrss's kopia repository took
|
||||
14 of the ~17 minutes
|
||||
- [ ] Run it on a schedule. It needs Docker and the MinIO key, so not in
|
||||
the cluster itself: the Mac (launchd) or node001, ideally with a
|
||||
read-only MinIO user
|
||||
|
||||
### 3. authentik 2026.2.1 → 2026.8.5
|
||||
|
||||
Since 2026-10-24 authentik is the front door for every member of the
|
||||
group. Renovate PRs #20 (2026.2.3) and #22 (2026.8.5) had been open since
|
||||
April and May.
|
||||
|
||||
- [x] Upgraded 2026-10-25 in two hops, since releases can't be skipped:
|
||||
chart 2026.5.6, then 2026.8.5. Each took about three minutes with no
|
||||
downtime; the old pods kept serving until the new ones were ready.
|
||||
Safety net: `pg_dump -Fc` in `~/authentik-pre-2026.5.dump` (15 MB) on
|
||||
opti1 and Longhorn snapshot `authentik-pg-pre-2026-5`. Checked after
|
||||
each hop: the seven OIDC discovery endpoints and their issuers, the
|
||||
login page, immich, every blueprint successful, the LDAP outpost
|
||||
checking in on the new version
|
||||
- 2026.5 listens on `[::]` instead of `0.0.0.0`. IPv6 is on in the pods
|
||||
(`bindv6only` 0), so IPv4 keeps working
|
||||
- 2026.8 only believes `X-Forwarded-*` from
|
||||
`listen.trusted_proxy_cidrs`, which defaults to the private ranges
|
||||
(10.0.0.0/8 covers Envoy's pods); redirects stay https
|
||||
- The managed LDAP outpost didn't follow on its own after either hop;
|
||||
`outpost_controller.send(<outpost pk>)` in `ak shell` rolled it over
|
||||
- The `redis:` values were left over from before authentik dropped
|
||||
Redis; the chart has no such key, so they went
|
||||
- [x] Log in once through each app: immich through Scouts Online, Argo CD,
|
||||
Vault, Longhorn, FreshRSS, Actual, mail
|
||||
- [ ] After a week without problems: delete the dump and the snapshot
|
||||
- [x] Base URL (system setting or `AUTHENTIK_WEB__BASE_URL`), required
|
||||
from 2026.11: already `https://authentik.rubenhensen.nl`, filled in by
|
||||
the 2026.8 migration from the embedded outpost's host. In 2026.8.5 it is
|
||||
only stored; on main it fills itself in the same way and sets the
|
||||
embedded outpost's host from it. OIDC issuers still come from the
|
||||
request's host, so immich's issuer on auth.scoutingmbg.nl is unaffected
|
||||
(checked 2026-10-25 in the source)
|
||||
|
||||
### 4. Vault 1.17.2 → 2.2.1
|
||||
|
||||
Vault unseals with Shamir keys, so after every reboot (the SSD install,
|
||||
for one) it stays sealed and ESO stops refreshing secrets until someone
|
||||
unseals it.
|
||||
|
||||
- [x] Upgraded 2026-10-25, straight from 1.17.2 to 2.2.1. HashiCorp
|
||||
doesn't require going through every release, and the change tracker
|
||||
lists no breaking change that applies here: `disable_mlock` is set
|
||||
(required for raft since 1.20), the chart sets `SKIP_SETCAP` and runs
|
||||
Vault as uid 100 (2.0.1's IPC_LOCK requirement, dropped again in 2.0.2),
|
||||
and ESO uses a token and KV v2. `tools/vault-roll.sh 2.2.1` restarted
|
||||
the standbys first and the active node last, unsealing each; vault-1
|
||||
took over as active within seconds. Safety net: Longhorn snapshots
|
||||
`vault-{0,1,2}-pre-2-2-1`. Afterwards all three ran 2.2.1 at the same
|
||||
raft index, and all 24 ExternalSecrets refreshed after a force-sync
|
||||
- The OIDC job called `vault auth tune -listing_visibility`, a flag that
|
||||
doesn't exist, so the OIDC mount's listing visibility was never set.
|
||||
Fixed; the job now uses the 2.2.1 CLI instead of 1.15
|
||||
- [x] There is one unseal key (1 share, threshold 1), kept safe outside
|
||||
this cluster (2026-10-25); without it the data in Vault is lost
|
||||
- [x] Unsealing is in the SSD install steps
|
||||
- [ ] After a week without problems: delete the three snapshots
|
||||
|
||||
### 5. Backups: which tool keeps what
|
||||
|
||||
Findings from 2026-10-25:
|
||||
|
||||
- Velero backs up every mounted volume through kopia, including the immich
|
||||
library (133 GB), which Longhorn also backs up to the same NAS. Most runs
|
||||
take 10s to 3 min, since kopia only reads changed files. 3 of the last 13
|
||||
read everything again: 37 min on 10-21, 30 min on 10-24 (the lease loss
|
||||
at 01:09), 13 min for the weekly on 10-25. Why those runs found no
|
||||
usable parent is unclear; the 10-24 one was the first after the Velero
|
||||
1.18 upgrade restarted the node agent. Once Longhorn's data is on the
|
||||
NVMe SSD these reads no longer hit the disk dqlite is on.
|
||||
- Velero holds the photos longest. Longhorn keeps 7 backups per volume
|
||||
(count-based, so extra runs push out older ones: immich-claim's oldest
|
||||
daily is from 10-22); Velero keeps dailies 30 days and weeklies 90.
|
||||
Dropping immich from Velero means raising Longhorn's retention first.
|
||||
- Longhorn's recurring job skips detached volumes
|
||||
(`allow-recurring-job-while-volume-detached` is false). immich-claim got
|
||||
no Longhorn backup on 10-24: the server was at 0 replicas for the
|
||||
database migration from 22:18 to 00:06 UTC.
|
||||
- Velero copies the CNPG and MariaDB data directories file by file while
|
||||
the databases run, which is not a consistent copy. The Longhorn backups
|
||||
start from a snapshot and are crash-consistent. CNPG can back up to
|
||||
MinIO itself (barman cloud plugin), with point-in-time recovery.
|
||||
- The PartiallyFailed daily backup of 10-23 (emptyDirs of Velero's own
|
||||
maintenance job pods) was fixed that afternoon by
|
||||
`velero/skip-emptydir-policy.yaml`.
|
||||
|
||||
- [ ] Whether the immich library stays in Velero. It stays for now
|
||||
(2026-10-25); decide again with the off-site copy (2)
|
||||
- [ ] CNPG backups through the barman cloud plugin
|
||||
- [ ] Velero's target, MinIO on the NAS, is no longer maintained: no
|
||||
community images since October 2025, maintenance mode since December
|
||||
2025, and the repository is archived. Move Velero to the Garage from 2
|
||||
and switch MinIO off
|
||||
|
||||
### 6. Monitoring
|
||||
|
||||
Nothing collects metrics or logs, not even metrics-server (`kubectl top`
|
||||
fails). The dqlite stalls were tracked down by hand from the API server's
|
||||
metrics, and Velero's scheduled backups failed every night from August
|
||||
until 2026-10-21 without anyone noticing.
|
||||
|
||||
- [x] A stopgap for the worst blind spots (2026-10-25,
|
||||
`gatus/backup-check.yaml`): an hourly CronJob reads the API and pushes
|
||||
six external endpoints to s2 (group "cluster"): the newest daily and
|
||||
weekly Velero backup Completed and recent, every attached Longhorn
|
||||
volume healthy with a backup younger than 26h, no Vault pod sealed,
|
||||
every Argo CD app Synced and Healthy, every CNPG cluster healthy.
|
||||
Gatus alerts through ntfy after two failed reports, or when no report
|
||||
arrives for 3 hours. The token comes from an ESO Password generator.
|
||||
Tested with made-up data for each failure (a Failed or old backup, a
|
||||
degraded or unbacked-up volume, a sealed pod)
|
||||
- [x] metrics-server (2026-10-25, `apps/templates/metrics-server-helm.yaml`):
|
||||
`kubectl top` works; it keeps its data in memory, so it adds no disk
|
||||
writes. The first look: immich v3 checks file checksums every night from
|
||||
03:00 UTC for up to an hour (IntegrityService), reading ~100 MB/s from
|
||||
sda; it doesn't overlap the backups at 00:00 and 01:00
|
||||
- [ ] After the second SSD (a time series database writes all the time
|
||||
and would add to today's stalls): Prometheus or
|
||||
VictoriaMetrics with Grafana, alerting to ntfy. Loki later
|
||||
- [ ] Alerts worth having: disk latency and fill, lease losses and
|
||||
controller restarts, backups that don't complete, Longhorn volumes that
|
||||
aren't healthy, Vault sealed
|
||||
|
||||
### 7. Limits, probes, network policies
|
||||
|
||||
Counted 2026-10-25 over the 73 running containers:
|
||||
|
||||
- 59 have no requests and 64 no memory limit, among them all of Argo CD,
|
||||
authentik, cert-manager, ESO, mariadb-operator and Vault, and freshrss,
|
||||
gitea, immich and serpbear. The node has 32 GB with 14.6 GB in use; one
|
||||
runaway pod can take the node down, dqlite with it.
|
||||
- No probes on gitea, freshrss, serpbear, authentik's LDAP outpost, the
|
||||
ESO controller, dex and Argo CD's redis.
|
||||
- NetworkPolicies exist only in argocd and longhorn-system. Public are
|
||||
immich (every member, plus public share links), mbgwp (WordPress) and
|
||||
authentik.
|
||||
- Running as root as far as the securityContext tells (images not
|
||||
checked): authentik, bolletjestrui, freshrss, gatus, gitea, immich,
|
||||
ntfy, serpbear, mariadb-operator.
|
||||
|
||||
- [x] NetworkPolicies for immich, mbgwp and authentik
|
||||
(`<namespace>/networkpolicy.yaml`, 2026-10-25). Before, WordPress could
|
||||
reach the NAS's DSM, the router, the API server, Vault and immich. Now
|
||||
each of the three reaches only its own pods, DNS and the internet
|
||||
(without the private ranges), plus the API server for the CNPG
|
||||
instances and authentik's worker. Ingress only from Envoy, the CNPG and
|
||||
MariaDB operators, the node (kubelet probes) and, for the LDAP outpost,
|
||||
from anywhere. Checked afterwards: the sites, the OIDC endpoints and
|
||||
logins, Longhorn's login through Envoy, the LDAP NodePort, CNPG
|
||||
healthy, a MariaDB backup and a share-sync run. The node's addresses
|
||||
(192.168.1.204 and Calico's 10.1.7.64) are written out, so a new node
|
||||
means new policies
|
||||
- [x] The same for gitea, freshrss, serpbear, ntfy, actual-budget,
|
||||
bolletjestrui and gatus (2026-10-25), plus gatus → ntfy in-cluster.
|
||||
home-assistant has no pods (it points at 192.168.1.202). Vault now only
|
||||
takes connections from ESO, Envoy (the UI) and the node (the injector's
|
||||
webhook); its pods reach each other, DNS, the API server and the
|
||||
internet. Checked: every host answers as before, gatus s2 16/16, the
|
||||
OIDC logins of Vault and FreshRSS reach authentik, all 24
|
||||
ExternalSecrets refresh, raft intact; Gitea no longer reaches the NAS
|
||||
or Vault, and a pod in `default` no longer reaches Vault or Gitea
|
||||
- [ ] The infrastructure namespaces (cert-manager, cnpg-system,
|
||||
external-secrets, envoy-gateway-system, velero, mariadb-system, dns,
|
||||
default) still have none; `default` can reach the LAN and everything
|
||||
without a policy
|
||||
- [x] Requests: PR #33, merged 2026-10-25 11:23 UTC, for everything that
|
||||
had none except the Vault server, from `kubectl top` every 5 minutes
|
||||
from 03:13 to 08:40 UTC (highest memory plus 10%, CPU at p95, 10m
|
||||
floor). Rolled out in about eight minutes; both CNPG instances
|
||||
restarted and came back healthy, the OIDC endpoints, the logins and
|
||||
immich answered, no OOM kills. The node now has 3770m CPU (62%, of which
|
||||
1440m is Longhorn's two instance managers) and 9158Mi memory (28%)
|
||||
requested. Still without requests: Longhorn (22 containers, its chart),
|
||||
the Vault servers, the LDAP outpost, immich's PG14 cluster and three in
|
||||
kube-system
|
||||
- [ ] Memory limits, once there are daytime numbers: the night ones miss
|
||||
immich's machine learning at work (it idles at 234Mi)
|
||||
- [x] WordPress (scoutingmbg.nl) was OOMKilled at 08:27:59 UTC on
|
||||
2026-10-25, its third restart: a crawler asked for 88 pages and assets
|
||||
within a few seconds (normally ~6 a minute), Apache started a PHP worker
|
||||
for each (~45-60 MB each, `MaxRequestWorkers` was the default 150), and
|
||||
the container went past its 1Gi limit. Unrelated to the
|
||||
NetworkPolicies. Now capped at 12 workers through the chart's
|
||||
`apachePortsConfig` (ports.conf comes after mods-enabled/*.conf), checked
|
||||
with `apache2ctl -t` in the same image first. Replaying the burst (90
|
||||
page requests, 40 at a time): all 200, at most 13 Apache processes and
|
||||
572Mi, no restart; the price is waiting (4.3s median, up to ~22s at the
|
||||
peak) instead of a crash
|
||||
- [ ] Optional, no plugins wanted on WordPress: a small nginx cache in the
|
||||
cluster between Envoy and WordPress that keeps anonymous GETs for a few
|
||||
minutes and passes anything with a WordPress cookie through. A page
|
||||
renders in 0.4-0.7s when the site is quiet and OPcache is on, so the
|
||||
waiting in a burst is queueing; the cap alone already prevents the crash
|
||||
- [ ] Fewer plugins on the site (17 now; up to whoever runs it):
|
||||
`litespeed-cache` only caches pages on a LiteSpeed server, so it does
|
||||
little here, `wordpress-importer` is usually for a one-off import, and
|
||||
`code-snippets` runs PHP from the dashboard
|
||||
- [ ] Rate limiting per visitor in Envoy needs the client's address, which
|
||||
node001 loses: it passes TLS through, so every request arrives from
|
||||
46.224.26.65. That needs the PROXY protocol from node001's nginx to Envoy
|
||||
(ClientTrafficPolicy `enableProxyProtocol`)
|
||||
- [x] Probes for gitea (`/api/healthz`), freshrss (TCP, since
|
||||
mod_auth_openidc answers 401 to non-browsers) and serpbear (`/login`)
|
||||
(2026-10-25). Liveness only after 5 failures 30s apart, to ride out the
|
||||
SSD's stalls. Still without probes: authentik's LDAP outpost (deployed
|
||||
by authentik), the ESO controller, dex and Argo CD's redis (upstream
|
||||
manifests)
|
||||
- [ ] Non-root where the image allows it
|
||||
|
||||
### 8. Renovate and CI
|
||||
|
||||
10 Renovate PRs are open, the oldest from February, and nothing checks a
|
||||
PR before Argo CD applies it.
