DynamoGraphDeployment nvidia.com/v1beta1, nvidia.com/v1alpha1

nvidia.com/v1beta1

# DynamoGraphDeployment is the Schema for the dynamographdeployments API.

# v1beta1 is a served version: the API server accepts reads and writes against it, and transparently

# converts to/from v1alpha1 (still the storage version until a later MR flips it). Conversion goes

# through the operator's conversion webhook; see api/v1alpha1/*_conversion.go.

apiVersion: nvidia.com/v1beta1

kind: DynamoGraphDeployment

metadata:

# Name must be unique within a namespace.

# Namespace defines the space within which each name must be unique.

namespace: "<string>" # required

# Annotations is an unstructured key value map stored with a resource.

# annotations:

# <key>: "<string>"

# CreationTimestamp is set by the server when a resource is created.

# creationTimestamp: "<string>"

# Number of seconds allowed for graceful deletion.

# deletionGracePeriodSeconds: <int64>

# DeletionTimestamp is set by the server when graceful deletion is requested.

# deletionTimestamp: "<string>"

# Finalizers must be empty before the object is deleted from the registry.

# finalizers:

# - "<string>"

# GenerateName is an optional prefix used by the server to generate a unique name.

# generateName: "<string>"

# Generation is a sequence number representing a specific desired state.

# generation: <int64>

# Labels are key value pairs used to organize and select objects.

# labels:

# <key>: "<string>"

# ManagedFields records which actor manages which fields.

# managedFields:

# - # APIVersion defines the version of this field set.

# apiVersion: "<string>"

# FieldsType is the discriminator for the fields format.

# fieldsType: "<string>"

# FieldsV1 stores a versioned field set.

# fieldsV1: {} # preserveUnknownFields

# Manager identifies the workflow managing these fields.

# manager: "<string>"

# Operation is the type of operation that produced this managedFields entry.

# operation: "<string>"

# Subresource is the name of the subresource used to update the object.

# subresource: "<string>"

# Time is when this managedFields entry was added.

# time: "<string>"

# OwnerReferences lists objects depended on by this object.

ownerReferences: # optional

- # API version of the referent.

apiVersion: "<string>" # required

# Kind of the referent.

kind: "<string>" # required

# Name of the referent.

# UID of the referent.

uid: "<string>" # required

# BlockOwnerDeletion controls foreground deletion behavior.

# blockOwnerDeletion: <boolean>

# Controller marks the managing controller owner reference.

# controller: <boolean>

# ResourceVersion is an opaque internal version value.

# resourceVersion: "<string>"

# SelfLink is a deprecated read-only field.

# selfLink: "<string>"

# UID is the unique in time and space value for this object.

# uid: "<string>"

# spec defines the desired state for this graph deployment.

spec: # optional

# annotations to propagate to all child resources (PCS, DCD, Deployments, and pod templates).

# Component-level (`podTemplate`) values take precedence on conflict.

# annotations:

# <key>: "<string>"

# backendFramework specifies the backend framework (e.g. "sglang", "vllm", "trtllm").

# backendFramework: "sglang" # enum: "vllm" | "trtllm"

# components are the components deployed as part of this graph. Each entry carries its own stable

# logical `name`, and names must be unique within the list. Component types are generally

# repeatable, except `type: epp` which may appear at most once.

components: # optional, listType: map, listMapKeys: name

- # name is the stable logical identifier for this component within its DynamoGraphDeployment.

