Compare commits

..
1 Commits
Author SHA1 Message Date
renovate[bot] d40560ad56 chore(deps): update helm chart authentik to v2026.8.4 2026-10-15 07:29:51 +00:00
31 changed files with 55 additions and 10149 deletions

No files matched your search

-14
View File
@@ -36,20 +36,6 @@ spec:
extraEnvVars:
ACTUAL_OPENID_SERVER_HOSTNAME: https://ynab.rubenhensen.nl
# Node trusts its built-in roots, which still include the ones
# above the compromised eMudhra intermediates. Use patched-ca-bundle
# through OpenSSL instead until Node ships a fix.
NODE_OPTIONS: --use-openssl-ca
SSL_CERT_FILE: /etc/ssl/certs/ca-certificates.crt
volumes:
- name: patched-ca-bundle
configMap:
name: patched-ca-bundle
volumeMounts:
- name: patched-ca-bundle
mountPath: /etc/ssl/certs
readOnly: true
# Service configuration
service:
File diff suppressed because it is too large. Load diff
+1 -20
View File
@@ -16,7 +16,7 @@ spec:
sources:
- chart: authentik
repoURL: https://charts.goauthentik.io
targetRevision: 2026.8.5
targetRevision: 2026.8.4
helm:
values: |
authentik:
@@ -86,18 +86,8 @@ spec:
secretKeyRef:
name: actualbudget-oidc-client-secret
key: client_secret
# Point OpenSSL and requests (which uses certifi otherwise) at
# patched-ca-bundle, mounted below until the image drops the
# compromised eMudhra intermediates.
- name: SSL_CERT_FILE
value: /etc/ssl/certs/ca-certificates.crt
- name: REQUESTS_CA_BUNDLE
value: /etc/ssl/certs/ca-certificates.crt
server:
volumes:
- name: patched-ca-bundle
configMap:
name: patched-ca-bundle
- name: blueprint-vault
configMap:
name: authentik-blueprint-vault
@@ -141,9 +131,6 @@ spec:
- name: blueprint-session
mountPath: /blueprints/custom/session-duration.yaml
subPath: session-duration.yaml
- name: patched-ca-bundle
mountPath: /etc/ssl/certs
readOnly: true
ingress:
enabled: true
ingressClassName: nginx
@@ -157,9 +144,6 @@ spec:
- authentik.rubenhensen.nl
worker:
volumes:
- name: patched-ca-bundle
configMap:
name: patched-ca-bundle
- name: blueprint-vault
configMap:
name: authentik-blueprint-vault
@@ -203,9 +187,6 @@ spec:
- name: blueprint-session
mountPath: /blueprints/custom/session-duration.yaml
subPath: session-duration.yaml
- name: patched-ca-bundle
mountPath: /etc/ssl/certs
readOnly: true
postgresql:
enabled: false
redis:
@@ -1,7 +1,7 @@
apiVersion: argoproj.io/v1alpha1
kind: Application
metadata:
name: gatus-folder
name: ip-updater
namespace: argocd
finalizers:
- resources-finalizer.argocd.argoproj.io
@@ -10,12 +10,13 @@ spec:
source:
repoURL: https://github.com/rubenhensen/k8scd.git
targetRevision: HEAD
path: gatus
path: ip-updater
destination:
server: https://kubernetes.default.svc
namespace: gatus
namespace: ip-updater
syncPolicy:
syncOptions:
- CreateNamespace=true
automated:
selfHeal: true
prune: true
-4
View File
@@ -16,10 +16,6 @@ spec:
chart: wordpress
helm:
values: |
# Stopped until PHP is patched (CERT-EU 2026-018, CVE-2026-109618,
# CVE-2026-109619). Set back to 1 once the image ships a fixed PHP.
replicaCount: 0
# Official WordPress image configuration
image:
registry: docker.io
-21
View File
@@ -1,21 +0,0 @@
apiVersion: argoproj.io/v1alpha1
kind: Application
metadata:
name: ntfy-folder
namespace: argocd
finalizers:
- resources-finalizer.argocd.argoproj.io
spec:
project: default
source:
repoURL: https://github.com/rubenhensen/k8scd.git
targetRevision: HEAD
path: ntfy
destination:
server: https://kubernetes.default.svc
namespace: ntfy
syncPolicy:
syncOptions:
- CreateNamespace=true
automated:
selfHeal: true
+1 -3
View File
@@ -9,7 +9,6 @@ resources:
- https://raw.githubusercontent.com/argoproj/argo-cd/refs/tags/v2.14.2/manifests/install.yaml
- ingress.yaml
- oidc-secret.yaml
- patched-ca-bundle.yaml
patches:
- target:
@@ -19,5 +18,4 @@ patches:
name: argocd-notifications-controller
path: overlays/argocd-notifications-controller-patch.yaml
- path: overlays/argocd-cm.patch.yaml
- path: overlays/argocd-rbac-cm.patch.yaml
- path: overlays/patched-ca-bundle.patch.yaml
- path: overlays/argocd-rbac-cm.patch.yaml
@@ -1,111 +0,0 @@
# Mount patched-ca-bundle over /etc/ssl/certs so git, helm and the Go
# binaries stop trusting the compromised eMudhra intermediates. The whole
# directory is replaced because OpenSSL and Go also read the per-root files
# next to ca-certificates.crt. Drop this once Argo CD ships a fixed image.
apiVersion: apps/v1
kind: Deployment
metadata:
name: argocd-server
spec:
template:
spec:
containers:
- name: argocd-server
volumeMounts:
- name: patched-ca-bundle
mountPath: /etc/ssl/certs
readOnly: true
volumes:
- name: patched-ca-bundle
configMap:
name: patched-ca-bundle
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: argocd-repo-server
spec:
template:
spec:
containers:
- name: argocd-repo-server
volumeMounts:
- name: patched-ca-bundle
mountPath: /etc/ssl/certs
readOnly: true
volumes:
- name: patched-ca-bundle
configMap:
name: patched-ca-bundle
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: argocd-application-controller
spec:
template:
spec:
containers:
- name: argocd-application-controller
volumeMounts:
- name: patched-ca-bundle
mountPath: /etc/ssl/certs
readOnly: true
volumes:
- name: patched-ca-bundle
configMap:
name: patched-ca-bundle
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: argocd-applicationset-controller
spec:
template:
spec:
containers:
- name: argocd-applicationset-controller
volumeMounts:
- name: patched-ca-bundle
mountPath: /etc/ssl/certs
readOnly: true
volumes:
- name: patched-ca-bundle
configMap:
name: patched-ca-bundle
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: argocd-notifications-controller
spec:
template:
spec:
containers:
- name: argocd-notifications-controller
volumeMounts:
- name: patched-ca-bundle
mountPath: /etc/ssl/certs
readOnly: true
volumes:
- name: patched-ca-bundle
configMap:
name: patched-ca-bundle
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: argocd-dex-server
spec:
template:
spec:
containers:
- name: dex
volumeMounts:
- name: patched-ca-bundle
mountPath: /etc/ssl/certs
readOnly: true
volumes:
- name: patched-ca-bundle
configMap:
name: patched-ca-bundle
File diff suppressed because it is too large. Load diff
File diff suppressed because it is too large. Load diff
-19
View File
@@ -63,25 +63,6 @@ records:
expire: 300
type: A
content: "46.224.26.65"
# Gatus status pages. s2 points straight at home, not through the
# Hetzner tunnel, so it stays reachable when Hetzner is down.
- name: "s1"
expire: 300
type: A
content: "46.224.26.65"
- name: "s2"
expire: 300
type: A
content: "62.41.86.27"
# ntfy for Gatus alerts, one next to each Gatus. Same reasoning as s2.
- name: "ntfy1"
expire: 300
type: A
content: "46.224.26.65"
- name: "ntfy2"
expire: 300
type: A
content: "62.41.86.27"
- name: "@"
expire: 300
type: MX
+1 -3
View File
@@ -8,9 +8,7 @@ metadata:
io.kompose.service: freshrss
name: freshrss
spec:
# Stopped until PHP is patched (CERT-EU 2026-018, CVE-2026-109618,
# CVE-2026-109619). Set back to 1 once the image ships a fixed PHP.
replicas: 0
replicas: 1
selector:
matchLabels:
io.kompose.service: freshrss
-105
View File
@@ -1,105 +0,0 @@
# Gatus
Two Gatus instances check the same endpoints from two places:
| Status page | Runs on | Config |
|---|---|---|
| https://s1.rubenhensen.nl | Hetzner (node001) | `nix-infra-machine/nodes/node001.nix` |
| https://s2.rubenhensen.nl | Home cluster | `gatus/config.yaml` (this folder) |
Each one also checks the other's `/health`. The s2 DNS record points straight
at the home IP instead of going through the Hetzner tunnel, so s2 stays
reachable when Hetzner is down.