|
||||
|
||||
- [x] `.github/workflows/validate.yaml` runs `tools/ci/validate.py` on
|
||||
every PR and push (2026-10-25): it renders all 36 apps the way Argo CD
|
||||
does (the apps chart, every Application's chart with its values, value
|
||||
files and parameters, kustomizations, plain folders, and
|
||||
external-snapshotter cloned with its patches) and validates the result
|
||||
with kubeconform (strict, CRD schemas from the datree catalog), plus a
|
||||
duplicate-key check on every YAML file. Helm 4.2.1 like Argo CD 3.5,
|
||||
versions pinned and checksummed, kept current by Renovate through the
|
||||
`# renovate:` comments. Tested by planting a typo in a Deployment, a
|
||||
chart version that doesn't exist and a value the immich chart's schema
|
||||
rejects; all three fail the run. Locally:
|
||||
`docker run --rm -v $PWD:/repo:ro <image with helm, kustomize, kubeconform, PyYAML> python /repo/tools/ci/validate.py`
|
||||
- It found `syncPolicy.automated` twice in
|
||||
`apps/templates/snapshot-controller-helm.yaml` (once with `prune: true`,
|
||||
added 2025-03-03); Argo CD kept the last one, without prune. Now listed
|
||||
once, as it ran. Prune was probably meant; turn it on deliberately if so
|
||||
- [x] This repo's own rules, in `tools/ci/validate.py` rather than
|
||||
conftest (2026-10-25), on what the repo's own folders render: no Secret
|
||||
with data in git, and every image has a tag other than latest (both
|
||||
fail the run; tested with a planted Secret and an untagged image), plus
|
||||
PR annotations for containers without requests or probes. freshrss's
|
||||
`alpine/git` init container had no tag; now `v2.52.0`
|
||||
- [ ] Automerge patch versions of low-risk apps now that CI runs
|
||||
- [x] Renovate listed external-snapshotter twice (#15 and #24): its
|
||||
`argocd` manager and a custom `github-tags` regex both matched. The
|
||||
regex is gone; Renovate should close #15 by itself
|
||||
- [x] Renovate only looked at six folders for images and only at
|
||||
apps/templates for Applications, so it never offered updates for the
|
||||
vault, immich, velero, mariadb-operator and actualbudget charts, or for
|
||||
images in freshrss, mbgwp, dns, vault and immich, or for CNPG's
|
||||
`imageName` (authentik still runs PostgreSQL 17.4). Both managers now
|
||||
cover every app folder, a regex manager reads `imageName` in
|
||||
`*/postgresql-cluster*.yaml`, and major PostgreSQL updates are off
|
||||
(those need pg_upgrade or a dump). Expect a batch of new PRs
|
||||
(2026-10-25; `renovate-config-validator` passes). They only come once
|
||||
fewer than 10 Renovate PRs are open (`config:recommended`'s
|
||||
`prConcurrentLimit`); until then they wait under "Rate-Limited" on the
|
||||
Dependency Dashboard (#2)
|
||||
- [x] Merged 2026-10-25 and checked after the sync: #28 cert-manager
|
||||
v1.21.3 (security release; all three pods on v1.21.3), #24
|
||||
external-snapshotter v8.7.0 (its manifests ship the v8.6.0 image, as
|
||||
v8.2.1 shipped v8.2.0; both replicas up, no errors), #25 WordPress chart
|
||||
0.16.7 (image unchanged, site 200), #31 python 3.15.1 (the cluster check
|
||||
ran clean on it). Closed: #19, #29, and #15 by Renovate. Later the same
|
||||
day: #23 ntfy v2.34.0, #27 go-dqlite v3.0.4, #33 (see 7) and #26 Gitea
|
||||
28.2.0 (migrations up to 357 ran clean, `/api/healthz` 200; no backup of
|
||||
its own beforehand, the nightly ones are the way back)
|
||||
- [x] #17 external-secrets 2.14.0, merged 2026-10-25 11:50 UTC after a
|
||||
manual rebase (#33 had added values on the next line, which git counts
|
||||
as a conflict). All three pods on v2.14.0, the store Ready, and 24 of 25
|
||||
ExternalSecrets refreshed on a force-sync; the 25th is the generated
|
||||
`gatus/backup-check-token`, which never refreshes by design
|
||||
|
||||
### 9. One node
|
||||
|
||||
One node, one SSD, one replica per volume. The second SSD takes away the
|
||||
disk contention; a second and third node (nix-infra, like node001) is the
|
||||
step after that, if downtime starts to matter.
|
||||
|
||||
### 10. Repo and cluster cleanup
|
||||
|
||||
- [x] Done 2026-10-25: `disable/` and the `.DS_Store` files, now in
|
||||
`.gitignore`; `secrets/hensenio-smtp.yaml` and `velero/minio-es.yaml`
|
||||
(commented out in full), and with the first the `secrets-folder` app;
|
||||
`backup-testing/test-velero-backup.sh.bak` (an older copy); the 15
|
||||
completed kopia maintenance jobs of repositories that no longer exist
|
||||
(nextcloud, owntracks, sogo, sogo-mail, ttrss)
|
||||
- [ ] freshrss mounts `freshrss-claim2` and `freshrss-claim3` as whole
|
||||
volumes over the file paths `data/config.custom.php` and
|
||||
`data/config-user.custom.php`, so FreshRSS sees two empty directories
|
||||
there and the volumes hold nothing (0 bytes in every backup). Drop both
|
||||
mounts and the two PVCs, or make them ConfigMap files if custom config
|
||||
is wanted
|
||||
- [ ] `kubectl delete namespace secrets`, empty since its app went
|
||||
- [ ] 41 Failed Velero backups: the dailies from 2026-09-26 to 10-21 and
|
||||
the weeklies since 08-02. Velero doesn't restore from a Failed backup;
|
||||
left alone they expire by 2027-01-16.
|
||||
`kubectl -n velero exec deploy/velero -c velero -- /velero backup delete $(kubectl -n velero get backups.velero.io -o json | jq -r '.items[] | select(.status.phase=="Failed") | .metadata.name' | xargs) --confirm`
|
||||
- [ ] The mariadb-operator Backup `mbgwp-pre-migration-backup`, a dump
|
||||
from 2026-02-22 on its own 10 GiB volume (which has a Longhorn backup
|
||||
from 2026-10-22). The PVC has no owner, so it goes separately:
|
||||
`kubectl -n mbgwp delete backups.k8s.mariadb.com mbgwp-pre-migration-backup && kubectl -n mbgwp delete pvc mbgwp-pre-migration-backup`
|
||||
- [ ] 50 of the 70 Longhorn backup volumes on the NAS belong to volumes
|
||||
that no longer exist. Keep the final backups of 2026-10-22 (ghost-blog,
|
||||
stalwart, whisper). The rest are from apps removed long ago: nextcloud
|
||||
(2025-03), owntracks, traccar, ttrss, whisper-priv, whisper-webui,
|
||||
ghost, sogo, sogo-mail, outrun-game, the old mbg-wordpress and
|
||||
mbgwp-helm volumes, immich's database before CNPG. Decide per app and
|
||||
delete in the Longhorn UI (Backup)
|
||||
- [ ] opti1, without sudo: `rm ~/calico-3.29.3.yaml ~/cni-3.25.1-backup.yaml ~/hosts.toml.docker.io.bak ~/dqlite-vacuum`,
|
||||
rollback material for steps that can't be undone any more (the tool's
|
||||
source is in tools/)
|
||||
- [ ] opti1, with sudo: `/root/backend-*` and `/root/dqlite-pre-*` (from
|
||||
before 1.33, 1.34 and the VACUUM; 1.34 migrated the schema, so none of
|
||||
them fits 1.36) and `~/containerd.bak` (root-owned, from 2025-02)
|
||||
- [ ] `rm -r ~/cadir` on opti1: a CA key and certificate made four minutes
|
||||
before the real keyUsage fix on 2026-03-21 (OpenSSL's default subject
|
||||
"Internet Widgits Pty Ltd", valid for a year) and never installed;
|
||||
microk8s's CA is the `CN=microk8s-ca` one from 19:16 that day, valid
|
||||
until 2036
|
||||
|
||||
### 11. Known vulnerabilities
|
||||
|
||||
A one-off scan on 2026-10-25 of all 52 images running in the cluster
|
||||
(Trivy 0.75.0, remote, linux/amd64, HIGH and CRITICAL only). Counts are
|
||||
critical / high:
|
||||
|
||||
| Image | Crit | High | What to do |
|
||||
|---|---|---|---|
|
||||
| tensorchord/cloudnative-pgvecto.rs:14-v0.2.1 | 38 | 342 | immich's old PG14 cluster; goes with the cleanup from 2026-10-27 |
|
||||
| cloudnative-pg/postgresql:17.4 | 27 | 260 | authentik's database, a Debian 11 image. Renovate now offers 17.7; a `17.x-standard-trixie` image is more current |
|
||||
| tensorchord/cloudnative-vectorchord:17.11-1.1.1 | 17 | 136 | immich's database; look for a newer tag |
|
||||
| longhornio/longhorn-instance-manager:v1.7.3 | 11 | 159 | still serves 16 volumes, see below |
|
||||
| actualbudget/actual-server:26.6.0 | 8 | 83 | chart 1.8.9; Renovate now covers it |
|
||||
| gitea/gitea:1.27.3 | 8 | 43 | PR #26 (28.2.0) |
|
||||
| immich-server / machine-learning v3.3.5 | 7, 7 | 113, 78 | a newer immich release |
|
||||
| towfiqi/serpbear:3.1.0 | 6 | 77 | a newer release |
|
||||
| rubenhensen/bolletjestrui:main-10268f1 | 5 | 76 | rebuild on a current base image |
|
||||
| coredns/coredns:1.10.1 | 5 | 70 | see below |
|
||||
| dexidp/dex:v2.45.1, argocd v3.5.6, redis 8.2.3 | 4, 1, 2 | | come with Argo CD |
|
||||
| mariadb:11.4.5 | 4 | 65 | the newest 11.4 patch; Renovate now covers it |
|
||||
| calico v3.29.3 | 2-3 | ~50 | comes with microk8s |
|
||||
| goauthentik ldap / server 2026.8.5 | 3, 1 | 74, 65 | the next authentik patch |
|
||||
|
||||
Nothing critical in Envoy, Vault, Velero, cert-manager, ESO, ntfy, gatus or
|
||||
metrics-server.
|
||||
|
||||
- [ ] 16 volumes still have their engine in Longhorn 1.7.3's instance
|
||||
manager (`instance-manager-07d66a5…`, running since March): vault ×3,
|
||||
authentik-postgres, immich-postgres (PG14), mbgwp (mariadb and
|
||||
wordpress), gitea, freshrss ×3, ntfy, gatus, serpbear, bolletjestrui,
|
||||
actual-budget. On one node a pod restart never detaches the volume (the
|
||||
new pod lands on the same node), so only a real detach moves the engine
|
||||
to 1.13's instance manager: scale to 0, wait until Longhorn shows the
|
||||
volume detached, scale back (Argo CD's selfHeal undoes a scale-down, so
|
||||
pause it for the app). Vault comes back sealed; CNPG clusters want
|
||||
`cnpg.io/hibernation=on` instead of a scale-down. The old instance
|
||||
manager goes away by itself once it serves nothing
|
||||
- [ ] CoreDNS runs 1.10.1 from when the addon was enabled; the addon
|
||||
repository has 1.14.3. `sudo microk8s disable dns && sudo microk8s enable dns:1.1.1.1`
|
||||
(a short DNS outage for the whole cluster; check the Corefile after)
|
||||
- [ ] The Trivy Operator for scans that keep running (on the wishlist)
|
||||
|
||||
## wishlist.txt (2026-01-25)
|
||||
|
||||
- Done: Renovate; secrets out of git (Vault and ESO); SSO through authentik
|
||||
(Argo CD, Vault, Longhorn, FreshRSS, Actual, mail, immich); Gitea as a
|
||||
GitHub alternative; nix-infra for node001; most of the repo cleanup.
