refactor(k8s): consolidate to infra/+apps/ single-source tree, dedicated per-app CNPG (authentik-db/temporal-db), wire monitoring-config, forgejo→cicd ns, drop orphan/stale (data-schemas, ollama, story-crater, sqs/argocd, key-rotation)

This commit is contained in:
Story Crater Bot
2026-08-18 15:08:03 -07:00
parent 54fa540b33
commit 41f5b05395
241 changed files with 467 additions and 10416 deletions
@@ -0,0 +1,5 @@
apiVersion: v2
name: kafka-cluster
description: Strimzi Kafka/KafkaNodePool CRs for the kmsvc Kafka cluster (design.md §7)
type: application
version: 0.1.0
@@ -0,0 +1,30 @@
apiVersion: kafka.strimzi.io/v1beta2
kind: Kafka
metadata:
name: {{ .Values.clusterName }}
namespace: {{ .Values.namespace }}
annotations:
strimzi.io/node-pools: enabled
strimzi.io/kraft: enabled
spec:
kafka:
version: 4.0.0
metadataVersion: 4.0-IV3
listeners:
- name: plain
port: 9092
type: internal
tls: false
- name: tls
port: 9093
type: internal
tls: true
config:
default.replication.factor: {{ .Values.kafka.replicationFactor }}
min.insync.replicas: {{ .Values.kafka.minInsyncReplicas }}
offsets.topic.replication.factor: {{ .Values.kafka.replicationFactor }}
transaction.state.log.replication.factor: {{ .Values.kafka.replicationFactor }}
transaction.state.log.min.isr: {{ .Values.kafka.minInsyncReplicas }}
entityOperator:
topicOperator: {}
userOperator: {}
@@ -0,0 +1,39 @@
apiVersion: kafka.strimzi.io/v1beta2
kind: KafkaNodePool
metadata:
name: {{ .Values.clusterName }}-pool
namespace: {{ .Values.namespace }}
labels:
strimzi.io/cluster: {{ .Values.clusterName }}
spec:
replicas: {{ .Values.nodePool.replicas }}
roles:
- controller
- broker
storage:
type: persistent-claim
size: {{ .Values.nodePool.storage.sizeGi }}Gi
class: {{ .Values.nodePool.storage.class }}
deleteClaim: false
resources:
limits:
memory: {{ .Values.nodePool.resources.memory }}
cpu: {{ .Values.nodePool.resources.cpu | quote }}
requests:
memory: {{ .Values.nodePool.resources.memory }}
cpu: {{ .Values.nodePool.resources.cpu | quote }}
template:
pod:
affinity:
podAntiAffinity:
preferredDuringSchedulingIgnoredDuringExecution:
- weight: 100
podAffinityTerm:
topologyKey: {{ .Values.nodePool.antiAffinityTopologyKey }}
labelSelector:
matchLabels:
strimzi.io/cluster: {{ .Values.clusterName }}
kafkaContainer:
env:
- name: KAFKA_HEAP_OPTS
value: {{ .Values.nodePool.heapOpts | quote }}
@@ -0,0 +1,26 @@
clusterName: kmsvc
namespace: sqs
nodePool:
replicas: 3
storage:
class: longhorn
# Longhorn's per-node scheduling budget on the current 2-node cluster has
# only ~36Gi of headroom left (other PVCs already reserve the rest), and
# each node hosts one replica of all 3 broker volumes -- so 3 * sizeGi
# must fit in that headroom. Revisit once the 3rd node joins.
sizeGi: 10
resources:
memory: 5Gi
cpu: "2"
heapOpts: "-Xms2g -Xmx2g"
