values.yaml 30.7 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

  # -- NATS server address for operator communication (leave empty to use the bundled NATS chart). Format: "nats://hostname:port"
32
  natsAddr: ""
33

34
  # -- 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"
35
  etcdAddr: ""
36

Biswa Panda's avatar
Biswa Panda committed
37
38
39
40
  nats:
    # -- Whether the NATS is enabled
    enabled: true

41
42
43
  # -- 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
44
  namespaceRestriction:
45
46
    # -- 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
47
    # -- Target namespace for operator deployment (leave empty for current namespace)
48
    targetNamespace:
49
50
51
52
53
54
55
    # 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

56
57
58
59
60
61
62
  # -- 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

63
64
  # -- The Dynamo discovery backend to use. Default is "kubernetes" for Kubernetes API service discovery. Set to "etcd" to use ETCD for discovery. --
  discoveryBackend: "kubernetes"
65
66

  # Controller manager configuration
67
  controllerManager:
68
    # -- Node tolerations for controller manager pods
69
    tolerations: []
70

71
    # -- Affinity for controller manager pods
72
    affinity: {}
73

74
75
76
77
78
79
80
    # 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: ""

81
    manager:
82
      # Container image configuration for the operator manager
83
      image:
84
        # -- Official NVIDIA Dynamo operator image repository
85
        repository: "nvcr.io/nvidia/ai-dynamo/kubernetes-operator"
86
        # -- Image tag (leave empty to use chart default)
87
        tag: ""
88
        # -- Image pull policy - when to pull the image
89
        pullPolicy: IfNotPresent
90
91

      # Command line arguments for the operator manager
92
      args:
93
        # -- Health probe endpoint for Kubernetes health checks
94
        - --health-probe-bind-address=:8081
95
        # -- Metrics endpoint for Prometheus scraping (localhost only for security)
96
        - --metrics-bind-address=127.0.0.1:8080
97
98

  # -- Secrets for pulling private container images
99
  imagePullSecrets: []
100
101

  # Core Dynamo platform configuration
102
  dynamo:
103
    # -- How long to wait before forcefully terminating Grove instances
104
    groveTerminationDelay: 4h
105
106

    # Docker registry configuration for private repositories
107
    dockerRegistry:
108
      # -- Whether to use Kubernetes secrets for registry authentication
109
      useKubernetesSecret: false
110
      # -- Docker registry server URL
111
      server:
112
      # -- Registry username
113
      username:
114
      # -- Registry password (consider using existingSecretName instead)
115
      password:
116
      # -- Name of existing Kubernetes secret containing registry credentials
117
      existingSecretName:
118
      # -- Whether the registry uses HTTPS
119
      secure: true
120
121

    # Ingress configuration for external access
122
    ingress:
123
      # -- Whether to create ingress resources
124
      enabled: false
125
      # -- Ingress class name (e.g., "nginx", "traefik")
126
      className:
127
      # -- Secret name containing TLS certificates
128
      tlsSecretName: my-tls-secret
129
130

    # Istio service mesh configuration
131
    istio:
132
      # -- Whether to enable Istio integration
133
      enabled: false
134
      # -- Istio gateway name for routing
135
      gateway:
136
137

    # -- Host suffix for generated ingress hostnames
138
    ingressHostSuffix: ""
139
140

    # -- Whether VirtualServices should support HTTPS routing
141
    virtualServiceSupportsHTTPS: false
142

143
144
145
146
147
    # 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: ""

148
149
150
151
152
153
154
155
156
    # 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

157
158
159
160
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
  # 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"

215
216
217
218
219
  # 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
220
    enabled: false
221

222
223
224
    # -- Path written by worker when model is loaded and ready for checkpointing
    readyForCheckpointFilePath: "/tmp/ready-for-checkpoint"

225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
    # 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: ""

253
254
255
256
# 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
257
258
259
260
  # -- Node tolerations for Grove pods
  tolerations: []
  # -- Affinity for Grove pods
  affinity: {}
261
262
263
264
265

# 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
266
267
268
269
270
271
  # 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: {}
272

273
274
# etcd configuration - distributed key-value store
# Installation is controlled by global.etcd.install above.
275
etcd:
276
  image:
277
    # -- 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
278
    repository: bitnamilegacy/etcd
279
    tag: 3.5.18-debian-12-r5
280

281
  # Persistent storage configuration for etcd data
282
  persistence:
283
    # Whether to enable persistent storage (recommended for production)
284
285
286
    enabled: true
    # Use the cluster default storage-class or override with a named class
    storageClass: null
287
    # Size of persistent volume for etcd data
288
    size: 1Gi
289
290

  # Pre-upgrade job configuration
291
  preUpgradeJob:
292
    # Whether to run pre-upgrade validation jobs
293
    enabled: false
294
295

