Kubernetes Operator로 W&B 배포

api:
  install: true
  image:
    repository: wandb/megabinary
    tag: 0.74.1  # 실제 사용하는 버전으로 바꾸세요
  pod:
    securityContext:
      fsGroup: 10001
      fsGroupChangePolicy: Always
      runAsGroup: 0
      runAsNonRoot: true
      runAsUser: 10001
      seccompProfile:
        type: RuntimeDefault
  container:
    securityContext:
      allowPrivilegeEscalation: false
      capabilities:
        drop:
          - ALL
      privileged: false
      readOnlyRootFilesystem: false

Default host selected:  https://wandb.company-name.com
Find detailed logs for this test at: /var/folders/pn/b3g3gnc11_sbsykqkm3tx5rh0000gp/T/tmpdtdjbxua/wandb
Checking if logged in...................................................✅
Checking signed URL upload..............................................✅
Checking ability to send large payloads through proxy...................✅
Checking requests to base url...........................................✅
Checking requests made over signed URLs.................................✅
Checking CORs configuration of the bucket...............................✅
Checking wandb package version is up to date............................✅
Checking logged metrics, saving and downloading a file..................✅
Checking artifact save and download workflows...........................✅

spec:
  values:
    weave-trace:
      install: true

    mcp-server:
      install: true
      image:
        repository: us-docker.pkg.dev/wandb-production/public/wandb/mcp-server
        tag: "0.3.3"
      datadog:
        enabled: true
        mode: "agent"
        service: "wandb-mcp-server-<environment>"
        env: "<environment>"
        deploymentType: "self-managed"
        customer: "<customer-name>"
        extraTags:
          - "region:<region>"
          - "tier:<tier>"
      privacy:
        logLevel: "standard"

kubectl apply -f operator.yaml

kubectl get pod -l app.kubernetes.io/component=mcp-server
kubectl port-forward svc/wandb-mcp-server 8080:8080
curl -s http://localhost:8080/mcp/health

curl -s "https://<HOST_URI>/mcp/health"

bucket:
  kmsKey: <kms key arn>  # 암호화용 KMS 키(선택)
  name: <bucket name>    # 예시: wandb
  path: ""               # 빈 문자열로 유지하세요
  provider: s3
  region: <region>       # 예시: us-east-1

bucket:
  kmsKey: null
  name: <s3 endpoint>    # 예시: s3.example.com:9000
  path: <bucket name>    # 예시: wandb
  provider: s3
  region: <region>       # 예시: us-east-1

bucket:
  path: "wandb?tls=true"

mc config host add local http://$MINIO_HOST:$MINIO_PORT "$MINIO_ACCESS_KEY" "$MINIO_SECRET_KEY" --api s3v4
mc mb --region=us-east-1 local/wandb-files

apiVersion: apps.wandb.com/v1
kind: WeightsAndBiases
metadata:
  labels:
    app.kubernetes.io/name: weightsandbiases
    app.kubernetes.io/instance: wandb
  name: wandb
  namespace: default
spec:
  values:
    global:
      host: https://<HOST_URI>
      license: eyJhbGnUzaH...j9ZieKQ2x5GGfw
      bucket:
        <details depend on the provider>
      mysql:
        <redacted>
    ingress:
      annotations:
        <redacted>

apiVersion: apps.wandb.com/v1
kind: WeightsAndBiases
metadata:
  labels:
    app.kubernetes.io/name: weightsandbiases
    app.kubernetes.io/instance: wandb
  name: wandb
  namespace: default
spec:
  values:
    global:
      host: https://abc-wandb.sandbox-gcp.wandb.ml
      bucket:
        name: abc-wandb-moving-pipefish
        provider: gcs
      mysql:
        database: wandb_local
        host: 10.218.0.2
        name: wandb_local
        password: 8wtX6cJHizAZvYScjDzZcUarK4zZGjpV
        port: 3306
        user: wandb
      redis:
        host: redis.example.com
        port: 6379
        password: password
      api:
        enabled: true
      glue:
        enabled: true
      executor:
        enabled: true
      license: eyJhbGnUzaHgyQjQyQWhEU3...ZieKQ2x5GGfw
    ingress:
      annotations:
        ingress.gcp.kubernetes.io/pre-shared-cert: abc-wandb-cert-creative-puma
        kubernetes.io/ingress.class: gce
        kubernetes.io/ingress.global-static-ip-name: abc-wandb-operator-address