# design.md §7: 3 real zones now exist (talos-cp-1=az-a, talos-worker-1=az-b,
# talos-worker-2=az-c), so anti-affinity keys off zone instead of hostname —
# spreads the 3 broker pods one-per-zone/one-per-node (equivalent today,
# but zone is the correct long-term key if a node ever gets replaced within
# the same zone).
antiAffinityTopologyKey: topology.kubernetes.io/zone
kafka:
replicationFactor: 3
minInsyncReplicas: 2
@@ -0,0 +1,5 @@
apiVersion: v2
name: management-service
description: kmsvc message-plane gRPC+REST server (design.md §1, §7a, §9)
type: application
version: 0.1.0
@@ -0,0 +1,12 @@
apiVersion: v1
kind: ConfigMap
metadata:
name: management-service-config
namespace: {{ .Values.namespace }}
data:
KMSVC_KAFKA_BROKERS: {{ .Values.env.kafkaBrokers | quote }}
KMSVC_REDIS_ADDR: {{ .Values.env.redisAddr | quote }}
KMSVC_AUTHENTIK_ISSUER_URL: {{ .Values.env.authentikIssuerURL | quote }}
KMSVC_AUTHENTIK_AUDIENCE: {{ .Values.env.authentikAudience | quote }}
KMSVC_GRPC_LISTEN_ADDR: ":{{ .Values.grpcPort }}"
KMSVC_HTTP_LISTEN_ADDR: ":{{ .Values.httpPort }}"
@@ -0,0 +1,49 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: management-service
namespace: {{ .Values.namespace }}
spec:
replicas: {{ .Values.replicaCount }}
selector:
matchLabels:
app: management-service
template:
metadata:
labels:
app: management-service
spec:
topologySpreadConstraints:
- maxSkew: 1
topologyKey: kubernetes.io/hostname
whenUnsatisfiable: ScheduleAnyway
labelSelector:
matchLabels:
app: management-service
containers:
- name: management-service
image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
imagePullPolicy: {{ .Values.image.pullPolicy }}
ports:
- name: grpc
containerPort: {{ .Values.grpcPort }}
- name: http
containerPort: {{ .Values.httpPort }}
env:
- name: GOMEMLIMIT
value: {{ .Values.goMemLimit | quote }}
envFrom:
- configMapRef:
name: management-service-config
resources:
{{- toYaml .Values.resources | nindent 12 }}
readinessProbe:
tcpSocket:
port: {{ .Values.httpPort }}
initialDelaySeconds: 5
periodSeconds: 10
livenessProbe:
tcpSocket:
port: {{ .Values.httpPort }}
initialDelaySeconds: 10
periodSeconds: 20
@@ -0,0 +1,27 @@
{{- if .Values.hpa.enabled }}
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
name: management-service
namespace: {{ .Values.namespace }}
spec:
scaleTargetRef:
apiVersion: apps/v1
kind: Deployment
name: management-service
minReplicas: {{ .Values.hpa.minReplicas }}
maxReplicas: {{ .Values.hpa.maxReplicas }}
metrics:
- type: Resource
resource:
name: cpu
target:
type: Utilization
averageUtilization: {{ .Values.hpa.targetCPUUtilizationPercentage }}
- type: Resource
resource:
name: memory
target:
type: Utilization
averageUtilization: {{ .Values.hpa.targetMemoryUtilizationPercentage }}
{{- end }}
@@ -0,0 +1,27 @@
{{- if and .Values.ingress.enabled .Values.ingress.grpcEnabled }}
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: management-service-grpc
namespace: {{ .Values.namespace }}
annotations:
cert-manager.io/cluster-issuer: {{ .Values.ingress.clusterIssuer }}
nginx.ingress.kubernetes.io/backend-protocol: "GRPC"
spec:
ingressClassName: {{ .Values.ingress.className }}
tls:
- hosts:
- {{ .Values.ingress.host }}
secretName: {{ .Values.ingress.tlsSecretName }}
rules:
- host: {{ .Values.ingress.host }}
http:
paths:
- path: {{ .Values.ingress.grpcPathPrefix }}
pathType: Prefix
backend:
service:
name: management-service
port:
number: {{ .Values.grpcPort }}
{{- end }}
@@ -0,0 +1,26 @@
{{- if .Values.ingress.enabled }}
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: management-service
namespace: {{ .Values.namespace }}
annotations:
cert-manager.io/cluster-issuer: {{ .Values.ingress.clusterIssuer }}
spec:
ingressClassName: {{ .Values.ingress.className }}
tls:
- hosts:
- {{ .Values.ingress.host }}
secretName: {{ .Values.ingress.tlsSecretName }}
rules:
- host: {{ .Values.ingress.host }}
http:
paths:
- path: /
pathType: Prefix
backend:
service:
name: management-service
port:
number: {{ .Values.httpPort }}
{{- end }}
@@ -0,0 +1,16 @@
apiVersion: v1
kind: Service
metadata:
name: management-service
namespace: {{ .Values.namespace }}
spec:
selector:
app: management-service
ports:
- name: grpc
port: {{ .Values.grpcPort }}
targetPort: {{ .Values.grpcPort }}
- name: http
port: {{ .Values.httpPort }}
targetPort: {{ .Values.httpPort }}
type: ClusterIP
@@ -0,0 +1,50 @@
namespace: sqs
replicaCount: 3
image:
repository: ghcr.io/riotpiaole/kmsvc-management-service
tag: latest
pullPolicy: Always
grpcPort: 9090
httpPort: 8080
env:
kafkaBrokers: "kmsvc-kafka-bootstrap.sqs.svc.cluster.local:9092"
redisAddr: "kmsvc-redis-master.sqs.svc.cluster.local:6379"
authentikIssuerURL: ""
authentikAudience: ""
resources:
requests:
cpu: 200m
memory: 256Mi
limits:
cpu: "1"
