Add deployment manifests, custody-class guard and request counters
AUDIT-WP-0005-T03 (progress). Manifests validated --dry-run=server --validate=strict against railiance01; not applied, since deployment is gated on RAPP-POSTGRES-WP-0002 and T02 credentials. Nothing here mutates the cluster. Conventions read off the deployed user-engine workload rather than invented: digest-pinned image from forgejo.coulomb.social, runAsNonRoot with RuntimeDefault seccomp, no privilege escalation, all capabilities dropped, readOnlyRootFilesystem, probes on a named http port, same resource envelope. The namespace carries railiance.io/postgres-client: platform-pg, which is what platform-pg-consumer-ingress in rapp-postgres admits; without that label the pod cannot reach the database at all. NetworkPolicies default-deny both directions, then permit ingress from the user-engine namespace only, a separately labelled operator read path, and egress to PostgreSQL in databases plus DNS. Three decisions worth naming. Liveness is /healthz while readiness is /readyz, so a database outage drops the pod from the Service rather than restarting it in a loop. readOnlyRootFilesystem enforces the empty-filesystem property rather than trusting it, so the SQLite fallback physically cannot accumulate audit records on ephemeral storage. AUDIT_CORE_REQUIRE_CUSTODY_CLASS=archive makes a missing database URL a startup failure instead of a silent downgrade to the development store. Counters deferred from WP-0004-T06 are exposed as JSON at /v1/stats behind the read privilege, not as Prometheus exposition format: the cluster runs no Prometheus, no ServiceMonitor CRD and no other scrape target, so an exposition endpoint would target a scrape path that does not exist. Usable with curl now and a small step from /metrics later. Tests 77 -> 80. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
parent
88d16847ff
commit
2f4e1adf66
6 changed files with 393 additions and 5 deletions
157
deploy/audit-core.yaml
Normal file
157
deploy/audit-core.yaml
Normal file
|
|
@ -0,0 +1,157 @@
|
|||
# audit-core receiver — railiance01 (AUDIT-WP-0005-T03).
|
||||
#
|
||||
# Conventions match the deployed user-engine workload: digest-pinned image from
|
||||
# forgejo.coulomb.social, non-root with a read-only root filesystem, and probes
|
||||
# on a named http port.
|
||||
#
|
||||
# Apply order matters: the namespace label railiance.io/postgres-client is what
|
||||
# platform-pg-consumer-ingress in the databases namespace admits, so without it
|
||||
# the pod cannot reach the database at all.
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: Namespace
|
||||
metadata:
|
||||
name: audit-core
|
||||
labels:
|
||||
kubernetes.io/metadata.name: audit-core
|
||||
railiance.io/workload-class: platform
|
||||
# Admitted by NetworkPolicy platform-pg-consumer-ingress (rapp-postgres).
|
||||
railiance.io/postgres-client: platform-pg
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: audit-core
|
||||
namespace: audit-core
|
||||
labels:
|
||||
app.kubernetes.io/name: audit-core
|
||||
spec:
|
||||
type: ClusterIP
|
||||
selector:
|
||||
app.kubernetes.io/name: audit-core
|
||||
ports:
|
||||
- name: http
|
||||
port: 8080
|
||||
targetPort: http
|
||||
protocol: TCP
|
||||
---
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: audit-core
|
||||
namespace: audit-core
|
||||
labels:
|
||||
app.kubernetes.io/name: audit-core
|
||||
annotations:
|
||||
# Rollback position. Update both together; `kubectl rollout undo` returns to
|
||||
# the previous digest, and the schema note records whether that is safe.
|
||||
audit-core.railiance.io/rollback-note: >-
|
||||
Migrations 0001-0004 are additive (CREATE TABLE/INDEX/TRIGGER IF NOT
|
||||
EXISTS) and are not reversed by a rollback. An older image runs against
|
||||
the newer schema without harm. A future migration that drops or narrows a
|
||||
column breaks that property and must state its own rollback position
|
||||
before it is released.
|
||||
spec:
|
||||
replicas: 1
|
||||
revisionHistoryLimit: 5
|
||||
strategy:
|
||||
type: RollingUpdate
|
||||
rollingUpdate:
|
||||
maxUnavailable: 0
|
||||
maxSurge: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: audit-core
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: audit-core
|
||||
spec:
|
||||
securityContext:
|
||||
runAsNonRoot: true
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
# In-flight events must not be lost on rollout; the app shuts down
|
||||
# gracefully on SIGTERM (AUDIT-WP-0004-T06).
|
||||
terminationGracePeriodSeconds: 30
|
||||
containers:
|
||||
- name: audit-core
|
||||
# REPLACE at release time with the built digest. A mutable tag is not
|
||||
# an immutable image, and `:latest` must never be the only reference.
|
||||
image: forgejo.coulomb.social/coulomb/audit-core@sha256:REPLACE_AT_RELEASE
|
||||
imagePullPolicy: IfNotPresent
|
||||
ports:
|
||||
- name: http
|
||||
containerPort: 8080
|
||||
env:
|
||||
- name: AUDIT_CORE_HOST
|
||||
value: "0.0.0.0"
|
||||
- name: AUDIT_CORE_HTTP_PORT
|
||||
value: "8080"
