Compare commits

..

20 Commits

Author SHA1 Message Date
Min RK
69bb34b943 release 1.2.2 2020-11-27 14:44:42 +01:00
Min RK
728fbc68e0 Merge pull request #3285 from meeseeksmachine/auto-backport-of-pr-3284-on-1.2.x
Backport PR #3284 on branch 1.2.x (Changelog for 1.2.2)
2020-11-27 14:41:45 +01:00
Min RK
0dad9a3f39 Backport PR #3284: Changelog for 1.2.2 2020-11-27 13:41:32 +00:00
Min RK
41f291c0c9 Merge pull request #3282 from meeseeksmachine/auto-backport-of-pr-3257-on-1.2.x
Backport PR #3257 on branch 1.2.x (Update services-basics.md to use jupyterhub_idle_culler)
2020-11-27 10:05:01 +01:00
Min RK
9a5b11d5e1 Merge pull request #3283 from meeseeksmachine/auto-backport-of-pr-3250-on-1.2.x
Backport PR #3250 on branch 1.2.x (remove push-branch conditions for CI)
2020-11-27 10:04:11 +01:00
Erik Sundell
b47159b31e Backport PR #3250: remove push-branch conditions for CI 2020-11-27 09:03:54 +00:00
Erik Sundell
bbe377b70a Backport PR #3257: Update services-basics.md to use jupyterhub_idle_culler 2020-11-27 08:59:11 +00:00
Min RK
374a3a7b36 Merge pull request #3273 from meeseeksmachine/auto-backport-of-pr-3237-on-1.2.x
Backport PR #3237 on branch 1.2.x ([proxy.py] Improve robustness when detecting and closing existing proxy processes)
2020-11-26 10:01:46 +01:00
Min RK
32c493e5ab Merge pull request #3272 from meeseeksmachine/auto-backport-of-pr-3252-on-1.2.x
Backport PR #3252 on branch 1.2.x (Standardize "Sign in" capitalization on the login page)
2020-11-20 10:34:41 +01:00
Min RK
edfd363758 Merge pull request #3271 from meeseeksmachine/auto-backport-of-pr-3265-on-1.2.x
Backport PR #3265 on branch 1.2.x (Fix RootHandler when default_url is a callable)
2020-11-20 10:34:31 +01:00
Min RK
d72a5ca3e4 Merge pull request #3274 from meeseeksmachine/auto-backport-of-pr-3255-on-1.2.x
Backport PR #3255 on branch 1.2.x (Environment marker on pamela)
2020-11-20 10:34:22 +01:00
Min RK
3a6309a570 Backport PR #3255: Environment marker on pamela 2020-11-20 09:17:45 +00:00
Min RK
588407200f Backport PR #3237: [proxy.py] Improve robustness when detecting and closing existing proxy processes 2020-11-20 09:17:08 +00:00
Min RK
5cc36a6809 Backport PR #3252: Standardize "Sign in" capitalization on the login page 2020-11-20 09:16:57 +00:00
Min RK
5733eb76c2 Backport PR #3265: Fix RootHandler when default_url is a callable 2020-11-20 09:15:46 +00:00
Min RK
d9719e3538 Merge pull request #3269 from meeseeksmachine/auto-backport-of-pr-3261-on-1.2.x
Backport PR #3261 on branch 1.2.x (Only preserve params when ?next= is unspecified)
2020-11-20 10:10:43 +01:00
Min RK
7c91fbea93 Merge pull request #3270 from meeseeksmachine/auto-backport-of-pr-3246-on-1.2.x
Backport PR #3246 on branch 1.2.x (Migrate from travis to GitHub actions)
2020-11-20 10:10:30 +01:00
Min RK
5076745085 back to dev 2020-11-20 09:54:14 +01:00
Min RK
39eea2f053 Backport PR #3246: Migrate from travis to GitHub actions 2020-11-20 08:51:59 +00:00
Min RK
998f5d7b6c Backport PR #3261: Only preserve params when ?next= is unspecified 2020-11-20 08:48:02 +00:00
235 changed files with 4183 additions and 22422 deletions