|
||||
- Partly: network policies, probes, requests and limits, non-root (7);
|
||||
backup testing (a script, not scheduled; 2); understanding Longhorn
|
||||
(docs/longhorn-second-ssd.md).
|
||||
- Open: Prometheus, Grafana, Loki, Alertmanager and which alerts (6);
|
||||
conftest and CI/CD (8); Trivy; a staging environment; an image registry;
|
||||
three nodes and opti1 on nix-infra (9); less manual work per new app.
|
||||
kube-hunter is no longer developed; the Trivy Operator or kube-bench
|
||||
cover that ground.
|
||||
- Dropped: shrinking the immich PVC to 200 GB. Longhorn can't shrink a
|
||||
volume, and with personal accounts the library will grow. Deleting stale
|
||||
snapshots (docs/longhorn-second-ssd.md) frees more.
|
||||
@@ -267,9 +267,31 @@ whatever time of day the hourly schedule had drifted to.
|
||||
CD app), the CNPG operator (`additionalArgs`) and Envoy Gateway
|
||||
(`provider.kubernetes.leaderElection`). Longhorn's CSI sidecars and
|
||||
global manager have no setting for it
|
||||
- [ ] `~/iosample.sh` on opti1 logs sda's counters and io pressure every 2s
|
||||
- [x] `~/iosample.sh` on opti1 logs sda's counters and io pressure every 2s
|
||||
for 26h (from 2026-10-24 12:35 UTC) into `~/iosample.log`, to put
|
||||
numbers on the disk latency during tonight's backups
|
||||
numbers on the disk latency during tonight's backups. Read on 2026-10-25
|
||||
at 02:35 UTC, per 10 minutes:
|
||||
- Quiet: ~50 writes/s, 0.5-2 ms per write on average, "full" IO
|
||||
pressure under 15%
|
||||
- 14:30-23:15: 250-440 writes/s and 200-400 reads/s, 6-20 ms per write,
|
||||
pressure 45-75%. Longhorn merging immich-claim's deleted snapshots
|
||||
(docs/longhorn-second-ssd.md)
|
||||
- Longhorn backups 00:00-00:15: up to 1,220 reads/s, pressure 69%; the
|
||||
Velero backup at 01:00 was incremental and short (pressure 29%)
|
||||
- The authentik and Vault upgrades 01:20-01:40 (image pulls,
|
||||
migrations): 19-33 ms per write, single 2s windows near 2 s per write,
|
||||
pressure 78%. The CSI sidecars and Longhorn's global manager lost
|
||||
their leases at 01:31
|
||||
Per minute against dqlite's own errors (2026-10-24 12:35 to 2026-10-25
|
||||
11:30, leaving out the CNPG range cancels): all 67 minutes with errors
|
||||
had sda ~100% busy, single 2s windows at 200 ms to 2.2 s per write and
|
||||
"full" pressure at 45-78%, against a median minute peak of 24 ms. The
|
||||
worst minute after the merges was the rollout of eight merged PRs at
|
||||
2026-10-25 11:25-11:27 (77 errors in one minute). The snapshot-controller,
|
||||
CNPG and Envoy Gateway held their 60s leases through all of it
|
||||
Ubuntu's sysstat already keeps per-device history every 10 minutes
|
||||
without a script: `sar -d -f /var/log/sysstat/sa24` showed sda at
|
||||
~26 MB/s read and ~27 MB/s written, 9 ms await, during the merging
|
||||
- [ ] Structural fix: a second SSD, see docs/longhorn-second-ssd.md. The OptiPlex 5060 (Micro, going by the
|
||||
i5-8600T) has an M.2 slot that takes NVMe, and no NVMe device is
|
||||
present; the Apacer AS350 is a DRAM-less 2.5" SATA SSD. An NVMe SSD with
|
||||
|
||||
@@ -23,7 +23,7 @@ spec:
|
||||
io.kompose.service: freshrss
|
||||
spec:
|
||||
initContainers:
|
||||
- image: alpine/git
|
||||
- image: alpine/git:v2.52.0
|
||||
name: git
|
||||
command:
|
||||
- git
|
||||
@@ -79,6 +79,23 @@ spec:
|
||||
ports:
|
||||
- containerPort: 80
|
||||
protocol: TCP
|
||||
resources:
|
||||
requests:
|
||||
cpu: 50m
|
||||
memory: 176Mi
|
||||
# TCP, because mod_auth_openidc answers 401 to anything that isn't a
|
||||
# browser.
|
||||
readinessProbe:
|
||||
tcpSocket:
|
||||
port: 80
|
||||
periodSeconds: 10
|
||||
livenessProbe:
|
||||
tcpSocket:
|
||||
port: 80
|
||||
initialDelaySeconds: 60
|
||||
periodSeconds: 30
|
||||
timeoutSeconds: 10
|
||||
failureThreshold: 5
|
||||
volumeMounts:
|
||||
- mountPath: /var/www/FreshRSS/data
|
||||
name: data
|
||||
|
||||
@@ -0,0 +1,58 @@
|
||||
# FreshRSS faces the internet through Envoy, so its pods only reach each
|
||||
# other, DNS and the internet: not the LAN (NAS, router), the Kubernetes
|
||||
# API or other namespaces.
|
||||
# Feeds and the OIDC login (authentik's public address) go out over
|
||||
# the internet.
|
||||
# Ingress comes from Envoy and the node itself (kubelet probes; 10.1.7.64
|
||||
# is the node's Calico VXLAN address, projectcalico.org/IPv4VXLANTunnelAddr).
|
||||
# Same layout as mbgwp/networkpolicy.yaml.
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: default
|
||||
spec:
|
||||
podSelector: {}
|
||||
policyTypes:
|
||||
- Ingress
|
||||
- Egress
|
||||
ingress:
|
||||
- from:
|
||||
- podSelector: {}
|
||||
- from:
|
||||
- ipBlock:
|
||||
cidr: 192.168.1.204/32
|
||||
- ipBlock:
|
||||
cidr: 10.1.7.64/32
|
||||
- from:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: envoy-gateway-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: envoy
|
||||
ports:
|
||||
- port: 80
|
||||
egress:
|
||||
- to:
|
||||
- podSelector: {}
|
||||
- to:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: kube-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
k8s-app: kube-dns
|
||||
ports:
|
||||
- protocol: UDP
|
||||
port: 53
|
||||
- protocol: TCP
|
||||
port: 53
|
||||
- to:
|
||||
- ipBlock:
|
||||
cidr: 0.0.0.0/0
|
||||
except:
|
||||
- 10.0.0.0/8
|
||||
- 100.64.0.0/10
|
||||
- 169.254.0.0/16
|
||||
- 172.16.0.0/12
|
||||
- 192.168.0.0/16
|
||||
@@ -58,6 +58,20 @@ spec:
|
||||
selector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: authentik
|
||||
- name: https-auth-scoutingmbg
|
||||
protocol: HTTPS
|
||||
port: 443
|
||||
hostname: auth.scoutingmbg.nl
|
||||
tls:
|
||||
certificateRefs:
|
||||
- name: auth-scoutingmbg-tls
|
||||
namespace: authentik
|
||||
allowedRoutes:
|
||||
namespaces:
|
||||
from: Selector
|
||||
selector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: authentik
|
||||
- name: https-vic
|
||||
protocol: HTTPS
|
||||
port: 443
|
||||
|
||||
@@ -0,0 +1,285 @@
|
||||
# Checks what Gatus can't see from outside and reports it to Gatus as
|
||||
# external endpoints (group "cluster" on s2), which alert through ntfy when
|
||||
# a check fails or when no report arrives (heartbeat). Velero's scheduled
|
||||
# backups failed every night from August to 2026-10-21 without anyone
|
||||
# noticing; a sealed Vault after a reboot looks fine from outside too.
|
||||
#
|
||||
# Every hour, from the Kubernetes API:
|
||||
# - velero-daily / velero-weekly: the newest finished backup of the
|
||||
# schedule is Completed and younger than 26h / 8 days
|
||||
# - longhorn: every attached volume is healthy and has a completed backup
|
||||
# younger than 26h (detached volumes are skipped; the recurring job skips
|
||||
# them too)
|
||||
# - vault-unsealed: all Vault pods report vault-sealed=false
|
||||
# - argocd-apps: every Argo CD application is Synced and Healthy
|
||||
# - postgres: every CloudNativePG cluster is in a healthy state
|
||||
#
|
||||
# The token is generated by ESO and never leaves the cluster; Gatus reads
|
||||
# it from the same Secret.
|
||||
apiVersion: generators.external-secrets.io/v1alpha1
|
||||
kind: Password
|
||||
metadata:
|
||||
name: backup-check-token
|
||||
spec:
|
||||
length: 40
|
||||
digits: 10
|
||||
symbols: 0
|
||||
noUpper: false
|
||||
allowRepeat: true
|
||||
secretKeys:
|
||||
- BACKUP_CHECK_TOKEN
|
||||
---
|
||||
apiVersion: external-secrets.io/v1
|
||||
kind: ExternalSecret
|
||||
metadata:
|
||||
name: backup-check-token
|
||||
spec:
|
||||
# Generate once; a new token would need a Gatus restart.
|
||||
refreshInterval: "0"
|
||||
target:
|
||||
name: backup-check-token
|
||||
creationPolicy: Owner
|
||||
dataFrom:
|
||||
- sourceRef:
|
||||
generatorRef:
|
||||
apiVersion: generators.external-secrets.io/v1alpha1
|
||||
kind: Password
|
||||
name: backup-check-token
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
name: backup-check
|
||||
---
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRole
|
||||
metadata:
|
||||
name: backup-check
|
||||
rules:
|
||||
- apiGroups: ["velero.io"]
|
||||
resources: ["backups"]
|
||||
verbs: ["list"]
|
||||
- apiGroups: ["longhorn.io"]
|
||||
resources: ["backups", "volumes"]
|
||||
verbs: ["list"]
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["list"]
|
||||
- apiGroups: ["argoproj.io"]
|
||||
resources: ["applications"]
|
||||
verbs: ["list"]
|
||||
- apiGroups: ["postgresql.cnpg.io"]
|
||||
resources: ["clusters"]
|
||||
verbs: ["list"]
|
||||
---
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRoleBinding
|
||||
metadata:
|
||||
name: backup-check
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: ClusterRole
|
||||
name: backup-check
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: backup-check
|
||||
namespace: gatus
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: backup-check
|
||||
data:
|
||||
check.py: |
|
||||
import datetime as dt
|
||||
import json
|
||||
import os
|
||||
import ssl
|
||||
import sys
|
||||
import urllib.parse
|
||||
import urllib.request
|
||||
|
||||
SA = "/var/run/secrets/kubernetes.io/serviceaccount"
|
||||
API = "https://kubernetes.default.svc"
|
||||
GATUS = os.environ.get("GATUS_URL", "http://gatus:8080")
|
||||
TOKEN = os.environ["BACKUP_CHECK_TOKEN"]
|
||||
NOW = dt.datetime.now(dt.timezone.utc)
|
||||
FINISHED = {"Completed", "PartiallyFailed", "Failed", "FailedValidation"}
|
||||
|
||||
with open(f"{SA}/token") as f:
|
||||
sa_token = f.read()
|
||||
api_ctx = ssl.create_default_context(cafile=f"{SA}/ca.crt")
|
||||
|
||||
|
||||
def items(path):
|
||||
req = urllib.request.Request(API + path, headers={"Authorization": f"Bearer {sa_token}"})
|
||||
with urllib.request.urlopen(req, context=api_ctx, timeout=30) as r:
|
||||
return json.load(r)["items"]
|
||||
|
||||
|
||||
def parse(ts):
|
||||
return dt.datetime.fromisoformat(ts.replace("Z", "+00:00"))
|
||||
|
||||
|
||||
def age(ts):
|
||||
hours = (NOW - parse(ts)).total_seconds() / 3600
|
||||
return f"{hours:.0f}h"
|
||||
|
||||
|
||||
def velero(schedule, max_hours):
|
||||
backups = [
|
||||