|
||||
# Refuses to start on anything but archive-class custody, so a
|
||||
# missing database URL fails loudly instead of silently downgrading
|
||||
# to the development store.
|
||||
- name: AUDIT_CORE_REQUIRE_CUSTODY_CLASS
|
||||
value: archive
|
||||
- name: AUDIT_CORE_DATABASE_SCHEMA
|
||||
value: audit_core
|
||||
- name: AUDIT_CORE_THREADS
|
||||
value: "8"
|
||||
- name: AUDIT_CORE_REQUEST_TIMEOUT
|
||||
value: "30"
|
||||
- name: AUDIT_CORE_DB_STATEMENT_TIMEOUT_MS
|
||||
value: "30000"
|
||||
# Both secrets are delivered through the OpenBao lane
|
||||
# (AUDIT-WP-0005-T02) — never committed, never set by hand.
|
||||
- name: AUDIT_CORE_DATABASE_URL
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: audit-core-database
|
||||
key: url
|
||||
- name: AUDIT_CORE_SENDERS
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: audit-core-senders
|
||||
key: senders.json
|
||||
resources:
|
||||
requests:
|
||||
cpu: 50m
|
||||
memory: 64Mi
|
||||
limits:
|
||||
cpu: 500m
|
||||
memory: 256Mi
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
drop: ["ALL"]
|
||||
# Custody lives in PostgreSQL. Nothing of value is written to the
|
||||
# pod filesystem, and a read-only root enforces that rather than
|
||||
# trusting it — the SQLite fallback cannot silently start
|
||||
# accumulating audit records on ephemeral storage.
|
||||
readOnlyRootFilesystem: true
|
||||
volumeMounts:
|
||||
- name: tmp
|
||||
mountPath: /tmp
|
||||
startupProbe:
|
||||
httpGet: {path: /healthz, port: http}
|
||||
periodSeconds: 3
|
||||
failureThreshold: 20
|
||||
readinessProbe:
|
||||
# /readyz checks the backend is reachable and durable, so the pod
|
||||
# leaves the Service when custody is unavailable rather than
|
||||
# accepting events it cannot store.
|
||||
httpGet: {path: /readyz, port: http}
|
||||
periodSeconds: 10
|
||||
timeoutSeconds: 2
|
||||
failureThreshold: 3
|
||||
livenessProbe:
|
||||
# Deliberately /healthz, not /readyz: a database outage must not
|
||||
# restart the pod in a loop. Losing readiness is the correct
|
||||
# response; restarting solves nothing and loses in-flight work.
|
||||
httpGet: {path: /healthz, port: http}
|
||||
periodSeconds: 20
|
||||
timeoutSeconds: 2
|
||||
failureThreshold: 3
|
||||
volumes:
|
||||
- name: tmp
|
||||
emptyDir: {}
|
||||
85
deploy/networkpolicies.yaml
Normal file
85
deploy/networkpolicies.yaml
Normal file
|
|
@ -0,0 +1,85 @@
|
|||
# Default-deny plus the narrowest set of exceptions (AUDIT-WP-0005-T03).
|
||||
#
|
||||
# The receiver holds the audit trail, so reachability is part of its threat
|
||||
# model: only the declared sender may write, and only the declared operator
|
||||
# path may read.
|
||||
---
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: audit-core-default-deny
|
||||
namespace: audit-core
|
||||
spec:
|
||||
podSelector: {}
|
||||
policyTypes: [Ingress, Egress]
|
||||
# No rules: everything not permitted below is denied.
|
||||
---
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: audit-core-sender-ingress
|
||||
namespace: audit-core
|
||||
spec:
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: audit-core
|
||||
policyTypes: [Ingress]
|
||||
ingress:
|
||||
# user-engine is the only sender. A second sender is a deliberate change
|
||||
# here and a matching entry in AUDIT_CORE_SENDERS — the network rule and
|
||||
# the credential binding must move together.
|
||||
- from:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: user-engine
|
||||
ports:
|
||||
- {protocol: TCP, port: 8080}
|
||||
---
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: audit-core-operator-ingress
|
||||
namespace: audit-core
|
||||
spec:
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: audit-core
|
||||
policyTypes: [Ingress]
|
||||
ingress:
|
||||
# Operator read path: lookup, dead letters, secret findings, stats.
|
||||
# Namespace-scoped rather than open, and still gated on a credential
|
||||
# carrying may_read — the network rule is the outer of two checks, not the
|
||||
# only one.
|
||||
- from:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
railiance.io/audit-core-reader: "true"
|
||||
ports:
|
||||
- {protocol: TCP, port: 8080}
|
||||
---
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: audit-core-egress
|
||||
namespace: audit-core
|
||||
spec:
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: audit-core
|
||||
policyTypes: [Egress]
|
||||
egress:
|
||||
# PostgreSQL custody store. This is the only destination the receiver needs;
|
||||
# it calls no other service.
|
||||
- to:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: databases
|
||||
ports:
|
||||
- {protocol: TCP, port: 5432}
|
||||
- to:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: kube-system
|
||||
ports:
|
||||
- {protocol: UDP, port: 53}
|
||||
- {protocol: TCP, port: 53}
|
||||
Loading…
Add table
Add a link
Reference in a new issue