33
.circleci/config.yml Normal file
View File

@@ -0,0 +1,33 @@
# Python CircleCI 2.0 configuration file
# Updating CircleCI configuration from v1 to v2
# Check https://circleci.com/docs/2.0/language-python/ for more details
#
version: 2
jobs:
build:
machine: true
steps:
- checkout
- run:
name: build images
command: |
docker build -t jupyterhub/jupyterhub .
docker build -t jupyterhub/jupyterhub-onbuild onbuild
docker build -t jupyterhub/jupyterhub:alpine -f dockerfiles/Dockerfile.alpine .
docker build -t jupyterhub/singleuser singleuser
- run:
name: smoke test jupyterhub
command: |
docker run --rm -it jupyterhub/jupyterhub jupyterhub --help
- run:
name: verify static files
command: |
docker run --rm -it -v $PWD/dockerfiles:/io jupyterhub/jupyterhub python3 /io/test.py
# Tell CircleCI to use this workflow when it builds the site
workflows:
version: 2
default:
jobs:
- build

View File

@@ -1,192 +0,0 @@
# Build releases and (on tags) publish to PyPI
name: Release
# always build releases (to make sure wheel-building works)
# but only publish to PyPI on tags
on:
push:
branches:
- "!dependabot/**"
tags:
- "*"
pull_request:
jobs:
build-release:
runs-on: ubuntu-20.04
steps:
- uses: actions/checkout@v2
- uses: actions/setup-python@v2
with:
python-version: 3.8
- uses: actions/setup-node@v1
with:
node-version: "14"
- name: install build package
run: |
pip install --upgrade pip
pip install build
pip freeze
- name: build release
run: |
python -m build --sdist --wheel .
ls -l dist
- name: verify wheel
run: |
cd dist
pip install ./*.whl
# verify data-files are installed where they are found
cat <<EOF | python
import os
from jupyterhub._data import DATA_FILES_PATH
print(f"DATA_FILES_PATH={DATA_FILES_PATH}")
assert os.path.exists(DATA_FILES_PATH), DATA_FILES_PATH
for subpath in (
"templates/page.html",
"static/css/style.min.css",
"static/components/jquery/dist/jquery.js",
):
path = os.path.join(DATA_FILES_PATH, subpath)
assert os.path.exists(path), path
print("OK")
EOF
# ref: https://github.com/actions/upload-artifact#readme
- uses: actions/upload-artifact@v2
with:
name: jupyterhub-${{ github.sha }}
path: "dist/*"
if-no-files-found: error
- name: Publish to PyPI
if: startsWith(github.ref, 'refs/tags/')
env:
TWINE_USERNAME: __token__
TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
run: |
pip install twine
twine upload --skip-existing dist/*
publish-docker:
runs-on: ubuntu-20.04
services:
# So that we can test this in PRs/branches
local-registry:
image: registry:2
ports:
- 5000:5000
steps:
- name: Should we push this image to a public registry?
run: |
if [ "${{ startsWith(github.ref, 'refs/tags/') || (github.ref == 'refs/heads/main') }}" = "true" ]; then
# Empty => Docker Hub
echo "REGISTRY=" >> $GITHUB_ENV
else
echo "REGISTRY=localhost:5000/" >> $GITHUB_ENV
fi
- uses: actions/checkout@v2
# Setup docker to build for multiple platforms, see:
# https://github.com/docker/build-push-action/tree/v2.4.0#usage
# https://github.com/docker/build-push-action/blob/v2.4.0/docs/advanced/multi-platform.md
- name: Set up QEMU (for docker buildx)
uses: docker/setup-qemu-action@25f0500ff22e406f7191a2a8ba8cda16901ca018 # associated tag: v1.0.2
- name: Set up Docker Buildx (for multi-arch builds)
uses: docker/setup-buildx-action@2a4b53665e15ce7d7049afb11ff1f70ff1610609 # associated tag: v1.1.2
with:
# Allows pushing to registry on localhost:5000
driver-opts: network=host