The endpoint list exists twice, so a new service has to be added in both
places. s1 builds its list from `tunneledHosts`, so new tunneled hosts show up
there automatically. s2 needs them added by hand.
## Alerting
Each Gatus sends alerts to an ntfy instance on its own node:
`ntfy1.rubenhensen.nl` (Hetzner, node001.nix) and `ntfy2.rubenhensen.nl`
(home, `ntfy/` in this repo). Subscribe the phone app to topic `alerts` on
both servers, with the same login on each.
Only the watcher that sees a service from outside alerts on it:
- s1 alerts on everything that runs at home (all tunneled apps, Scouting MBG)
and on s2.
- s2 alerts on mail and on s1.
An outage on either node still reaches you, through the other node's ntfy,
and you get one notification per outage instead of two. An alert fires after
3 failed checks in a row (about 3 minutes), and you get another notification
when the service recovers.
Both ntfy servers deny everything except the provisioned user. The
credentials are the same on both:
- Home: Vault `kv/ntfy` with `auth_users`, `auth_tokens` and `gatus_token`,
pulled in by External Secrets.
- Hetzner: the nix-infra secrets `ntfy-auth-users`, `ntfy-auth-tokens` and
`ntfy-gatus-token`.
## Reading the two pages
- s1 sees the homelab from outside, so trust it for homelab services. s2 sees
Hetzner from outside, so trust it for mail and anything else on Hetzner.
- Every `*.rubenhensen.nl` app is tunneled Hetzner → home, so a Hetzner
outage shows all of them as down on both pages. That is accurate: nobody
can reach them then.
- If s1 and s2 disagree about an endpoint, the problem is the network path
between one watcher and that service, not the service itself.
- Neither page has history for the time its own node was down.
## Later: one URL with self-hosted DNS failover
This is the plan for replacing s1/s2 with a single `status.rubenhensen.nl`
that always points at a watcher that's up, with no third party involved.
Hand `status.rubenhensen.nl` over to two nameservers we run ourselves, one per
node, both PowerDNS Authoritative. PowerDNS LUA records health-check
addresses and only return the healthy ones:
```
@ 30 IN LUA A "ifurlup('https://status.rubenhensen.nl/health', {{'46.224.26.65'}, {'62.41.86.27'}})"
```
The double braces make two groups. PowerDNS returns the first group that has
a healthy address, so Hetzner is primary and home is the fallback. Each
nameserver runs the check from its own location.
| Situation | Hetzner NS | Home NS | Visitors end up on |
|---|---|---|---|
| Both up | answers Hetzner | answers Hetzner | Hetzner |
| Hetzner down | dead | Hetzner check fails, answers home | home |
| Home down / home internet down | answers Hetzner | dead | Hetzner |
| Hetzner up, its Gatus broken | own check fails, answers home | answers home | home |
A node that goes down takes its nameserver down with it, so DNS resolvers
switch to the other nameserver. The two nodes never have to agree with each
other: the answer depends on what the internet can reach. The 30s TTL caps
how long clients keep a stale answer.
Steps:
1. Parent zone (`dns/domains/rubenhensen.nl.yaml`, synced to TransIP): add
`status NS ns-hetzner.rubenhensen.nl.` and `status NS ns-home.rubenhensen.nl.`,
plus A records for `ns-hetzner` (46.224.26.65) and `ns-home` (62.41.86.27).
First check that TransIP accepts NS records for a subdomain.
2. Hetzner: run PowerDNS from node001.nix with `enable-lua-records=yes` and
the bind backend. Use the same zone file as home. Open 53/udp and 53/tcp.
3. Home: run PowerDNS in the cluster with the same zone file, on 53/udp and
53/tcp of the home IP (router port forward, and check how the cluster
exposes UDP).
4. Both Gatus instances also serve `status.rubenhensen.nl`. On Hetzner, add the
name to the SNI map, the same way as s1.
5. TLS: Hetzner gets its cert through HTTP-01 as usual. On Hetzner's :80 vhost
for `status`, serve local ACME challenges and proxy the rest to the home
cluster (`try_files $uri @home`). That way cert-manager's HTTP-01 also
works while DNS points at Hetzner. When Hetzner is down, DNS points home
and cert-manager reaches the home cluster directly.
