Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Replicate the NASA GHG profile list config for smithsonian #3838

Merged
merged 2 commits into from
Mar 25, 2024
Merged

Replicate the NASA GHG profile list config for smithsonian #3838

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8177a2b
Replicate the NASA GHG profile list config for smithsonian
yuvipanda Mar 23, 2024
f00c123
Use `pangeo` directly for slug
yuvipanda Mar 25, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
185 changes: 101 additions & 84 deletions config/clusters/smithsonian/common.values.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,7 @@ basehub:
url: https://www.si.edu/

hub:
allowNamedServers: true
config:
JupyterHub:
authenticator_class: github
Expand All @@ -60,99 +61,92 @@ basehub:

singleuser:
profileList:
# NOTE: About node sharing
#
# CPU/Memory requests/limits are actively considered still. This
# profile list is setup to involve node sharing as considered in
# https://github.com/2i2c-org/infrastructure/issues/2121.
#
# - Memory requests are different from the description, based on:
# what's found to remain allocate in k8s, subtracting 1GiB
# overhead for misc system pods, and transitioning from GB in
# description to GiB in mem_guarantee.
# - CPU requests are lower than the description, with a factor of
# 10%.
#
- display_name: "Small: up to 4 CPU / 32 GB RAM"
description: &profile_list_description "Start a container with at least a chosen share of capacity on a node of this type"
slug: small
- display_name: "Pangeo Notebook"
slug: modified-pangeo
yuvipanda marked this conversation as resolved.
Show resolved Hide resolved
description: Pangeo based notebook with a Python environment
default: true
profile_options:
image: &profile_options_image
display_name: Image
kubespawner_override:
image: quay.io/pangeo/pangeo-notebook:2024.03.22
profile_options: &profile_options
resource_allocation: &profile_options_resource_allocation
display_name: Resource Allocation
choices:
geospatial:
display_name: Rocker Geospatial
default: true
slug: geospatial
mem_1_9:
display_name: 1.9 GB RAM, upto 3.7 CPUs
kubespawner_override:
image: rocker/binder:4.3
image_pull_policy: Always
working_dir: /home/rstudio
default_url: /rstudio
scipy:
display_name: Jupyter SciPy Notebook
slug: scipy
kubespawner_override:
# FIXME: use quay.io/ for tags after 2023-10-20
image: "jupyter/scipy-notebook:2023-09-04"
pangeo:
display_name: Pangeo Notebook
slug: pangeo
kubespawner_override:
image: "quay.io/pangeo/pangeo-notebook:2023.08.29"
tensorflow: &image_tensorflow
display_name: Pangeo Tensorflow ML Notebook
slug: tensorflow
kubespawner_override:
image: "pangeo/ml-notebook:2023.08.29"
pytorch: &image_pytorch
display_name: Pangeo PyTorch ML Notebook
slug: pytorch
kubespawner_override:
image: "pangeo/pytorch-notebook:2023.08.29"
requests:
# NOTE: Node share choices are in active development, see comment
# next to profileList: above.
display_name: Node share
choices:
mem_1:
mem_guarantee: 1991341312
mem_limit: 1991341312
cpu_guarantee: 0.234375
cpu_limit: 3.75
node_selector:
node.kubernetes.io/instance-type: r5.xlarge
default: true
display_name: ~1 GB, ~0.125 CPU
mem_3_7:
display_name: 3.7 GB RAM, upto 3.7 CPUs
kubespawner_override:
mem_guarantee: 0.904G
cpu_guarantee: 0.013
mem_2:
display_name: ~2 GB, ~0.25 CPU
mem_guarantee: 3982682624
mem_limit: 3982682624
cpu_guarantee: 0.46875
cpu_limit: 3.75
node_selector:
node.kubernetes.io/instance-type: r5.xlarge
mem_7_4:
display_name: 7.4 GB RAM, upto 3.7 CPUs
kubespawner_override:
mem_guarantee: 1.809G
cpu_guarantee: 0.025
mem_4:
display_name: ~4 GB, ~0.5 CPU
mem_guarantee: 7965365248
mem_limit: 7965365248
cpu_guarantee: 0.9375
cpu_limit: 3.75
node_selector:
node.kubernetes.io/instance-type: r5.xlarge
mem_14_8:
display_name: 14.8 GB RAM, upto 3.7 CPUs
kubespawner_override:
mem_guarantee: 3.617G
cpu_guarantee: 0.05
mem_8:
display_name: ~8 GB, ~1.0 CPU
mem_guarantee: 15930730496
mem_limit: 15930730496
cpu_guarantee: 1.875
cpu_limit: 3.75
node_selector:
node.kubernetes.io/instance-type: r5.xlarge
mem_29_7:
display_name: 29.7 GB RAM, upto 3.7 CPUs
kubespawner_override:
mem_guarantee: 7.234G
cpu_guarantee: 0.1
mem_16:
display_name: ~16 GB, ~2.0 CPU
mem_guarantee: 31861460992
mem_limit: 31861460992
cpu_guarantee: 3.75
cpu_limit: 3.75
node_selector:
node.kubernetes.io/instance-type: r5.xlarge
mem_60_6:
display_name: 60.6 GB RAM, upto 15.7 CPUs
kubespawner_override:
mem_guarantee: 14.469G
cpu_guarantee: 0.2
mem_32:
display_name: ~32 GB, ~4.0 CPU
mem_guarantee: 65094813696
mem_limit: 65094813696
cpu_guarantee: 7.86
cpu_limit: 15.72
node_selector:
node.kubernetes.io/instance-type: r5.4xlarge
mem_121_2:
display_name: 121.2 GB RAM, upto 15.7 CPUs
kubespawner_override:
mem_guarantee: 28.937G
cpu_guarantee: 0.4
mem_guarantee: 130189627392
mem_limit: 130189627392
cpu_guarantee: 15.72
cpu_limit: 15.72
node_selector:
node.kubernetes.io/instance-type: r5.4xlarge
- display_name: "Rocker Geospatial with RStudio"
slug: rocker
description: R environment with many geospatial libraries pre-installed
kubespawner_override:
cpu_limit: null
mem_limit: null
node_selector:
node.kubernetes.io/instance-type: r5.xlarge

