Compare commits

..
1 Commits
Author SHA1 Message Date
Ruben Hensen 68b692a112 docs: requests are in PR 33 2026-10-25 07:10:37 +01:00
16 changed files with 14 additions and 203 deletions

No files matched your search

-8
View File
@@ -99,10 +99,6 @@ 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:
@@ -188,10 +184,6 @@ spec:
mountPath: /etc/ssl/certs
readOnly: true
worker:
resources:
requests:
cpu: 100m
memory: 336Mi
volumes:
- name: patched-ca-bundle
configMap:
-14
View File
@@ -34,20 +34,6 @@ 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
-4
View File
@@ -24,10 +24,6 @@ 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
-16
View File
@@ -18,22 +18,6 @@ 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
+1 -2
View File
@@ -21,5 +21,4 @@ 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/resources.patch.yaml
- path: overlays/patched-ca-bundle.patch.yaml
-100
View File
@@ -1,100 +0,0 @@
# 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
-4
View File
@@ -8,10 +8,6 @@ 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
+13 -5
View File
@@ -13,7 +13,8 @@ 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.
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.
@@ -33,8 +34,9 @@ docs/longhorn-second-ssd.md:
- [ ] 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. The snap is held,
so microk8s gets no updates at all until someone refreshes it
- [ ] 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
@@ -265,8 +267,14 @@ Counted 2026-10-25 over the 73 running containers:
external-secrets, envoy-gateway-system, velero, mariadb-system, dns,
default) still have none; `default` can reach the LAN and everything
without a policy
- [ ] Requests and memory limits, the big ones first (immich, authentik,
Argo CD's repo-server)
- [ ] Requests: PR #33 (2026-10-25, CI green, not merged) sets them for
everything that had none except the Vault server, from `kubectl top`
every 5 minutes overnight (highest memory plus 10%, CPU at p95, 10m
floor); about 1.2 CPU and 7 GiB together. Merging restarts most pods,
including both CNPG instances (half a minute without a database for
authentik and immich)
- [ ] Memory limits, once there are daytime numbers: the night ones miss
immich's machine learning at work (it idles at 234Mi)
- [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
-4
View File
@@ -79,10 +79,6 @@ 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:
-4
View File
@@ -50,10 +50,6 @@ spec:
- containerPort: 3000
name: http
protocol: TCP
resources:
requests:
cpu: 20m
memory: 336Mi
# /api/healthz checks the database and the cache.
readinessProbe:
httpGet:
-14
View File
@@ -63,10 +63,6 @@ spec:
main:
containers:
main:
resources:
requests:
cpu: 10m
memory: 64Mi
image:
repository: docker.io/valkey/valkey
tag: 9.1.2-alpine@sha256:48332870af354a799964c0012ae1194a0bf2bf894eb508f945810596dc2d8d11
@@ -89,10 +85,6 @@ 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.
@@ -117,12 +109,6 @@ 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
-4
View File
@@ -9,10 +9,6 @@ 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:
-12
View File
@@ -16,26 +16,14 @@ 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:
-4
View File
@@ -56,10 +56,6 @@ spec:
ports:
- containerPort: 3000
protocol: TCP
resources:
requests:
cpu: 10m
memory: 160Mi
readinessProbe:
httpGet:
path: /login
-4
View File
@@ -3,10 +3,6 @@ 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
-4
View File
@@ -68,10 +68,6 @@ 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: