mirror of
https://github.com/rubenhensen/k8scd.git
synced 2026-11-16 14:29:09 +01:00
Compare commits
28
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
5bb1422594 | ||
|
|
72f49bed51 | ||
|
|
f4b42757cd | ||
|
|
f529bd99ee | ||
|
|
74dec430b8 | ||
|
|
6fe0acc061 | ||
|
|
bb34b601d9 | ||
|
|
e98668d5fa | ||
|
|
389f911823 | ||
|
|
8f1c6a5b6e | ||
|
|
770631fdc0 | ||
|
|
855317b84d | ||
|
|
d69f2638d1 | ||
|
|
90e552c9f5 | ||
|
|
ad14995ba0 | ||
|
|
c359384ade | ||
|
|
a4fc386ee8 | ||
|
|
0dc0bc4322 | ||
|
|
d843f31d86 | ||
|
|
da23357946 | ||
|
|
b9d88f41b9 | ||
|
|
3c4a8cc8db | ||
|
|
d17e78130d | ||
|
|
22c5a325d6 | ||
|
|
ef07307f93 | ||
|
|
aa940134ea | ||
|
|
f86ed09cd8 | ||
|
|
6d2bc379ba |
No files matched your search
@@ -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:
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -18,6 +18,22 @@ spec:
|
||||
- chart: external-secrets
|
||||
repoURL: https://charts.external-secrets.io
|
||||
targetRevision: 2.13.0
|
||||
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: 0.15.1
|
||||
targetRevision: 0.15.0
|
||||
chart: wordpress
|
||||
helm:
|
||||
values: |
|
||||
|
||||
@@ -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
|
||||
@@ -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`.
|
||||
@@ -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
+212
@@ -0,0 +1,212 @@
|
||||
#!/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}
|
||||
MINIO=${MINIO:-http://192.168.1.99:9000}
|
||||
BUCKET=velero-backups
|
||||
PORT=${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 $what" >&2; exit 1; fi
|
||||
sleep 5
|
||||
done
|
||||
}
|
||||
|
||||
backup=${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\n' "$MINIO" >> "$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
|
||||
@@ -54,6 +54,16 @@ between them live.
|
||||
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
|
||||
|
||||
+158
-20
@@ -8,11 +8,14 @@ bottom.
|
||||
|
||||
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, all Synced/Healthy; every Longhorn volume has one
|
||||
replica. 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. node001 runs mail and tunnels the public hosts home.
|
||||
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 on the backups and Vault's seal from inside the cluster.
|
||||
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
|
||||
|
||||
@@ -77,7 +80,25 @@ friend.
|
||||
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
|
||||
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:
|
||||
- [ ] Run `backup-testing/restore-test.sh` (it reads the MinIO key from
|
||||
the cluster), then schedule it
|
||||
|
||||
### 3. authentik 2026.2.1 → 2026.8.5
|
||||
|
||||
@@ -105,10 +126,13 @@ April and May.
|
||||
- [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
|
||||
- [ ] Base URL (system setting or `AUTHENTIK_WEB__BASE_URL`) becomes
|
||||
required in 2026.11. authentik answers on authentik.rubenhensen.nl and
|
||||
auth.scoutingmbg.nl (immich's issuer), so find out first what the
|
||||
setting does with two hostnames
|
||||
- [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
|
||||
|
||||
@@ -179,15 +203,21 @@ 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
|
||||
four external endpoints to s2 (group "cluster"): the newest daily and
|
||||
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, and no Vault pod sealed.
|
||||
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): metrics-server, then Prometheus or
|
||||
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
|
||||
@@ -237,7 +267,12 @@ Counted 2026-10-25 over the 73 running containers:
|
||||
without a policy
|
||||
- [ ] Requests and memory limits, the big ones first (immich, authentik,
|
||||
Argo CD's repo-server)
|
||||
- [ ] Probes
|
||||
- [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
|
||||
@@ -245,9 +280,68 @@ Counted 2026-10-25 over the 73 running containers:
|
||||
10 Renovate PRs are open, the oldest from February, and nothing checks a
|
||||
PR before Argo CD applies it.
|
||||
|
||||
- [ ] A GitHub Actions workflow that renders the Helm apps and runs
|
||||
kubeconform on every PR, with conftest for this repo's rules
|
||||
- [ ] Automerge patch versions of low-risk apps once that runs
|
||||
- [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)
|
||||
- [ ] The open PRs, all validated on 2026-10-25 against main as it is now
|
||||
(rebases requested, so the checks show on the PRs once Renovate has
|
||||
pushed). Merging is yours; merging deploys:
|
||||
- #28 cert-manager v1.21.3: security release, "All users should
|
||||
upgrade" (drops the compromised eMudhra root, fixes an ARI renewal
|
||||
loop and a private key copy path). Merge first
|
||||
- #24 external-snapshotter v8.2.1 → v8.7.0: 8.6 moved VolumeGroupSnapshot
|
||||
to v1 and 8.7 turns its feature gate on; the cluster already serves the
|
||||
v1 CRDs. Merge; close #15
|
||||
- #25 WordPress chart 0.15.0 → 0.16.7: the image is pinned
|
||||
(7.1.3-php8.3-apache), so the render only changes labels and
|
||||
checksums (a pod restart). Merge; #19 (0.15.1) is superseded
|
||||
- #26 Gitea 1.27.3 → 28.2.0 (Gitea renumbered after 1.27): security
|
||||
fixes; the breaking changes are to egress host lists
|
||||
(`ALLOWED_DOMAINS` and friends), none of which are set here. Database
|
||||
migrations can't be undone, so merge after a fresh backup
|
||||
- #23 ntfy v2.28.0 → v2.34.0: six releases in 17 days; 2.31.0 had a
|
||||
database load bug that ntfy.sh rolled back (fixed in 2.31.1). No
|
||||
breaking migrations. Fine, or wait a few days for 2.34 to settle
|
||||
- #17 external-secrets 2.13.0 → 2.14.0: no breaking changes in the
|
||||
notes; every secret goes through it, so merge when there's time to
|
||||
watch a force-sync
|
||||
- #27 go-dqlite v3.0.4 for `tools/dqlite-vacuum`: builds; harmless
|
||||
- #29 yaml.v3 for the same tool: builds, but the code imports yaml.v2,
|
||||
so it only adds an unused requirement. Close
|
||||
- #31 python 3.15.1 for `gatus/backup-check.yaml`: the check's tests
|
||||
(made-up data for every failure) pass on that image. Merge
|
||||
|
||||
### 9. One node
|
||||
|
||||
@@ -285,9 +379,53 @@ step after that, if downtime starts to matter.
