values.yaml 30.8 KB
Newer Older
1
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
2
3
4
5
6
7
8
9
10
11
12
13
14
15
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# Used to generate top-level secrets (overridden by custom-values.yaml)
16

17
18
19
20
21
22
23
global:
  etcd:
    # -- Whether this chart should install the bundled etcd subchart.
    # When true, deploys etcd and auto-configures the operator with its address.
    # When false, etcd is not deployed. Use dynamo-operator.etcdAddr to point at an external instance if you are bringing your own etcd.
    install: false

24
25
26
# Subcharts configuration

# Dynamo operator configuration
27
dynamo-operator:
28
  # -- Whether to enable the Dynamo Kubernetes operator deployment
29
  enabled: true
30

31
32
33
34
  # -- Whether to manage CRDs via a pre-install/pre-upgrade hook Job.
  # The Job runs the operator image with the crd-apply tool to apply CRDs via server-side apply.
  upgradeCRD: true

35
  # -- NATS server address for operator communication (leave empty to use the bundled NATS chart). Format: "nats://hostname:port"
36
  natsAddr: ""
37

38
  # -- etcd server address for an external etcd instance. Only needed when using external etcd without the bundled subchart. Format: "http://hostname:port" or "https://hostname:port"
39
  etcdAddr: ""
40

Biswa Panda's avatar
Biswa Panda committed
41
42
43
44
  nats:
    # -- Whether the NATS is enabled
    enabled: true

45
46
47
  # -- URL for the Model Express server if not deployed by this helm chart. This is ignored if Model Express server is installed by this helm chart (global.model-express.enabled is true).
  modelExpressURL: ""
  # -- Namespace access controls for the operator
48
  namespaceRestriction:
49
50
    # -- Whether to restrict operator to specific namespaces. By default, the operator will run with cluster-wide permissions. Only 1 instance of the operator should be deployed in the cluster. If you want to deploy multiple operator instances, you can set this to true and specify the target namespace (by default, the target namespace is the helm release namespace).
    enabled: false
51
    # -- Target namespace for operator deployment (leave empty for current namespace)
52
    targetNamespace:
53
54
55
56
57
58
59
    # Namespace scope marker lease configuration (used to prevent conflicts when running both cluster-wide and namespace-restricted operators)
    lease:
      # Duration before the namespace scope marker lease expires if not renewed (namespace-restricted mode only). When a namespace-restricted operator is running, it creates a lease in its namespace. The cluster-wide operator detects this lease and excludes that namespace from processing. If the namespace operator stops renewing the lease (e.g., crashes), the lease expires and the cluster-wide operator automatically resumes processing that namespace.
      duration: 30s
      # Interval for renewing the namespace scope marker lease (namespace-restricted mode only). The namespace-restricted operator renews its lease at this interval to signal it's still running.
      renewInterval: 10s

60
61
62
63
64
65
66
  # -- GPU discovery configuration (only applies when namespaceRestriction.enabled=true)
  gpuDiscovery:
    # -- Whether to provision a ClusterRole for the namespace-scoped operator to read GPU node labels.
    # When true (default), Helm creates a ClusterRole/ClusterRoleBinding granting node read access.
    # Set to false if your installer lacks ClusterRole creation permissions.
    enabled: true

67
68
  # -- The Dynamo discovery backend to use. Default is "kubernetes" for Kubernetes API service discovery. Set to "etcd" to use ETCD for discovery. --
  discoveryBackend: "kubernetes"
69
70

  # Controller manager configuration
71
  controllerManager:
72
    # -- Node tolerations for controller manager pods
73
    tolerations: []
74

75
    # -- Affinity for controller manager pods
76
    affinity: {}
77

78
79
80
81
82
83
84
    # Leader election configuration for cluster-wide coordination
    leaderElection:
      # -- Leader election ID for cluster-wide coordination. WARNING: All cluster-wide operators must use the SAME ID to prevent split-brain. Different IDs would allow multiple leaders simultaneously.
      id: ""  # If empty, defaults to: dynamo.nvidia.com (shared across all cluster-wide operators)
      # -- Namespace for leader election leases (only used in cluster-wide mode). If empty, defaults to kube-system for cluster-wide coordination. All cluster-wide operators should use the SAME namespace for proper leader election.
      namespace: ""

