-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathpytorch.helm
531 lines (519 loc) · 20.6 KB
/
pytorch.helm
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
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
215
216
217
218
219
220
221
222
223
224
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
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
## @section Global parameters
## Global Docker image parameters
## Please, note that this will override the image parameters, including dependencies, configured to use the global value
## Current available global Docker image parameters: imageRegistry, imagePullSecrets and storageClass
## @param global.imageRegistry Global Docker image registry
## @param global.imagePullSecrets Global Docker registry secret names as an array
## @param global.storageClass Global StorageClass for Persistent Volume(s)
##
global:
imageRegistry: ""
## E.g.
## imagePullSecrets:
## - myRegistryKeySecretName
##
imagePullSecrets: []
storageClass: ""
## @section Common parameters
## @param kubeVersion Override Kubernetes version
##
kubeVersion: ""
## @param nameOverride String to partially override common.names.fullname template (will maintain the release name)
##
nameOverride: ""
## @param commonLabels Labels to add to all deployed objects
##
commonLabels: {}
## @param commonAnnotations Annotations to add to all deployed objects
##
commonAnnotations: {}
## @param fullnameOverride String to fully override common.names.fullname template
##
fullnameOverride: ""
## @param extraDeploy Array of extra objects to deploy with the release
##
extraDeploy: []
## Enable diagnostic mode in the deployment
##
diagnosticMode:
## @param diagnosticMode.enabled Enable diagnostic mode (all probes will be disabled and the command will be overridden)
##
enabled: false
## @param diagnosticMode.command Command to override all containers in the deployment
##
command:
- sleep
## @param diagnosticMode.args Args to override all containers in the deployment
##
args:
- infinity
## @section PyTorch parameters
## Bitnami PyTorch image version
## ref: https://hub.docker.com/r/bitnami/pytorch/tags/
## @param image.registry PyTorch image registry
## @param image.repository PyTorch image repository
## @param image.tag PyTorch image tag (immutable tags are recommended)
## @param image.pullPolicy Image pull policy
## @param image.pullSecrets Specify docker-registry secret names as an array
##
image:
registry: docker.io
repository: bitnami/pytorch
tag: 1.11.0-debian-11-r3
## Specify a imagePullPolicy
## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent'
## ref: https://kubernetes.io/docs/user-guide/images/#pre-pulling-images
##
pullPolicy: IfNotPresent
## Optionally specify an array of imagePullSecrets.
## Secrets must be manually created in the namespace.
## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
## Example:
## pullSecrets:
## - myRegistryKeySecretName
##
pullSecrets: []
## @param worldSize Number of nodes that will run the code
## WORLD_SIZE will be set to this value
##
worldSize: 1
## port PyTorch master port. DEPRECATED Use containerPorts.pytorch instead
##
## port: 49875
## @param containerPorts.pytorch PyTorch master port. `MASTER_PORT` will be set to this value
##
containerPorts:
pytorch: 49875
## Configure extra options for liveness probe
## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-probes/#configure-probes
## @param livenessProbe.enabled Enable livenessProbe
## @param livenessProbe.initialDelaySeconds Initial delay seconds for livenessProbe
## @param livenessProbe.periodSeconds Period seconds for livenessProbe
## @param livenessProbe.timeoutSeconds Timeout seconds for livenessProbe
## @param livenessProbe.failureThreshold Failure threshold for livenessProbe
## @param livenessProbe.successThreshold Success threshold for livenessProbe
##
livenessProbe:
enabled: true
initialDelaySeconds: 5
periodSeconds: 5
timeoutSeconds: 5
successThreshold: 1
failureThreshold: 5
## Configure extra options for readiness probe
## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-probes/#configure-probes
## @param readinessProbe.enabled Enable readinessProbe
## @param readinessProbe.initialDelaySeconds Initial delay seconds for readinessProbe
## @param readinessProbe.periodSeconds Period seconds for readinessProbe
## @param readinessProbe.timeoutSeconds Timeout seconds for readinessProbe
## @param readinessProbe.failureThreshold Failure threshold for readinessProbe
## @param readinessProbe.successThreshold Success threshold for readinessProbe
##
readinessProbe:
enabled: true
initialDelaySeconds: 5
periodSeconds: 5
timeoutSeconds: 3
successThreshold: 1
failureThreshold: 5
## Configure extra options for startup probe
## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-startup-probes/#configure-probes