6. Requirements: a static home IP (`homeIP` in node001.nix already assumes
one), and port 53 open on both nodes.
After that, s1/s2 can be removed, or kept as direct links to each instance.
-146
View File
@@ -1,146 +0,0 @@
# s2.rubenhensen.nl: Gatus on the home cluster.
# Its twin s1.rubenhensen.nl runs on the Hetzner box, see
# nix-infra-machine/nodes/node001.nix. Keep the endpoint lists in sync.
storage:
type: sqlite
path: /data/data.db
ui:
title: Status (homelab)
header: s2 · homelab
buttons:
- name: s1 (Hetzner)
link: https://s1.rubenhensen.nl
# NTFY_TOKEN comes from the gatus-ntfy secret (Vault kv/ntfy)
alerting:
ntfy:
url: http://ntfy.ntfy.svc.cluster.local
topic: alerts
token: ${NTFY_TOKEN}
priority: 4
click: https://s2.rubenhensen.nl
default-alert:
failure-threshold: 3
success-threshold: 2
send-on-resolved: true
# s2 is the outside view of Hetzner, so it alerts on mail and on s1. The
# home services are left to s1.
endpoints:
# Tunneled through Hetzner to the home cluster
- name: rss
group: rubenhensen.nl
url: https://rss.rubenhensen.nl
interval: 60s
# mod_auth_openidc answers 401 instead of redirecting to the login
# page unless the client asks for HTML
headers:
Accept: text/html
conditions: &http-ok
- "[STATUS] == 200"
- "[CERTIFICATE_EXPIRATION] > 168h"
- name: authentik
group: rubenhensen.nl
url: https://authentik.rubenhensen.nl
interval: 60s
conditions: *http-ok
- name: vault
group: rubenhensen.nl
url: https://vault.rubenhensen.nl
interval: 60s
conditions: *http-ok
- name: ynab
group: rubenhensen.nl
url: https://ynab.rubenhensen.nl
interval: 60s
conditions: *http-ok
- name: argocd
group: rubenhensen.nl
url: https://argocd.rubenhensen.nl
interval: 60s
conditions: *http-ok
- name: ha
group: rubenhensen.nl
url: https://ha.rubenhensen.nl
interval: 60s
conditions: *http-ok
- name: longhorn
group: rubenhensen.nl
url: https://longhorn.rubenhensen.nl
interval: 60s
# Behind basic auth, so 401 means it's up
conditions:
- "[STATUS] == 401"
- "[CERTIFICATE_EXPIRATION] > 168h"
- name: lingo
group: rubenhensen.nl
url: https://lingo.rubenhensen.nl
interval: 60s
conditions: *http-ok
- name: blog
group: rubenhensen.nl
url: https://blog.rubenhensen.nl
interval: 60s
conditions: *http-ok
- name: serpbear
group: rubenhensen.nl
url: https://serpbear.rubenhensen.nl
interval: 60s
conditions: *http-ok
- name: git
group: rubenhensen.nl
url: https://git.rubenhensen.nl
interval: 60s
conditions: *http-ok
- name: vic
group: rubenhensen.nl
url: https://vic.rubenhensen.nl
interval: 60s
conditions: *http-ok
# Stalwart on Hetzner
- name: webmail
group: mail
url: https://mail.rubenhensen.nl
interval: 60s
conditions: *http-ok
alerts: &ntfy
- type: ntfy
- name: smtp
group: mail
url: tcp://mail.rubenhensen.nl:25
interval: 60s
conditions:
- "[CONNECTED] == true"
alerts: *ntfy
- name: imaps
group: mail
url: tls://mail.rubenhensen.nl:993
interval: 60s
conditions:
- "[CONNECTED] == true"
- "[CERTIFICATE_EXPIRATION] > 168h"
alerts: *ntfy
# Served straight from the home IP
- name: scoutingmbg.nl
group: Scouting MBG
url: https://scoutingmbg.nl
interval: 60s
conditions: *http-ok
- name: foto.scoutingmbg.nl
group: Scouting MBG
url: https://foto.scoutingmbg.nl/_app
interval: 60s
conditions: *http-ok
# The other watcher
- name: s1 (Hetzner)
group: watchers
url: https://s1.rubenhensen.nl/health
interval: 60s
conditions:
- "[STATUS] == 200"
- "[BODY].status == UP"
alerts: *ntfy
-10
View File
@@ -1,10 +0,0 @@
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: gatus-data
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 1Gi
-57
View File
@@ -1,57 +0,0 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: gatus
spec:
replicas: 1
selector:
matchLabels:
app: gatus
strategy:
type: Recreate
template:
metadata:
labels:
app: gatus
spec:
containers:
- name: gatus
image: twinproduction/gatus:v5.37.0
env:
- name: GATUS_CONFIG_PATH
value: /config/config.yaml
- name: TZ
value: Europe/Amsterdam
envFrom:
- secretRef:
name: gatus-ntfy
ports:
- containerPort: 8080
protocol: TCP
readinessProbe:
httpGet:
path: /health
port: 8080
livenessProbe:
httpGet:
path: /health
port: 8080
resources:
requests:
memory: "64Mi"
cpu: "20m"
limits:
memory: "256Mi"
volumeMounts:
- name: config
mountPath: /config
readOnly: true
- name: data
mountPath: /data
volumes:
- name: config
configMap:
name: gatus-config
- name: data
persistentVolumeClaim:
claimName: gatus-data
-11
View File
@@ -1,11 +0,0 @@
apiVersion: v1
kind: Service
metadata:
name: gatus
spec:
ports:
- name: http
port: 8080
targetPort: 8080
selector:
app: gatus
-25
View File
@@ -1,25 +0,0 @@
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: gatus-ingress
annotations:
cert-manager.io/cluster-issuer: prod-cluster-issuer
nginx.ingress.kubernetes.io/backend-protocol: "HTTP"
nginx.ingress.kubernetes.io/ssl-passthrough: "false"
spec:
ingressClassName: nginx
rules:
- host: s2.rubenhensen.nl
http:
paths:
- path: /
pathType: Prefix
backend:
service:
name: gatus
port:
number: 8080
tls:
- secretName: letsencrypt-prod
hosts:
- s2.rubenhensen.nl
-16
View File
@@ -1,16 +0,0 @@
apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization
namespace: gatus
resources:
- external-secret.yaml
- data-persistentvolumeclaim.yaml
- gatus-deployment.yaml
- gatus-service.yaml
- ingress.yaml
configMapGenerator:
- name: gatus-config
files:
- config.yaml
+39
View File
@@ -0,0 +1,39 @@
apiVersion: batch/v1
kind: CronJob
metadata:
name: ip-updater
spec:
schedule: "*/5 * * * *"
successfulJobsHistoryLimit: 1
failedJobsHistoryLimit: 3
jobTemplate:
spec:
template:
spec:
containers:
- name: ip-updater
image: alpine:3.19
command: ["/bin/sh", "-c"]
args:
- |
apk add --no-cache openssh-client curl > /dev/null 2>&1
cp /ssh-key/private_key /tmp/ssh_key
chmod 600 /tmp/ssh_key
IP=$(curl -s --max-time 10 https://api.ipify.org)
if [ -z "$IP" ]; then
echo "Failed to get external IP"
exit 1
fi
echo "Current external IP: $IP"
ssh -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null \
-i /tmp/ssh_key root@46.224.26.65 "$IP"
volumeMounts:
- name: ssh-key
mountPath: /ssh-key
readOnly: true
volumes:
- name: ssh-key
secret:
secretName: ip-updater-ssh-key
defaultMode: 0400
restartPolicy: OnFailure
@@ -1,17 +1,17 @@
apiVersion: external-secrets.io/v1beta1
kind: ExternalSecret
metadata:
name: gatus-ntfy
name: ip-updater-ssh-key
spec:
secretStoreRef:
name: vault-backend
kind: ClusterSecretStore
refreshInterval: 15m
target:
name: gatus-ntfy
name: ip-updater-ssh-key
creationPolicy: Owner
data:
- secretKey: NTFY_TOKEN
- secretKey: private_key
remoteRef:
key: kv/ntfy
property: gatus_token
key: kv/ip-updater
property: ssh_private_key
-198
View File
@@ -38,75 +38,6 @@ let
locations."/".proxyPass = "http://${homeIP}";
};
}) tunneledHosts);