b for b in items("/apis/velero.io/v1/namespaces/velero/backups")
|
||||
if b["metadata"].get("labels", {}).get("velero.io/schedule-name") == schedule
|
||||
and b.get("status", {}).get("phase") in FINISHED
|
||||
]
|
||||
if not backups:
|
||||
return f"no finished {schedule} backup"
|
||||
newest = max(backups, key=lambda b: b["status"].get("startTimestamp", ""))
|
||||
status = newest["status"]
|
||||
name = newest["metadata"]["name"]
|
||||
if status["phase"] != "Completed":
|
||||
return f"{name} is {status['phase']} ({status.get('errors', 0)} errors)"
|
||||
done = status.get("completionTimestamp")
|
||||
if not done or (NOW - parse(done)).total_seconds() > max_hours * 3600:
|
||||
return f"newest {schedule} backup {name} is {age(done or status['startTimestamp'])} old"
|
||||
return None
|
||||
|
||||
|
||||
def longhorn(max_hours):
|
||||
newest = {}
|
||||
for b in items("/apis/longhorn.io/v1beta2/namespaces/longhorn-system/backups"):
|
||||
s = b.get("status", {})
|
||||
if s.get("state") == "Completed" and s.get("backupCreatedAt"):
|
||||
v = s.get("volumeName")
|
||||
newest[v] = max(newest.get(v, ""), s["backupCreatedAt"])
|
||||
problems = []
|
||||
for v in items("/apis/longhorn.io/v1beta2/namespaces/longhorn-system/volumes"):
|
||||
s = v.get("status", {})
|
||||
if s.get("state") != "attached":
|
||||
continue
|
||||
name = v["metadata"]["name"]
|
||||
pvc = s.get("kubernetesStatus", {}).get("pvcName") or name
|
||||
if s.get("robustness") != "healthy":
|
||||
problems.append(f"{pvc} is {s.get('robustness')}")
|
||||
last = newest.get(name)
|
||||
if not last:
|
||||
problems.append(f"{pvc} has no backup")
|
||||
elif (NOW - parse(last)).total_seconds() > max_hours * 3600:
|
||||
problems.append(f"{pvc} last backed up {age(last)} ago")
|
||||
return "; ".join(problems) or None
|
||||
|
||||
|
||||
def vault():
|
||||
pods = items("/api/v1/namespaces/vault/pods?labelSelector=component%3Dserver")
|
||||
if not pods:
|
||||
return "no Vault pods"
|
||||
sealed = [p["metadata"]["name"] for p in pods
|
||||
if p["metadata"].get("labels", {}).get("vault-sealed") != "false"]
|
||||
return f"sealed: {', '.join(sealed)}" if sealed else None
|
||||
|
||||
|
||||
def argocd():
|
||||
bad = []
|
||||
for a in items("/apis/argoproj.io/v1alpha1/namespaces/argocd/applications"):
|
||||
s = a.get("status", {})
|
||||
sync = s.get("sync", {}).get("status")
|
||||
health = s.get("health", {}).get("status")
|
||||
if sync != "Synced" or health != "Healthy":
|
||||
bad.append(f"{a['metadata']['name']} {sync}/{health}")
|
||||
return "; ".join(bad) or None
|
||||
|
||||
|
||||
def postgres():
|
||||
bad = [f"{c['metadata']['namespace']}/{c['metadata']['name']}: {c.get('status', {}).get('phase')}"
|
||||
for c in items("/apis/postgresql.cnpg.io/v1/clusters")
|
||||
if c.get("status", {}).get("phase") != "Cluster in healthy state"]
|
||||
return "; ".join(bad) or None
|
||||
|
||||
|
||||
def push(key, error):
|
||||
query = {"success": "false" if error else "true"}
|
||||
if error:
|
||||
query["error"] = error[:500]
|
||||
url = f"{GATUS}/api/v1/endpoints/{key}/external?{urllib.parse.urlencode(query)}"
|
||||
req = urllib.request.Request(url, method="POST", headers={"Authorization": f"Bearer {TOKEN}"})
|
||||
with urllib.request.urlopen(req, timeout=30) as r:
|
||||
r.read()
|
||||
|
||||
|
||||
checks = {
|
||||
"cluster_velero-daily": lambda: velero("daily-backup", 26),
|
||||
"cluster_velero-weekly": lambda: velero("weekly-backup", 8 * 24 + 2),
|
||||
"cluster_longhorn": lambda: longhorn(26),
|
||||
"cluster_vault-unsealed": vault,
|
||||
"cluster_argocd-apps": argocd,
|
||||
"cluster_postgres": postgres,
|
||||
}
|
||||
failed_pushes = 0
|
||||
for key, check in checks.items():
|
||||
try:
|
||||
error = check()
|
||||
except Exception as e: # report a broken check as a failure
|
||||
error = f"check failed: {e}"
|
||||
print(f"{key}: {error or 'ok'}", flush=True)
|
||||
try:
|
||||
push(key, error)
|
||||
except Exception as e:
|
||||
print(f"{key}: push to Gatus failed: {e}", flush=True)
|
||||
failed_pushes += 1
|
||||
sys.exit(1 if failed_pushes else 0)
|
||||
---
|
||||
apiVersion: batch/v1
|
||||
kind: CronJob
|
||||
metadata:
|
||||
name: backup-check
|
||||
spec:
|
||||
schedule: "17 * * * *"
|
||||
concurrencyPolicy: Forbid
|
||||
successfulJobsHistoryLimit: 1
|
||||
failedJobsHistoryLimit: 3
|
||||
jobTemplate:
|
||||
spec:
|
||||
backoffLimit: 1
|
||||
activeDeadlineSeconds: 300
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app: backup-check
|
||||
spec:
|
||||
serviceAccountName: backup-check
|
||||
restartPolicy: Never
|
||||
securityContext:
|
||||
runAsNonRoot: true
|
||||
runAsUser: 65534
|
||||
runAsGroup: 65534
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
containers:
|
||||
- name: check
|
||||
image: python:3.15.1-alpine3.24
|
||||
command: ["python", "/script/check.py"]
|
||||
env:
|
||||
- name: PYTHONDONTWRITEBYTECODE
|
||||
value: "1"
|
||||
envFrom:
|
||||
- secretRef:
|
||||
name: backup-check-token
|
||||
resources:
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 32Mi
|
||||
limits:
|
||||
memory: 128Mi
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
readOnlyRootFilesystem: true
|
||||
capabilities:
|
||||
drop: ["ALL"]
|
||||
volumeMounts:
|
||||
- name: script
|
||||
mountPath: /script
|
||||
readOnly: true
|
||||
volumes:
|
||||
- name: script
|
||||
configMap:
|
||||
name: backup-check
|
||||
@@ -136,3 +136,48 @@ endpoints:
|
||||
- "[STATUS] == 200"
|
||||
- "[BODY].status == UP"
|
||||
alerts: *ntfy
|
||||
|
||||
# Pushed every hour by the backup-check CronJob (backup-check.yaml), which
|
||||
# looks at what can't be seen from outside. s2 alerts on these itself: s1
|
||||
# has no view into the cluster.
|
||||
external-endpoints:
|
||||
- name: velero-daily
|
||||
group: cluster
|
||||
token: ${BACKUP_CHECK_TOKEN}
|
||||
heartbeat:
|
||||
interval: 3h
|
||||
alerts: &cluster-alert
|
||||
- type: ntfy
|
||||
failure-threshold: 2
|
||||
success-threshold: 1
|
||||
send-on-resolved: true
|
||||
- name: velero-weekly
|
||||
group: cluster
|
||||
token: ${BACKUP_CHECK_TOKEN}
|
||||
heartbeat:
|
||||
interval: 3h
|
||||
alerts: *cluster-alert
|
||||
- name: longhorn
|
||||
group: cluster
|
||||
token: ${BACKUP_CHECK_TOKEN}
|
||||
heartbeat:
|
||||
interval: 3h
|
||||
alerts: *cluster-alert
|
||||
- name: vault-unsealed
|
||||
group: cluster
|
||||
token: ${BACKUP_CHECK_TOKEN}
|
||||
heartbeat:
|
||||
interval: 3h
|
||||
alerts: *cluster-alert
|
||||
- name: argocd-apps
|
||||
group: cluster
|
||||
token: ${BACKUP_CHECK_TOKEN}
|
||||
heartbeat:
|
||||
interval: 3h
|
||||
alerts: *cluster-alert
|
||||
- name: postgres
|
||||
group: cluster
|
||||
token: ${BACKUP_CHECK_TOKEN}
|
||||
heartbeat:
|
||||
interval: 3h
|
||||
alerts: *cluster-alert
|
||||
@@ -25,6 +25,9 @@ spec:
|
||||
envFrom:
|
||||
- secretRef:
|
||||
name: gatus-ntfy
|
||||
# Token for the external endpoints, see backup-check.yaml
|
||||
- secretRef:
|
||||
name: backup-check-token
|
||||
ports:
|
||||
- containerPort: 8080
|
||||
protocol: TCP
|
||||
|
||||
@@ -10,6 +10,8 @@ resources:
|
||||
- gatus-service.yaml
|
||||
- certificate.yaml
|
||||
- httproute.yaml
|
||||
- networkpolicy.yaml
|
||||
- backup-check.yaml
|
||||
|
||||
configMapGenerator:
|
||||
- name: gatus-config
|
||||
|
||||
@@ -0,0 +1,85 @@
|
||||
# Gatus faces the internet through Envoy, so its pods only reach each
|
||||
# other, DNS and the internet: not the LAN (NAS, router), the Kubernetes
|
||||
# API or other namespaces.
|
||||
# Its checks go to public addresses; alerts go to ntfy in-cluster.
|
||||
# Ingress comes from Envoy and the node itself (kubelet probes; 10.1.7.64
|
||||
# is the node's Calico VXLAN address, projectcalico.org/IPv4VXLANTunnelAddr).
|
||||
# Same layout as mbgwp/networkpolicy.yaml.
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: default
|
||||
spec:
|
||||
podSelector: {}
|
||||
policyTypes:
|
||||
- Ingress
|
||||
- Egress
|
||||
ingress:
|
||||
- from:
|
||||
- podSelector: {}
|
||||
- from:
|
||||
- ipBlock:
|
||||
cidr: 192.168.1.204/32
|
||||
- ipBlock:
|
||||
cidr: 10.1.7.64/32
|
||||
- from:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: envoy-gateway-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: envoy
|
||||
ports:
|
||||
- port: 8080
|
||||
egress:
|
||||
- to:
|
||||
- podSelector: {}
|
||||
- to:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: kube-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
k8s-app: kube-dns
|
||||
ports:
|
||||
- protocol: UDP
|
||||
port: 53
|
||||
- protocol: TCP
|
||||
port: 53
|
||||
- to:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: ntfy
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app: ntfy
|
||||
ports:
|
||||
- port: 80
|
||||
- to:
|
||||
- ipBlock:
|
||||
cidr: 0.0.0.0/0
|
||||
except:
|
||||
- 10.0.0.0/8
|
||||
- 100.64.0.0/10
|
||||
- 169.254.0.0/16
|
||||
- 172.16.0.0/12
|
||||
- 192.168.0.0/16
|
||||
---
|
||||
# backup-check.yaml reads backups, volumes and Vault's pods from the API
|
||||
# server (the node, port 16443).
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: backup-check-to-api
|
||||
spec:
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app: backup-check
|
||||
policyTypes:
|
||||
- Egress
|
||||
egress:
|
||||
- to:
|
||||
- ipBlock:
|
||||
cidr: 192.168.1.204/32
|
||||
ports:
|
||||
- port: 16443
|
||||
@@ -20,7 +20,7 @@ spec:
|
||||
fsGroup: 1000
|
||||
containers:
|
||||
- name: gitea
|
||||
image: gitea/gitea:1.27.3
|
||||
image: gitea/gitea:28.2.0
|
||||
env:
|
||||
- name: USER_UID
|
||||
value: "1000"
|
||||
@@ -50,6 +50,25 @@ spec:
|
||||
- containerPort: 3000
|
||||
name: http
|
||||
protocol: TCP
|
||||
resources:
|
||||
requests:
|
||||
cpu: 20m
|
||||
memory: 336Mi
|
||||
# /api/healthz checks the database and the cache.
|
||||
readinessProbe:
|
||||
httpGet:
|
||||
path: /api/healthz
|
||||
port: http
|
||||
periodSeconds: 10
|
||||
timeoutSeconds: 5
|
||||
livenessProbe:
|
||||
httpGet:
|
||||
path: /api/healthz
|
||||
port: http
|
||||
initialDelaySeconds: 60
|
||||
periodSeconds: 30
|
||||
timeoutSeconds: 10
|
||||
failureThreshold: 5
|
||||
volumeMounts:
|
||||
- mountPath: /data
|
||||
name: data
|
||||
|
||||
@@ -0,0 +1,57 @@
|
||||
# Gitea faces the internet through Envoy, so its pods only reach each
|
||||
# other, DNS and the internet: not the LAN (NAS, router), the Kubernetes
|
||||
# API or other namespaces.
|
||||
# Mirrors and webhooks go out over the internet.
|
||||
# Ingress comes from Envoy and the node itself (kubelet probes; 10.1.7.64
|
||||
# is the node's Calico VXLAN address, projectcalico.org/IPv4VXLANTunnelAddr).
|
||||
# Same layout as mbgwp/networkpolicy.yaml.
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: default
|
||||
spec:
|
||||
podSelector: {}
|
||||
policyTypes:
|
||||
- Ingress
|
||||
- Egress
|
||||
ingress:
|
||||
- from:
|
||||
- podSelector: {}
|
||||
- from:
|
||||
- ipBlock:
|
||||
cidr: 192.168.1.204/32
|
||||
- ipBlock:
|
||||
cidr: 10.1.7.64/32
|
||||
- from:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: envoy-gateway-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: envoy
|
||||
ports:
|
||||
- port: 3000
|
||||
egress:
|
||||
- to:
|
||||
- podSelector: {}
|
||||
- to:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: kube-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
k8s-app: kube-dns
|
||||
ports:
|
||||
- protocol: UDP
|
||||
port: 53
|
||||
- protocol: TCP
|
||||
port: 53
|
||||
- to:
|
||||
- ipBlock:
|
||||
cidr: 0.0.0.0/0
|
||||
except:
|
||||
- 10.0.0.0/8
|
||||
- 100.64.0.0/10
|
||||
- 169.254.0.0/16
|
||||
- 172.16.0.0/12
|
||||
- 192.168.0.0/16
|
||||
+28
-3
@@ -63,6 +63,10 @@ spec:
|
||||
main:
|
||||
containers:
|
||||
main:
|
||||
resources:
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 64Mi
|
||||
image:
|
||||
repository: docker.io/valkey/valkey
|
||||
tag: 9.1.2-alpine@sha256:48332870af354a799964c0012ae1194a0bf2bf894eb508f945810596dc2d8d11
|
||||
@@ -85,6 +89,10 @@ spec:
|
||||
image:
|
||||
repository: ghcr.io/immich-app/immich-server
|
||||
pullPolicy: IfNotPresent
|
||||
resources:
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 1280Mi
|
||||
# Node trusts its built-in roots, which still include the
|
||||
# ones above the compromised eMudhra intermediates. Use
|
||||
# patched-ca-bundle through OpenSSL until Node ships a fix.
|
||||
@@ -109,10 +117,19 @@ spec:
|
||||
image:
|
||||
repository: ghcr.io/immich-app/immich-machine-learning
|
||||
pullPolicy: IfNotPresent
|
||||
# Idle at night (234Mi); the models take over a GiB when
|
||||
# it works.
|
||||
resources:
|
||||
requests:
|
||||
cpu: 50m
|
||||
memory: 1Gi
|
||||
env:
|
||||
TRANSFORMERS_CACHE: /cache
|
||||
HF_XET_CACHE: /cache/huggingface-xet
|
||||
MPLCONFIGDIR: /cache/matplotlib-config
|
||||
# The optimized models of v3.3.0: faster, less memory,
|
||||
# and the same results, so no jobs to run again.
|
||||
MACHINE_LEARNING_MODEL_REVISION: v2
|
||||
# Trust store without the compromised eMudhra
|
||||
# intermediates; requests would otherwise use certifi.
|
||||
SSL_CERT_FILE: /etc/ssl/certs/ca-certificates.crt
|
||||
@@ -125,11 +142,19 @@ spec:
|
||||
globalMounts:
|
||||
- path: /etc/ssl/certs
|
||||
readOnly: true
|
||||
# The models and their one-off preparation, kept across restarts.
|
||||
# Downloaded again if lost, so no backups: the no-backup group
|
||||
# keeps it out of Longhorn's default one (backup-daily), and
|
||||
# Velero skips that label too (velero/skip-emptydir-policy.yaml).
|
||||
cache:
|
||||
enabled: true
|
||||
# Optional: to avoid downloading the ML models every start, use
|
||||
# a persistentVolumeClaim with size, accessMode and storageClass
|
||||
type: emptyDir
|
||||
type: persistentVolumeClaim
|
||||
storageClass: longhorn
|
||||
accessMode: ReadWriteOnce
|
||||
size: 10Gi
|
||||
labels:
|
||||
recurring-job.longhorn.io/source: enabled
|
||||
recurring-job-group.longhorn.io/no-backup: enabled
|
||||
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
|
||||
@@ -27,7 +27,7 @@ spec:
|
||||
# immich_role and immich_quota claims (authentik/blueprint-scouting.yaml).
|
||||
oauth:
|
||||
enabled: true
|
||||
issuerUrl: https://authentik.rubenhensen.nl/application/o/immich/
|
||||
issuerUrl: https://auth.scoutingmbg.nl/application/o/immich/
|
||||
clientId: immich
|
||||
clientSecret: "{{ .client_secret }}"
|
||||
scope: openid email profile immich
|
||||
|
||||
@@ -0,0 +1,102 @@
|
||||
# immich faces the internet (every member of the group logs in, and shared
|
||||
# links are public), so its pods only reach each other, DNS and the
|
||||
# internet: not the LAN (NAS, router), the Kubernetes API or other
|
||||
# namespaces. The OIDC login with authentik goes out through its public
|
||||
# address. Ingress comes from Envoy, the CNPG operator and the node itself
|
||||
# (kubelet probes; 10.1.7.64 is the node's Calico VXLAN address,
|
||||
# projectcalico.org/IPv4VXLANTunnelAddr).
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: default
|
||||
spec:
|
||||
podSelector: {}
|
||||
policyTypes:
|
||||
- Ingress
|
||||
- Egress
|
||||
ingress:
|
||||
- from:
|
||||
- podSelector: {}
|
||||
- from:
|
||||
- ipBlock:
|
||||
cidr: 192.168.1.204/32
|
||||
- ipBlock:
|
||||
cidr: 10.1.7.64/32
|
||||
egress:
|
||||
- to:
|
||||
- podSelector: {}
|
||||
- to:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: kube-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
k8s-app: kube-dns
|
||||
ports:
|
||||
- protocol: UDP
|
||||
port: 53
|
||||
- protocol: TCP
|
||||
port: 53
|
||||
# The internet: authentik's public address, the ML models from Hugging
|
||||
# Face.
|
||||
- to:
|
||||
- ipBlock:
|
||||
cidr: 0.0.0.0/0
|
||||
except:
|
||||
- 10.0.0.0/8
|
||||
- 100.64.0.0/10
|
||||
- 169.254.0.0/16
|
||||
- 172.16.0.0/12
|
||||
- 192.168.0.0/16
|
||||
---
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: server-from-envoy
|
||||
spec:
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/instance: helm-immich
|
||||
app.kubernetes.io/name: server
|
||||
policyTypes:
|
||||
- Ingress
|
||||
ingress:
|
||||
- from:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: envoy-gateway-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: envoy
|
||||
ports:
|
||||
- port: 2283
|
||||
---
|
||||
# The CNPG operator checks each instance on its status port and connects to
|
||||
# PostgreSQL; the instance manager inside each pod watches its Cluster
|
||||
# through the API server (the node, port 16443).
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: postgres-cnpg
|
||||
spec:
|
||||
podSelector:
|
||||
matchExpressions:
|
||||
- key: cnpg.io/cluster
|
||||
operator: Exists
|
||||
policyTypes:
|
||||
- Ingress
|
||||
- Egress
|
||||
ingress:
|
||||
- from:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: cnpg-system
|
||||
ports:
|
||||
- port: 8000
|
||||
- port: 5432
|
||||
egress:
|
||||
- to:
|
||||
- ipBlock:
|
||||
cidr: 192.168.1.204/32
|
||||
ports:
|
||||
- port: 16443
|
||||
@@ -9,6 +9,10 @@ spec:
|
||||
# CNPG image with VectorChord and pgvector, which immich 2.x and 3.x use
|
||||
# for its vector indexes (pgvecto.rs is gone in immich 3.0).
|
||||
imageName: ghcr.io/tensorchord/cloudnative-vectorchord:17.11-1.1.1
|
||||
resources:
|
||||
requests:
|
||||
cpu: 20m
|
||||
memory: 320Mi
|
||||
|
||||
postgresql:
|
||||
shared_preload_libraries:
|
||||
|
||||
@@ -16,14 +16,26 @@ spec:
|
||||
targetRevision: 25.10.4
|
||||
helm:
|
||||
values: |
|
||||
resources:
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 48Mi
|
||||
metrics:
|
||||
enabled: true
|
||||
serviceMonitor:
|
||||
enabled: false
|
||||
webhook:
|
||||
resources:
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 32Mi
|
||||
serviceMonitor:
|
||||
enabled: false
|
||||
certController:
|
||||
resources:
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 32Mi
|
||||
serviceMonitor:
|
||||
enabled: false
|
||||
syncPolicy:
|
||||
|
||||
@@ -0,0 +1,87 @@
|
||||
# WordPress faces the internet, so if it is ever taken over it should only
|
||||
# reach its own database, DNS and the internet: not the LAN (NAS, router),
|
||||
# the Kubernetes API or other namespaces. Ingress comes from Envoy, the
|
||||
# mariadb-operator and the node itself (kubelet probes; 10.1.7.64 is the
|
||||
# node's Calico VXLAN address, projectcalico.org/IPv4VXLANTunnelAddr).
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: default
|
||||
spec:
|
||||
podSelector: {}
|
||||
policyTypes:
|
||||
- Ingress
|
||||
- Egress
|
||||
ingress:
|
||||
- from:
|
||||
- podSelector: {}
|
||||
- from:
|
||||
- ipBlock:
|
||||
cidr: 192.168.1.204/32
|
||||
- ipBlock:
|
||||
cidr: 10.1.7.64/32
|
||||
egress:
|
||||
- to:
|
||||
- podSelector: {}
|
||||
- to:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: kube-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
k8s-app: kube-dns
|
||||
ports:
|
||||
- protocol: UDP
|
||||
port: 53
|
||||
- protocol: TCP
|
||||
port: 53
|
||||
# The internet, which includes this site's own public address
|
||||
# (wp-cron's loopback requests go out and come back through Envoy).
|
||||
- to:
|
||||
- ipBlock:
|
||||
cidr: 0.0.0.0/0
|
||||
except:
|
||||
- 10.0.0.0/8
|
||||
- 100.64.0.0/10
|
||||
- 169.254.0.0/16
|
||||
- 172.16.0.0/12
|
||||
- 192.168.0.0/16
|
||||
---
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: wordpress-from-envoy
|
||||
spec:
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: wordpress
|
||||
policyTypes:
|
||||
- Ingress
|
||||
ingress:
|
||||
- from:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: envoy-gateway-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: envoy
|
||||
ports:
|
||||
- port: 8000
|
||||
---
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: mariadb-from-operator
|
||||
spec:
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: mariadb
|
||||
policyTypes:
|
||||
- Ingress
|
||||
ingress:
|
||||
- from:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: mariadb-system
|
||||
ports:
|
||||
- port: 3306
|
||||
@@ -0,0 +1,35 @@
|
||||
# Garage on the NAS
|
||||
|
||||
S3 storage for Velero, on the Synology (192.168.1.99) in Docker, outside
|
||||
the cluster. Replaced MinIO, which is no longer maintained. One node, data
|
||||
in `/volume1/docker/garage/{meta,data}`. S3 API on port 3900, admin API on
|
||||
3903, both LAN only. Set up 2026-10-25 with Garage v2.5.0.
|
||||
|
||||
The NAS is reached as `ssh -p 34000 rubenhensen@192.168.1.99`; docker is
|
||||
in `/usr/local/bin`, which a non-interactive SSH session doesn't have on
|
||||
its PATH.
|
||||
|
||||
## Setup
|
||||
|
||||
`garage.toml` here has placeholders for the two secrets; on the NAS they
|
||||
were filled in once with `openssl rand -hex 32` (`rpc_secret`) and
|
||||
`openssl rand -base64 32` (`admin_token`), and only exist there.
|
||||
|
||||
```
|
||||
cd /volume1/docker/garage
|
||||
docker compose up -d
|
||||
g="docker exec garage /garage"
|
||||
$g layout assign -z nas -c 800G <node id from $g status>
|
||||
$g layout apply --version 1
|
||||
$g bucket create velero-backups
|
||||
$g key create velero
|
||||
$g bucket allow --read --write --key velero velero-backups
|
||||
```
|
||||
|
||||
Velero's key is in Vault as `kv/velero-s3` (`access_key_id`,
|
||||
`secret_access_key`) and reaches Velero through
|
||||
`velero/external-secret.yaml`. Without the cluster, `$g key info velero
|
||||
--show-secret` on the NAS shows it again.
|
||||
|
||||
Renovate updates the image tag in `compose.yaml`, but nothing deploys it:
|
||||
after merging, `docker compose pull && docker compose up -d` on the NAS.
|
||||
@@ -0,0 +1,12 @@
|
||||
services:
|
||||
garage:
|
||||
image: dxflrs/garage:v2.5.0
|
||||
container_name: garage
|
||||
restart: unless-stopped
|
||||
ports:
|
||||
- "3900:3900" # S3 API
|
||||
- "3903:3903" # admin API
|
||||
volumes:
|
||||
- ./garage.toml:/etc/garage.toml:ro
|
||||
- ./meta:/var/lib/garage/meta
|
||||
- ./data:/var/lib/garage/data
|
||||
@@ -0,0 +1,29 @@
|
||||
# One node on the Synology. Velero's kopia data is encrypted, so
|
||||
# compression would only cost CPU.
|
||||
#
|
||||
# SQLite rather than the default LMDB: LMDB can be corrupted by an unclean
|
||||
# shutdown, and a single node has no other node to repair from. With
|
||||
# metadata_fsync SQLite runs WAL with synchronous=NORMAL, which only syncs
|
||||
# at checkpoints; LMDB with metadata_fsync synced every transaction, ~270
|
||||
# writes/s on the NAS's two disks with Garage idle. Converted 2026-10-25
|
||||
# with `garage convert-db`.
|
||||
metadata_dir = "/var/lib/garage/meta"
|
||||
data_dir = "/var/lib/garage/data"
|
||||
db_engine = "sqlite"
|
||||
metadata_fsync = true
|
||||
data_fsync = true
|
||||
metadata_auto_snapshot_interval = "6h"
|
||||
replication_factor = 1
|
||||
compression_level = "none"
|
||||
|
||||
rpc_bind_addr = "[::]:3901"
|
||||
rpc_public_addr = "127.0.0.1:3901"
|
||||
rpc_secret = "@RPC_SECRET@"
|
||||
|
||||
[s3_api]
|
||||
s3_region = "garage"
|
||||
api_bind_addr = "[::]:3900"
|
||||
|
||||
[admin]
|
||||
api_bind_addr = "[::]:3903"
|
||||
admin_token = "@ADMIN_TOKEN@"
|
||||
@@ -19,6 +19,11 @@ let
|
||||
"serpbear.rubenhensen.nl"
|
||||
"git.rubenhensen.nl"
|
||||
"vic.rubenhensen.nl"
|
||||
# The group's DNS points these at rubenhensen.nl, i.e. here
|
||||
"scoutingmbg.nl"
|
||||
"www.scoutingmbg.nl"
|
||||
"foto.scoutingmbg.nl"
|
||||
"auth.scoutingmbg.nl"
|
||||
];
|
||||
|
||||
sniMapEntries =
|
||||
|
||||
@@ -10,3 +10,4 @@ resources:
|
||||
- ntfy-service.yaml
|
||||
- certificate.yaml
|
||||
- httproute.yaml
|
||||
- networkpolicy.yaml
|
||||
@@ -0,0 +1,67 @@
|
||||
# ntfy faces the internet through Envoy, so its pods only reach each
|
||||
# other, DNS and the internet: not the LAN (NAS, router), the Kubernetes
|
||||
# API or other namespaces.
|
||||
# Push notifications go out over the internet.
|
||||
# Ingress comes from Envoy and the node itself (kubelet probes; 10.1.7.64
|
||||
# is the node's Calico VXLAN address, projectcalico.org/IPv4VXLANTunnelAddr).
|
||||
# Same layout as mbgwp/networkpolicy.yaml.
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: default
|
||||
spec:
|
||||
podSelector: {}
|
||||
policyTypes:
|
||||
- Ingress
|
||||
- Egress
|
||||
ingress:
|
||||
- from:
|
||||
- podSelector: {}
|
||||
- from:
|
||||
- ipBlock:
|
||||
cidr: 192.168.1.204/32
|
||||
- ipBlock:
|
||||
cidr: 10.1.7.64/32
|
||||
- from:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: envoy-gateway-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: envoy
|
||||
ports:
|
||||
- port: 80
|
||||
# Gatus sends its alerts to ntfy in-cluster.
|
||||
- from:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: gatus
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app: gatus
|
||||
ports:
|
||||
- port: 80
|
||||
egress:
|
||||
- to:
|
||||
- podSelector: {}
|
||||
- to:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: kube-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
k8s-app: kube-dns
|
||||
ports:
|
||||
- protocol: UDP
|
||||
port: 53
|
||||
- protocol: TCP
|
||||
port: 53
|
||||
- to:
|
||||
- ipBlock:
|
||||
cidr: 0.0.0.0/0
|
||||
except:
|
||||
- 10.0.0.0/8
|
||||
- 100.64.0.0/10
|
||||
- 169.254.0.0/16
|
||||
- 172.16.0.0/12
|
||||
- 192.168.0.0/16
|
||||
@@ -16,7 +16,7 @@ spec:
|
||||
spec:
|
||||
containers:
|
||||
- name: ntfy
|
||||
image: binwiederhier/ntfy:v2.28.0
|
||||
image: binwiederhier/ntfy:v2.34.0
|
||||
args: ["serve"]
|
||||
env:
|
||||
- name: NTFY_BASE_URL
|
||||
|
||||
+34
-23
@@ -1,11 +1,12 @@
|
||||
{
|
||||
"$schema": "https://docs.renovatebot.com/renovate-schema.json",
|
||||
"extends": [
|
||||
"config:recommended"
|
||||
"config:recommended",
|
||||
"customManagers:githubActionsVersions"
|
||||
],
|
||||
"argocd": {
|
||||
"managerFilePatterns": [
|
||||
"/apps/templates/.+\\.yaml$/"
|
||||
"/^(?!(nix-infra-machine|backup-testing|docs|tools|\\.github)/)[^/]+/.+\\.yaml$/"
|
||||
]
|
||||
},
|
||||
"helm-values": {
|
||||
@@ -15,25 +16,10 @@
|
||||
},
|
||||
"kubernetes": {
|
||||
"managerFilePatterns": [
|
||||
"/apps/templates/.+\\.yaml$/",
|
||||
"/serpbear/.+\\.yaml$/",
|
||||
"/bolletjestrui/.+\\.yaml$/",
|
||||
"/gitea/.+\\.yaml$/",
|
||||
"/gatus/.+\\.yaml$/",
|
||||
"/ntfy/.+\\.yaml$/"
|
||||
"/^(?!(nix-infra-machine|backup-testing|docs|tools|\\.github)/)[^/]+/.+\\.yaml$/"
|
||||
]
|
||||
},
|
||||
"customManagers": [
|
||||
{
|
||||
"customType": "regex",
|
||||
"managerFilePatterns": [
|
||||
"/apps/templates/.+\\.yaml$/"
|
||||
],
|
||||
"matchStrings": [
|
||||
"repoURL: https://github.com/(?<depName>[^/]+/[^/\\.]+)\\.git\\n\\s+targetRevision: (?<currentValue>.*)"
|
||||
],
|
||||
"datasourceTemplate": "github-tags"
|
||||
},
|
||||
{
|
||||
"customType": "regex",
|
||||
"managerFilePatterns": [
|
||||
@@ -43,6 +29,17 @@
|
||||
"repoURL: (?<registryUrl>.*?)\\n\\s+targetRevision: (?<currentValue>[^\\s]+)\\n\\s+chart: (?<depName>[^\\s]+)"
|
||||
],
|
||||
"datasourceTemplate": "helm"
|
||||
},
|
||||
{
|
||||
"customType": "regex",
|
||||
"description": "CloudNativePG clusters name their image in imageName",
|
||||
"managerFilePatterns": [
|
||||
"/^[^/]+/postgresql-cluster[^/]*\\.yaml$/"
|
||||
],
|
||||
"matchStrings": [
|
||||
"imageName: (?<depName>[^:\\s]+):(?<currentValue>\\S+)"
|
||||
],
|
||||
"datasourceTemplate": "docker"
|
||||
}
|
||||
],
|
||||
"packageRules": [
|
||||
@@ -55,12 +52,26 @@
|
||||
"separateMinorPatch": true
|
||||
},
|
||||
{
|
||||
"matchDatasources": [
|
||||
"github-tags"
|
||||
"description": "CI renders with the same Helm as Argo CD (3.5 ships Helm 4.2); move it together with Argo CD",
|
||||
"matchFileNames": [
|
||||
".github/workflows/**"
|
||||
],
|
||||
"semanticCommits": "enabled",
|
||||
"commitMessageTopic": "{{depName}}",
|
||||
"separateMinorPatch": true
|
||||
"matchDepNames": [
|
||||
"helm/helm"
|
||||
],
|
||||
"enabled": false
|
||||
},
|
||||
{
|
||||
"description": "A PostgreSQL major upgrade needs pg_upgrade or a dump, not a tag bump",
|
||||
"matchDepNames": [
|
||||
"ghcr.io/cloudnative-pg/postgresql",
|
||||
"ghcr.io/tensorchord/cloudnative-vectorchord",
|
||||
"ghcr.io/tensorchord/cloudnative-pgvecto.rs"
|
||||
],
|
||||
"matchUpdateTypes": [
|
||||
"major"
|
||||
],
|
||||
"enabled": false
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,18 +0,0 @@
|
||||
# apiVersion: external-secrets.io/v1beta1
|
||||
# kind: ExternalSecret
|
||||
# metadata:
|
||||
# name: hensenio-smtp-secrets
|
||||
# namespace: blog
|
||||
# spec:
|
||||
# refreshInterval: "15m"
|
||||
# secretStoreRef:
|
||||
# name: vault-backend
|
||||
# kind: ClusterSecretStore
|
||||
# target:
|
||||
# name: hensenio-smtp
|
||||
# creationPolicy: Owner
|
||||
# data:
|
||||
# - secretKey: smtp-password
|
||||
# remoteRef:
|
||||
# key: kv/hensenio/smtp
|
||||
# property: password
|
||||
@@ -0,0 +1,56 @@
|
||||
# SerpBear faces the internet through Envoy, so its pods only reach each
|
||||
# other, DNS and the internet: not the LAN (NAS, router), the Kubernetes
|
||||
# API or other namespaces. Its scraper APIs are on the internet.
|
||||
# Ingress comes from Envoy and the node itself (kubelet probes; 10.1.7.64
|
||||
# is the node's Calico VXLAN address, projectcalico.org/IPv4VXLANTunnelAddr).
|
||||
# Same layout as mbgwp/networkpolicy.yaml.
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: default
|
||||
spec:
|
||||
podSelector: {}
|
||||
policyTypes:
|
||||
- Ingress
|
||||
- Egress
|
||||
ingress:
|
||||
- from:
|
||||
- podSelector: {}
|
||||
- from:
|
||||
- ipBlock:
|
||||
cidr: 192.168.1.204/32
|
||||
- ipBlock:
|
||||
cidr: 10.1.7.64/32
|
||||
- from:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: envoy-gateway-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: envoy
|
||||
ports:
|
||||
- port: 3000
|
||||
egress:
|
||||
- to:
|
||||
- podSelector: {}
|
||||
- to:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: kube-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
k8s-app: kube-dns
|
||||
ports:
|
||||
- protocol: UDP
|
||||
port: 53
|
||||
- protocol: TCP
|
||||
port: 53
|
||||
- to:
|
||||
- ipBlock:
|
||||
cidr: 0.0.0.0/0
|
||||
except:
|
||||
- 10.0.0.0/8
|
||||
- 100.64.0.0/10
|
||||
- 169.254.0.0/16
|
||||
- 172.16.0.0/12
|
||||
- 192.168.0.0/16
|
||||
@@ -56,6 +56,23 @@ spec:
|
||||
ports:
|
||||
- containerPort: 3000
|
||||
protocol: TCP
|
||||
resources:
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 160Mi
|
||||
readinessProbe:
|
||||
httpGet:
|
||||
path: /login
|
||||
port: 3000
|
||||
periodSeconds: 10
|
||||
timeoutSeconds: 5
|
||||
livenessProbe:
|
||||
tcpSocket:
|
||||
port: 3000
|
||||
initialDelaySeconds: 60
|
||||
periodSeconds: 30
|
||||
timeoutSeconds: 10
|
||||
failureThreshold: 5
|
||||
volumeMounts:
|
||||
- mountPath: /app/data
|
||||
name: data
|
||||
|
||||
@@ -0,0 +1,306 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Render every Argo CD app in this repo the way Argo CD does and validate
|
||||
the output with kubeconform, so a broken manifest or a chart bump that no
|
||||
longer renders fails the PR instead of the sync.
|
||||
|
||||
Run from anywhere; needs helm, kustomize, kubeconform, git and PyYAML.
|
||||
The apps/ chart is rendered first, then every Application found in it and
|
||||
in the app folders. Sources:
|
||||
- a chart: helm template with the Application's values, value files and
|
||||
parameters
|
||||
- a path in this repo: helm template (Chart.yaml), kustomize build
|
||||
(kustomization.yaml) or the folder's YAML files (directory include and
|
||||
exclude)
|
||||
- a path in another git repository: cloned at targetRevision, then the
|
||||
same, with the Application's kustomize patches applied
|
||||
Every YAML file in the repo is also checked for duplicate keys, which
|
||||
YAML parsers resolve silently by keeping the last one.
|
||||
|
||||
Repo rules, on what this repo's own folders render (not on charts or
|
||||
remote bases):
|
||||
- no Secret with data: secrets come from Vault through ESO
|
||||
- every image has a tag other than latest
|
||||
- warnings (annotations on the PR) for containers without requests or
|
||||
probes
|
||||
"""
|
||||
import fnmatch
|
||||
import os
|
||||
import pathlib
|
||||
import subprocess
|
||||
import sys
|
||||
import tempfile
|
||||
import time
|
||||
|
||||
import yaml
|
||||
|
||||
ROOT = pathlib.Path(__file__).resolve().parents[2]
|
||||
OWN_REPOS = {"https://github.com/rubenhensen/k8scd.git", "https://github.com/rubenhensen/k8scd"}
|
||||
SKIP_DIRS = {".git", ".github", "nix-infra-machine", "docs", "tools", "backup-testing"}
|
||||
# Helm's view of the cluster; the JSON schemas only go up to 1.34.
|
||||
KUBE_VERSION = "1.36.0"
|
||||
SCHEMA_VERSION = "1.34.12"
|
||||
CRD_SCHEMAS = ("https://raw.githubusercontent.com/datreeio/CRDs-catalog/main/"
|
||||
"{{.Group}}/{{.ResourceKind}}_{{.ResourceAPIVersion}}.json")
|
||||
|
||||
failures = []
|
||||
|
||||
|
||||
def run(cmd, **kw):