## @param startupProbe.enabled Enable startupProbe
## @param startupProbe.initialDelaySeconds Initial delay seconds for startupProbe
## @param startupProbe.periodSeconds Period seconds for startupProbe
## @param startupProbe.timeoutSeconds Timeout seconds for startupProbe
## @param startupProbe.failureThreshold Failure threshold for startupProbe
## @param startupProbe.successThreshold Success threshold for startupProbe
##
startupProbe:
enabled: true
initialDelaySeconds: 5
periodSeconds: 5
timeoutSeconds: 3
successThreshold: 1
failureThreshold: 5
## @param customLivenessProbe Custom livenessProbe that overrides the default one
##
customLivenessProbe: {}
## @param customReadinessProbe Custom readinessProbe that overrides the default one
##
customReadinessProbe: {}
## @param customStartupProbe Custom startupProbe that overrides the default one
##
customStartupProbe: {}
## Pod Security Context
## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/
## securityContext.enabled DEPRECATED Use podSecurityContext.enabled instead
## securityContext.fsGroup DEPRECATED Use podSecurityContext.fsGroup instead
## securityContext.runAsUser DEPRECATED Use podSecurityContext.runAsUser instead
## securityContext:
## enabled: true
## fsGroup: 1001
## runAsUser: 1001
## @param podSecurityContext.enabled Enabled Pytorch pods' Security Context
## @param podSecurityContext.fsGroup Set Pytorch pods' Security Context fsGroup
## @param podSecurityContext.runAsUser Set Pytorch pods' Security Context runAsUser
##
podSecurityContext:
enabled: true
fsGroup: 1001
runAsUser: 1001
## Configure Container Security Context
## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-container
## @param containerSecurityContext.enabled Enabled Pytorch containers' Security Context
## @param containerSecurityContext.runAsUser Set Pytorch containers' Security Context runAsUser
## @param containerSecurityContext.runAsNonRoot Set Pytorch containers' Security Context runAsNonRoot
## @param containerSecurityContext.readOnlyRootFilesystem Set Pytorch containers' Security Context runAsNonRoot
##
containerSecurityContext:
enabled: true
runAsUser: 1001
runAsNonRoot: true
readOnlyRootFilesystem: false
## Pytorch resource requests and limits
## ref: http://kubernetes.io/docs/user-guide/compute-resources/
## @param resources.limits The resources limits for the Pytorch containers
## @param resources.requests The requested resources for the Pytorch containers
##
resources:
limits: {}
requests: {}
## PyTorch configuration. This will be executed as: python [file] [args]
## @param entrypoint.file Main entrypoint to your application
## @param entrypoint.args Args required by your entrypoint
##
entrypoint:
file: ""
args: []
## mode DEPRECATED. Use architecture instead
##
## mode: standalone
## @param architecture Run PyTorch in standalone or distributed mode. Possible values: `standalone`, `distributed`
##
architecture: standalone
## @param hostAliases Deployment pod host aliases
## https://kubernetes.io/docs/concepts/services-networking/add-entries-to-pod-etc-hosts-with-host-aliases/
##
hostAliases: []
## @param command Override default container command (useful when using custom images)
##
command: []
## @param args Override default container args (useful when using custom images)
##
args: []
## @param podLabels Extra labels for Pytorch pods
## ref: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/
##
podLabels: {}
## @param podAnnotations Annotations for Pytorch pods
## ref: https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/
##
podAnnotations: {}
## @param existingConfigmap Config map that contains the files you want to load in PyTorch
##
existingConfigmap: ""
## Enable in order to download files from git repository.
##
cloneFilesFromGit:
## @param cloneFilesFromGit.enabled Enable in order to download files from git repository
##
enabled: false
## @param cloneFilesFromGit.repository Repository that holds the files
##
repository: ""
## @param cloneFilesFromGit.revision Revision from the repository to checkout
##
revision: ""
## @param cloneFilesFromGit.extraVolumeMounts Add extra volume mounts for the Git container
## Useful to mount keys to connect through ssh. (normally used with extraVolumes)
## E.g:
## extraVolumeMounts:
## - name: ssh-dir
## mountPath: /.ssh/
##
extraVolumeMounts: []
## @param podAffinityPreset Pod affinity preset. Ignored if `affinity` is set. Allowed values: `soft` or `hard`
## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#inter-pod-affinity-and-anti-affinity
##
podAffinityPreset: ""
## @param podAntiAffinityPreset Pod anti-affinity preset. Ignored if `affinity` is set. Allowed values: `soft` or `hard`
## Ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#inter-pod-affinity-and-anti-affinity
##
podAntiAffinityPreset: soft
## Node affinity preset
## Ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#node-affinity
##
nodeAffinityPreset:
## @param nodeAffinityPreset.type Node affinity preset type. Ignored if `affinity` is set. Allowed values: `soft` or `hard`
##
type: ""
## @param nodeAffinityPreset.key Node label key to match Ignored if `affinity` is set.
## E.g.
## key: "kubernetes.io/e2e-az-name"
##
key: ""