  # Number of etcd replicas (1 for single-node, 3+ for HA)
296
  replicaCount: 1
297
298
299

  # Authentication and authorization settings
  # Explicitly remove authentication for simplified internal communication
300
301
  auth:
    rbac:
302
      # Whether to create RBAC authentication (disabled for internal use)
303
304
      create: false

305
  # Health check configuration
306
  readinessProbe:
307
    # Whether to enable readiness probes (disabled to reduce startup complexity)
308
309
310
    enabled: false

  livenessProbe:
311
    # Whether to enable liveness probes (disabled to reduce startup complexity)
312
313
    enabled: false

314
315
316
317
318
319
  # 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

320
  # Node tolerations for etcd pods (allows scheduling on specific nodes)
321
322
  tolerations: []

323
324
325
  # Affinity for etcd pods
  affinity: {}

326
# NATS configuration - messaging system for operator communication
327
nats:
328
  # -- 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."
329
  enabled: true
330
331
332
333

  # 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
334
  tlsCA:
335
    # Whether to enable TLS CA configuration
336
337
    enabled: false

338
  # Core NATS server configuration
339
  config:
340
    # NATS clustering for high availability (multiple NATS servers)
341
    cluster:
342
      # Whether to enable NATS clustering (disabled for single-node setups)
343
344
      enabled: false

345
    # JetStream - persistent messaging and streaming capabilities
346
    jetstream:
347
      # Whether to enable JetStream (recommended for persistent messaging)
348
349
      enabled: true

350
      # File-based storage for JetStream streams and consumers
351
      fileStore:
352
        # Whether to enable file storage (persistent across restarts)
353
        enabled: true
354
        # Directory path for JetStream file storage
355
356
357
        dir: /data

        ############################################################
358
        # Persistent Volume Claim for JetStream file storage
359
360
        ############################################################
        pvc:
361
          # Whether to create a PVC for JetStream storage
362
          enabled: true
363
          # Size of the persistent volume for JetStream data
364
          size: 10Gi
365
          # Storage class name (leave empty for default)
366
367
          storageClassName:

368
          # Advanced PVC configuration (merge additional fields)
369
370
371
          # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#persistentvolumeclaim-v1-core
          merge: {}
          patch: []
372
          # PVC name (defaults to "{{ include "nats.fullname" $ }}-js")
373
374
          name:

375
        # Maximum size for JetStream file storage (defaults to PVC size)
376
377
        maxSize:

378
      # Memory-based storage for JetStream (non-persistent)
379
      memoryStore:
380
        # Whether to enable memory storage (faster but not persistent)
381
382
        enabled: false

383
384
      # Advanced JetStream configuration
      # For options see: https://docs.nats.io/running-a-nats-service/configuration#jetstream
385
386
387
      merge: {}
      patch: []

388
    # Core NATS server settings
389
    nats:
390
      # Port for NATS client connections
391
      port: 4222
392
393

      # TLS configuration for encrypted connections
394
      tls:
395
        # Whether to enable TLS encryption
396
        enabled: false
397
398
        # Advanced TLS configuration
        # For options see: https://docs.nats.io/running-a-nats-service/configuration/securing_nats/tls
399
400
401
        merge: {}
        patch: []

402
    # Leaf nodes for creating NATS topologies and remote connections
403
    leafnodes:
404
      # Whether to enable leaf node connections
405
406
      enabled: false

407
    # WebSocket support for browser-based NATS clients
408
    websocket:
409
      # Whether to enable WebSocket protocol support
410
411
      enabled: false

412
    # MQTT protocol bridge for IoT device connectivity
413
    mqtt:
414
      # Whether to enable MQTT protocol support
415
416
      enabled: false

417
    # Gateway connections for multi-cluster NATS deployments
418
    gateway:
419
      # Whether to enable gateway connections
420
421
      enabled: false

422
    # HTTP monitoring endpoint for NATS server metrics
423
    monitor:
424
      # Whether to enable HTTP monitoring interface
425
      enabled: true
426
      # Port for monitoring HTTP endpoint
427
      port: 8222
428
429

      # TLS configuration for monitoring endpoint
430
      tls:
431
432
        # 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
433
434
        enabled: false

435
    # Go pprof profiling endpoint for performance debugging
436
    profiling:
437
      # Whether to enable profiling endpoint (for debugging only)
438
      enabled: false
439
      # Port for profiling endpoint
440
441
      port: 65432

442
    # Account resolver for multi-tenant NATS deployments
443
    resolver:
444
      # Whether to enable account resolution (for advanced multi-tenancy)
445
446
      enabled: false

447
448
449
    # 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
450
451
    serverNamePrefix: ""