- name: Setup push rights to Docker Hub
# This was setup by...
# 1. Creating a Docker Hub service account "jupyterhubbot"
# 2. Creating a access token for the service account specific to this
# repository: https://hub.docker.com/settings/security
# 3. Making the account part of the "bots" team, and granting that team
# permissions to push to the relevant images:
# https://hub.docker.com/orgs/jupyterhub/teams/bots/permissions
# 4. Registering the username and token as a secret for this repo:
# https://github.com/jupyterhub/jupyterhub/settings/secrets/actions
if: env.REGISTRY != 'localhost:5000/'
run: |
docker login -u "${{ secrets.DOCKERHUB_USERNAME }}" -p "${{ secrets.DOCKERHUB_TOKEN }}"
# https://github.com/jupyterhub/action-major-minor-tag-calculator
# If this is a tagged build this will return additional parent tags.
# E.g. 1.2.3 is expanded to Docker tags
# [{prefix}:1.2.3, {prefix}:1.2, {prefix}:1, {prefix}:latest] unless
# this is a backported tag in which case the newer tags aren't updated.
# For branches this will return the branch name.
# If GITHUB_TOKEN isn't available (e.g. in PRs) returns no tags [].
- name: Get list of jupyterhub tags
id: jupyterhubtags
uses: jupyterhub/action-major-minor-tag-calculator@v1
with:
githubToken: ${{ secrets.GITHUB_TOKEN }}
prefix: "${{ env.REGISTRY }}jupyterhub/jupyterhub:"
defaultTag: "${{ env.REGISTRY }}jupyterhub/jupyterhub:noref"
branchRegex: ^\w[\w-.]*$
- name: Build and push jupyterhub
uses: docker/build-push-action@e1b7f96249f2e4c8e4ac1519b9608c0d48944a1f # associated tag: v2.4.0
with:
context: .
platforms: linux/amd64,linux/arm64
push: true
# tags parameter must be a string input so convert `gettags` JSON
# array into a comma separated list of tags
tags: ${{ join(fromJson(steps.jupyterhubtags.outputs.tags)) }}
# jupyterhub-onbuild
- name: Get list of jupyterhub-onbuild tags
id: onbuildtags
uses: jupyterhub/action-major-minor-tag-calculator@v1
with:
githubToken: ${{ secrets.GITHUB_TOKEN }}
prefix: "${{ env.REGISTRY }}jupyterhub/jupyterhub-onbuild:"
defaultTag: "${{ env.REGISTRY }}jupyterhub/jupyterhub-onbuild:noref"
branchRegex: ^\w[\w-.]*$
- name: Build and push jupyterhub-onbuild
uses: docker/build-push-action@e1b7f96249f2e4c8e4ac1519b9608c0d48944a1f # associated tag: v2.4.0
with:
build-args: |
BASE_IMAGE=${{ fromJson(steps.jupyterhubtags.outputs.tags)[0] }}
context: onbuild
platforms: linux/amd64,linux/arm64
push: true
tags: ${{ join(fromJson(steps.onbuildtags.outputs.tags)) }}
# jupyterhub-demo
- name: Get list of jupyterhub-demo tags
id: demotags
uses: jupyterhub/action-major-minor-tag-calculator@v1
with:
githubToken: ${{ secrets.GITHUB_TOKEN }}
prefix: "${{ env.REGISTRY }}jupyterhub/jupyterhub-demo:"
defaultTag: "${{ env.REGISTRY }}jupyterhub/jupyterhub-demo:noref"
branchRegex: ^\w[\w-.]*$
- name: Build and push jupyterhub-demo
uses: docker/build-push-action@e1b7f96249f2e4c8e4ac1519b9608c0d48944a1f # associated tag: v2.4.0
with:
build-args: |
BASE_IMAGE=${{ fromJson(steps.onbuildtags.outputs.tags)[0] }}
context: demo-image
# linux/arm64 currently fails:
# ERROR: Could not build wheels for argon2-cffi which use PEP 517 and cannot be installed directly
# ERROR: executor failed running [/bin/sh -c python3 -m pip install notebook]: exit code: 1
platforms: linux/amd64
push: true
tags: ${{ join(fromJson(steps.demotags.outputs.tags)) }}