|
||||
- [ ] 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)
|
||||
- [ ] `~/cadir` on opti1 holds a CA key and certificate from 2026-03-21
|
||||
that are not microk8s's current CA. Find out whether anything still
|
||||
trusts it; if not, delete it
|
||||
- [ ] `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)
|
||||
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -11,6 +11,8 @@
|
||||
# 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.
|
||||
@@ -63,6 +65,12 @@ rules:
|
||||
- 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
|
||||
@@ -170,6 +178,24 @@ data:
|
||||
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:
|
||||
@@ -185,6 +211,8 @@ data:
|
||||
"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():
|
||||
|
||||
@@ -169,3 +169,15 @@ external-endpoints:
|
||||
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
|
||||
@@ -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
|
||||
|
||||
@@ -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.
|
||||
@@ -109,6 +117,12 @@ 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
|
||||
|
||||
@@ -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:
|
||||
|
||||
+32
-22
@@ -6,7 +6,7 @@
|
||||
],
|
||||
"argocd": {
|
||||
"managerFilePatterns": [
|
||||
"/apps/templates/.+\\.yaml$/"
|
||||
"/^(?!(nix-infra-machine|backup-testing|docs|tools|\\.github)/)[^/]+/.+\\.yaml$/"
|
||||
]
|
||||
},
|
||||
"helm-values": {
|
||||
@@ -16,25 +16,10 @@
|
||||
},
|
||||
"kubernetes": {
|
||||
"managerFilePatterns": [
|
||||
"/apps/templates/.+\\.yaml$/",
|
||||
"/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$/"
|
||||
],
|
||||
"matchStrings": [
|
||||
"repoURL: https://github.com/(?<depName>[^/]+/[^/\\.]+)\\.git\\n\\s+targetRevision: (?<currentValue>.*)"
|
||||
],
|
||||
"datasourceTemplate": "github-tags"
|
||||
},
|
||||
{
|
||||
"customType": "regex",
|
||||
"managerFilePatterns": [
|
||||
@@ -44,6 +29,17 @@
|
||||
"repoURL: (?<registryUrl>.*?)\\n\\s+targetRevision: (?<currentValue>[^\\s]+)\\n\\s+chart: (?<depName>[^\\s]+)"
|
||||
],
|
||||
"datasourceTemplate": "helm"
|
||||
},
|
||||
{
|
||||
"customType": "regex",
|
||||
"description": "CloudNativePG clusters name their image in imageName",
|
||||
"managerFilePatterns": [
|
||||
"/^[^/]+/postgresql-cluster[^/]*\\.yaml$/"
|
||||
],
|
||||
"matchStrings": [
|
||||
"imageName: (?<depName>[^:\\s]+):(?<currentValue>\\S+)"
|
||||
],
|
||||
"datasourceTemplate": "docker"
|
||||
}
|
||||
],
|
||||
"packageRules": [
|
||||
@@ -56,12 +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
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -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
|
||||
|
||||
+57
-3
@@ -15,6 +15,13 @@ in the app folders. Sources:
|
||||
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
|
||||
@@ -22,6 +29,7 @@ import pathlib
|
||||
import subprocess
|
||||
import sys
|
||||
import tempfile
|
||||
import time
|
||||
|
||||
import yaml
|
||||
|
||||
@@ -38,7 +46,15 @@ failures = []
|
||||
|
||||
|
||||
def run(cmd, **kw):
|
||||
return subprocess.run(cmd, check=True, capture_output=True, text=True, **kw).stdout
|
||||
# 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):
|
||||
@@ -78,7 +94,41 @@ def check_duplicate_keys():
|
||||
failures.append(f"{path.relative_to(ROOT)}: {e}")
|
||||
|
||||
|
||||
def validate(label, manifests):
|
||||
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]
|
||||
@@ -103,6 +153,8 @@ def validate(label, manifests):
|
||||
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 []
|
||||
|
||||
|
||||
@@ -238,7 +290,9 @@ def main():
|
||||
failures.append(f"{label}: render failed")
|
||||
continue
|
||||
if manifests is not None:
|
||||
validate(label, manifests)
|
||||
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):")
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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:
|
||||
|
||||
Reference in new issue
Block a user