# It must be unique within the parent's `spec.components` list.

# For standalone DynamoComponentDeployment objects, the defaulting webhook populates `name`

# from `metadata.name` on admission, so users typically do not need to set it explicitly.

# `name` is decoupled from the underlying Kubernetes resource name so that the operator can

# rename child workloads (e.g. suffixing worker DCDs with a hash during rolling updates)

# without losing the stable identity that downstream consumers (labels, status maps, DGDSA

# references, planner RBAC, EPP filters) depend on.

# compilationCache configures a PVC-backed compilation cache. The operator handles

# backend-specific mount paths and environment variables, so users do not need to hand-wire

# them into `podTemplate`. Extracted from v1alpha1's `volumeMount.useAsCompilationCache` flag.

compilationCache: # optional

# pvcName references a user-created PVC by name. The PVC must exist in the same namespace as

# the DynamoGraphDeployment.

pvcName: "<string>" # required, minLength: 1

# mountPath overrides the backend-specific default mount path. When empty, the operator

# selects a default appropriate for the backend framework.

# mountPath: "<string>"

# eppConfig holds EPP-specific configuration for Endpoint Picker Plugin components. Only

# meaningful when `type` is `epp`.

eppConfig: # optional

# config allows specifying EPP `EndpointPickerConfig` directly as a structured object. The

# operator marshals this to YAML and creates a ConfigMap automatically. Mutually exclusive

# with `configMapRef`. One of `configMapRef` or `config` must be specified.

config: # optional, preserveUnknownFields

# Plugins is the list of plugins that will be instantiated.

plugins: # required

- # Type specifies the plugin type to be instantiated.

type: "<string>" # required

# Name provides a name for plugin entries to reference. If omitted, the value of the

# Plugin's Type field will be used.

# name: "<string>"

# Parameters are the set of parameters to be passed to the plugin's factory function.

# The factory function is responsible to parse the parameters.

# parameters: {} # preserveUnknownFields

# SchedulingProfiles is the list of named SchedulingProfiles that will be created.

schedulingProfiles: # required

- # Name specifies the name of this SchedulingProfile

# Plugins is the list of plugins for this SchedulingProfile. They are assigned to the

# appropriate "slots" based on their type.

plugins: # required

- # PluginRef specifies a partiular Plugin instance to be associated with this

# SchedulingProfile. The reference is to the name of an entry of the Plugins

# defined in the configuration's Plugins section

pluginRef: "<string>" # required

# Weight is the weight fo be used if this plugin is a Scorer.

# weight: <integer>

# APIVersion defines the versioned schema of this representation of an object. Servers

# should convert recognized schemas to the latest internal value, and may reject

# unrecognized values. More info:

# https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources

# apiVersion: "<string>"

# FeatureGates is a set of flags that enable various experimental features with the EPP.

# If omitted non of these experimental features will be enabled.

# featureGates:

# - "<string>"

# Kind is a string value representing the REST resource this object represents. Servers

# may infer this from the endpoint the client submits requests to. Cannot be updated. In

# CamelCase. More info:

# https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds

# kind: "<string>"

# SaturationDetector when present specifies the configuration of the Saturation detector.

# If not present, default values are used.

# saturationDetector:

# KVCacheUtilThreshold defines the KV cache utilization (0.0 to 1.0) above which a pod

# is considered to have insufficient capacity.

# kvCacheUtilThreshold: <number>

# MetricsStalenessThreshold defines how old a pod's metrics can be. If a pod's metrics

# are older than this, it might be excluded from "good capacity" considerations or

# treated as having no capacity for safety.

# metricsStalenessThreshold: "<string>"

# QueueDepthThreshold defines the backend waiting queue size above which a pod is

# considered to have insufficient capacity for new requests.

# queueDepthThreshold: <integer>

# configMapRef references a user-provided ConfigMap containing EPP configuration. Mutually

# exclusive with `config`.

configMapRef: # optional, mapType: atomic

# The key to select.

key: "<string>" # required

# Name of the referent. This field is effectively required, but due to backwards

# compatibility is allowed to be empty. Instances of this type with an empty value here

# are almost certainly wrong. More info:

# https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

# name: "" # default

# Specify whether the ConfigMap or its key must be defined

# optional: <boolean>

# experimental groups opt-in preview features whose API shape and behavior may change in

# breaking ways between v1beta1 releases, including disappearing without a name-preserving

# graduation path. In v1beta1 this block holds `gpuMemoryService` and `failover` (which remain

# tightly coupled -- failover requires GMS -- and are expected to evolve together as the

# DRA-based GPU sharing story matures), and `checkpoint` (whose interaction with the

# standalone DynamoCheckpoint resource and identity-hash computation is still settling).

# Fields here are explicitly NOT covered by the normal v1beta1 deprecation policy; do not

# depend on them for production workloads.

experimental: # optional

# checkpoint configures container-image snapshotting and restore for this component. When

# set, the DGD controller can produce a DGD-scoped DynamoCheckpoint CR and later restore

# pods in the same DGD generation from that checkpoint for faster cold start. The

# user-facing shape of this field is still settling, which is why it lives under

# `experimental` in v1beta1 instead of at the top level.

checkpoint: # optional

# checkpointRef references an existing DynamoCheckpoint CR by `metadata.name`. When set,

# this component's `identity` is ignored and the referenced checkpoint is used directly.

# checkpointRef: "<string>"

# Deprecated: identity is ignored by DGD-managed automatic checkpoints. Automatic

# checkpoints are scoped to the owning DGD/component generation and are never reused

# across DGDs.

identity: # optional

# backendFramework is the runtime framework (`vllm`, `sglang`, `trtllm`).

backendFramework: "vllm" # required, enum: "sglang" | "trtllm"