memory: 512Mi
# Go's GC only reacts to GOGC by default and has no idea about the cgroup
# memory limit above -- it'll happily grow heap until the kernel OOMKills it.
# Setting GOMEMLIMIT to ~90% of the container limit makes the GC self-throttle
# before that happens. Keep this in sync with resources.limits.memory.
goMemLimit: "460MiB"
hpa:
enabled: true
minReplicas: 3
maxReplicas: 9
targetCPUUtilizationPercentage: 70
targetMemoryUtilizationPercentage: 80
ingress:
enabled: true
className: nginx
clusterIssuer: homelab-ca
host: kmsvc.riotpiao.com
tlsSecretName: kmsvc-tls
# kmsvc-cli connects via gRPC directly to --server/KMSVC_SERVER (default
# kmsvc.riotpiao.com:443, see kmsvc-cli's README), so raw gRPC needs an
# external path too — scoped to the gRPC service's own path prefix on the
# same host/port, rather than opening the whole host to gRPC passthrough.
grpcEnabled: true
grpcPathPrefix: /kafkamgmt.v1.QueueService/
+5
View File
@@ -0,0 +1,5 @@
apiVersion: v2
name: queue-crd
description: Queue CRD definition + queue-operator Deployment/RBAC (design.md §2a)
type: application
version: 0.1.0
@@ -0,0 +1,274 @@
---
apiVersion: apiextensions.k8s.io/v1
kind: CustomResourceDefinition
metadata:
annotations:
controller-gen.kubebuilder.io/version: v0.21.0
name: queues.kmsvc.io
spec:
group: kmsvc.io
names:
kind: Queue
listKind: QueueList
plural: queues
shortNames:
- queue
- queues
singular: queue
scope: Namespaced
versions:
- additionalPrinterColumns:
- jsonPath: .spec.fifoQueue
name: FIFO
type: boolean
- jsonPath: .status.phase
name: Phase
type: string
name: v1
schema:
openAPIV3Schema:
description: Queue is the Schema for the queues API — see design.md §2a.
properties:
apiVersion:
description: |-
APIVersion defines the versioned schema of this representation of an object.
Servers should convert recognized schemas to the latest internal value, and
may reject unrecognized values.
More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources
type: string
kind:
description: |-
Kind is a string value representing the REST resource this object represents.
Servers may infer this from the endpoint the client submits requests to.
Cannot be updated.
In CamelCase.
More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds
type: string
metadata:
type: object
spec:
description: QueueSpec defines the desired state of a Queue (design.md
§2a).
properties:
deadLetterTargetQueue:
description: |-
DeadLetterTargetQueue is the name of another Queue to route exhausted
messages to. Must not point at itself or at another DLQ (design.md §5).
type: string
delaySeconds:
description: DelaySeconds is the default delivery delay applied to
sent messages.
format: int32
maximum: 900
minimum: 0
type: integer
fifoQueue:
default: false
description: FIFOQueue enables per-MessageGroupId ordering and deduplication
semantics.
type: boolean
isDLQ:
description: |-
IsDLQ marks this queue as itself a dead-letter queue, used to enforce
the no-DLQ-chaining validation rule in design.md §5.
type: boolean
maxReceiveCount:
default: 5
description: |-
MaxReceiveCount is how many times a message may be redelivered before
being routed to DeadLetterTargetQueue.
format: int32
minimum: 1
type: integer
maxShards:
default: 8
description: MaxShards is the ceiling on shard count the operator
may split up to (design.md §2c).