View File

@@ -1,7 +1,7 @@
# This is a GitHub workflow defining a set of jobs with a set of steps. # This is a GitHub workflow defining a set of jobs with a set of steps.
# ref: https://docs.github.com/en/free-pro-team@latest/actions/reference/workflow-syntax-for-github-actions # ref: https://docs.github.com/en/free-pro-team@latest/actions/reference/workflow-syntax-for-github-actions
# #
name: Test name: Run tests
# Trigger the workflow's on all PRs but only on pushed tags or commits to # Trigger the workflow's on all PRs but only on pushed tags or commits to
# main/master branch to avoid PRs developed in a GitHub fork's dedicated branch # main/master branch to avoid PRs developed in a GitHub fork's dedicated branch
@@ -9,13 +9,48 @@ name: Test
on: on:
pull_request: pull_request:
push: push:
workflow_dispatch:
defaults:
run:
# Declare bash be used by default in this workflow's "run" steps.
#
# NOTE: bash will by default run with:
# --noprofile: Ignore ~/.profile etc.
# --norc: Ignore ~/.bashrc etc.
# -e: Exit directly on errors
# -o pipefail: Don't mask errors from a command piped into another command
shell: bash
env: env:
# UTF-8 content may be interpreted as ascii and causes errors without this. # UTF-8 content may be interpreted as ascii and causes errors without this.
LANG: C.UTF-8 LANG: C.UTF-8
jobs: jobs:
# Run "pre-commit run --all-files"
pre-commit:
runs-on: ubuntu-20.04
timeout-minutes: 2
steps:
- uses: actions/checkout@v2
- uses: actions/setup-python@v2
with:
python-version: 3.8
# ref: https://github.com/pre-commit/action
- uses: pre-commit/action@v2.0.0
- name: Help message if pre-commit fail
if: ${{ failure() }}
run: |
echo "You can install pre-commit hooks to automatically run formatting"
echo "on each commit with:"
echo " pre-commit install"
echo "or you can run by hand on staged files with"
echo " pre-commit run"
echo "or after-the-fact on already committed files with"
echo " pre-commit run --all-files"
# Run "pytest jupyterhub/tests" in various configurations # Run "pytest jupyterhub/tests" in various configurations
pytest: pytest:
runs-on: ubuntu-20.04 runs-on: ubuntu-20.04
@@ -42,10 +77,6 @@ jobs:
# Tests everything when the user instances are started with # Tests everything when the user instances are started with
# jupyter_server instead of notebook. # jupyter_server instead of notebook.
# #
# ssl:
# Tests everything using internal SSL connections instead of
# unencrypted HTTP
#
# main_dependencies: # main_dependencies:
# Tests everything when the we use the latest available dependencies # Tests everything when the we use the latest available dependencies
# from: ipytraitlets. # from: ipytraitlets.
@@ -54,14 +85,10 @@ jobs:
# GitHub UI when the workflow run, we avoid using true/false as # GitHub UI when the workflow run, we avoid using true/false as
# values by instead duplicating the name to signal true. # values by instead duplicating the name to signal true.
include: include:
- python: "3.6"
oldest_dependencies: oldest_dependencies
- python: "3.6" - python: "3.6"
subdomain: subdomain subdomain: subdomain
- python: "3.7" - python: "3.7"
db: mysql db: mysql
- python: "3.7"
ssl: ssl
- python: "3.8" - python: "3.8"
db: postgres db: postgres
- python: "3.8" - python: "3.8"
@@ -82,9 +109,6 @@ jobs:
echo "MYSQL_HOST=127.0.0.1" >> $GITHUB_ENV echo "MYSQL_HOST=127.0.0.1" >> $GITHUB_ENV
echo "JUPYTERHUB_TEST_DB_URL=mysql+mysqlconnector://root@127.0.0.1:3306/jupyterhub" >> $GITHUB_ENV echo "JUPYTERHUB_TEST_DB_URL=mysql+mysqlconnector://root@127.0.0.1:3306/jupyterhub" >> $GITHUB_ENV
fi fi
if [ "${{ matrix.ssl }}" == "ssl" ]; then
echo "SSL_ENABLED=1" >> $GITHUB_ENV
fi
if [ "${{ matrix.db }}" == "postgres" ]; then if [ "${{ matrix.db }}" == "postgres" ]; then
echo "PGHOST=127.0.0.1" >> $GITHUB_ENV echo "PGHOST=127.0.0.1" >> $GITHUB_ENV
echo "PGUSER=test_user" >> $GITHUB_ENV echo "PGUSER=test_user" >> $GITHUB_ENV
@@ -95,6 +119,7 @@ jobs:
echo "JUPYTERHUB_SINGLEUSER_APP=jupyterhub.tests.mockserverapp.MockServerApp" >> $GITHUB_ENV echo "JUPYTERHUB_SINGLEUSER_APP=jupyterhub.tests.mockserverapp.MockServerApp" >> $GITHUB_ENV
fi fi
- uses: actions/checkout@v2 - uses: actions/checkout@v2
# NOTE: actions/setup-node@v1 make use of a cache within the GitHub base # NOTE: actions/setup-node@v1 make use of a cache within the GitHub base
# environment and setup in a fraction of a second. # environment and setup in a fraction of a second.
- name: Install Node v14 - name: Install Node v14
@@ -105,7 +130,6 @@ jobs:
run: | run: |
npm install npm install
npm install -g configurable-http-proxy npm install -g configurable-http-proxy
npm install -g yarn
npm list npm list
# NOTE: actions/setup-python@v2 make use of a cache within the GitHub base # NOTE: actions/setup-python@v2 make use of a cache within the GitHub base
@@ -119,14 +143,6 @@ jobs:
pip install --upgrade pip pip install --upgrade pip
pip install --upgrade . -r dev-requirements.txt pip install --upgrade . -r dev-requirements.txt
if [ "${{ matrix.oldest_dependencies }}" != "" ]; then
# take any dependencies in requirements.txt such as tornado>=5.0
# and transform them to tornado==5.0 so we can run tests with
# the earliest-supported versions
cat requirements.txt | grep '>=' | sed -e 's@>=@==@g' > oldest-requirements.txt
pip install -r oldest-requirements.txt
fi
if [ "${{ matrix.main_dependencies }}" != "" ]; then if [ "${{ matrix.main_dependencies }}" != "" ]; then
pip install git+https://github.com/ipython/traitlets#egg=traitlets --force pip install git+https://github.com/ipython/traitlets#egg=traitlets --force
fi fi
@@ -185,31 +201,6 @@ jobs:
# https://github.com/actions/runner/issues/241 # https://github.com/actions/runner/issues/241
run: | run: |
pytest -v --maxfail=2 --color=yes --cov=jupyterhub jupyterhub/tests pytest -v --maxfail=2 --color=yes --cov=jupyterhub jupyterhub/tests
- name: Run yarn jest test
run: |
cd jsx && yarn && yarn test
- name: Submit codecov report - name: Submit codecov report
run: | run: |
codecov codecov
docker-build:
runs-on: ubuntu-20.04
timeout-minutes: 10
steps:
- uses: actions/checkout@v2
- name: build images
run: |
docker build -t jupyterhub/jupyterhub .
docker build -t jupyterhub/jupyterhub-onbuild onbuild
docker build -t jupyterhub/jupyterhub:alpine -f dockerfiles/Dockerfile.alpine .
docker build -t jupyterhub/singleuser singleuser
- name: smoke test jupyterhub
run: |
docker run --rm -t jupyterhub/jupyterhub jupyterhub --help
- name: verify static files
run: |
docker run --rm -t -v $PWD/dockerfiles:/io jupyterhub/jupyterhub python3 /io/test.py