# model is the model identifier (e.g. "meta-llama/Llama-3-70B").

model: "<string>" # required, minLength: 1

# dtype is the data type (`fp16`, `bf16`, `fp8`, etc.). Deprecated for DGD-managed

# automatic checkpoints; it only participates in the legacy identity hash fallback for

# standalone objects.

# dtype: "<string>"

# dynamoVersion is the Dynamo platform version. Deprecated for DGD-managed automatic

# checkpoints; it only participates in the legacy identity hash fallback for standalone

# objects.

# dynamoVersion: "<string>"

# extraParameters are additional parameters that affect the checkpoint hash. Deprecated

# for DGD-managed automatic checkpoints; it only participates in the legacy identity

# hash fallback for standalone objects.

# extraParameters:

# <key>: "<string>"

# maxModelLen is the maximum sequence length. Deprecated for DGD-managed automatic

# checkpoints; it only participates in the legacy identity hash fallback for standalone

# objects.

# maxModelLen: <int32> # minimum: 1

# pipelineParallelSize is the pipeline parallel configuration. Deprecated for

# DGD-managed automatic checkpoints; it only participates in the legacy identity hash

# fallback for standalone objects.

# pipelineParallelSize: 1 # default, minimum: 1

# tensorParallelSize is the tensor parallel configuration. Deprecated for DGD-managed

# automatic checkpoints; it only participates in the legacy identity hash fallback for

# standalone objects.

# tensorParallelSize: 1 # default, minimum: 1

# job customizes the checkpoint Job that is created in Auto mode.

# job:

# gmsClientContainers lists checkpoint Job containers that should receive GMS client

# wiring. Requires gpuMemoryService on the component.

# gmsClientContainers: # listType: set

# - "<string>"

# podTemplate customizes the checkpoint Job pod. The operator starts from the selected

# workload container and merges this template so users can add helper containers such as

# gms-saver.

# podTemplate: {} # preserveUnknownFields

# mode defines how checkpoint creation is handled. `Auto`: DGD controller creates the

# DynamoCheckpoint CR automatically. `Manual`: user must create the DynamoCheckpoint CR.

# mode: "Auto" # default, enum: "Manual"

# targetContainerName is the workload container to snapshot and restore.

# targetContainerName: "main" # default, minLength: 1, maxLength: 63

# failover configures active-passive GPU failover for this component. Requires

# `gpuMemoryService` to also be set, and `failover.mode` must match `gpuMemoryService.mode`

# (enforced by the validation webhook).

# failover:

# mode selects the failover deployment topology. Must match

# `spec.experimental.gpuMemoryService.mode` (or

# `spec.components[*].experimental.gpuMemoryService.mode` inside a DynamoGraphDeployment).

# mode: "IntraPod" # default, enum: "InterPod"

# numShadows is the number of shadow (standby) engine containers per rank. Reserved for

# future use; the operator currently creates exactly one shadow.

# numShadows: 1 # default, minimum: 1, maximum: 1

# gpuMemoryService configures the GPU Memory Service (GMS). When set, GPU access for GMS

# clients is managed via DRA.

gpuMemoryService: # optional

# deviceClassName is the DRA `DeviceClass` to request GPUs from.

# deviceClassName: "gpu.nvidia.com" # default

# extraClientContainers lists additional user-declared containers that should be wired as

# GMS clients in service pods. Checkpoint Job clients are declared under

# checkpoint.job.gmsClientContainers. In each rendered pod, only matching container names

# are wired; absent names are ignored.

# extraClientContainers: # listType: set

# - "<string>"

# extraClientPods declares additional GMS client pods for inter-pod GMS. This field is

# reserved for future use and is rejected until inter-pod client orchestration is wired.

extraClientPods: # optional, listType: map, listMapKeys: name

- # name identifies this client pod.