image: rocker/binder:4.3
image_pull_policy: Always
# Launch RStudio after the user logs in
default_url: /rstudio
# Ensures container working dir is homedir
# https://github.com/2i2c-org/infrastructure/issues/2559
working_dir: /home/rstudio
profile_options: *profile_options
- display_name: NVIDIA Tesla T4, ~16 GB, ~4 CPUs
slug: gpu
description: "Start a container on a dedicated node with a GPU"
Expand All @@ -163,8 +157,16 @@ basehub:
image:
display_name: Image
choices:
tensorflow: *image_tensorflow
pytorch: *image_pytorch
tensorflow:
display_name: Pangeo Tensorflow ML Notebook
slug: tensorflow
kubespawner_override:
image: "pangeo/ml-notebook:2024.03.22"
pytorch:
display_name: Pangeo PyTorch ML Notebook
slug: pytorch
kubespawner_override:
image: "pangeo/pytorch-notebook:2024.03.22"
kubespawner_override:
mem_limit: null
environment:
Expand All @@ -174,3 +176,18 @@ basehub:
node.kubernetes.io/instance-type: g4dn.xlarge
extra_resource_limits:
nvidia.com/gpu: "1"
- display_name: "Bring your own image"
description: Specify your own docker image (must have python and jupyterhub installed in it)
slug: custom
profile_options:
image:
display_name: Image
unlisted_choice:
enabled: True
display_name: "Custom image"
validation_regex: "^.+:.+$"
validation_message: "Must be a publicly available docker image, of form <image-name>:<tag>"
kubespawner_override:
image: "{value}"
choices: {}
resource_allocation: *profile_options_resource_allocation