4
.gitignore vendored
View File

@@ -8,7 +8,6 @@ dist
docs/_build docs/_build
docs/build docs/build
docs/source/_static/rest-api docs/source/_static/rest-api
docs/source/rbac/scope-table.md
.ipynb_checkpoints .ipynb_checkpoints
# ignore config file at the top-level of the repo # ignore config file at the top-level of the repo
# but not sub-dirs # but not sub-dirs
@@ -29,6 +28,3 @@ htmlcov
.pytest_cache .pytest_cache
pip-wheel-metadata pip-wheel-metadata
docs/source/reference/metrics.rst docs/source/reference/metrics.rst
oldest-requirements.txt
jupyterhub-proxy.pid
examples/server-api/service-token

View File

@@ -1,30 +1,19 @@
repos: repos:
- repo: https://github.com/asottile/pyupgrade - repo: https://github.com/asottile/reorder_python_imports
rev: v2.26.0 rev: v1.9.0
hooks:
- id: pyupgrade
args:
- --py36-plus
- repo: https://github.com/asottile/reorder_python_imports
rev: v2.6.0
hooks: hooks:
- id: reorder-python-imports - id: reorder-python-imports
- repo: https://github.com/psf/black - repo: https://github.com/psf/black
rev: 21.8b0 rev: 19.10b0
hooks: hooks:
- id: black - id: black
- repo: https://github.com/pre-commit/mirrors-prettier - repo: https://github.com/pre-commit/pre-commit-hooks
rev: v2.4.0 rev: v2.4.0
hooks:
- id: prettier
- repo: https://github.com/PyCQA/flake8
rev: "3.9.2"
hooks:
- id: flake8
- repo: https://github.com/pre-commit/pre-commit-hooks
rev: v4.0.1
hooks: hooks:
- id: end-of-file-fixer - id: end-of-file-fixer
- id: check-json
- id: check-yaml
- id: check-case-conflict - id: check-case-conflict
- id: check-executables-have-shebangs - id: check-executables-have-shebangs
- id: requirements-txt-fixer - id: requirements-txt-fixer
- id: flake8

View File

@@ -1,2 +0,0 @@
share/jupyterhub/templates/
share/jupyterhub/static/js/admin-react.js

View File

@@ -1 +1 @@
Please refer to [Project Jupyter's Code of Conduct](https://github.com/jupyter/governance/blob/HEAD/conduct/code_of_conduct.md). Please refer to [Project Jupyter's Code of Conduct](https://github.com/jupyter/governance/blob/master/conduct/code_of_conduct.md).