# podTemplate configures the pod to run as a GMS client.

podTemplate: {} # required, preserveUnknownFields

# mode selects the GMS deployment topology.

# mode: "IntraPod" # default, enum: "InterPod"

# frontendSidecar optionally designates a container in `podTemplate.spec.containers` as the

# frontend sidecar. The value must match the `name` of a container in that list; the operator

# merges its frontend-sidecar defaults (auto-generated Dynamo env vars, ports, health probes)

# into that container the same way it merges into `"main"`. The full container definition

# (image, args, envFrom, env) lives in `podTemplate` -- this eliminates the redundant `image`,

# `args`, `envFromSecret`, and `envs` fields from v1alpha1's `FrontendSidecarSpec`. The

# validation webhook rejects values that do not match any container name in

# `podTemplate.spec.containers`.

# frontendSidecar: "<string>"

# globalDynamoNamespace places the component in the global Dynamo namespace rather than the

# per-deployment namespace derived from the DGD name.

# globalDynamoNamespace: <boolean>

# modelRef references a model served by this component. When specified, a headless service is

# created for endpoint discovery.

modelRef: # optional

# name is the base model identifier (e.g. "llama-3-70b-instruct-v1").

# revision is the model revision/version.

# revision: "<string>"

# multinode configures multinode components.

# multinode:

# nodeCount is the number of nodes to deploy for the multinode component. Total GPUs used is

# `nodeCount * container GPU request`.

# nodeCount: 2 # default, minimum: 2

# podTemplate is the pod template used to create the component's pods. The operator injects

# its defaults (image, command, env, ports, probes, resources, volume mounts) into the

# container named `"main"` inside `podTemplate.spec.containers`, merging user overrides by

# name. If no container named `"main"` is present, the operator auto-generates it with

# standard defaults. All other containers in `podTemplate.spec.containers` are treated as

# user-managed sidecars: the operator does not inject defaults into them, so sidecars must

# specify required fields (e.g. `image`) themselves. The validation webhook rejects pod

# templates where a non-`"main"` container is missing a required field such as `image`.

podTemplate: # optional

# Standard object's metadata. More info:

# https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#metadata

# metadata:

# annotations:

# <key>: "<string>"

# finalizers:

# - "<string>"

# labels:

# <key>: "<string>"

# name: "<string>"

# namespace: "<string>"

# Specification of the desired behavior of the pod. More info:

# https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#spec-and-status

spec: # optional

# List of containers belonging to the pod. Containers cannot currently be added or

# removed. There must be at least one container in a Pod. Cannot be updated.

containers: # required, listType: map, listMapKeys: name

- # Name of the container specified as a DNS_LABEL. Each container in a pod must have a

# unique name (DNS_LABEL). Cannot be updated.

# Arguments to the entrypoint. The container image's CMD is used if this is not

# provided. Variable references $(VAR_NAME) are expanded using the container's

# environment. If a variable cannot be resolved, the reference in the input string

# will be unchanged. Double $$ are reduced to a single $, which allows for escaping

# the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal

# "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the

# variable exists or not. Cannot be updated. More info:

# https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell

# args: # listType: atomic

# - "<string>"

# Entrypoint array. Not executed within a shell. The container image's ENTRYPOINT is

# used if this is not provided. Variable references $(VAR_NAME) are expanded using the

# container's environment. If a variable cannot be resolved, the reference in the

# input string will be unchanged. Double $$ are reduced to a single $, which allows

# for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string

# literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of

# whether the variable exists or not. Cannot be updated. More info:

# https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell

# command: # listType: atomic

# - "<string>"

# List of environment variables to set in the container. Cannot be updated.

env: # optional, listType: map, listMapKeys: name

- # Name of the environment variable. May consist of any printable ASCII characters