format: int32
minimum: 1
type: integer
messageRetentionPeriodSeconds:
default: 345600
description: MessageRetentionPeriodSeconds maps to the underlying
Kafka topic's retention.ms.
format: int32
maximum: 1209600
minimum: 60
type: integer
minShards:
default: 1
description: MinShards is the floor on shard count; the operator never
merges below this.
format: int32
minimum: 1
type: integer
partitionsPerShard:
default: 6
description: PartitionsPerShard is the Kafka partition count on each
shard's topic.
format: int32
minimum: 1
type: integer
shardSplitCooldownSeconds:
default: 300
description: |-
ShardSplitCooldownSeconds is the minimum age a shard must reach before it
is eligible to be split again, preventing rapid re-splitting of a child
that hasn't yet absorbed its share of traffic.
format: int32
minimum: 0
type: integer
shardSplitThresholdBytesPerSec:
default: 5242880
description: |-
ShardSplitThresholdBytesPerSec is the sustained per-shard throughput that
triggers a split into two child shards (design.md §2c).
format: int64
minimum: 1
type: integer
visibilityTimeoutSeconds:
default: 30
description: |-
VisibilityTimeoutSeconds is how long a received-but-unacked message stays
invisible to other consumers before being redelivered.
format: int32
maximum: 43200
minimum: 0
type: integer
type: object
status:
description: QueueStatus defines the observed state of a Queue.
properties:
conditions:
description: Conditions hold detailed status information.
items:
description: Condition contains details for one aspect of the current
state of this API Resource.
properties:
lastTransitionTime:
description: |-
lastTransitionTime is the last time the condition transitioned from one status to another.
This should be when the underlying condition changed. If that is not known, then using the time when the API field changed is acceptable.
format: date-time
type: string
message:
description: |-
message is a human readable message indicating details about the transition.
This may be an empty string.
maxLength: 32768
type: string
observedGeneration:
description: |-
observedGeneration represents the .metadata.generation that the condition was set based upon.
For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date
with respect to the current state of the instance.
format: int64
minimum: 0
type: integer
reason:
description: |-
reason contains a programmatic identifier indicating the reason for the condition's last transition.
Producers of specific condition types may define expected values and meanings for this field,
and whether the values are considered a guaranteed API.
The value should be a CamelCase string.
This field may not be empty.
maxLength: 1024
minLength: 1
pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$
type: string
status:
description: status of the condition, one of True, False, Unknown.
enum:
- "True"
- "False"
- Unknown
type: string
type:
description: type of condition in CamelCase or in foo.example.com/CamelCase.
maxLength: 316
pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$
type: string
required:
- lastTransitionTime
- message
- reason
- status
- type
type: object
type: array
phase:
description: Phase is the current reconciliation phase.
enum:
- Pending
- Ready
- Failed
type: string
shards:
description: |-
Shards lists every shard backing this queue, active or draining
(design.md §2a/§2c).
items:
description: ShardStatus describes one shard backing a Queue (design.md
§2a/§2c).
properties:
availabilityZones:
description: |-
AvailabilityZones lists the topology.kubernetes.io/zone values of every
node currently hosting a Kafka replica of this shard's topic, resolved
from the broker pods' node placement each reconcile. Empty until the
first successful resolution (e.g. node lookup failed transiently).
items:
type: string
type: array
createdAt:
description: |-
CreatedAt timestamps when this shard was created, used to enforce
ShardSplitCooldownSeconds.
format: date-time
type: string
hashRangeEnd:
format: int64
type: integer
hashRangeStart:
description: |-
HashRangeStart/HashRangeEnd define the [start, end) murmur2 hash range
this shard owns over the 32-bit key space. Stored as int64 (not uint32)
because controller-gen maps Go uint32 to OpenAPI format:int32, whose max
(2147483647) is smaller than FullHashRangeEnd (0xFFFFFFFF) and the
apiserver rejects the status update.
format: int64
type: integer
id:
description: ID is the shard's identifier, used in its topic
name (kmsvc.{queue}.shard-{id}).
type: string
parentId:
description: |-
ParentID is the shard ID this shard was split from, empty for the
original shard-0.
type: string
phase:
description: Phase is this shard's lifecycle state.
enum:
- Active
- Closing
- Closed
type: string
topic:
description: Topic is the underlying Kafka topic name for this
shard.