View File

@@ -1,9 +1,9 @@
# Contributing to JupyterHub # Contributing to JupyterHub
Welcome! As a [Jupyter](https://jupyter.org) project, Welcome! As a [Jupyter](https://jupyter.org) project,
you can follow the [Jupyter contributor guide](https://jupyter.readthedocs.io/en/latest/contributing/content-contributor.html). you can follow the [Jupyter contributor guide](https://jupyter.readthedocs.io/en/latest/contributor/content-contributor.html).
Make sure to also follow [Project Jupyter's Code of Conduct](https://github.com/jupyter/governance/blob/HEAD/conduct/code_of_conduct.md) Make sure to also follow [Project Jupyter's Code of Conduct](https://github.com/jupyter/governance/blob/master/conduct/code_of_conduct.md)
for a friendly and welcoming collaborative environment. for a friendly and welcoming collaborative environment.
## Setting up a development environment ## Setting up a development environment
@@ -18,6 +18,7 @@ JupyterHub requires Python >= 3.5 and nodejs.
As a Python project, a development install of JupyterHub follows standard practices for the basics (steps 1-2). As a Python project, a development install of JupyterHub follows standard practices for the basics (steps 1-2).
1. clone the repo 1. clone the repo
```bash ```bash
git clone https://github.com/jupyterhub/jupyterhub git clone https://github.com/jupyterhub/jupyterhub
@@ -28,20 +29,17 @@ As a Python project, a development install of JupyterHub follows standard practi
cd jupyterhub cd jupyterhub
python3 -m pip install --editable . python3 -m pip install --editable .
``` ```
3. install the development requirements, 3. install the development requirements,
which include things like testing tools which include things like testing tools
```bash ```bash
python3 -m pip install -r dev-requirements.txt python3 -m pip install -r dev-requirements.txt
``` ```
4. install configurable-http-proxy with npm: 4. install configurable-http-proxy with npm:
```bash ```bash
npm install -g configurable-http-proxy npm install -g configurable-http-proxy
``` ```
5. set up pre-commit hooks for automatic code formatting, etc. 5. set up pre-commit hooks for automatic code formatting, etc.
```bash ```bash

View File

@@ -21,7 +21,7 @@
# your jupyterhub_config.py will be added automatically # your jupyterhub_config.py will be added automatically
# from your docker directory. # from your docker directory.
ARG BASE_IMAGE=ubuntu:focal-20200729 ARG BASE_IMAGE=ubuntu:focal-20200729@sha256:6f2fb2f9fb5582f8b587837afd6ea8f37d8d1d9e41168c90f410a6ef15fa8ce5
FROM $BASE_IMAGE AS builder FROM $BASE_IMAGE AS builder
USER root USER root

View File

@@ -6,37 +6,29 @@
**[License](#license)** | **[License](#license)** |
**[Help and Resources](#help-and-resources)** **[Help and Resources](#help-and-resources)**
---
Please note that this repository is participating in a study into the sustainability of open source projects. Data will be gathered about this repository for approximately the next 12 months, starting from 2021-06-11.
Data collected will include the number of contributors, number of PRs, time taken to close/merge these PRs, and issues closed.
For more information, please visit
[our informational page](https://sustainable-open-science-and-software.github.io/) or download our [participant information sheet](https://sustainable-open-science-and-software.github.io/assets/PIS_sustainable_software.pdf).
---
# [JupyterHub](https://github.com/jupyterhub/jupyterhub) # [JupyterHub](https://github.com/jupyterhub/jupyterhub)
[![Latest PyPI version](https://img.shields.io/pypi/v/jupyterhub?logo=pypi)](https://pypi.python.org/pypi/jupyterhub) [![Latest PyPI version](https://img.shields.io/pypi/v/jupyterhub?logo=pypi)](https://pypi.python.org/pypi/jupyterhub)
[![Latest conda-forge version](https://img.shields.io/conda/vn/conda-forge/jupyterhub?logo=conda-forge)](https://anaconda.org/conda-forge/jupyterhub) [![Latest conda-forge version](https://img.shields.io/conda/vn/conda-forge/jupyterhub?logo=conda-forge)](https://www.npmjs.com/package/jupyterhub)
[![Documentation build status](https://img.shields.io/readthedocs/jupyterhub?logo=read-the-docs)](https://jupyterhub.readthedocs.org/en/latest/) [![Documentation build status](https://img.shields.io/readthedocs/jupyterhub?logo=read-the-docs)](https://jupyterhub.readthedocs.org/en/latest/)
[![GitHub Workflow Status - Test](https://img.shields.io/github/workflow/status/jupyterhub/jupyterhub/Test?logo=github&label=tests)](https://github.com/jupyterhub/jupyterhub/actions) [![TravisCI build status](https://img.shields.io/travis/com/jupyterhub/jupyterhub?logo=travis)](https://travis-ci.com/jupyterhub/jupyterhub)
[![DockerHub build status](https://img.shields.io/docker/build/jupyterhub/jupyterhub?logo=docker&label=build)](https://hub.docker.com/r/jupyterhub/jupyterhub/tags) [![DockerHub build status](https://img.shields.io/docker/build/jupyterhub/jupyterhub?logo=docker&label=build)](https://hub.docker.com/r/jupyterhub/jupyterhub/tags)
