feat(jupyterhub): GPU support
This commit is contained in:
@@ -9,7 +9,7 @@ export JUPYTERHUB_NFS_PV_ENABLED := env("JUPYTERHUB_NFS_PV_ENABLED", "")
|
||||
export JUPYTERHUB_STORAGE_CLASS := env("JUPYTERHUB_STORAGE_CLASS", "")
|
||||
export JUPYTERHUB_VAULT_INTEGRATION_ENABLED := env("JUPYTERHUB_VAULT_INTEGRATION_ENABLED", "")
|
||||
export JUPYTERHUB_AIRFLOW_DAGS_PERSISTENCE_ENABLED := env("JUPYTERHUB_AIRFLOW_DAGS_PERSISTENCE_ENABLED", "")
|
||||
export JUPYTER_PYTHON_KERNEL_TAG := env("JUPYTER_PYTHON_KERNEL_TAG", "python-3.12-50")
|
||||
export JUPYTER_PYTHON_KERNEL_TAG := env("JUPYTER_PYTHON_KERNEL_TAG", "python-3.12-51")
|
||||
export KERNEL_IMAGE_BUUN_STACK_REPOSITORY := env("KERNEL_IMAGE_BUUN_STACK_REPOSITORY", "buun-stack-notebook")
|
||||
export KERNEL_IMAGE_BUUN_STACK_CUDA_REPOSITORY := env("KERNEL_IMAGE_BUUN_STACK_CUDA_REPOSITORY", "buun-stack-cuda-notebook")
|
||||
export JUPYTER_PROFILE_MINIMAL_ENABLED := env("JUPYTER_PROFILE_MINIMAL_ENABLED", "false")
|
||||
@@ -20,6 +20,8 @@ export JUPYTER_PROFILE_PYTORCH_ENABLED := env("JUPYTER_PROFILE_PYTORCH_ENABLED",
|
||||
export JUPYTER_PROFILE_TENSORFLOW_ENABLED := env("JUPYTER_PROFILE_TENSORFLOW_ENABLED", "false")
|
||||
export JUPYTER_PROFILE_BUUN_STACK_ENABLED := env("JUPYTER_PROFILE_BUUN_STACK_ENABLED", "false")
|
||||
export JUPYTER_PROFILE_BUUN_STACK_CUDA_ENABLED := env("JUPYTER_PROFILE_BUUN_STACK_CUDA_ENABLED", "false")
|
||||
export JUPYTERHUB_GPU_ENABLED := env("JUPYTERHUB_GPU_ENABLED", "")
|
||||
export JUPYTERHUB_GPU_LIMIT := env("JUPYTERHUB_GPU_LIMIT", "1")
|
||||
export JUPYTERHUB_VAULT_TOKEN_TTL := env("JUPYTERHUB_VAULT_TOKEN_TTL", "24h")
|
||||
export NOTEBOOK_VAULT_TOKEN_TTL := env("NOTEBOOK_VAULT_TOKEN_TTL", "24h")
|
||||
export NOTEBOOK_VAULT_TOKEN_MAX_TTL := env("NOTEBOOK_VAULT_TOKEN_MAX_TTL", "168h")
|
||||
@@ -38,6 +40,8 @@ export VAULT_ADDR := "https://" + VAULT_HOST
|
||||
export MONITORING_ENABLED := env("MONITORING_ENABLED", "")
|
||||
export PROMETHEUS_NAMESPACE := env("PROMETHEUS_NAMESPACE", "monitoring")
|
||||
export DOCKER_CMD := env("DOCKER_CMD", "docker")
|
||||
export EXTERNAL_SECRETS_NAMESPACE := env("EXTERNAL_SECRETS_NAMESPACE", "external-secrets")
|
||||
export K8S_VAULT_NAMESPACE := env("K8S_VAULT_NAMESPACE", "vault")
|
||||
|
||||
[private]
|
||||
default:
|
||||
@@ -61,6 +65,37 @@ create-namespace:
|
||||
delete-namespace:
|
||||
kubectl delete namespace ${JUPYTERHUB_NAMESPACE} --ignore-not-found
|
||||
|
||||
# Create JupyterHub crypt key secret
|
||||
create-crypt-key-secret:
|
||||
#!/bin/bash
|
||||
set -euo pipefail
|
||||
crypt_key=$(just utils::random-password)
|
||||
|
||||
if helm status external-secrets -n ${EXTERNAL_SECRETS_NAMESPACE} &>/dev/null; then
|
||||
echo "External Secrets Operator detected. Storing crypt key in Vault..."
|
||||
just vault::put jupyterhub/config crypt-key="${crypt_key}"
|
||||
|
||||
kubectl delete secret jupyterhub-crypt-key -n ${JUPYTERHUB_NAMESPACE} --ignore-not-found
|
||||
kubectl delete externalsecret jupyterhub-crypt-key -n ${JUPYTERHUB_NAMESPACE} --ignore-not-found
|
||||
|
||||
gomplate -f jupyterhub-crypt-key-external-secret.gomplate.yaml \
|
||||
-o jupyterhub-crypt-key-external-secret.yaml
|
||||
kubectl apply -f jupyterhub-crypt-key-external-secret.yaml
|
||||
|
||||
echo "Waiting for ExternalSecret to sync..."