 # 프로토콜을 포함한 FQDN을 제공하세요
global:
  # 예시 호스트 이름, 자신의 것으로 교체하세요
  host: https://wandb.example.com

global:
  bucket:
    provider: "s3"
    name: ""
    kmsKey: ""
    region: ""

global:
  bucket:
    provider: "gcs"
    name: ""

global:
  bucket:
    provider: "az"
    name: ""
    secretKey: ""

global:
  bucket:
    # 예시 값입니다. 본인의 값으로 교체하세요
    provider: s3
    name: storage.example.com
    kmsKey: null
    path: wandb
    region: default
    accessKey: 5WOA500...P5DK7I
    secretKey: HDKYe4Q...JAp1YyjysnX

global:
  bucket:
    # 예시 값입니다. 자신의 값으로 교체하세요
    provider: s3
    name: storage.example.com
    kmsKey: null
    path: wandb
    region: default
    secret:
      secretName: bucket-secret
      accessKeyName: ACCESS_KEY
      secretKeyName: SECRET_KEY

global:
   mysql:
     # 예시 값입니다. 자신의 값으로 교체하세요
     host: db.example.com
     port: 3306
     database: wandb_local
     user: wandb
     password: 8wtX6cJH...ZcUarK4zZGjpV 

global:
   mysql:
     # 예시 값입니다. 자신의 값으로 교체하세요
     host: db.example.com
     port: 3306
     database: wandb_local
     user: wandb
     passwordSecret:
       name: database-secret
       passwordKey: MYSQL_WANDB_PASSWORD

global:
  # 예시 라이선스, 자신의 것으로 교체하세요
  license: eyJhbGnUzaHgyQjQy...VFnPS_KETXg1hi

global:
  licenseSecret:
    name: license-secret
    key: CUSTOMER_WANDB_LICENSE

global:
# IMPORTANT: Ingress는 YAML에서 'global'과 같은 수준에 있습니다 (하위 항목이 아님)
ingress:
  class: ""

kubectl create secret tls wandb-ingress-tls --key wandb-ingress-tls.key --cert wandb-ingress-tls.crt

global:
# 중요: Ingress는 YAML에서 'global'과 같은 수준에 있습니다('global'의 하위가 아님)
ingress:
  class: ""
  annotations:
    {}
    # kubernetes.io/ingress.class: nginx
    # kubernetes.io/tls-acme: "true"
  tls: 
    - secretName: wandb-ingress-tls
      hosts:
        - <HOST_URI>

ingress:
  annotations:
    nginx.ingress.kubernetes.io/proxy-body-size: 0

app:
  serviceAccount:
    name: custom-service-account
    create: true

parquet:
  serviceAccount:
    name: custom-service-account
    create: true

global:
  ...

app:
  serviceAccount:
    name: custom-service-account
    create: false

parquet:
  serviceAccount:
    name: custom-service-account
    create: false
    
global:
  ...

app:
  serviceAccount:
    name: custom-service-account
    create: true

console:
  serviceAccount:
    name: custom-service-account
    create: true

global:
  ...

app:
  serviceAccount:
    name: custom-service-account
    create: false

console:
  serviceAccount:
    name: another-custom-service-account
    create: true

global:
  ...

redis:
  install: false

global:
  redis:
    host: ""
    port: 6379
    password: ""
    parameters: {}
    caCert: ""

kubectl create secret generic redis-secret --from-literal=redis-password=supersecret

redis:
  install: false

global:
  redis:
    host: redis.example
    port: 9001
    auth:
      enabled: true
      secret: redis-secret
      key: redis-password

global:
  extraEnv:
    LDAP_ADDRESS: ldaps://ldap.company.example.com
    LDAP_BASE_DN: cn=accounts,dc=company,dc=example,dc=com
    LDAP_USER_BASE_DN: cn=users,cn=accounts,dc=company,dc=example,dc=com
    LDAP_GROUP_BASE_DN: cn=groups,cn=accounts,dc=company,dc=example,dc=com
    LDAP_BIND_DN: uid=ldapbind,cn=sysaccounts,cn=etc,dc=company,dc=example,dc=com
    LDAP_BIND_PW: ********************
    LDAP_ATTRIBUTES: email=mail,name=cn
    LDAP_TLS_ENABLE: "true"
    LDAP_LOGIN: "true"
    LDAP_USER_OBJECT_CLASS: user
    LDAP_GROUP_OBJECT_CLASS: group

global: 
  auth:
    sessionLengthHours: 720
    oidc:
      clientId: ""
      secret: ""
      # IdP에서 요구하는 경우에만 포함하세요.
      authMethod: ""
      issuer: ""

global:
  email:
    smtp:
      host: ""
      port: 587
      user: ""
      password: ""

global:
  extraEnv:
    GLOBAL_ENV: "example"

