Files
cairnobs/deploy/helm/sentry/templates/redpanda.yaml
T
jcoffey-dev 3eb0f4c589 Phase 4: SSO scaffolding, RBAC enforcement, tenant-scoped dashboards, audit logging, K8s deployment
RBAC (api/internal/authz) is live on /query and /dashboards, backed by a
new enterprise/ module (session issuance, audit logging, RBAC storage,
OIDC/SAML protocol wiring) that core never imports -- only calls over
HTTP. Found and fixed a real cross-tenant vulnerability in dashboards
(no tenant_id filtering at all) while writing the threat model doc.

Two things are explicitly NOT done, documented rather than hidden:
tenant isolation for log data itself (/query still shares one ClickHouse
connection and Tantivy index across every tenant -- RBAC controls who
can query, not what a query can see), and human SSO login (protocol
wiring exists, no HTTP handler calls it yet). See
docs/security/threat-model.md and docs/phase-4-runbook.md.

Also adds deploy/ (Go Operator + Helm chart, validated offline only --
no cluster was reachable in this environment).
2026-08-13 22:16:59 -07:00

109 lines
3.5 KiB
YAML

apiVersion: apps/v1
kind: StatefulSet
metadata:
name: {{ .Release.Name }}-redpanda
labels:
{{- include "sentry.labels" . | nindent 4 }}
{{- include "sentry.selectorLabels" (list $ "redpanda") | nindent 4 }}
spec:
serviceName: {{ .Release.Name }}-redpanda
replicas: 1
selector:
matchLabels:
{{- include "sentry.selectorLabels" (list $ "redpanda") | nindent 6 }}
template:
metadata:
labels:
{{- include "sentry.selectorLabels" (list $ "redpanda") | nindent 8 }}
spec:
containers:
- name: redpanda
image: "{{ .Values.redpanda.image.repository }}:{{ .Values.redpanda.image.tag }}"
imagePullPolicy: {{ .Values.global.imagePullPolicy }}
args:
- redpanda
- start
- --smp=1
- --memory=1G
- --reserve-memory=0M
- --overprovisioned
- --node-id=0
- --check=false
- --kafka-addr=PLAINTEXT://0.0.0.0:9092
- --advertise-kafka-addr=PLAINTEXT://{{ .Release.Name }}-redpanda:9092
ports:
- name: kafka
containerPort: 9092
- name: admin
containerPort: 9644
volumeMounts:
- name: data
mountPath: /var/lib/redpanda/data
readinessProbe:
exec:
command: ["rpk", "cluster", "health", "--exit-when-healthy"]
initialDelaySeconds: 5
periodSeconds: 5
resources:
{{- toYaml .Values.redpanda.resources | nindent 12 }}
volumeClaimTemplates:
- metadata:
name: data
spec:
accessModes: ["ReadWriteOnce"]
resources:
requests:
storage: {{ .Values.redpanda.persistence.size }}
---
apiVersion: v1
kind: Service
metadata:
name: {{ .Release.Name }}-redpanda
labels:
{{- include "sentry.labels" . | nindent 4 }}
{{- include "sentry.selectorLabels" (list $ "redpanda") | nindent 4 }}
spec:
clusterIP: None
selector:
{{- include "sentry.selectorLabels" (list $ "redpanda") | nindent 4 }}
ports:
- name: kafka
port: 9092
- name: admin
port: 9644
---
# One-shot: creates the sentry.logs.raw topic. Same image
# transport/Dockerfile builds for docker-compose.yml's redpanda-provision
# service. Deliberately a plain Job, not a Helm hook -- see
# deploy/helm/sentry/README.md's "Startup ordering" section for why
# (StatefulSets-as-hooks breaks helm upgrade/uninstall's ownership
# tracking of stateful resources). backoffLimit gives it room to retry
# until redpanda's StatefulSet is actually ready; ingest/search's own
# crash-and-restart-on-connect-failure covers the rest of the ordering,
# same as every dependency in this chart.
apiVersion: batch/v1
kind: Job
metadata:
name: {{ .Release.Name }}-redpanda-provision
labels:
{{- include "sentry.labels" . | nindent 4 }}
spec:
backoffLimit: 6
template:
metadata:
labels:
{{- include "sentry.selectorLabels" (list $ "redpanda-provision") | nindent 8 }}
spec:
restartPolicy: OnFailure
containers:
- name: redpanda-provision
image: "{{ .Values.redpanda.provisionImage.repository }}:{{ .Values.redpanda.provisionImage.tag }}"
imagePullPolicy: {{ .Values.global.imagePullPolicy }}
env:
- name: REDPANDA_BROKERS
value: "{{ .Release.Name }}-redpanda:9092"
- name: REDPANDA_ADMIN_HOSTS
value: "{{ .Release.Name }}-redpanda:9644"
- name: REDPANDA_TOPIC_PARTITIONS
value: "6"