85
    manager:
86
      # Container image configuration for the operator manager
87
      image:
88
        # -- Official NVIDIA Dynamo operator image repository
89
        repository: "nvcr.io/nvidia/ai-dynamo/kubernetes-operator"
90
        # -- Image tag (leave empty to use chart default)
91
        tag: ""
92
        # -- Image pull policy - when to pull the image
93
        pullPolicy: IfNotPresent
94
95

      # Command line arguments for the operator manager
96
      args:
97
        # -- Health probe endpoint for Kubernetes health checks
98
        - --health-probe-bind-address=:8081
99
        # -- Metrics endpoint for Prometheus scraping (localhost only for security)
100
        - --metrics-bind-address=127.0.0.1:8080
101
102

  # -- Secrets for pulling private container images
103
  imagePullSecrets: []
104
105

  # Core Dynamo platform configuration
106
  dynamo:
107
    # -- How long to wait before forcefully terminating Grove instances
108
    groveTerminationDelay: 4h
109
110

    # Docker registry configuration for private repositories
111
    dockerRegistry:
112
      # -- Whether to use Kubernetes secrets for registry authentication
113
      useKubernetesSecret: false
114
      # -- Docker registry server URL
115
      server:
116
      # -- Registry username
117
      username:
118
      # -- Registry password (consider using existingSecretName instead)
119
      password:
120
      # -- Name of existing Kubernetes secret containing registry credentials
121
      existingSecretName:
122
      # -- Whether the registry uses HTTPS
123
      secure: true
124
125

    # Ingress configuration for external access
126
    ingress:
127
      # -- Whether to create ingress resources
128
      enabled: false
129
      # -- Ingress class name (e.g., "nginx", "traefik")
130
      className:
131
      # -- Secret name containing TLS certificates
132
      tlsSecretName: my-tls-secret
133
134

    # Istio service mesh configuration
135
    istio:
136
      # -- Whether to enable Istio integration
137
      enabled: false
138
      # -- Istio gateway name for routing
139
      gateway:
140
141

    # -- Host suffix for generated ingress hostnames
142
    ingressHostSuffix: ""
143
144

    # -- Whether VirtualServices should support HTTPS routing
145
    virtualServiceSupportsHTTPS: false
146

147
148
149
150
151
    # Metrics configuration
    metrics:
      # -- Endpoint that services can use to retrieve metrics. If set, dynamo operator will automatically inject the PROMETHEUS_ENDPOINT environment variable into services it manages. Users can override the value of the PROMETHEUS_ENDPOINT environment variable by modifying the corresponding deployment's environment variables
      prometheusEndpoint: ""

152
153
154
155
156
157
158
159
160
    # MPI Run configuration
    mpiRun:
      # -- Name of the secret containing the SSH key for MPI Run
      secretName: "mpi-run-ssh-secret"
      # SSH key generation configuration
      sshKeygen:
        # -- Whether to enable SSH key generation for MPI Run
        enabled: true

161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
  # Webhook configuration for admission control and validation
  webhook:
    # Certificate configuration for webhook TLS
    certificateSecret:
      # -- Name of the Kubernetes secret containing webhook TLS certificates. The secret must contain three keys: tls.crt (server certificate), tls.key (server private key), and ca.crt (Certificate Authority certificate).
      name: webhook-server-cert

      # -- Whether to manage the certificate secret externally. When false (default), certificates are automatically generated via Helm hooks during installation. When true, you must create the secret manually before installing the chart.
      external: false

    # -- Certificate validity duration in days for auto-generated certificates. Only used when certManager.enabled=false and certificateSecret.external=false. After this duration, certificates will expire and need to be regenerated.
    certificateValidity: 365

    # Container image for certificate generation and CA injection jobs
    # Only used when certManager.enabled=false and certificateSecret.external=false
    certGenerator:
      image:
        # -- Container image repository for certificate generation jobs. This image must contain both openssl and kubectl commands.
        repository: bitnami/kubectl
        # -- Container image tag for certificate generation jobs
        tag: latest
        # -- Image pull policy for certificate generation jobs
        pullPolicy: IfNotPresent

    # -- CA bundle (base64 encoded) for webhook validation. Only used when certificateSecret.external=true. For automatic certificate generation or cert-manager integration, leave this empty as it will be injected automatically.
    caBundle: ""