# except '='.

# Variable references $(VAR_NAME) are expanded using the previously defined

# environment variables in the container and any service environment variables. If

# a variable cannot be resolved, the reference in the input string will be

# unchanged. Double $$ are reduced to a single $, which allows for escaping the

# $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal

# "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether

# the variable exists or not. Defaults to "".

# value: "<string>"

# Source for the environment variable's value. Cannot be used if value is not

# empty.

valueFrom: # optional

# Selects a key of a ConfigMap.

configMapKeyRef: # optional, mapType: atomic

# The key to select.

key: "<string>" # required

# Name of the referent. This field is effectively required, but due to

# backwards compatibility is allowed to be empty. Instances of this type with

# an empty value here are almost certainly wrong. More info:

# https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

# name: "" # default

# Specify whether the ConfigMap or its key must be defined

# optional: <boolean>

# Selects a field of the pod: supports metadata.name, metadata.namespace,

# `metadata.labels['<KEY>']`, `metadata.annotations['<KEY>']`, spec.nodeName,

# spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs.

fieldRef: # optional, mapType: atomic

# Path of the field to select in the specified API version.

fieldPath: "<string>" # required

# Version of the schema the FieldPath is written in terms of, defaults to

# "v1".

# apiVersion: "<string>"

# FileKeyRef selects a key of the env file. Requires the EnvFiles feature gate

# to be enabled.

fileKeyRef: # optional, mapType: atomic

# The key within the env file. An invalid key will prevent the pod from

# starting. The keys defined within a source may consist of any printable

# ASCII characters except '='. During Alpha stage of the EnvFiles feature

# gate, the key size is limited to 128 characters.

key: "<string>" # required

# The path within the volume from which to select the file. Must be relative

# and may not contain the '..' path or start with '..'.

path: "<string>" # required

# The name of the volume mount containing the env file.

volumeName: "<string>" # required

# Specify whether the file or its key must be defined. If the file or key does

# not exist, then the env var is not published. If optional is set to true and

# the specified key does not exist, the environment variable will not be set

# in the Pod's containers.

# If optional is set to false and the specified key does not exist, an error

# will be returned during Pod creation.

# optional: false # default

# Selects a resource of the container: only resources limits and requests

# (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu,

# requests.memory and requests.ephemeral-storage) are currently supported.

resourceFieldRef: # optional, mapType: atomic

# Required: resource to select

resource: "<string>" # required

# Container name: required for volumes, optional for env vars

# containerName: "<string>"

# Specifies the output format of the exposed resources, defaults to "1"

# divisor: <int-or-string> # intOrString

# Selects a key of a secret in the pod's namespace

secretKeyRef: # optional, mapType: atomic

# The key of the secret to select from. Must be a valid secret key.

key: "<string>" # required

# Name of the referent. This field is effectively required, but due to

# backwards compatibility is allowed to be empty. Instances of this type with

# an empty value here are almost certainly wrong. More info:

# https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

# name: "" # default

# Specify whether the Secret or its key must be defined

# optional: <boolean>

# List of sources to populate environment variables in the container. The keys defined

# within a source may consist of any printable ASCII characters except '='. When a key

# exists in multiple sources, the value associated with the last source will take

# precedence. Values defined by an Env with a duplicate key will take precedence.

# Cannot be updated.

# envFrom: # listType: atomic

# - # The ConfigMap to select from

# configMapRef: # mapType: atomic

# Name of the referent. This field is effectively required, but due to backwards

# compatibility is allowed to be empty. Instances of this type with an empty

# value here are almost certainly wrong. More info:

# https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

# name: "" # default

# Specify whether the ConfigMap must be defined

# optional: <boolean>

# Optional text to prepend to the name of each environment variable. May consist

# of any printable ASCII characters except '='.

# prefix: "<string>"

# The Secret to select from

# secretRef: # mapType: atomic

# Name of the referent. This field is effectively required, but due to backwards

# compatibility is allowed to be empty. Instances of this type with an empty

# value here are almost certainly wrong. More info:

# https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

# name: "" # default

# Specify whether the Secret must be defined

# optional: <boolean>

# Container image name. More info:

# https://kubernetes.io/docs/concepts/containers/images This field is optional to

# allow higher level config management to default or override container images in

# workload controllers like Deployments and StatefulSets.

# image: "<string>"

# Image pull policy. One of Always, Never, IfNotPresent. Defaults to Always if :latest

# tag is specified, or IfNotPresent otherwise. Cannot be updated. More info:

# https://kubernetes.io/docs/concepts/containers/images#updating-images

# imagePullPolicy: "<string>"

# Actions that the management system should take in response to container lifecycle

# events. Cannot be updated.

lifecycle: # optional