## @param nodeAffinityPreset.values Node label values to match. Ignored if `affinity` is set.
## E.g.
## values:
## - e2e-az1
## - e2e-az2
##
values: []
## @param affinity Affinity for pod assignment. Evaluated as a template.
## Ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity
## Note: podAffinityPreset, podAntiAffinityPreset, and nodeAffinityPreset will be ignored when it's set
##
affinity: {}
## @param nodeSelector Node labels for pod assignment. Evaluated as a template.
## ref: https://kubernetes.io/docs/user-guide/node-selection/
##
nodeSelector: {}
## @param tolerations Tolerations for pod assignment. Evaluated as a template.
## ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/
##
tolerations: []
## @param updateStrategy.type Pytorch statefulset strategy type
## ref: https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#update-strategies
##
updateStrategy:
## StrategyType
## Can be set to RollingUpdate or OnDelete
##
type: RollingUpdate
## @param podManagementPolicy Statefulset Pod management policy, it needs to be Parallel to be able to complete the cluster join
## Ref: https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#pod-management-policies
##
podManagementPolicy: OrderedReady
## @param priorityClassName Pytorch pods' priorityClassName
##
priorityClassName: ""
## @param topologySpreadConstraints Topology Spread Constraints for pod assignment spread across your cluster among failure-domains. Evaluated as a template
## Ref: https://kubernetes.io/docs/concepts/workloads/pods/pod-topology-spread-constraints/#spread-constraints-for-pods
##
topologySpreadConstraints: []
## @param schedulerName Name of the k8s scheduler (other than default) for Pytorch pods
## ref: https://kubernetes.io/docs/tasks/administer-cluster/configure-multiple-schedulers/
##
schedulerName: ""
## @param terminationGracePeriodSeconds Seconds Redmine pod needs to terminate gracefully
## ref: https://kubernetes.io/docs/concepts/workloads/pods/pod/#termination-of-pods
##
terminationGracePeriodSeconds: ""
## @param lifecycleHooks for the Pytorch container(s) to automate configuration before or after startup
##
lifecycleHooks: {}
## @param extraEnvVars Array with extra environment variables to add to Pytorch nodes
## e.g:
## extraEnvVars:
## - name: FOO
## value: "bar"
##
extraEnvVars: []
## @param extraEnvVarsCM Name of existing ConfigMap containing extra env vars for Pytorch nodes
##
extraEnvVarsCM: ""
## @param extraEnvVarsSecret Name of existing Secret containing extra env vars for Pytorch nodes
##
extraEnvVarsSecret: ""
## @param extraVolumes Optionally specify extra list of additional volumes for the Pytorch pod(s)
##
extraVolumes: []
## @param extraVolumeMounts Optionally specify extra list of additional volumeMounts for the Pytorch container(s)
##
extraVolumeMounts: []
## @param sidecars Add additional sidecar containers to the Pytorch pod(s)
## e.g:
## sidecars:
## - name: your-image-name
## image: your-image
## imagePullPolicy: Always
## ports:
## - name: portname
## containerPort: 1234
##
sidecars: {}
## @param initContainers Add additional init containers to the %%MAIN_CONTAINER_NAME%% pod(s)
## ref: https://kubernetes.io/docs/concepts/workloads/pods/init-containers/
## e.g:
## initContainers:
## - name: your-image-name
## image: your-image
## imagePullPolicy: Always
## command: ['sh', '-c', 'echo "hello world"']
##
initContainers: {}
## @section Traffic Exposure Parameters
## Service for the scheduler node
##
service:
## @param service.type Kubernetes service type
##
type: LoadBalancer
## service.port DEPRECATED Use service.ports.pytorch instead
##
## port: 49875
## @param service.ports.pytorch Scheduler Service port
##
ports:
pytorch: 49875
## Node ports to expose
## service.nodePort DEPRECATED Use service.nodePorts.pytorch instead
##
## nodePort: ""
## @param service.nodePorts.pytorch Node port for Pytorch
## NOTE: choose port between <30000-32767>
##
nodePorts:
pytorch: ""
## @param service.clusterIP Pytorch service Cluster IP
## e.g.:
## clusterIP: None
##
clusterIP: ""
## @param service.loadBalancerIP Pytorch service Load Balancer IP
## ref: https://kubernetes.io/docs/concepts/services-networking/service/#type-loadbalancer
##
loadBalancerIP: ""
## @param service.loadBalancerSourceRanges Pytorch service Load Balancer sources
## ref: https://kubernetes.io/docs/tasks/access-application-cluster/configure-cloud-provider-firewall/#restrict-access-for-loadbalancer-service
## e.g:
## loadBalancerSourceRanges:
## - 10.10.10.0/24
##
loadBalancerSourceRanges: []
## @param service.externalTrafficPolicy Pytorch service external traffic policy
## ref http://kubernetes.io/docs/tasks/access-application-cluster/create-external-load-balancer/#preserving-the-client-source-ip
##
externalTrafficPolicy: Cluster
## @param service.annotations Additional custom annotations for Pytorch service
##
annotations: {}
## @param service.extraPorts Extra ports to expose in Pytorch service (normally used with the `sidecars` value)
##
extraPorts: []
## @param service.sessionAffinity Control where client requests go, to the same pod or round-robin
## Values: ClientIP or None
## ref: https://kubernetes.io/docs/user-guide/services/
##
sessionAffinity: None
## @param service.sessionAffinityConfig Additional settings for the sessionAffinity
## sessionAffinityConfig:
## clientIP:
## timeoutSeconds: 300
##
sessionAffinityConfig: {}
## @section Init Container Parameters
## Bitnami git image version
## ref: https://hub.docker.com/r/bitnami/git/tags/
## @param git.registry Git image registry
## @param git.repository Git image repository
## @param git.tag Git image tag (immutable tags are recommended)
## @param git.pullPolicy Git image pull policy
## @param git.pullSecrets Specify docker-registry secret names as an array
##
git:
registry: docker.io
repository: bitnami/git
tag: 2.36.1-debian-11-r3
pullPolicy: IfNotPresent
## Optionally specify an array of imagePullSecrets.
## Secrets must be manually created in the namespace.
## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
## Example:
## pullSecrets:
## - myRegistryKeySecretName
##
pullSecrets: []
## 'volumePermissions' init container parameters
## Changes the owner and group of the persistent volume mount point to runAsUser:fsGroup values
## based on the *podSecurityContext/*containerSecurityContext parameters
##
volumePermissions:
## @param volumePermissions.enabled Enable init container that changes volume permissions in the data directory (for cases where the default k8s `runAsUser` and `fsUser` values do not work)
##
enabled: false
## @param volumePermissions.image.registry Init container volume-permissions image registry
## @param volumePermissions.image.repository Init container volume-permissions image repository
## @param volumePermissions.image.tag Init container volume-permissions image tag (immutable tags are recommended)
## @param volumePermissions.image.pullPolicy Init container volume-permissions image pull policy
## @param volumePermissions.image.pullSecrets Specify docker-registry secret names as an array
##
image:
registry: docker.io
repository: bitnami/bitnami-shell
tag: 11-debian-11-r3
pullPolicy: IfNotPresent
## Optionally specify an array of imagePullSecrets.
## Secrets must be manually created in the namespace.
## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
## Example:
## pullSecrets:
## - myRegistryKeySecretName
##
pullSecrets: []
## Init container' resource requests and limits
## ref: https://kubernetes.io/docs/user-guide/compute-resources/
## We usually recommend not to specify default resources and to leave this as a conscious
## choice for the user. This also increases chances charts run on environments with little
## resources, such as Minikube. If you do want to specify resources, uncomment the following
## lines, adjust them as necessary, and remove the curly braces after 'resources:'.
## @param volumePermissions.resources.limits The resources limits for the container
## @param volumePermissions.resources.requests The requested resources for the container
##
resources:
## Example:
## limits:
## cpu: 100m
## memory: 128Mi
limits: {}
## Examples:
## requests:
## cpu: 100m
## memory: 128Mi
requests: {}
## @section Persistence Parameters
## Enable persistence using Persistent Volume Claims
## ref: https://kubernetes.io/docs/user-guide/persistent-volumes/
##
persistence:
## @param persistence.enabled Enable persistence using Persistent Volume Claims
##
enabled: true
## @param persistence.mountPath Path to mount the volume at.
##
mountPath: /bitnami/pytorch
## @param persistence.subPath The subdirectory of the volume to mount to, useful in dev environments and one PV for multiple services
##
subPath: ""
## @param persistence.storageClass Storage class of backing PVC
## If defined, storageClassName: <storageClass>
## If set to "-", storageClassName: "", which disables dynamic provisioning
## If undefined (the default) or set to null, no storageClassName spec is
## set, choosing the default provisioner. (gp2 on AWS, standard on
## GKE, AWS & OpenStack)
##
storageClass: ""
## @param persistence.annotations Persistent Volume Claim annotations
##
annotations: {}
## @param persistence.accessModes Persistent Volume Access Modes
##
accessModes:
- ReadWriteOnce
## @param persistence.size Size of data volume
##
size: 8Gi
## @param persistence.existingClaim The name of an existing PVC to use for persistence
##
existingClaim: ""
## @param persistence.selector Selector to match an existing Persistent Volume for WordPress data PVC
## If set, the PVC can't have a PV dynamically provisioned for it
## E.g.
## selector:
## matchLabels:
## app: my-app
##
selector: {}
## @param persistence.dataSource Custom PVC data source
##
dataSource: {}