|
||||
# Registries rate-limit now and then (ghcr.io answers 429); try again.
|
||||
for attempt in range(3):
|
||||
try:
|
||||
return subprocess.run(cmd, check=True, capture_output=True, text=True, **kw).stdout
|
||||
except subprocess.CalledProcessError as e:
|
||||
transient = any(s in (e.stderr or "") for s in ("429", "toomanyrequests", "timeout", "connection reset"))
|
||||
if not transient or attempt == 2:
|
||||
raise
|
||||
time.sleep(10 * (attempt + 1))
|
||||
|
||||
|
||||
class UniqueKeyLoader(yaml.SafeLoader):
|
||||
pass
|
||||
|
||||
|
||||
def construct_mapping(loader, node, deep=False):
|
||||
keys = set()
|
||||
for key_node, _ in node.value:
|
||||
key = loader.construct_object(key_node, deep=deep)
|
||||
if key in keys:
|
||||
raise yaml.constructor.ConstructorError(
|
||||
None, None, f"duplicate key {key!r}", key_node.start_mark)
|
||||
keys.add(key)
|
||||
return loader.construct_mapping(node, deep)
|
||||
|
||||
|
||||
UniqueKeyLoader.add_constructor(
|
||||
yaml.resolver.BaseResolver.DEFAULT_MAPPING_TAG, construct_mapping)
|
||||
|
||||
|
||||
def yaml_files():
|
||||
for path in sorted(ROOT.rglob("*.y*ml")):
|
||||
rel = path.relative_to(ROOT)
|
||||
if rel.parts[0] in SKIP_DIRS or path.suffix not in (".yaml", ".yml"):
|
||||
continue
|
||||
yield path
|
||||
|
||||
|
||||
def check_duplicate_keys():
|
||||
for path in yaml_files():
|
||||
if path.parent.name == "templates": # Helm templates aren't YAML yet
|
||||
continue
|
||||
try:
|
||||
list(yaml.load_all(path.read_text(), Loader=UniqueKeyLoader))
|
||||
except yaml.YAMLError as e:
|
||||
failures.append(f"{path.relative_to(ROOT)}: {e}")
|
||||
|
||||
|
||||
def pod_specs(doc):
|
||||
spec = doc.get("spec") or {}
|
||||
kind = doc.get("kind")
|
||||
if kind == "Pod":
|
||||
yield spec
|
||||
elif kind == "CronJob":
|
||||
yield spec.get("jobTemplate", {}).get("spec", {}).get("template", {}).get("spec", {})
|
||||
elif kind in ("Deployment", "StatefulSet", "DaemonSet", "ReplicaSet", "Job"):
|
||||
yield spec.get("template", {}).get("spec", {})
|
||||
|
||||
|
||||
def check_rules(label, docs):
|
||||
for d in docs:
|
||||
name = f"{d.get('kind')}/{d.get('metadata', {}).get('name')}"
|
||||
if d.get("kind") == "Secret" and (d.get("data") or d.get("stringData")):
|
||||
failures.append(f"{label}: {name} has data in git; put it in Vault and use an ExternalSecret")
|
||||
for spec in pod_specs(d):
|
||||
containers = spec.get("containers", []) + spec.get("initContainers", [])
|
||||
for c in containers:
|
||||
image = c.get("image", "")
|
||||
tag = image.split("@")[0].rsplit("/", 1)[-1].partition(":")[2]
|
||||
if "@" not in image and tag in ("", "latest"):
|
||||
failures.append(f"{label}: {name} container {c.get('name')} has no fixed tag ({image})")
|
||||
for c in spec.get("containers", []):
|
||||
missing = []
|
||||
if not c.get("resources", {}).get("requests"):
|
||||
missing.append("requests")
|
||||
if d.get("kind") in ("Deployment", "StatefulSet", "DaemonSet") and not (
|
||||
c.get("readinessProbe") or c.get("livenessProbe")):
|
||||
missing.append("probes")
|
||||
if missing:
|
||||
print(f"::warning title={label}::{name} container {c.get('name')} has no {' or '.join(missing)}")
|
||||
|
||||
|
||||
def validate(label, manifests, rules=False):
|
||||
"""kubeconform on rendered manifests; returns the parsed documents."""
|
||||
try:
|
||||
docs = [d for d in yaml.safe_load_all(manifests) if d]
|
||||
except yaml.YAMLError:
|
||||
docs = None # kubeconform reports where
|
||||
if docs is not None:
|
||||
# Argo CD skips documents that aren't objects, like a values file
|
||||
# next to the manifests.
|
||||
objects = [d for d in docs if isinstance(d, dict) and "kind" in d]
|
||||
if len(objects) < len(docs):
|
||||
print(f" {label}: skipping {len(docs) - len(objects)} document(s) without a kind")
|
||||
manifests = yaml.safe_dump_all(objects, sort_keys=False)
|
||||
result = subprocess.run(
|
||||
["kubeconform", "-summary", "-output", "text", "-strict",
|
||||
"-kubernetes-version", SCHEMA_VERSION, "-ignore-missing-schemas",
|
||||
"-schema-location", "default", "-schema-location", CRD_SCHEMAS],
|
||||
input=manifests, capture_output=True, text=True)
|
||||
lines = [l for l in result.stdout.splitlines() if l.strip()]
|
||||
summary = lines[-1] if lines else ""
|
||||
print(f" {label}: {summary.replace('Summary: ', '')}")
|
||||
if result.returncode != 0:
|
||||
for l in lines[:-1]:
|
||||
print(f" {l}")
|
||||
failures.append(f"{label}: {summary or result.stderr.strip()}")
|
||||
if rules and docs:
|
||||
check_rules(label, [d for d in docs if isinstance(d, dict)])
|
||||
return docs or []
|
||||
|
||||
|
||||
def helm_template(name, namespace, chart_args, helm):
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
args = ["helm", "template", helm.get("releaseName", name), *chart_args,
|
||||
"--namespace", namespace, "--kube-version", KUBE_VERSION,
|
||||
"--include-crds"]
|
||||
if helm.get("values"):
|
||||
values = pathlib.Path(tmp, "values.yaml")
|
||||
values.write_text(helm["values"])
|
||||
args += ["-f", str(values)]
|
||||
if helm.get("valuesObject"):
|
||||
values = pathlib.Path(tmp, "values-object.yaml")
|
||||
values.write_text(yaml.safe_dump(helm["valuesObject"]))
|
||||
args += ["-f", str(values)]
|
||||
for vf in helm.get("valueFiles", []):
|
||||
# $values/<path> points at this repo through a source with ref: values
|
||||
args += ["-f", str(ROOT / vf.split("/", 1)[1]) if vf.startswith("$") else vf]
|
||||
for p in helm.get("parameters", []):
|
||||
flag = "--set-string" if p.get("forceString") else "--set"
|
||||
args += [flag, f"{p['name']}={p['value']}"]
|
||||
return run(args)
|
||||
|
||||
|
||||
def directory(path, spec):
|
||||
include = spec.get("include", "*.yaml")
|
||||
exclude = spec.get("exclude", "")
|
||||
files = sorted(path.rglob("*") if spec.get("recurse") else path.glob("*"))
|
||||
docs = []
|
||||
for f in files:
|
||||
if f.suffix not in (".yaml", ".yml", ".json") or not f.is_file():
|
||||
continue
|
||||
name = f.name
|
||||
if not any(fnmatch.fnmatch(name, g) for g in include.strip("{}").split(",")):
|
||||
continue
|
||||
if exclude and any(fnmatch.fnmatch(name, g) for g in exclude.strip("{}").split(",")):
|
||||
continue
|
||||
docs.append(f.read_text())
|
||||
return "\n---\n".join(docs)
|
||||
|
||||
|
||||
def kustomize(path, spec):
|
||||
if not spec:
|
||||
return run(["kustomize", "build", str(path)])
|
||||
# The Application's kustomize options on top, as Argo CD does.
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
k = {"apiVersion": "kustomize.config.k8s.io/v1beta1", "kind": "Kustomization",
|
||||
"resources": [os.path.relpath(path, tmp)]}
|
||||
for key in ("patches", "images", "namespace", "commonLabels", "namePrefix", "nameSuffix"):
|
||||
if key in spec:
|
||||
k[key] = spec[key]
|
||||
pathlib.Path(tmp, "kustomization.yaml").write_text(yaml.safe_dump(k))
|
||||
return run(["kustomize", "build", "--load-restrictor", "LoadRestrictionsNone", tmp])
|
||||
|
||||
|
||||
def render_path(app, src, base):
|
||||
path = base / src.get("path", ".")
|
||||
namespace = app["spec"]["destination"].get("namespace", "default")
|
||||
if (path / "Chart.yaml").exists():
|
||||
if (path / "Chart.lock").exists():
|
||||
run(["helm", "dependency", "build", str(path)])
|
||||
return helm_template(app["metadata"]["name"], namespace, [str(path)], src.get("helm", {}))
|
||||
if (path / "kustomization.yaml").exists() or src.get("kustomize"):
|
||||
return kustomize(path, src.get("kustomize"))
|
||||
return directory(path, src.get("directory", {}))
|
||||
|
||||
|
||||
def render(app, src, clones):
|
||||
name = app["metadata"]["name"]
|
||||
namespace = app["spec"]["destination"].get("namespace", "default")
|
||||
repo = src["repoURL"]
|
||||
if src.get("chart"):
|
||||
if repo.startswith("http"):
|
||||
chart_args = [src["chart"], "--repo", repo]
|
||||
else:
|
||||
chart_args = [f"oci://{repo.rstrip('/')}/{src['chart']}"]
|
||||
chart_args += ["--version", src["targetRevision"]]
|
||||
return helm_template(name, namespace, chart_args, src.get("helm", {}))
|
||||
if src.get("ref") and "path" not in src:
|
||||
return None # only provides value files
|
||||
if repo in OWN_REPOS:
|
||||
return render_path(app, src, ROOT)
|
||||
key = (repo, src.get("targetRevision", "HEAD"))
|
||||
if key not in clones:
|
||||
tmp = tempfile.mkdtemp()
|
||||
run(["git", "clone", "--quiet", "--depth", "1", "--branch", key[1], repo, tmp])
|
||||
clones[key] = pathlib.Path(tmp)
|
||||
return render_path(app, src, clones[key])
|
||||
|
||||
|
||||
def applications(docs):
|
||||
return [d for d in docs if isinstance(d, dict) and d.get("kind") == "Application"
|
||||
and d.get("apiVersion", "").startswith("argoproj.io/")]
|
||||
|
||||
|
||||
def main():
|
||||
print("Duplicate keys")
|
||||
check_duplicate_keys()
|
||||
|
||||
print("Applications")
|
||||
apps = applications(validate("apps (chart)", run(
|
||||
["helm", "template", "apps", str(ROOT / "apps"), "--kube-version", KUBE_VERSION])))
|
||||
for path in yaml_files():
|
||||
if path.parts[len(ROOT.parts)] == "apps":
|
||||
continue
|
||||
try:
|
||||
apps += applications([d for d in yaml.safe_load_all(path.read_text()) if d])
|
||||
except yaml.YAMLError:
|
||||
pass # reported by the duplicate key check or by the app that uses it
|
||||
|
||||
clones = {}
|
||||
seen = set()
|
||||
for app in sorted(apps, key=lambda a: a["metadata"]["name"]):
|
||||
name = app["metadata"]["name"]
|
||||
if name in seen:
|
||||
continue
|
||||
seen.add(name)
|
||||
spec = app["spec"]
|
||||
sources = spec.get("sources") or [spec["source"]]
|
||||
for i, src in enumerate(sources):
|
||||
label = name if len(sources) == 1 else f"{name}[{i}]"
|
||||
try:
|
||||
manifests = render(app, src, clones)
|
||||
except subprocess.CalledProcessError as e:
|
||||
print(f" {label}: render failed")
|
||||
lines = []
|
||||
for line in (e.stderr or e.stdout).strip().splitlines():
|
||||
if not lines or line != lines[-1]: # Helm repeats schema errors
|
||||
lines.append(line)
|
||||
for line in lines[:20]:
|
||||
print(f" {line}")
|
||||
failures.append(f"{label}: render failed")
|
||||
continue
|
||||
if manifests is not None:
|
||||
own = src.get("repoURL") in OWN_REPOS and not src.get("chart") and not (
|
||||
ROOT / src.get("path", ".") / "Chart.yaml").exists()
|
||||
validate(label, manifests, rules=own)
|
||||
|
||||
if failures:
|
||||
print(f"\n{len(failures)} problem(s):")
|
||||
for f in failures:
|
||||
print(f"- {f}")
|
||||
sys.exit(1)
|
||||
print("\nAll apps render and validate.")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -3,7 +3,7 @@ module dqlite-vacuum
|
||||
go 1.27.3
|
||||
|
||||
require (
|
||||
github.com/canonical/go-dqlite/v3 v3.0.1
|
||||
github.com/canonical/go-dqlite/v3 v3.0.4
|
||||
gopkg.in/yaml.v2 v2.4.0
|
||||
)
|
||||
|
||||
|
||||
@@ -2,7 +2,10 @@ github.com/Rican7/retry v0.3.1 h1:scY4IbO8swckzoA/11HgBwaZRJEyY9vaNJshcdhp1Mc=
|
||||
github.com/Rican7/retry v0.3.1/go.mod h1:CxSDrhAyXmTMeEuRAnArMu1FHu48vtfjLREWqVl7Vw0=
|
||||
github.com/canonical/go-dqlite/v3 v3.0.1 h1:eUTcEHetVi1+zr+ZFz7PU0G+0eK66GZ7DKhi+wHs1f0=
|
||||
github.com/canonical/go-dqlite/v3 v3.0.1/go.mod h1:Kb/9JVog9XeIlnlnSyO1JgMoE4PoKXZCB8fJNcvvHAc=
|
||||
github.com/canonical/go-dqlite/v3 v3.0.4 h1:JhITsrvVL0pii9arxDksXfsRqBI+je1VpcqVuzDllUM=
|
||||
github.com/canonical/go-dqlite/v3 v3.0.4/go.mod h1:6O+E6MiYesijRUOECyywp16iT+N4QOrvjDWWiMJ/xF0=
|
||||
github.com/cpuguy83/go-md2man/v2 v2.0.4/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o=
|
||||
github.com/cpuguy83/go-md2man/v2 v2.0.6/go.mod h1:oOW0eioCTA6cOiMLiUPZOpcVxMig6NIQQ7OS05n1F4g=
|
||||
github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
|
||||
github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
|
||||
github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
|
||||
@@ -26,7 +29,9 @@ github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZN
|
||||
github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
|
||||
github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
|
||||
github.com/spf13/cobra v1.8.1/go.mod h1:wHxEcudfqmLYa8iTfL+OuZPbBZkmvliBWKIezN3kD9Y=
|
||||
github.com/spf13/cobra v1.10.1/go.mod h1:7SmJGaTHFVBY0jW4NXGluQoLvhqFQM+6XSKD+P4XaB0=
|
||||
github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
|
||||
github.com/spf13/pflag v1.0.9/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
|
||||
github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
|
||||
github.com/stretchr/testify v1.7.0 h1:nwc3DEeHmmLAfoZucVR881uASk0Mfjw8xYJ99tb5CcY=