spec:
  values:
    global:
      extraEnv:
        GORILLA_DEFAULT_RATE_LIMITS_FILESTREAM: "5"
        GORILLA_DEFAULT_RATE_LIMITS_FILESTREAM_COUNT: "5"
        GORILLA_DEFAULT_RATE_LIMITS_FILESTREAM_PER_RUN_COUNT: "0.8"
        GORILLA_DEFAULT_RATE_LIMITS_FILESTREAM_SIZE: "10"
        GORILLA_DEFAULT_RATE_LIMITS_RUN_UPDATE_COUNT: "10"
        GORILLA_LIMITER: "redis://$HOST:6379?ttlInSeconds=900"

global:
  customCACerts:
  - |
    -----BEGIN CERTIFICATE-----
    MIIBnDCCAUKgAwIBAg.....................fucMwCgYIKoZIzj0EAwIwLDEQ
    MA4GA1UEChMHSG9tZU.....................tZUxhYiBSb290IENBMB4XDTI0
    MDQwMTA4MjgzMFoXDT.....................oNWYggsMo8O+0mWLYMAoGCCqG
    SM49BAMCA0gAMEUCIQ.....................hwuJgyQRaqMI149div72V2QIg
    P5GD+5I+02yEp58Cwxd5Bj2CvyQwTjTO4hiVl1Xd0M0=
    -----END CERTIFICATE-----
  - |
    -----BEGIN CERTIFICATE-----
    MIIBxTCCAWugAwIB.......................qaJcwCgYIKoZIzj0EAwIwLDEQ
    MA4GA1UEChMHSG9t.......................tZUxhYiBSb290IENBMB4XDTI0
    MDQwMTA4MjgzMVoX.......................UK+moK4nZYvpNpqfvz/7m5wKU
    SAAwRQIhAIzXZMW4.......................E8UFqsCcILdXjAiA7iTluM0IU
    aIgJYVqKxXt25blH/VyBRzvNhViesfkNUQ==
    -----END CERTIFICATE-----

global:
  caCertsConfigMap: custom-ca-certs

apiVersion: v1
kind: ConfigMap
metadata:
  name: custom-ca-certs
data:
  ca-cert1.crt: |
    -----BEGIN CERTIFICATE-----
    ...
    -----END CERTIFICATE-----
  ca-cert2.crt: |
    -----BEGIN CERTIFICATE-----
    ...
    -----END CERTIFICATE-----

pod:
  securityContext:
    runAsNonRoot: true
    runAsUser: 1001
    runAsGroup: 0
    fsGroup: 1001
    fsGroupChangePolicy: Always
    seccompProfile:
      type: RuntimeDefault
container:
  securityContext:
    capabilities:
      drop:
        - ALL
    readOnlyRootFilesystem: false
    allowPrivilegeEscalation: false 

global:
  ...
app:
  pod:
    securityContext:
      runAsNonRoot: true
      runAsUser: 1001
      runAsGroup: 0
      fsGroup: 1001
      fsGroupChangePolicy: Always
      seccompProfile:
        type: RuntimeDefault
  container:
    securityContext:
      capabilities:
        drop:
          - ALL
      readOnlyRootFilesystem: false
      allowPrivilegeEscalation: false 

customCACerts:
- |
  -----BEGIN CERTIFICATE-----
  MIIBnDCCAUKgAwIBAg.....................fucMwCgYIKoZIzj0EAwIwLDEQ
  MA4GA1UEChMHSG9tZU.....................tZUxhYiBSb290IENBMB4XDTI0
  MDQwMTA4MjgzMFoXDT.....................oNWYggsMo8O+0mWLYMAoGCCqG
  SM49BAMCA0gAMEUCIQ.....................hwuJgyQRaqMI149div72V2QIg
  P5GD+5I+02yEp58Cwxd5Bj2CvyQwTjTO4hiVl1Xd0M0=
  -----END CERTIFICATE-----
- |
  -----BEGIN CERTIFICATE-----
  MIIBxTCCAWugAwIB.......................qaJcwCgYIKoZIzj0EAwIwLDEQ
  MA4GA1UEChMHSG9t.......................tZUxhYiBSb290IENBMB4XDTI0
  MDQwMTA4MjgzMVoX.......................UK+moK4nZYvpNpqfvz/7m5wKU
  SAAwRQIhAIzXZMW4.......................E8UFqsCcILdXjAiA7iTluM0IU
  aIgJYVqKxXt25blH/VyBRzvNhViesfkNUQ==
  -----END CERTIFICATE-----

caCertsConfigMap: custom-ca-certs

apiVersion: v1
kind: ConfigMap
metadata:
  name: custom-ca-certs
data:
  ca-cert1.crt: |
    -----BEGIN CERTIFICATE-----
    ...
    -----END CERTIFICATE-----
  ca-cert2.crt: |
    -----BEGIN CERTIFICATE-----
    ...
    -----END CERTIFICATE-----

kubectl port-forward svc/wandb-console 8082

kubectl get pods
kubectl logs wandb-XXXXX-XXXXX

kubectl get ingressclass