|
||||
kubectl wait --for=condition=Ready externalsecret/jupyterhub-crypt-key \
|
||||
-n ${JUPYTERHUB_NAMESPACE} --timeout=60s
|
||||
else
|
||||
echo "External Secrets Operator not found. Creating secret directly..."
|
||||
kubectl delete secret jupyterhub-crypt-key -n ${JUPYTERHUB_NAMESPACE} --ignore-not-found
|
||||
kubectl create secret generic jupyterhub-crypt-key -n ${JUPYTERHUB_NAMESPACE} \
|
||||
--from-literal=crypt-key="${crypt_key}"
|
||||
|
||||
if helm status vault -n ${K8S_VAULT_NAMESPACE} &>/dev/null; then
|
||||
just vault::put jupyterhub/config crypt-key="${crypt_key}"
|
||||
fi
|
||||
fi
|
||||
|
||||
# Install JupyterHub
|
||||
install root_token='':
|
||||
#!/bin/bash
|
||||
@@ -73,12 +108,11 @@ install root_token='':
|
||||
)
|
||||
done
|
||||
|
||||
# Generate JUPYTERHUB_CRYPT_KEY if not exists
|
||||
if [ -z "${JUPYTERHUB_CRYPT_KEY:-}" ]; then
|
||||
echo "Generating JUPYTERHUB_CRYPT_KEY..."
|
||||
export JUPYTERHUB_CRYPT_KEY=$(just utils::random-password)
|
||||
echo "JUPYTERHUB_CRYPT_KEY=${JUPYTERHUB_CRYPT_KEY}" >> ../../.env.local
|
||||
echo "✓ JUPYTERHUB_CRYPT_KEY generated and saved to .env.local"
|
||||
just create-namespace
|
||||
|
||||
# Create crypt key secret if it doesn't exist
|
||||
if ! kubectl get secret jupyterhub-crypt-key -n ${JUPYTERHUB_NAMESPACE} &>/dev/null; then
|
||||
just create-crypt-key-secret
|
||||
fi
|
||||
|
||||
if helm status kube-prometheus-stack -n ${PROMETHEUS_NAMESPACE} &>/dev/null; then
|
||||
@@ -93,7 +127,25 @@ install root_token='':
|
||||
MONITORING_ENABLED="false"
|
||||
fi
|
||||
|
||||
just create-namespace
|
||||
# Check if nvidia-device-plugin is installed
|
||||
if helm status nvidia-device-plugin -n ${NVIDIA_DEVICE_PLUGIN_NAMESPACE:-nvidia-device-plugin} &>/dev/null; then
|
||||
if [ -z "${JUPYTERHUB_GPU_ENABLED}" ]; then
|
||||
if gum confirm "Enable GPU support for JupyterHub notebooks?"; then
|
||||
JUPYTERHUB_GPU_ENABLED="true"
|
||||
if [ -z "${JUPYTERHUB_GPU_LIMIT}" ]; then
|
||||
JUPYTERHUB_GPU_LIMIT=$(
|
||||
gum input --prompt="GPU limit per user (default: 1): " --width=100 \
|
||||
--placeholder="1" --value="1"
|
||||
)
|
||||
fi
|
||||
else
|
||||
JUPYTERHUB_GPU_ENABLED="false"
|
||||
fi
|
||||
fi
|
||||
else
|
||||
JUPYTERHUB_GPU_ENABLED="false"
|
||||
fi
|
||||
|
||||
# just k8s::copy-regcred ${JUPYTERHUB_NAMESPACE}
|
||||
just keycloak::create-client realm=${KEYCLOAK_REALM} client_id=${JUPYTERHUB_OIDC_CLIENT_ID} \
|
||||
redirect_url="https://${JUPYTERHUB_HOST}/hub/oauth_callback" \
|
||||
@@ -216,11 +268,18 @@ uninstall:
|
||||
helm uninstall jupyterhub -n ${JUPYTERHUB_NAMESPACE} --wait --ignore-not-found
|
||||
kubectl delete pods -n ${JUPYTERHUB_NAMESPACE} -l app.kubernetes.io/component=singleuser-server
|
||||
kubectl delete -n ${JUPYTERHUB_NAMESPACE} pvc jupyter-nfs-pvc --ignore-not-found
|
||||
kubectl delete -n ${JUPYTERHUB_NAMESPACE} secret jupyterhub-crypt-key --ignore-not-found
|
||||
kubectl delete -n ${JUPYTERHUB_NAMESPACE} externalsecret jupyterhub-crypt-key --ignore-not-found
|
||||
kubectl delete -n ${JUPYTERHUB_NAMESPACE} externalsecret jupyterhub-vault-token --ignore-not-found
|
||||
if kubectl get pv jupyter-nfs-pv &>/dev/null; then
|
||||
kubectl patch pv jupyter-nfs-pv -p '{"spec":{"claimRef":null}}'
|
||||
fi
|
||||
|
||||
# Clean up Vault entries if present
|
||||
if helm status vault -n ${K8S_VAULT_NAMESPACE} &>/dev/null; then
|
||||
just vault::delete jupyterhub/config || true
|
||||
fi
|
||||
|
||||
# Delete JupyterHub PV and StorageClass
|
||||
delete-pv:
|
||||
#!/bin/bash
|
||||
|
||||
Reference in New Issue
Block a user