    # -- Webhook failure policy controls how Kubernetes handles requests when the webhook is unavailable. 'Fail' (recommended for production) rejects requests if the webhook cannot be reached, ensuring strict validation. 'Ignore' allows requests through if the webhook is unavailable, providing availability over validation guarantees.
    failurePolicy: Fail

    # -- Timeout in seconds for webhook validation calls. If the webhook doesn't respond within this time, the request will be handled according to the failurePolicy.
    timeoutSeconds: 10

    # Namespace selector for webhook scope control
    # -- Custom namespace selector for webhook validation. Use this to include or exclude specific namespaces from webhook validation. For CLUSTER-WIDE operators, you can exclude namespaces managed by namespace-restricted operators by using: matchExpressions: [{ key: "dynamo-operator", operator: "NotIn", values: ["namespace-restricted"] }]. For NAMESPACE-RESTRICTED operators, leave empty as it will be auto-configured to match only the operator's namespace.
    namespaceSelector: {}

    # cert-manager integration for automated certificate lifecycle management
    certManager:
      # -- Whether to use cert-manager for automatic certificate management. Requires cert-manager to be installed in the cluster. When enabled, cert-manager will automatically generate, renew, and rotate certificates, and the automatic certificate generation via Helm hooks will be disabled.
      enabled: false

      # Certificate configuration for cert-manager
      certificate:
        # -- Certificate duration for webhook certificates managed by cert-manager (e.g., "8760h" for 1 year). cert-manager will automatically renew the certificate before it expires.
        duration: "8760h"

        # -- Time before certificate expiration to trigger renewal (e.g., "360h" for 15 days). cert-manager will attempt to renew the certificate when this threshold is reached.
        renewBefore: "360h"

        # Root CA configuration for cert-manager
        rootCA:
          # -- Duration for the root CA certificate (e.g., "87600h" for 10 years). The root CA typically has a much longer lifetime than the leaf certificates it signs.
          duration: "87600h"

          # -- Time before root CA expiration to trigger renewal (e.g., "720h" for 30 days). Renewing a CA can be disruptive as all signed certificates must be reissued.
          renewBefore: "720h"

219
220
221
222
223
  # Checkpoint configuration for fast pod restore using CRIU/cuda-checkpoint
  # NOTE: The checkpoint infrastructure (PVC + DaemonSet) must be installed separately
  # using the chrek Helm chart in each namespace where checkpointing is needed.
  checkpoint:
    # -- Whether to enable checkpoint/restore functionality
224
    enabled: false
225

226
227
228
    # -- Path written by worker when model is loaded and ready for checkpointing
    readyForCheckpointFilePath: "/tmp/ready-for-checkpoint"

229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
    # Storage configuration
    # These settings tell the operator where to find checkpoint storage
    # Must match the configuration in the chrek chart
    storage:
      # -- Storage backend type: pvc, s3, or oci
      type: pvc

      # PVC storage configuration (used when type=pvc)
      pvc:
        # -- Name of the PVC created by the chrek chart
        pvcName: "chrek-pvc"
        # -- Base path within the PVC for storing checkpoints
        basePath: "/checkpoints"

      # S3 storage configuration (used when type=s3)
      s3:
        # -- S3 URI in format: s3://[endpoint/]bucket/prefix
        uri: ""
        # -- Reference to a secret containing AWS credentials
        credentialsSecretRef: ""

      # OCI registry storage configuration (used when type=oci)
      oci:
        # -- OCI URI in format: oci://registry/repository
        uri: ""
        # -- Reference to a docker config secret for registry authentication
        credentialsSecretRef: ""

257
258
259
260
# Grove component - distributed inference orchestration
grove:
  # -- Whether to enable Grove for multi-node inference coordination, if enabled, the Grove operator will be deployed cluster-wide
  enabled: false
261
262
263
264
  # -- Node tolerations for Grove pods
  tolerations: []
  # -- Affinity for Grove pods
  affinity: {}
265
266
267
268
269

# Kai Scheduler component - advanced workload scheduling
kai-scheduler:
  # -- Whether to enable Kai Scheduler for intelligent resource allocation, if enabled, the Kai Scheduler operator will be deployed cluster-wide
  enabled: false
270
271
272
273
274
275
  # Global configuration for kai-scheduler (applies to all components including crd-upgrader)
  global:
    # -- Node tolerations for kai-scheduler pods
    tolerations: []
    # -- Affinity for kai-scheduler pods
    affinity: {}
276

