first commit

envs/dev/apps/cdc-job.yaml

@@ -0,0 +1,22 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: lake-cdc-job-dev
+  namespace: argocd
+spec:
+  project: default
+  sources:
+    - repoURL: <REPO_URL>
+      targetRevision: main
+      path: charts/lake-cdc-job
+      helm:
+        valueFiles:
+          - $values/envs/dev/values/cdc-job.yaml
+    - repoURL: <REPO_URL>
+      targetRevision: main
+      ref: values
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: dbiz-lake-dev
+  syncPolicy:
+    automated: { prune: true, selfHeal: true }

envs/dev/apps/infra.yaml

@@ -0,0 +1,22 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: lake-infra-dev
+  namespace: argocd
+spec:
+  project: default
+  source:
+    repoURL: <REPO_URL>
+    targetRevision: main
+    path: envs/dev/infra
+    directory:
+      recurse: true
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: dbiz-lake-dev
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true
+    syncOptions:
+      - CreateNamespace=true

envs/dev/apps/kafka-cluster.yaml

@@ -0,0 +1,17 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: lake-kafka-dev
+  namespace: argocd
+spec:
+  project: default
+  source:
+    repoURL: <REPO_URL>
+    targetRevision: main
+    path: envs/dev/kafka
+    directory: { recurse: true }
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: dbiz-lake-dev
+  syncPolicy:
+    automated: { prune: true, selfHeal: true }

envs/dev/apps/root.yaml

@@ -0,0 +1,20 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: lake-root-dev
+  namespace: argocd
+spec:
+  project: default
+  source:
+    repoURL: <REPO_URL>
+    targetRevision: main
+    path: envs/dev/apps
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: argocd
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true
+    syncOptions:
+      - CreateNamespace=true

envs/dev/apps/spark-operator.yaml

@@ -0,0 +1,25 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: lake-spark-operator-dev
+  namespace: argocd
+spec:
+  project: default
+  source:
+    repoURL: https://kubeflow.github.io/spark-operator
+    chart: spark-operator
+    targetRevision: 2.1.1            # pin (kiểm bản mới khi dựng)
+    helm:
+      releaseName: spark-operator
+      values: |
+        spark:
+          jobNamespaces:
+            - dbiz-lake-dev
+        webhook:
+          enable: true
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: dbiz-lake-dev
+  syncPolicy:
+    automated: { prune: true, selfHeal: true }
+    syncOptions: [ CreateNamespace=true ]

envs/dev/apps/strimzi-operator.yaml

@@ -0,0 +1,19 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: lake-strimzi-operator-dev
+  namespace: argocd
+spec:
+  project: default
+  source:
+    repoURL: https://strimzi.io/charts/
+    chart: strimzi-kafka-operator
+    targetRevision: 0.45.0          # pin version (kiểm bản mới nhất khi dựng thật)
+    helm:
+      releaseName: strimzi
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: dbiz-lake-dev
+  syncPolicy:
+    automated: { prune: true, selfHeal: true }
+    syncOptions: [ CreateNamespace=true ]

envs/dev/infra/external-services.yaml

@@ -0,0 +1,50 @@
+# Service + Endpoints không selector -> trỏ tới hạ tầng NGOÀI K8s (theo pattern argo-k8s).
+# MinIO lake: GIỮ NGUYÊN, K8s compute trỏ vào đây như S3 endpoint.
+# ĐIỀN IP THẬT của máy chạy MinIO (VM lake) trước khi apply.
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: minio-lake
+  namespace: dbiz-lake-dev
+spec:
+  ports:
+    - name: s3
+      port: 9000
+      targetPort: 9000
+---
+apiVersion: v1
+kind: Endpoints
+metadata:
+  name: minio-lake
+  namespace: dbiz-lake-dev
+subsets:
+  - addresses:
+      - ip: 192.168.110.37   # <-- ĐIỀN IP máy MinIO (VM lake)
+    ports:
+      - name: s3
+        port: 9000
+---
+# Postgres nguồn CRM (172.20.109.5) — để Debezium/Strimzi trỏ tới khi CDC
+apiVersion: v1
+kind: Service
+metadata:
+  name: crm-source-pg
+  namespace: dbiz-lake-dev
+spec:
+  ports:
+    - name: pg
+      port: 5432
+      targetPort: 5432
+---
+apiVersion: v1
+kind: Endpoints
+metadata:
+  name: crm-source-pg
+  namespace: dbiz-lake-dev
+subsets:
+  - addresses:
+      - ip: 172.20.109.5
+    ports:
+      - name: pg
+        port: 5432

envs/dev/kafka/kafka.yaml

@@ -0,0 +1,45 @@
+# Strimzi Kafka (KRaft mode, không Zookeeper). PV qua Longhorn.
+# Dev: 1 broker; prod: 3 broker (đổi replicas + storage).
+apiVersion: kafka.strimzi.io/v1beta2
+kind: KafkaNodePool
+metadata:
+  name: dual-role
+  namespace: dbiz-lake-dev
+  labels:
+    strimzi.io/cluster: lake-kafka
+spec:
+  replicas: 1
+  roles: [ controller, broker ]
+  storage:
+    type: persistent-claim
+    size: 20Gi
+    class: longhorn
+    deleteClaim: false
+---
+apiVersion: kafka.strimzi.io/v1beta2
+kind: Kafka
+metadata:
+  name: lake-kafka
+  namespace: dbiz-lake-dev
+  annotations:
+    strimzi.io/node-pools: enabled
+    strimzi.io/kraft: enabled
+spec:
+  kafka:
+    version: 3.9.0
+    listeners:
+      - name: plain
+        port: 9092
+        type: internal
+        tls: false
+    config:
+      # message to (giải bài RecordTooLarge đã gặp): 10MB
+      message.max.bytes: 10485760
+      offsets.topic.replication.factor: 1
+      transaction.state.log.replication.factor: 1
+      transaction.state.log.min.isr: 1
+      default.replication.factor: 1
+      min.insync.replicas: 1
+  entityOperator:
+    topicOperator: {}
+    userOperator: {}

envs/dev/values/cdc-job.yaml

@@ -0,0 +1,23 @@
+# DBIZ lake — "khách số 0". Nhân bản: copy file này, đổi customer + nguồn + bucket.
+customer: dbiz
+image:
+  repository: git.dbiz.com/dbiz/spark-cdc   # <-- Gitea registry built-in (git.dbiz.com/dbiz/spark-cdc)
+  tag: "latest"
+imagePullSecret: gitea-registry
+
+kafka:
+  bootstrap: "lake-kafka-kafka-bootstrap:9092"
+topicPattern: "crm\\.public\\..*"
+targetTable: "iceberg.raw_crm.cdc_events"
+triggerInterval: "30 seconds"
+
+catalog:
+  uri: "http://polaris:8181/api/catalog"
+  warehouse: "dbiz_warehouse"
+s3:
+  endpoint: "http://minio-lake:9000"
+  region: "us-east-1"
+
+checkpoint:
+  storageClass: longhorn
+  size: 5Gi