452
453
454
    # Advanced NATS configuration merging and patching
    # For complete options see: https://docs.nats.io/running-a-nats-service/configuration
    # Special rules apply:
455
456
457
458
459
    #  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
460
    # Example:
461
462
463
464
465
466
467
468
    #   merge:
    #     $include: ./my-config.conf
    #     zzz$include: ./my-config-last.conf
    #     server_name: nats
    #     authorization:
    #       token: << $TOKEN >>
    #     jetstream:
    #       max_memory_store: << 1GB >>
469
    merge:
470
471
472
      # 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
473
474
475
    patch: []

  ############################################################
476
  # NATS container configuration in StatefulSet
477
478
  ############################################################
  container:
479
    # NATS server container image configuration
480
    image:
481
      # Official NATS server repository
482
      repository: nats
483
      # NATS server version (Alpine-based for smaller size)
484
      tag: 2.10.21-alpine
485
      # Image pull policy (leave empty for chart default)
486
      pullPolicy:
487
      # Custom registry URL (leave empty for Docker Hub)
488
489
      registry:

490
491
    # Container port configuration
    # Note: Ports must also be enabled in the config section above
492
493
    # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#containerport-v1-core
    ports:
494
      # Main NATS client connection port
495
      nats: {}
496
      # Leaf node connection port
497
      leafnodes: {}
498
      # WebSocket connection port
499
      websocket: {}
500
      # MQTT protocol port
501
      mqtt: {}
502
      # Cluster communication port
503
      cluster: {}
504
      # Gateway connection port
505
      gateway: {}
506
      # HTTP monitoring port
507
      monitor: {}
508
      # Go profiling port
509
510
      profiling: {}

511
512
513
    # Environment variables for the NATS container
    # Map with key as env var name, value can be string or map
    # Example:
514
515
516
517
518
519
520
521
522
    #   env:
    #     GOMEMLIMIT: 7GiB
    #     TOKEN:
    #       valueFrom:
    #         secretKeyRef:
    #           name: nats-auth
    #           key: token
    env: {}

523
    # Advanced container configuration merging and patching
524
525
526
527
528
    # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#container-v1-core
    merge: {}
    patch: []

  ############################################################
529
  # Configuration reloader container for hot config updates
530
531
  ############################################################
  reloader:
532
    # Whether to enable the config reloader sidecar container
533
    enabled: true
534
535

    # Config reloader container image
536
    image:
537
      # Official NATS config reloader repository
538
      repository: natsio/nats-server-config-reloader
539
      # Config reloader version
540
      tag: 0.16.0
541
      # Image pull policy (leave empty for chart default)
542
      pullPolicy:
543
      # Custom registry URL (leave empty for Docker Hub)
544
545
      registry:

546
    # Environment variables for the reloader container
547
548
    env: {}

549
550
    # Volume mount prefixes from NATS container to share with reloader
    # All NATS container volume mounts with these prefixes will be mounted into the reloader
551
552
553
    natsVolumeMountPrefixes:
    - /etc/

554
    # Advanced reloader container configuration
555
556
557
558
559
    # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#container-v1-core
    merge: {}
    patch: []

  ############################################################
560
  # Prometheus metrics exporter container (optional)
561
  ############################################################
562
  # Note: config.monitor must be enabled for this to work
563
  promExporter:
564
    # Whether to enable Prometheus metrics exporter sidecar
565
566
567
    enabled: false

  ############################################################
568
  # Kubernetes Service for NATS access
569
570
  ############################################################
  service:
571
    # Whether to create a Kubernetes Service for NATS
572
573
    enabled: true

574
575
576
    # 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
577
578
    # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#serviceport-v1-core
    ports:
579
      # Main NATS client connection port
580
581
      nats:
        enabled: true
582
      # Leaf node connection port
583
584
      leafnodes:
        enabled: true
585
      # WebSocket connection port
586
587
      websocket:
        enabled: true
588
      # MQTT protocol port
589
590
      mqtt:
        enabled: true
591
      # Cluster communication port (typically internal only)
592
593
      cluster:
        enabled: false
594
      # Gateway connection port (typically internal only)
595
596
      gateway:
        enabled: false
597
      # HTTP monitoring port (typically internal only)
598
599
      monitor:
        enabled: false
600
      # Go profiling port (typically internal only)
601
602
603
      profiling:
        enabled: false

604
    # Advanced service configuration
605
606
607
    # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#service-v1-core
    merge: {}
    patch: []
608
    # Service name (defaults to "{{ include "nats.fullname" $ }}")
609
610
611
    name:

  ############################################################
612
  # Advanced NATS Kubernetes resource configuration
613
614
  ############################################################