# PostStart is called immediately after a container is created. If the handler

# fails, the container is terminated and restarted according to its restart policy.

# Other management of the container blocks until the hook completes. More info:

# https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks

postStart: # optional

# Exec specifies a command to execute in the container.

# exec:

# Command is the command line to execute inside the container, the working

# directory for the command is root ('/') in the container's filesystem. The

# command is simply exec'd, it is not run inside a shell, so traditional shell

# instructions ('|', etc) won't work. To use a shell, you need to explicitly

# call out to that shell. Exit status of 0 is treated as live/healthy and

# non-zero is unhealthy.

# command: # listType: atomic

# - "<string>"

# HTTPGet specifies an HTTP GET request to perform.

httpGet: # optional

# Name or number of the port to access on the container. Number must be in the

# range 1 to 65535. Name must be an IANA_SVC_NAME.

port: <int-or-string> # required, intOrString

# Host name to connect to, defaults to the pod IP. You probably want to set

# "Host" in httpHeaders instead.

# host: "<string>"

# Custom headers to set in the request. HTTP allows repeated headers.

httpHeaders: # optional, listType: atomic

- # The header field name. This will be canonicalized upon output, so

# case-variant names will be understood as the same header.

# The header field value

value: "<string>" # required

# Path to access on the HTTP server.

# path: "<string>"

# Scheme to use for connecting to the host. Defaults to HTTP.

# scheme: "<string>"

# Sleep represents a duration that the container should sleep.

sleep: # optional

# Seconds is the number of seconds to sleep.

seconds: <int64> # required

# Deprecated. TCPSocket is NOT supported as a LifecycleHandler and kept for

# backward compatibility. There is no validation of this field and lifecycle hooks

# will fail at runtime when it is specified.

tcpSocket: # optional

# Number or name of the port to access on the container. Number must be in the

# range 1 to 65535. Name must be an IANA_SVC_NAME.

port: <int-or-string> # required, intOrString

# Optional: Host name to connect to, defaults to the pod IP.

# host: "<string>"

# PreStop is called immediately before a container is terminated due to an API

# request or management event such as liveness/startup probe failure, preemption,

# resource contention, etc. The handler is not called if the container crashes or

# exits. The Pod's termination grace period countdown begins before the PreStop hook

# is executed. Regardless of the outcome of the handler, the container will

# eventually terminate within the Pod's termination grace period (unless delayed by

# finalizers). Other management of the container blocks until the hook completes or

# until the termination grace period is reached. More info:

# https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks

preStop: # optional

# Exec specifies a command to execute in the container.

# exec:

# Command is the command line to execute inside the container, the working

# directory for the command is root ('/') in the container's filesystem. The

# command is simply exec'd, it is not run inside a shell, so traditional shell

# instructions ('|', etc) won't work. To use a shell, you need to explicitly

# call out to that shell. Exit status of 0 is treated as live/healthy and

# non-zero is unhealthy.

# command: # listType: atomic

# - "<string>"

# HTTPGet specifies an HTTP GET request to perform.

httpGet: # optional

# Name or number of the port to access on the container. Number must be in the

# range 1 to 65535. Name must be an IANA_SVC_NAME.

port: <int-or-string> # required, intOrString

# Host name to connect to, defaults to the pod IP. You probably want to set

# "Host" in httpHeaders instead.

# host: "<string>"

# Custom headers to set in the request. HTTP allows repeated headers.

httpHeaders: # optional, listType: atomic

- # The header field name. This will be canonicalized upon output, so

# case-variant names will be understood as the same header.

# The header field value

value: "<string>" # required

# Path to access on the HTTP server.

# path: "<string>"

# Scheme to use for connecting to the host. Defaults to HTTP.

# scheme: "<string>"

# Sleep represents a duration that the container should sleep.

sleep: # optional

# Seconds is the number of seconds to sleep.

seconds: <int64> # required

# Deprecated. TCPSocket is NOT supported as a LifecycleHandler and kept for

# backward compatibility. There is no validation of this field and lifecycle hooks

# will fail at runtime when it is specified.

tcpSocket: # optional

# Number or name of the port to access on the container. Number must be in the

# range 1 to 65535. Name must be an IANA_SVC_NAME.

port: <int-or-string> # required, intOrString