|
||||
github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
|
||||
|
||||
Executable
+74
@@ -0,0 +1,74 @@
|
||||
#!/bin/bash
|
||||
# Restart the Vault pods one at a time and unseal each one: the standbys
|
||||
# first, the active node last, as HashiCorp's HA upgrade guide asks. The
|
||||
# StatefulSet uses OnDelete, so this is how a new image from
|
||||
# vault/overrides.yaml reaches the pods once Argo CD has synced it. Also
|
||||
# useful after a reboot, minus the restarts: see "unseal only" below.
|
||||
#
|
||||
# Run it on a machine with kubectl access and the unseal key at hand:
|
||||
# tools/vault-roll.sh 2.2.1
|
||||
# It asks for the key once per pod (hidden input) and stores nothing.
|
||||
# Stop at any point with Ctrl-C; pods already done stay on the new version.
|
||||
#
|
||||
# Unseal only (after a reboot, all three come up sealed):
|
||||
# for p in vault-0 vault-1 vault-2; do kubectl -n vault exec -ti $p -- vault operator unseal; done
|
||||
set -euo pipefail
|
||||
ns=vault
|
||||
target=${1:?usage: $0 <version the pods should run, e.g. 2.2.1>}
|
||||
|
||||
image=$(kubectl -n $ns get sts vault -o jsonpath='{.spec.template.spec.containers[0].image}')
|
||||
if [[ $image != *:$target ]]; then
|
||||
echo "The StatefulSet has $image, not $target. Sync the vault app first." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
pods() { kubectl -n $ns get pods -l "app.kubernetes.io/name=vault,component=server,vault-active=$1" -o name | sed 's|pod/||'; }
|
||||
status() { kubectl -n $ns exec "$1" -- vault status -format=json 2>/dev/null || true; }
|
||||
summary() {
|
||||
status "$1" | jq -r --arg p "$1" '"\($p): \(.version), sealed \(.sealed), \(if .is_self then "active" else "standby" end), raft index \(.raft_committed_index)"'
|
||||
}
|
||||
|
||||
roll() {
|
||||
local pod=$1 rc
|
||||
echo
|
||||
echo "== $pod"
|
||||
kubectl -n $ns delete pod "$pod" --wait=true
|
||||
# vault status exits 0 when unsealed, 2 when sealed, 1 on errors (and
|
||||
# kubectl exec exits 1 while the container isn't running yet).
|
||||
while :; do
|
||||
rc=0
|
||||
kubectl -n $ns exec "$pod" -- vault status >/dev/null 2>&1 || rc=$?
|
||||
[[ $rc -ne 1 ]] && break
|
||||
sleep 2
|
||||
done
|
||||
if [[ $rc -eq 2 ]]; then
|
||||
kubectl -n $ns exec -ti "$pod" -- vault operator unseal
|
||||
fi
|
||||
kubectl -n $ns wait --for=condition=Ready "pod/$pod" --timeout=180s
|
||||
summary "$pod"
|
||||
local version
|
||||
version=$(status "$pod" | jq -r .version)
|
||||
if [[ $version != "$target" ]]; then
|
||||
echo "$pod runs $version, expected $target. Stopping." >&2
|
||||
exit 1
|
||||
fi
|
||||
}
|
||||
|
||||
active=$(pods true)
|
||||
standbys=$(pods false)
|
||||
if [[ $(echo "$active" | wc -w) -ne 1 || $(echo "$standbys" | wc -w) -ne 2 ]]; then
|
||||
echo "Expected one active node and two standbys, found active: $active, standbys: $standbys" >&2
|
||||
exit 1
|
||||
fi
|
||||
echo "Active: $active. Standbys: $(echo $standbys)."
|
||||
|
||||
for pod in $standbys; do
|
||||
roll "$pod"
|
||||
done
|
||||
# The active node goes last. Deleting the pod shuts Vault down cleanly, so
|
||||
# it hands the HA lock to an upgraded standby right away; no step-down.
|
||||
roll "$active"
|
||||
|
||||
echo
|
||||
echo "== done"
|
||||
for pod in vault-0 vault-1 vault-2; do summary "$pod"; done
|
||||
@@ -33,7 +33,7 @@ spec:
|
||||
spec:
|
||||
containers:
|
||||
- name: configure
|
||||
image: hashicorp/vault:1.15
|
||||
image: hashicorp/vault:2.2.1
|
||||
env:
|
||||
- name: VAULT_ADDR
|
||||
value: "http://vault-active.vault.svc:8200"
|
||||
@@ -51,7 +51,7 @@ spec:
|
||||
args:
|
||||
- |
|
||||
vault auth enable oidc 2>/dev/null || true
|
||||
vault auth tune -listing_visibility=unauth oidc/
|
||||
vault auth tune -listing-visibility=unauth oidc/
|
||||
vault policy write admin - <<'POLICY'
|
||||
path "*" {
|
||||
capabilities = ["create", "read", "update", "delete", "list", "sudo"]
|
||||
|
||||
@@ -0,0 +1,68 @@
|
||||
# Vault holds every secret, so only ESO, the UI through Envoy, and the
|
||||
# node reach it (the API server calls the injector's webhook from there;
|
||||
# 10.1.7.64 is the node's Calico VXLAN address,
|
||||
# projectcalico.org/IPv4VXLANTunnelAddr). Nothing uses agent injection.
|
||||
# The pods reach each other (raft on 8201, the OIDC job), DNS, the API
|
||||
# server (service registration labels the active pod, the injector) and
|
||||
# the internet (the OIDC login through authentik's public address).
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: default
|
||||
spec:
|
||||
podSelector: {}
|
||||
policyTypes:
|
||||
- Ingress
|
||||
- Egress
|
||||
ingress:
|
||||
- from:
|
||||
- podSelector: {}
|
||||
- from:
|
||||
- ipBlock:
|
||||
cidr: 192.168.1.204/32
|
||||
- ipBlock:
|
||||
cidr: 10.1.7.64/32
|
||||
- from:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: envoy-gateway-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: envoy
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: external-secrets
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: external-secrets
|
||||
ports:
|
||||
- port: 8200
|
||||
egress:
|
||||
- to:
|
||||
- podSelector: {}
|
||||
- to:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: kube-system
|
||||
podSelector:
|
||||
matchLabels:
|
||||
k8s-app: kube-dns
|
||||
ports:
|
||||
- protocol: UDP
|
||||
port: 53
|
||||
- protocol: TCP
|
||||
port: 53
|
||||
- to:
|
||||
- ipBlock:
|
||||
cidr: 192.168.1.204/32
|
||||
ports:
|
||||
- port: 16443
|
||||
- to:
|
||||
- ipBlock:
|
||||
cidr: 0.0.0.0/0
|
||||
except:
|
||||
- 10.0.0.0/8
|
||||
- 100.64.0.0/10
|
||||
- 169.254.0.0/16
|
||||
- 172.16.0.0/12
|
||||
- 192.168.0.0/16
|
||||
@@ -3,6 +3,10 @@ global:
|
||||
tlsDisable: true
|
||||
injector:
|
||||
enabled: true
|
||||
resources:
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 32Mi
|
||||
# The chart's default anti-affinity forbids two injector pods on one
|
||||
# node, so on this single node a rolling update can never start the new
|
||||
# pod while the old one runs. Recreate removes the old pod first, which
|
||||
@@ -14,9 +18,11 @@ injector:
|
||||
server:
|
||||
# Pinned to the running version: the chart would otherwise pull its own
|
||||
# default on the next pod restart, and with Shamir unsealing a Vault
|
||||
# upgrade needs someone with the unseal keys at hand.
|
||||
# upgrade needs someone with the unseal keys at hand. The StatefulSet
|
||||
# uses OnDelete, so after a sync tools/vault-roll.sh <tag> restarts and
|
||||
# unseals the pods one at a time.
|
||||
image:
|
||||
tag: "1.17.2"
|
||||
tag: "2.2.1"
|
||||
dataStorage:
|
||||
storageClass: longhorn
|
||||
standalone:
|
||||
|
||||
@@ -0,0 +1,30 @@
|
||||
# Velero's key for its bucket in Garage on the NAS (nas/garage), in the
|
||||
# AWS credentials file format the aws plugin and kopia read.
|
||||
apiVersion: external-secrets.io/v1
|
||||
kind: ExternalSecret
|
||||
metadata:
|
||||
name: velero-s3-credentials
|
||||
spec:
|
||||
secretStoreRef:
|
||||
name: vault-backend
|
||||
kind: ClusterSecretStore
|
||||
refreshInterval: 15m
|
||||
target:
|
||||
name: velero-s3-credentials
|
||||
creationPolicy: Owner
|
||||
template:
|
||||
engineVersion: v2
|
||||
data:
|
||||
cloud: |
|
||||
[default]
|
||||
aws_access_key_id={{ .access_key_id }}
|
||||
aws_secret_access_key={{ .secret_access_key }}
|
||||
data:
|
||||
- secretKey: access_key_id
|
||||
remoteRef:
|
||||
key: kv/velero-s3
|
||||
property: access_key_id
|
||||
- secretKey: secret_access_key
|
||||
remoteRef:
|
||||
key: kv/velero-s3
|
||||
property: secret_access_key
|
||||
@@ -1,23 +0,0 @@
|
||||
# apiVersion: external-secrets.io/v1beta1
|
||||
# kind: ExternalSecret
|
||||
# metadata:
|
||||
# name: velero-minio-credentials
|
||||
# namespace: velero
|
||||
# spec:
|
||||
# refreshInterval: "15s"
|
||||
# secretStoreRef:
|
||||
# name: vault-backend
|
||||
# kind: ClusterSecretStore
|
||||
# target:
|
||||
# name: velero-minio-credentials
|
||||
# creationPolicy: Owner
|
||||
# data:
|
||||
# - secretKey: cloud
|
||||
# remoteRef:
|
||||
# key: velero/minio-credentials
|
||||
# template:
|
||||
# engine: gotmpl
|
||||
# data: |
|
||||
# [default]
|
||||
# aws_access_key_id={{ .aws_access_key_id }}
|
||||
# aws_secret_access_key={{ .aws_secret_access_key }}
|
||||
@@ -1,6 +1,8 @@
|
||||
# Volume policy for the backup schedules. emptyDir volumes hold nothing
|
||||
# worth keeping, and backing them up fails when the pod is gone before its
|
||||
# volume is read, as happens with Velero's own repository maintenance jobs.
|
||||
# PVCs in Longhorn's no-backup group (caches, such as immich's ML models)
|
||||
# are skipped too.
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
@@ -14,3 +16,8 @@ data:
|
||||
- emptyDir
|
||||
action:
|
||||
type: skip
|
||||
- conditions:
|
||||
pvcLabels:
|
||||
recurring-job-group.longhorn.io/no-backup: enabled
|
||||
action:
|
||||
type: skip
|
||||
@@ -68,6 +68,10 @@ spec:
|
||||
nodeAgent:
|
||||
containerSecurityContext:
|
||||
privileged: true
|
||||
resources:
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 64Mi
|
||||
# 512Mi got the server OOMKilled 314 times, including halfway
|
||||
# through a backup of ~14.7k items.
|
||||
resources:
|
||||
|
||||
@@ -1,30 +0,0 @@
|
||||
- staging env
|
||||
- automated backup testing
|
||||
- conftest policy as code voor clean gitops repo regels. Leg fouten vast zodat ze niet meer gebeuren.
|
||||
- beter begrip van Longhorn en deletion policies enzo.
|
||||
- minder handmatig werk als ik een app wil deployen?
|
||||
- 3-node cluster
|
||||
- CI/CD pipeline
|
||||
- image registry
|
||||
- centralized logging met loki en grafana
|
||||
- metrics met prometheus en grafana
|
||||
- alertmanager met goede alerts
|
||||
- uitzoeken wat goede alerts zijn
|
||||
- hardware management met behulp van die idempotem client ding, ben de naam kwijt.
|
||||
Dan een nieuwe server opzetten compleet met dat,
|
||||
en dan overgaan door het als een nieuwe node toe te voegen en de andere uit te zetten.
|
||||
- authentik en alles met sso openid verbinden
|
||||
- Renovate voor automatische updates zodat ik niet zo achter raak.
|
||||
- Trivy vulnarability scanning (CVE scans)
|
||||
- Network policies
|
||||
- clean up repo
|
||||
- remove hardcodes secrets.
|
||||
- health probes to all services
|
||||
- limits and requests for all services.
|
||||
- non root security policy for all services.
|
||||
- kube hunter network scans
|
||||
- Draai mijn eigen github alternative
|
||||
- Scale down pvc immich to 200gb.
|
||||
|
||||
|
||||
|
||||
Reference in new issue
Block a user