615
  # StatefulSet configuration for NATS server persistence
616
  statefulSet:
617
    # Advanced StatefulSet configuration merging and patching
618
619
620
    # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#statefulset-v1-apps
    merge: {}
    patch: []
621
    # StatefulSet name (defaults to "{{ include "nats.fullname" $ }}")
622
623
    name:

624
  # Pod template configuration for NATS StatefulSet
625
  podTemplate:
626
627
    # Whether to add a hash of the ConfigMap as a pod annotation
    # This will cause the StatefulSet to roll when the ConfigMap is updated
628
629
    configChecksumAnnotation: true

630
631
632
633
634
635
636
    # 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
637
638
    topologySpreadConstraints: {}

639
    # Advanced pod template configuration
640
    # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#pod-v1-core
641
642
    merge:
      spec:
643
        # Node tolerations for NATS pods (allows scheduling on specific nodes)
644
        tolerations: []
645
646
        # Affinity for NATS pods
        affinity: {}
647
648
    patch: []

649
  # Headless service for StatefulSet pod discovery
650
  headlessService:
651
    # Advanced headless service configuration
652
653
654
    # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#service-v1-core
    merge: {}
    patch: []
655
    # Headless service name (defaults to "{{ include "nats.fullname" $ }}-headless")
656
657
    name:

658
  # ConfigMap for NATS server configuration
659
  configMap:
660
    # Advanced ConfigMap configuration
661
662
663
    # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#configmap-v1-core
    merge: {}
    patch: []
664
    # ConfigMap name (defaults to "{{ include "nats.fullname" $ }}-config")
665
666
    name:

667
  # Pod Disruption Budget for controlled rolling updates
668
  podDisruptionBudget:
669
    # Whether to create a PodDisruptionBudget (recommended for production)
670
671
    enabled: true

672
  # Service Account for NATS server pods
673
  serviceAccount:
674
    # Whether to create and use a dedicated service account
675
676
677
    enabled: false

  ############################################################
678
679
  # NATS Box - CLI tools and debugging container
  # NATS Box provides CLI tools for interacting with NATS server
680
681
  ############################################################
  natsBox:
682
    # Whether to deploy NATS Box for CLI access and debugging
683
    enabled: false
684
685

    ############################################################
686
    # NATS client contexts for authentication and connection
687
688
    ############################################################
    contexts:
689
      # Default context configuration
690
      default:
691
        # Credentials-based authentication
692
        creds:
693
          # Inline credentials file contents (base64 encoded)
694
          contents:
695
          # Name of existing secret containing credentials file
696
          secretName:
697
          # Directory to mount credentials (defaults to /etc/nats-creds/<context-name>)
698
          dir:
699
          # Key name in secret for credentials file
700
          key: nats.creds
701
702

        # NKey-based authentication (public/private key pairs)
703
        nkey:
704
          # Inline NKey file contents (base64 encoded)
705
          contents:
706
          # Name of existing secret containing NKey file
707
          secretName:
708
          # Directory to mount NKey (defaults to /etc/nats-nkeys/<context-name>)
709
          dir:
710
          # Key name in secret for NKey file
711
          key: nats.nk
712
713

        # TLS client certificate authentication
714
        tls:
715
          # Name of existing secret containing TLS client certificates
716
          secretName:
717
          # Directory to mount certificates (defaults to /etc/nats-certs/<context-name>)
718
          dir:
719
          # Certificate file name in secret
720
          cert: tls.crt
721
          # Private key file name in secret
722
723
          key: tls.key

724
725
        # Advanced context configuration
        # For options see: https://docs.nats.io/using-nats/nats-tools/nats_cli#nats-contexts
726
727
728
        merge: {}
        patch: []

729
    # Name of context to select by default for NATS CLI operations
730
731
732
    defaultContextName: default

    ############################################################
733
    # NATS Box container configuration
734
735
    ############################################################
    container:
736
      # NATS Box container image
737
      image:
738
        # Official NATS Box repository with CLI tools
739
        repository: natsio/nats-box
740
        # NATS Box version
741
        tag: 0.14.5
742
        # Image pull policy (leave empty for chart default)
743
        pullPolicy:
744
        # Custom registry URL (leave empty for Docker Hub)
745
746
        registry:

747
      # Environment variables for NATS Box container
748
749
      env: {}

750
      # Advanced container configuration
751
752
753
      # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#container-v1-core
      merge: {}
      patch: []
754
755

    # Service Account for NATS Box deployment
756
    serviceAccount:
757
      # Whether to create and use a dedicated service account for NATS Box
758
      enabled: false
759

760
    # Pod template configuration for NATS Box deployment
761
762
763
    podTemplate:
      merge:
        spec:
764
          # Node tolerations for NATS Box pods
765
          tolerations: []
766
767
          # Affinity for NATS Box pods
          affinity: {}
768
      patch: []