# Gatus endpoints for s1.rubenhensen.nl. Its twin s2.rubenhensen.nl runs
# on the home cluster with the same list, see gatus/config.yaml in k8scd.
# Keep the two in sync.
gatusHttp = group: name: url: {
inherit name group url;
interval = "60s";
conditions = [
"[STATUS] == 200"
"[CERTIFICATE_EXPIRATION] > 168h"
];
};
# Per-host tweaks on top of the default check.
gatusOverrides = {
# Behind basic auth, so 401 means it's up
"longhorn.rubenhensen.nl".conditions = [
"[STATUS] == 401"
"[CERTIFICATE_EXPIRATION] > 168h"
];
# mod_auth_openidc answers 401 instead of redirecting to the login
# page unless the client asks for HTML
"rss.rubenhensen.nl".headers.Accept = "text/html";
};
# s1 is the outside view of home, so it alerts on what runs there and on
# s2. Mail lives on this box, so s2 alerts on that.
gatusAlert = { alerts = [ { type = "ntfy"; } ]; };
gatusEndpoints =
map (h:
gatusHttp "rubenhensen.nl" (lib.removeSuffix ".rubenhensen.nl" h) "https://${h}"
// gatusAlert
// (gatusOverrides.${h} or { })) tunneledHosts
++ [
(gatusHttp "mail" "webmail" "https://mail.rubenhensen.nl")
{
name = "smtp";
group = "mail";
url = "tcp://mail.rubenhensen.nl:25";
interval = "60s";
conditions = [ "[CONNECTED] == true" ];
}
{
name = "imaps";
group = "mail";
url = "tls://mail.rubenhensen.nl:993";
interval = "60s";
conditions = [ "[CONNECTED] == true" "[CERTIFICATE_EXPIRATION] > 168h" ];
}
(gatusHttp "Scouting MBG" "scoutingmbg.nl" "https://scoutingmbg.nl" // gatusAlert)
(gatusHttp "Scouting MBG" "foto.scoutingmbg.nl" "https://foto.scoutingmbg.nl/_app" // gatusAlert)
({
name = "s2 (homelab)";
group = "watchers";
url = "https://s2.rubenhensen.nl/health";
interval = "60s";
conditions = [ "[STATUS] == 200" "[BODY].status == UP" ];
} // gatusAlert)
];
# Runs a service with secrets from LoadCredentialEncrypted exported as
# env vars, for services that only take secrets through the environment.
withCredentialEnv = name: vars: cmd: pkgs.writeShellScript "${name}-with-credentials" ''
${lib.concatStrings (lib.mapAttrsToList (var: cred: ''
export ${var}="$(cat "$CREDENTIALS_DIRECTORY/${cred}")"
'') vars)}
exec ${cmd}
'';
in
{
# ──────────────────────────────────────────────
@@ -122,17 +53,6 @@ in
80 # HTTP (ACME)
];
# ──────────────────────────────────────────────
# Trust store
# ──────────────────────────────────────────────
# Distrust the roots above the compromised eMudhra intermediates until
# nixpkgs ships NSS 3.131.1, see https://emudhra.we-have-a-problem.com.
# Everything this box talks to chains to ISRG Root X1.
security.pki.caCertificateBlacklist = [
"Comodo AAA Services root"
"emSign ECC Root CA - G3"
];
# ──────────────────────────────────────────────
# ACME / Let's Encrypt
# ──────────────────────────────────────────────
@@ -166,12 +86,9 @@ in
# SNI passthrough on 443:
# - mail.rubenhensen.nl (and anything else) → local stalwart on 8443
# - tunneled hosts → home cluster ingress on 443
# - s1 / ntfy1.rubenhensen.nl → local nginx on 8444 (Gatus, ntfy)
streamConfig = ''
map $ssl_preread_server_name $tunnel_upstream {
${sniMapEntries}
s1.rubenhensen.nl 127.0.0.1:8444;
ntfy1.rubenhensen.nl 127.0.0.1:8444;
default 127.0.0.1:8443;
}
@@ -220,121 +137,6 @@ ${sniMapEntries}
locations."/.well-known/acme-challenge/".root = "/var/lib/acme/acme-challenge";
locations."/".return = "301 https://$host$request_uri";
};
# Gatus status page. The stream block above passes its SNI to
# 8444, where nginx terminates TLS with its own ACME cert.
"s1.rubenhensen.nl" = {
listen = [
{ addr = "0.0.0.0"; port = 80; }
{ addr = "[::]"; port = 80; }
{ addr = "127.0.0.1"; port = 8444; ssl = true; }
];
enableACME = true;
forceSSL = true;
locations."/".proxyPass = "http://127.0.0.1:8090";
};