277
278
# etcd configuration - distributed key-value store
# Installation is controlled by global.etcd.install above.
279
etcd:
280
  image:
281
    # -- following bitnami announcement for brownout - https://github.com/bitnami/charts/tree/main/bitnami/etcd#%EF%B8%8F-important-notice-upcoming-changes-to-the-bitnami-catalog, we need to use the legacy repository until we migrate to the new "secure" repository
282
    repository: bitnamilegacy/etcd
283
    tag: 3.5.18-debian-12-r5
284

285
  # Persistent storage configuration for etcd data
286
  persistence:
287
    # Whether to enable persistent storage (recommended for production)
288
289
290
    enabled: true
    # Use the cluster default storage-class or override with a named class
    storageClass: null
291
    # Size of persistent volume for etcd data
292
    size: 1Gi
293
294

  # Pre-upgrade job configuration
295
  preUpgradeJob:
296
    # Whether to run pre-upgrade validation jobs
297
    enabled: false
298
299

  # Number of etcd replicas (1 for single-node, 3+ for HA)
300
  replicaCount: 1
301
302
303

  # Authentication and authorization settings
  # Explicitly remove authentication for simplified internal communication
304
305
  auth:
    rbac:
306
      # Whether to create RBAC authentication (disabled for internal use)
307
308
      create: false

309
  # Health check configuration
310
  readinessProbe:
311
    # Whether to enable readiness probes (disabled to reduce startup complexity)
312
313
314
    enabled: false

  livenessProbe:
315
    # Whether to enable liveness probes (disabled to reduce startup complexity)
316
317
    enabled: false

318
319
320
321
322
323
  # Pod Disruption Budget configuration
  # Should be enabled for HA deployments with 3+ replicas
  pdb:
    # Whether to create a PodDisruptionBudget (disabled for single-node deployments)
    create: false

324
  # Node tolerations for etcd pods (allows scheduling on specific nodes)
325
326
  tolerations: []

327
328
329
  # Affinity for etcd pods
  affinity: {}

330
# NATS configuration - messaging system for operator communication
331
nats:
332
  # -- Whether to enable NATS deployment, disable if you want to use an external NATS instance. For complete configuration options, see: https://github.com/nats-io/k8s/tree/main/helm/charts/nats , all nats settings should be prefixed with "nats."
333
  enabled: true
334
335
336
337

  # TLS Certificate Authority configuration for secure communication
  # Reference a common CA Certificate or Bundle in all nats config `tls` blocks and nats-box contexts
  # Note: `tls.verify` still must be set in the appropriate nats config `tls` blocks to require mTLS
338
  tlsCA:
339
    # Whether to enable TLS CA configuration
340
341
    enabled: false

342
  # Core NATS server configuration
343
  config:
344
    # NATS clustering for high availability (multiple NATS servers)
345
    cluster:
346
      # Whether to enable NATS clustering (disabled for single-node setups)
347
348
      enabled: false

349
    # JetStream - persistent messaging and streaming capabilities
350
    jetstream:
351
      # Whether to enable JetStream (recommended for persistent messaging)
352
353
      enabled: true

354
      # File-based storage for JetStream streams and consumers
355
      fileStore:
356
        # Whether to enable file storage (persistent across restarts)
357
        enabled: true
358
        # Directory path for JetStream file storage
359
360
361
        dir: /data

        ############################################################
362
        # Persistent Volume Claim for JetStream file storage
363
364
        ############################################################
        pvc:
365
          # Whether to create a PVC for JetStream storage
366
          enabled: true
367
          # Size of the persistent volume for JetStream data
368
          size: 10Gi
369
          # Storage class name (leave empty for default)
370
371
          storageClassName:

372
          # Advanced PVC configuration (merge additional fields)
373
374
375
          # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#persistentvolumeclaim-v1-core
          merge: {}
          patch: []
376
          # PVC name (defaults to "{{ include "nats.fullname" $ }}-js")
377
378
          name:

379
        # Maximum size for JetStream file storage (defaults to PVC size)
380
381
        maxSize:

382
      # Memory-based storage for JetStream (non-persistent)
383
      memoryStore:
384
        # Whether to enable memory storage (faster but not persistent)
385
386
        enabled: false

387
388
      # Advanced JetStream configuration
      # For options see: https://docs.nats.io/running-a-nats-service/configuration#jetstream
389
390
391
      merge: {}
      patch: []

392
    # Core NATS server settings
393
    nats:
394
      # Port for NATS client connections
395
      port: 4222
396
397

      # TLS configuration for encrypted connections
398
      tls:
399
        # Whether to enable TLS encryption
400
        enabled: false
401
402
        # Advanced TLS configuration
        # For options see: https://docs.nats.io/running-a-nats-service/configuration/securing_nats/tls
403
404
405
        merge: {}
        patch: []

406
    # Leaf nodes for creating NATS topologies and remote connections
407
    leafnodes:
408
      # Whether to enable leaf node connections
409
410
      enabled: false

411
    # WebSocket support for browser-based NATS clients
412
    websocket:
413
      # Whether to enable WebSocket protocol support
414
415
      enabled: false

416
    # MQTT protocol bridge for IoT device connectivity
417
    mqtt:
418
      # Whether to enable MQTT protocol support
419
420
      enabled: false

421
    # Gateway connections for multi-cluster NATS deployments
422
    gateway:
423
      # Whether to enable gateway connections
424
425
      enabled: false

426
    # HTTP monitoring endpoint for NATS server metrics
427
    monitor:
428
      # Whether to enable HTTP monitoring interface
429
      enabled: true
430
      # Port for monitoring HTTP endpoint
431
      port: 8222
432
433

      # TLS configuration for monitoring endpoint
434
      tls:
435
436
        # Whether to enable HTTPS for monitoring (requires config.nats.tls enabled)
        # When enabled, monitoring port will use HTTPS with the options from config.nats.tls
437
438
        enabled: false

439
    # Go pprof profiling endpoint for performance debugging
440
    profiling:
441
      # Whether to enable profiling endpoint (for debugging only)
442
      enabled: false
443
      # Port for profiling endpoint
444
445
      port: 65432

446
    # Account resolver for multi-tenant NATS deployments
447
    resolver:
448
      # Whether to enable account resolution (for advanced multi-tenancy)
449
450
      enabled: false

451
452
453
    # Server naming configuration
    # Adds a prefix to the server name, which defaults to the pod name
    # Helpful for ensuring server name is unique in a super cluster
454
455
    serverNamePrefix: ""

456
457
458
    # Advanced NATS configuration merging and patching
    # For complete options see: https://docs.nats.io/running-a-nats-service/configuration
    # Special rules apply:
459
460
461
462
463
    #  1. strings that start with << and end with >> will be unquoted
    #     use this for variables and numbers with units
    #  2. keys ending in $include will be switched to include directives
    #     keys are sorted alphabetically, use prefix before $includes to control includes ordering
    #     paths should be relative to /etc/nats-config/nats.conf
464
    # Example:
465
466
467
468
469
470
471
472
    #   merge:
    #     $include: ./my-config.conf
    #     zzz$include: ./my-config-last.conf
    #     server_name: nats
    #     authorization:
    #       token: << $TOKEN >>
    #     jetstream:
    #       max_memory_store: << 1GB >>
473
    merge:
474
475
476
      # 15MB to accommodate prompt embeddings: 10MB decoded → ~13.3MB base64-encoded + metadata
      # Also allows larger context: 256K tokens (int32 - 4 bytes each) = 1MB
      max_payload: 15728640
477
478
479
    patch: []

  ############################################################
480
  # NATS container configuration in StatefulSet
481
482
  ############################################################
  container:
483
    # NATS server container image configuration
484
    image:
485
      # Official NATS server repository
486
      repository: nats
487
      # NATS server version (Alpine-based for smaller size)
488
      tag: 2.10.21-alpine
489
      # Image pull policy (leave empty for chart default)
490
      pullPolicy:
491
      # Custom registry URL (leave empty for Docker Hub)
492
493
      registry:

494
495
    # Container port configuration
    # Note: Ports must also be enabled in the config section above
496
497
    # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#containerport-v1-core
    ports:
498
      # Main NATS client connection port
499
      nats: {}
500
      # Leaf node connection port
501
      leafnodes: {}
502
      # WebSocket connection port
503
      websocket: {}
504
      # MQTT protocol port
505
      mqtt: {}
506
      # Cluster communication port
507
      cluster: {}
508
      # Gateway connection port
509
      gateway: {}
510
      # HTTP monitoring port
511
      monitor: {}
512
      # Go profiling port
513
514
      profiling: {}

515
516
517
    # Environment variables for the NATS container
    # Map with key as env var name, value can be string or map
    # Example:
518
519
520
521
522
523
524
525
526
    #   env:
    #     GOMEMLIMIT: 7GiB
    #     TOKEN:
    #       valueFrom:
    #         secretKeyRef:
    #           name: nats-auth
    #           key: token
    env: {}

527
    # Advanced container configuration merging and patching
528
529
530
531
532
    # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#container-v1-core
    merge: {}
    patch: []

  ############################################################
533
  # Configuration reloader container for hot config updates
534
535
  ############################################################
  reloader:
536
    # Whether to enable the config reloader sidecar container
537
    enabled: true
538
539

    # Config reloader container image
540
    image:
541
      # Official NATS config reloader repository
542
      repository: natsio/nats-server-config-reloader
543
      # Config reloader version
544
      tag: 0.16.0
545
      # Image pull policy (leave empty for chart default)
546
      pullPolicy:
547
      # Custom registry URL (leave empty for Docker Hub)
548
549
      registry:

550
    # Environment variables for the reloader container
551
552
    env: {}

553
554
    # Volume mount prefixes from NATS container to share with reloader
    # All NATS container volume mounts with these prefixes will be mounted into the reloader
555
556
557
    natsVolumeMountPrefixes:
    - /etc/

558
    # Advanced reloader container configuration
559
560
561
562
563
    # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#container-v1-core
    merge: {}
    patch: []

  ############################################################
564
  # Prometheus metrics exporter container (optional)
565
  ############################################################
566
  # Note: config.monitor must be enabled for this to work
567
  promExporter:
568
    # Whether to enable Prometheus metrics exporter sidecar
569
570
571
    enabled: false

  ############################################################
572
  # Kubernetes Service for NATS access
573
574
  ############################################################
  service:
575
    # Whether to create a Kubernetes Service for NATS
576
577
    enabled: true

578
579
580
    # Service port configuration
    # Additional boolean field 'enabled' controls whether port is exposed in the service
    # Note: Ports must also be enabled in the config section above
581
582
    # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#serviceport-v1-core
    ports:
583
      # Main NATS client connection port
584
585
      nats:
        enabled: true
586
      # Leaf node connection port
587
588
      leafnodes:
        enabled: true
589
      # WebSocket connection port
590
591
      websocket:
        enabled: true
592
      # MQTT protocol port
593
594
      mqtt:
        enabled: true
595
      # Cluster communication port (typically internal only)
596
597
      cluster:
        enabled: false
598
      # Gateway connection port (typically internal only)
599
600
      gateway:
        enabled: false
601
      # HTTP monitoring port (typically internal only)
602
603
      monitor:
        enabled: false
604
      # Go profiling port (typically internal only)
605
606
607
      profiling:
        enabled: false

608
    # Advanced service configuration
609
610
611
    # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#service-v1-core
    merge: {}
    patch: []
612
    # Service name (defaults to "{{ include "nats.fullname" $ }}")
613
614
615
    name:

  ############################################################
616
  # Advanced NATS Kubernetes resource configuration
617
618
  ############################################################

619
  # StatefulSet configuration for NATS server persistence
620
  statefulSet:
621
    # Advanced StatefulSet configuration merging and patching
622
623
624
    # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#statefulset-v1-apps
    merge: {}
    patch: []
625
    # StatefulSet name (defaults to "{{ include "nats.fullname" $ }}")
626
627
    name:

628
  # Pod template configuration for NATS StatefulSet
629
  podTemplate:
630
631
    # Whether to add a hash of the ConfigMap as a pod annotation
    # This will cause the StatefulSet to roll when the ConfigMap is updated
632
633
    configChecksumAnnotation: true

634
635
636
637
638
639
640
    # Pod topology spread constraints for better distribution across nodes
    # Map of topologyKey: topologySpreadConstraint
    # labelSelector will be added automatically to match StatefulSet pods
    # Example:
    #   topologySpreadConstraints:
    #     kubernetes.io/hostname:
    #       maxSkew: 1
641
642
    topologySpreadConstraints: {}

