mirror of
https://github.com/sredevopsorg/deepseek-kubernetes-sandbox.git
synced 2026-11-03 01:13:24 +00:00
a8ef211aa4
Resuming a sandbox recreates its pod on the same PVC. The kubelet's default
fsGroup policy ("Always") recursively ORs 0660 into every file on each pod
start, so DSH's .credentials.yaml — created 0600 — comes back as 0660. The
credentials plugin refuses to boot in that case:
credentials-local: .../.credentials.yaml is readable beyond its owner
(mode 660); run "chmod 600 ..."
That makes the first resume after a suspend crash-loop, which breaks the
example's step 6 and any gateway wake-on-connect.
Set fsGroupChangePolicy: OnRootMismatch on both sandbox templates. The
kubelet then skips the recursive walk when the volume root already carries
the fsGroup ownership/mode applied on the first mount — exactly the
suspend/resume case, while a fresh PVC is still chowned correctly.
Document the upgrade path: Sandbox objects snapshot their pod template, so
existing sandboxes and warm-pool members need the policy patched (plus a
one-time chmod 600) or must be recreated.
Co-authored-by: SREDevOpsAgents <agents@sredevops.org>
110 lines
4.6 KiB
YAML
110 lines
4.6 KiB
YAML
# The reusable DSH Web blueprint. Warm pools stamp pod env BEFORE any user
|
|
# exists, so per-user secrets cannot live in pod env; the shared provider key
|
|
# is injected via envFrom, and claims that would bypass the warm pool are
|
|
# rejected outright (see 40-claim-rejected.yaml).
|
|
apiVersion: extensions.agents.x-k8s.io/v1beta1
|
|
kind: SandboxTemplate
|
|
metadata:
|
|
name: dsh-web
|
|
namespace: dsh-demo
|
|
spec:
|
|
# Claims must not inject env or volumeClaimTemplates: with Disallowed, such
|
|
# claims are REJECTED instead of silently taking the cold (non-warm-pool)
|
|
# provisioning path. Demonstrated in step 6.
|
|
envVarsInjectionPolicy: Disallowed
|
|
volumeClaimTemplatesPolicy: Disallowed
|
|
|
|
# Per-sandbox headless Service -> stable DNS (sandbox.status.serviceFQDN).
|
|
# The gateway routes each user to their DSH Web instance by this name.
|
|
service: true
|
|
|
|
# No gateway pod scopes ingress in this standalone demo, so the
|
|
# NetworkPolicy is left unmanaged. A production platform would use
|
|
# networkPolicyManagement: Managed and restrict ingress to its gateway on
|
|
# :3080 — with the shared provider key, that NetworkPolicy is the per-user
|
|
# isolation boundary.
|
|
networkPolicyManagement: Unmanaged
|
|
|
|
podTemplate:
|
|
spec:
|
|
# DSH Web is multi-arch (amd64 + arm64); no arch nodeSelector needed.
|
|
restartPolicy: "OnFailure"
|
|
securityContext:
|
|
runAsUser: 1000 # the 'node' user in the DSH image
|
|
runAsGroup: 1000
|
|
fsGroup: 1000
|
|
runAsNonRoot: true
|
|
# DSH's credentials plugin refuses to start when .credentials.yaml has
|
|
# any group/other permission bit (it creates the file 0600). The
|
|
# default kubelet fsGroup policy ("Always") recursively ORs 0660 into
|
|
# every file each time the pod starts, so a resumed sandbox comes back
|
|
# with 0660 and crash-loops before the gateway can proxy to it.
|
|
# OnRootMismatch skips that walk once the volume root already carries
|
|
# the fsGroup ownership/mode applied on the first mount.
|
|
# Keep in sync with deploy/k8s/sandbox-template.yaml.
|
|
fsGroupChangePolicy: OnRootMismatch
|
|
containers:
|
|
- name: dsh-web
|
|
image: ghcr.io/sredevopsorg/deepseek-kubernetes-sandbox:dsh-v0.2.1-rc.2
|
|
imagePullPolicy: IfNotPresent
|
|
ports:
|
|
- name: web
|
|
containerPort: 3080
|
|
envFrom:
|
|
- secretRef:
|
|
name: dsh-provider-keys
|
|
env:
|
|
# Empty => DSH derives links from the request Host, which the
|
|
# gateway forwards (plus X-Forwarded-*). Point this at the
|
|
# gateway base URL if you want hard-coded absolute links instead.
|
|
- name: DSH_PUBLIC_URL
|
|
value: ""
|
|
# DSH Host/Origin-fences /api. The gateway forwards the browser's
|
|
# Host, so DSH must trust the public gateway host. Empty is right
|
|
# for port-forward/localhost; for the optional Ingress set this to
|
|
# the same host as 60-ingress.yaml (e.g. dsh.example.com).
|
|
- name: DSH_TRUSTED_HOSTS
|
|
value: ""
|
|
# Probes target /favicon.svg: DSH gates / behind its launch-token
|
|
# cookie and answers 401 to an unauthenticated GET, which would
|
|
# otherwise fail readiness and then get the pod killed by liveness.
|
|
# /favicon.svg is served without auth and is the cheapest liveness
|
|
# signal that proves the HTTP server is actually serving requests.
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /favicon.svg
|
|
port: 3080
|
|
initialDelaySeconds: 5
|
|
periodSeconds: 5
|
|
failureThreshold: 30
|
|
livenessProbe:
|
|
httpGet:
|
|
path: /favicon.svg
|
|
port: 3080
|
|
initialDelaySeconds: 15
|
|
periodSeconds: 15
|
|
failureThreshold: 3
|
|
# The container only needs to serve HTTP; drop every capability and
|
|
# disallow privilege escalation. DSH writes only to DSH_HOME (PVC).
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
capabilities:
|
|
drop: ["ALL"]
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
resources:
|
|
requests: {cpu: 250m, memory: 512Mi}
|
|
limits: {cpu: "1", memory: 1Gi}
|
|
volumeMounts:
|
|
- name: dsh-home
|
|
mountPath: /home/node/.dsh # DSH_HOME: sessions, config, state
|
|
volumeClaimTemplates:
|
|
- metadata:
|
|
name: dsh-home
|
|
spec:
|
|
accessModes: ["ReadWriteOnce"]
|
|
resources:
|
|
requests:
|
|
storage: 5Gi
|
|
# storageClassName omitted => cluster default (kind & GKE both work)
|