# ntfy for Gatus alerts, same TLS setup as s1. Proxy settings follow
# the ntfy docs so subscriptions can stay open.
"ntfy1.rubenhensen.nl" = {
listen = [
{ addr = "0.0.0.0"; port = 80; }
{ addr = "[::]"; port = 80; }
{ addr = "127.0.0.1"; port = 8444; ssl = true; }
];
enableACME = true;
forceSSL = true;
locations."/" = {
proxyPass = "http://127.0.0.1:2586";
proxyWebsockets = true;
extraConfig = ''
proxy_buffering off;
proxy_request_buffering off;
proxy_connect_timeout 3m;
proxy_send_timeout 3m;
proxy_read_timeout 3m;
client_max_body_size 0;
'';
};
};
};
};
# ──────────────────────────────────────────────
# ntfy (ntfy1.rubenhensen.nl)
# ──────────────────────────────────────────────
# Users and tokens come from secrets, everything else is denied. The
# same login works on ntfy2.rubenhensen.nl at home.
services.ntfy-sh = {
enable = true;
settings = {
base-url = "https://ntfy1.rubenhensen.nl";
listen-http = "127.0.0.1:2586";
behind-proxy = true;
auth-file = "/var/lib/ntfy-sh/user.db";
auth-default-access = "deny-all";
cache-file = "/var/lib/ntfy-sh/cache.db";
# Needed for instant delivery on iOS. ntfy.sh only gets the message
# ID, never the content.
upstream-base-url = "https://ntfy.sh";
};
};
systemd.services.ntfy-sh.serviceConfig = {
LoadCredentialEncrypted = [
"ntfy-auth-users:/root/secrets/[%%secrets/ntfy-auth-users%%]"
"ntfy-auth-tokens:/root/secrets/[%%secrets/ntfy-auth-tokens%%]"
];
ExecStart = lib.mkForce (withCredentialEnv "ntfy-sh" {
NTFY_AUTH_USERS = "ntfy-auth-users";
NTFY_AUTH_TOKENS = "ntfy-auth-tokens";
} "${config.services.ntfy-sh.package}/bin/ntfy serve -c /etc/ntfy/server.yml");
};
# ──────────────────────────────────────────────
# Gatus (s1.rubenhensen.nl)
# ──────────────────────────────────────────────
services.gatus = {
enable = true;
settings = {
web = {
address = "127.0.0.1";
port = 8090;
};
storage = {
type = "sqlite";
path = "/var/lib/gatus/data.db";
};
ui = {
title = "Status (Hetzner)";
header = "s1 · Hetzner";
buttons = [
{ name = "s2 (homelab)"; link = "https://s2.rubenhensen.nl"; }
];
};
alerting.ntfy = {
url = "http://127.0.0.1:2586";
topic = "alerts";
token = "\${NTFY_TOKEN}";
priority = 4;
click = "https://s1.rubenhensen.nl";
default-alert = {
failure-threshold = 3;
success-threshold = 2;
send-on-resolved = true;
};
};
endpoints = gatusEndpoints;
};
};
systemd.services.gatus = {
after = [ "ntfy-sh.service" ];
serviceConfig = {
LoadCredentialEncrypted = [
"ntfy-gatus-token:/root/secrets/[%%secrets/ntfy-gatus-token%%]"
];
ExecStart = lib.mkForce (withCredentialEnv "gatus" {
NTFY_TOKEN = "ntfy-gatus-token";
} (lib.getExe config.services.gatus.package));
};
};
-10
View File
@@ -1,10 +0,0 @@
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: ntfy-data
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 1Gi
-21
View File
@@ -1,21 +0,0 @@
apiVersion: external-secrets.io/v1beta1
kind: ExternalSecret
metadata:
name: ntfy-auth
spec:
secretStoreRef:
name: vault-backend
kind: ClusterSecretStore
refreshInterval: 15m
target:
name: ntfy-auth
creationPolicy: Owner
data:
- secretKey: NTFY_AUTH_USERS
remoteRef:
key: kv/ntfy
property: auth_users
- secretKey: NTFY_AUTH_TOKENS
remoteRef:
key: kv/ntfy
property: auth_tokens
-28
View File
@@ -1,28 +0,0 @@
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: ntfy-ingress
annotations:
cert-manager.io/cluster-issuer: prod-cluster-issuer
nginx.ingress.kubernetes.io/backend-protocol: "HTTP"
nginx.ingress.kubernetes.io/ssl-passthrough: "false"
# Keep subscriptions open, as in the ntfy proxy docs
nginx.ingress.kubernetes.io/proxy-read-timeout: "180"
nginx.ingress.kubernetes.io/proxy-send-timeout: "180"
spec:
ingressClassName: nginx
rules:
- host: ntfy2.rubenhensen.nl
http:
paths:
- path: /
pathType: Prefix
backend:
service:
name: ntfy
port:
number: 80
tls:
- secretName: letsencrypt-prod
hosts:
- ntfy2.rubenhensen.nl
-11
View File
@@ -1,11 +0,0 @@
apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization
namespace: ntfy
resources:
- external-secret.yaml
- data-persistentvolumeclaim.yaml
- ntfy-deployment.yaml
- ntfy-service.yaml
- ingress.yaml
-66
View File
@@ -1,66 +0,0 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: ntfy
spec:
replicas: 1
selector:
matchLabels:
app: ntfy
strategy:
type: Recreate
template:
metadata:
labels:
app: ntfy
spec:
containers:
- name: ntfy
image: binwiederhier/ntfy:v2.28.0
args: ["serve"]
env:
- name: NTFY_BASE_URL
value: https://ntfy2.rubenhensen.nl
- name: NTFY_LISTEN_HTTP
value: ":80"
- name: NTFY_BEHIND_PROXY
value: "true"
- name: NTFY_AUTH_FILE
value: /var/lib/ntfy/user.db
- name: NTFY_AUTH_DEFAULT_ACCESS
value: deny-all
- name: NTFY_CACHE_FILE
value: /var/lib/ntfy/cache.db
# Needed for instant delivery on iOS. ntfy.sh only gets the
# message ID, never the content.
- name: NTFY_UPSTREAM_BASE_URL
value: https://ntfy.sh
- name: TZ
value: Europe/Amsterdam
envFrom:
- secretRef:
name: ntfy-auth
ports:
- containerPort: 80
protocol: TCP
readinessProbe:
httpGet:
path: /v1/health
port: 80
livenessProbe:
httpGet:
path: /v1/health
port: 80
resources:
requests:
memory: "32Mi"
cpu: "10m"
limits:
memory: "256Mi"
volumeMounts:
- name: data
mountPath: /var/lib/ntfy
volumes:
- name: data
persistentVolumeClaim:
claimName: ntfy-data
-11
View File
@@ -1,11 +0,0 @@
apiVersion: v1
kind: Service
metadata:
name: ntfy
spec:
ports:
- name: http
port: 80
targetPort: 80
selector:
app: ntfy
+1 -3
View File
@@ -18,9 +18,7 @@
"/apps/templates/.+\\.yaml$/",
"/serpbear/.+\\.yaml$/",
"/bolletjestrui/.+\\.yaml$/",
"/gitea/.+\\.yaml$/",
"/gatus/.+\\.yaml$/",
"/ntfy/.+\\.yaml$/"
"/gitea/.+\\.yaml$/"
]
},
"customManagers": [
+1 -3
View File
@@ -5,9 +5,7 @@ metadata:
spec:
provider:
vault:
# In-cluster, so syncing secrets doesn't depend on Hetzner or the home
# internet connection. Plain HTTP, like the ingress → Vault hop.
server: "http://vault-active.vault.svc:8200"
server: "https://vault.rubenhensen.nl"
path: "kv"
# Version is the Vault KV secret engine version.
# This can be either "v1" or "v2", defaults to "v2"
+2 -9
View File
@@ -11,11 +11,6 @@ spec:
targetRevision: 8.4.0
helm:
values: |
# The CRD upgrade hook pulls docker.io/bitnami/kubectl, which Bitnami
# has removed, so every sync hangs on it. The CRDs only change with
# the chart version; turn this back on (with another kubectl image)
# when bumping targetRevision.
upgradeCRDs: false
initContainers:
- name: velero-plugin-for-aws
image: velero/velero-plugin-for-aws:v1.11.1
@@ -48,15 +43,13 @@ spec:
nodeAgent:
containerSecurityContext:
privileged: true
# 512Mi got the server OOMKilled 314 times, including halfway
# through a backup of ~14.7k items.
resources:
requests:
cpu: 100m
memory: 512Mi
memory: 256Mi
limits:
cpu: 500m
memory: 2Gi
memory: 512Mi
destination:
server: https://kubernetes.default.svc