# Optional: Host name to connect to, defaults to the pod IP.

# host: "<string>"

# StopSignal defines which signal will be sent to a container when it is being

# stopped. If not specified, the default is defined by the container runtime in use.

# StopSignal can only be set for Pods with a non-empty .spec.os.name

# stopSignal: "<string>"

# Periodic probe of container liveness. Container will be restarted if the probe

# fails. Cannot be updated. More info:

# https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes

livenessProbe: # optional

# Exec specifies a command to execute in the container.

# exec:

# Command is the command line to execute inside the container, the working

# directory for the command is root ('/') in the container's filesystem. The

# command is simply exec'd, it is not run inside a shell, so traditional shell

# instructions ('|', etc) won't work. To use a shell, you need to explicitly call

# out to that shell. Exit status of 0 is treated as live/healthy and non-zero is

# unhealthy.

# command: # listType: atomic

# - "<string>"

# Minimum consecutive failures for the probe to be considered failed after having

# succeeded. Defaults to 3. Minimum value is 1.

# failureThreshold: <int32>

# GRPC specifies a GRPC HealthCheckRequest.

grpc: # optional

# Port number of the gRPC service. Number must be in the range 1 to 65535.

port: <int32> # required

# Service is the name of the service to place in the gRPC HealthCheckRequest (see

# https://github.com/grpc/grpc/blob/master/doc/health-checking.md).

# If this is not specified, the default behavior is defined by gRPC.

# service: "" # default

# HTTPGet specifies an HTTP GET request to perform.

httpGet: # optional

# Name or number of the port to access on the container. Number must be in the

# range 1 to 65535. Name must be an IANA_SVC_NAME.

port: <int-or-string> # required, intOrString

# Host name to connect to, defaults to the pod IP. You probably want to set "Host"

# in httpHeaders instead.

# host: "<string>"

# Custom headers to set in the request. HTTP allows repeated headers.

httpHeaders: # optional, listType: atomic

- # The header field name. This will be canonicalized upon output, so

# case-variant names will be understood as the same header.

# The header field value

value: "<string>" # required

# Path to access on the HTTP server.

# path: "<string>"

# Scheme to use for connecting to the host. Defaults to HTTP.

# scheme: "<string>"

# Number of seconds after the container has started before liveness probes are

# initiated. More info:

# https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes

# initialDelaySeconds: <int32>

# How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value

# is 1.

# periodSeconds: <int32>

# Minimum consecutive successes for the probe to be considered successful after

# having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is

# 1.

# successThreshold: <int32>

# TCPSocket specifies a connection to a TCP port.

tcpSocket: # optional

# Number or name of the port to access on the container. Number must be in the

# range 1 to 65535. Name must be an IANA_SVC_NAME.

port: <int-or-string> # required, intOrString

# Optional: Host name to connect to, defaults to the pod IP.

# host: "<string>"

# Optional duration in seconds the pod needs to terminate gracefully upon probe

# failure. The grace period is the duration in seconds after the processes running

# in the pod are sent a termination signal and the time when the processes are

# forcibly halted with a kill signal. Set this value longer than the expected

# cleanup time for your process. If this value is nil, the pod's

# terminationGracePeriodSeconds will be used. Otherwise, this value overrides the

# value provided by the pod spec. Value must be non-negative integer. The value zero

# indicates stop immediately via the kill signal (no opportunity to shut down). This

# is a beta field and requires enabling ProbeTerminationGracePeriod feature gate.

# Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset.

# terminationGracePeriodSeconds: <int64>

# Number of seconds after which the probe times out. Defaults to 1 second. Minimum

# value is 1. More info:

# https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes

# timeoutSeconds: <int32>

# List of ports to expose from the container. Not specifying a port here DOES NOT

# prevent that port from being exposed. Any port which is listening on the default

# "0.0.0.0" address inside a container will be accessible from the network. Modifying

# this array with strategic merge patch may corrupt the data. For more information See

# https://github.com/kubernetes/kubernetes/issues/108255. Cannot be updated.

ports: # optional, listType: map, listMapKeys: containerPort, protocol

- # Number of port to expose on the pod's IP address. This must be a valid port

# number, 0 < x < 65536.

containerPort: <int32> # required

# What host IP to bind the external port to.

# hostIP: "<string>"

# Number of port to expose on the host. If specified, this must be a valid port

# number, 0 < x < 65536. If HostNetwork is specified, this must match

# ContainerPort. Most containers do not need this.

# hostPort: <int32>

# If specified, this must be an IANA_SVC_NAME and unique within the pod. Each

# named port in a pod must have a unique name. Name for the port that can be

# referred to by services.

# name: "<string>"

# Protocol for port. Must be UDP, TCP, or SCTP. Defaults to "TCP".

# protocol: "TCP" # default

# Periodic probe of container service readiness. Container will be removed from

# service endpoints if the probe fails. Cannot be updated. More info:

# https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes

readinessProbe: # optional