643
    # Advanced pod template configuration
644
    # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#pod-v1-core
645
646
    merge:
      spec:
647
        # Node tolerations for NATS pods (allows scheduling on specific nodes)
648
        tolerations: []
649
650
        # Affinity for NATS pods
        affinity: {}
651
652
    patch: []

653
  # Headless service for StatefulSet pod discovery
654
  headlessService:
655
    # Advanced headless service configuration
656
657
658
    # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#service-v1-core
    merge: {}
    patch: []
659
    # Headless service name (defaults to "{{ include "nats.fullname" $ }}-headless")
660
661
    name:

662
  # ConfigMap for NATS server configuration
663
  configMap:
664
    # Advanced ConfigMap configuration
665
666
667
    # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#configmap-v1-core
    merge: {}
    patch: []
668
    # ConfigMap name (defaults to "{{ include "nats.fullname" $ }}-config")
669
670
    name:

671
  # Pod Disruption Budget for controlled rolling updates
672
  podDisruptionBudget:
673
    # Whether to create a PodDisruptionBudget (recommended for production)
674
675
    enabled: true

676
  # Service Account for NATS server pods
677
  serviceAccount:
678
    # Whether to create and use a dedicated service account
679
680
681
    enabled: false

  ############################################################
682
683
  # NATS Box - CLI tools and debugging container
  # NATS Box provides CLI tools for interacting with NATS server
684
685
  ############################################################
  natsBox:
686
    # Whether to deploy NATS Box for CLI access and debugging
687
    enabled: false
688
689

    ############################################################
690
    # NATS client contexts for authentication and connection
691
692
    ############################################################
    contexts:
693
      # Default context configuration
694
      default:
695
        # Credentials-based authentication
696
        creds:
697
          # Inline credentials file contents (base64 encoded)
698
          contents:
699
          # Name of existing secret containing credentials file
700
          secretName:
701
          # Directory to mount credentials (defaults to /etc/nats-creds/<context-name>)
702
          dir:
703
          # Key name in secret for credentials file
704
          key: nats.creds
705
706

        # NKey-based authentication (public/private key pairs)
707
        nkey:
708
          # Inline NKey file contents (base64 encoded)
709
          contents:
710
          # Name of existing secret containing NKey file
711
          secretName:
712
          # Directory to mount NKey (defaults to /etc/nats-nkeys/<context-name>)
713
          dir:
714
          # Key name in secret for NKey file
715
          key: nats.nk
716
717

        # TLS client certificate authentication
718
        tls:
719
          # Name of existing secret containing TLS client certificates
720
          secretName:
721
          # Directory to mount certificates (defaults to /etc/nats-certs/<context-name>)
722
          dir:
723
          # Certificate file name in secret
724
          cert: tls.crt
725
          # Private key file name in secret
726
727
          key: tls.key

728
729
        # Advanced context configuration
        # For options see: https://docs.nats.io/using-nats/nats-tools/nats_cli#nats-contexts
730
731
732
        merge: {}
        patch: []

733
    # Name of context to select by default for NATS CLI operations
734
735
736
    defaultContextName: default

    ############################################################
737
    # NATS Box container configuration
738
739
    ############################################################
    container:
740
      # NATS Box container image
741
      image:
742
        # Official NATS Box repository with CLI tools
743
        repository: natsio/nats-box
744
        # NATS Box version
745
        tag: 0.14.5
746
        # Image pull policy (leave empty for chart default)
747
        pullPolicy:
748
        # Custom registry URL (leave empty for Docker Hub)
749
750
        registry:

751
      # Environment variables for NATS Box container
752
753
      env: {}

754
      # Advanced container configuration
755
756
757
      # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#container-v1-core
      merge: {}
      patch: []
758
759

    # Service Account for NATS Box deployment
760
    serviceAccount:
761
      # Whether to create and use a dedicated service account for NATS Box
762
      enabled: false
763

764
    # Pod template configuration for NATS Box deployment
765
766
767
    podTemplate:
      merge:
        spec:
768
          # Node tolerations for NATS Box pods
769
          tolerations: []
770
771
          # Affinity for NATS Box pods
          affinity: {}
772
      patch: []