type: string
required:
- hashRangeEnd
- hashRangeStart
- id
- phase
- topic
type: object
type: array
type: object
type: object
served: true
storage: true
subresources:
status: {}
@@ -0,0 +1,38 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: queue-operator
namespace: {{ .Values.namespace }}
spec:
replicas: 1
selector:
matchLabels:
app: queue-operator
template:
metadata:
labels:
app: queue-operator
spec:
serviceAccountName: queue-operator
containers:
- name: queue-operator
image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
imagePullPolicy: {{ .Values.image.pullPolicy }}
command: ["/queue-operator"]
env:
- name: KMSVC_KAFKA_BROKERS
value: {{ .Values.kafkaBrokers | quote }}
- name: KMSVC_REDIS_ADDR
value: {{ .Values.redisAddr | quote }}
- name: GOMEMLIMIT
value: {{ .Values.goMemLimit | quote }}
- name: KMSVC_NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
- name: KMSVC_KAFKA_CLUSTER_NAME
value: {{ .Values.kafkaClusterName | quote }}
- name: KMSVC_KAFKA_POOL_NAME
value: {{ .Values.kafkaPoolName | quote }}
resources:
{{- toYaml .Values.resources | nindent 12 }}
@@ -0,0 +1,45 @@
apiVersion: v1
kind: ServiceAccount
metadata:
name: queue-operator
namespace: {{ .Values.namespace }}
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: queue-operator
rules:
- apiGroups: ["kmsvc.io"]
resources: ["queues", "temporalworkers"]
verbs: ["get", "list", "watch", "update", "patch"]
- apiGroups: ["kmsvc.io"]
resources: ["queues/status", "temporalworkers/status"]
verbs: ["get", "update", "patch"]
- apiGroups: ["kmsvc.io"]
resources: ["queues/finalizers", "temporalworkers/finalizers"]
verbs: ["update"]
- apiGroups: ["coordination.k8s.io"]
resources: ["leases"]
verbs: ["get", "list", "watch", "create", "update", "patch", "delete"]
- apiGroups: [""]
resources: ["events"]
verbs: ["create", "patch"]
- apiGroups: [""]
resources: ["pods", "nodes"]
verbs: ["get"]
- apiGroups: ["apps"]
resources: ["deployments"]
verbs: ["get", "list", "watch", "create", "update", "patch", "delete"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: queue-operator
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: queue-operator
subjects:
- kind: ServiceAccount
name: queue-operator
namespace: {{ .Values.namespace }}
@@ -0,0 +1,62 @@
apiVersion: apiextensions.k8s.io/v1
kind: CustomResourceDefinition
metadata:
name: temporalworkers.kmsvc.io
spec:
group: kmsvc.io
names:
kind: TemporalWorker
plural: temporalworkers
singular: temporalworker
scope: Namespaced
versions:
- name: v1
served: true
storage: true
schema:
openAPIV3Schema:
type: object
required:
- spec
properties:
apiVersion:
type: string
kind:
type: string
metadata:
type: object
spec:
type: object
description: Temporal worker specification
properties:
namespace:
type: string
description: Temporal namespace
taskQueue:
type: string
description: Task queue name
workflowTypes:
type: array
items:
type: string
description: List of workflow types to execute
activityTypes:
type: array
items:
type: string
description: List of activity types to execute
concurrency:
type: integer
minimum: 1
description: Worker concurrency level
status:
type: object
description: Temporal worker status
properties:
ready:
type: boolean
lastHeartbeat:
type: string
format: date-time
error:
type: string
+26
View File
@@ -0,0 +1,26 @@
namespace: sqs
image:
repository: ghcr.io/riotpiaole/kmsvc-management-service
tag: latest
pullPolicy: Always
kafkaBrokers: "kmsvc-kafka-bootstrap.sqs.svc.cluster.local:9092"
redisAddr: "kmsvc-redis-master.sqs.svc.cluster.local:6379"
# Must match kafka-cluster chart's clusterName/derived pool name -- used to
# resolve "<kafkaClusterName>-<kafkaPoolName>-<brokerID>" broker pod names
# for AZ-aware Queue status (design.md §2a).
kafkaClusterName: kmsvc
kafkaPoolName: kmsvc-pool
resources:
requests:
cpu: 100m
memory: 128Mi
limits:
cpu: 500m
memory: 256Mi
# See management-service/values.yaml's goMemLimit comment -- same reasoning.
goMemLimit: "230MiB"