[![Test coverage of code](https://codecov.io/gh/jupyterhub/jupyterhub/branch/main/graph/badge.svg)](https://codecov.io/gh/jupyterhub/jupyterhub) [![CircleCI build status](https://img.shields.io/circleci/build/github/jupyterhub/jupyterhub?logo=circleci)](https://circleci.com/gh/jupyterhub/jupyterhub)<!-- CircleCI Token: b5b65862eb2617b9a8d39e79340b0a6b816da8cc -->
[![Test coverage of code](https://codecov.io/gh/jupyterhub/jupyterhub/branch/master/graph/badge.svg)](https://codecov.io/gh/jupyterhub/jupyterhub)
[![GitHub](https://img.shields.io/badge/issue_tracking-github-blue?logo=github)](https://github.com/jupyterhub/jupyterhub/issues) [![GitHub](https://img.shields.io/badge/issue_tracking-github-blue?logo=github)](https://github.com/jupyterhub/jupyterhub/issues)
[![Discourse](https://img.shields.io/badge/help_forum-discourse-blue?logo=discourse)](https://discourse.jupyter.org/c/jupyterhub) [![Discourse](https://img.shields.io/badge/help_forum-discourse-blue?logo=discourse)](https://discourse.jupyter.org/c/jupyterhub)
[![Gitter](https://img.shields.io/badge/social_chat-gitter-blue?logo=gitter)](https://gitter.im/jupyterhub/jupyterhub) [![Gitter](https://img.shields.io/badge/social_chat-gitter-blue?logo=gitter)](https://gitter.im/jupyterhub/jupyterhub)
With [JupyterHub](https://jupyterhub.readthedocs.io) you can create a With [JupyterHub](https://jupyterhub.readthedocs.io) you can create a
**multi-user Hub** that spawns, manages, and proxies multiple instances of the **multi-user Hub** which spawns, manages, and proxies multiple instances of the
single-user [Jupyter notebook](https://jupyter-notebook.readthedocs.io) single-user [Jupyter notebook](https://jupyter-notebook.readthedocs.io)
server. server.
[Project Jupyter](https://jupyter.org) created JupyterHub to support many [Project Jupyter](https://jupyter.org) created JupyterHub to support many
users. The Hub can offer notebook servers to a class of students, a corporate users. The Hub can offer notebook servers to a class of students, a corporate
data science workgroup, a scientific research project, or a high-performance data science workgroup, a scientific research project, or a high performance
computing group. computing group.
## Technical overview ## Technical overview
@@ -50,28 +42,37 @@ Three main actors make up JupyterHub:
Basic principles for operation are: Basic principles for operation are:
- Hub launches a proxy. - Hub launches a proxy.
- The Proxy forwards all requests to Hub by default. - Proxy forwards all requests to Hub by default.
- Hub handles login and spawns single-user servers on demand. - Hub handles login, and spawns single-user servers on demand.
- Hub configures proxy to forward URL prefixes to the single-user notebook - Hub configures proxy to forward url prefixes to the single-user notebook
servers. servers.
JupyterHub also provides a JupyterHub also provides a
[REST API](https://petstore3.swagger.io/?url=https://raw.githubusercontent.com/jupyter/jupyterhub/HEAD/docs/rest-api.yml#/default) [REST API](http://petstore.swagger.io/?url=https://raw.githubusercontent.com/jupyter/jupyterhub/master/docs/rest-api.yml#/default)
for administration of the Hub and its users. for administration of the Hub and its users.
## Installation ## Installation
### Check prerequisites ### Check prerequisites
- A Linux/Unix based system - A Linux/Unix based system
- [Python](https://www.python.org/downloads/) 3.6 or greater - [Python](https://www.python.org/downloads/) 3.5 or greater
- [nodejs/npm](https://www.npmjs.com/) - [nodejs/npm](https://www.npmjs.com/)
- If you are using **`conda`**, the nodejs and npm dependencies will be installed for * If you are using **`conda`**, the nodejs and npm dependencies will be installed for
you by conda. you by conda.
- If you are using **`pip`**, install a recent version (at least 12.0) of * If you are using **`pip`**, install a recent version of
[nodejs/npm](https://docs.npmjs.com/getting-started/installing-node). [nodejs/npm](https://docs.npmjs.com/getting-started/installing-node).
For example, install it on Linux (Debian/Ubuntu) using:
```
sudo apt-get install npm nodejs-legacy
```
The `nodejs-legacy` package installs the `node` executable and is currently
required for npm to work on Debian/Ubuntu.
- If using the default PAM Authenticator, a [pluggable authentication module (PAM)](https://en.wikipedia.org/wiki/Pluggable_authentication_module). - If using the default PAM Authenticator, a [pluggable authentication module (PAM)](https://en.wikipedia.org/wiki/Pluggable_authentication_module).
- TLS certificate and key for HTTPS communication - TLS certificate and key for HTTPS communication
@@ -87,11 +88,12 @@ To install JupyterHub along with its dependencies including nodejs/npm:
conda install -c conda-forge jupyterhub conda install -c conda-forge jupyterhub
``` ```
If you plan to run notebook servers locally, install JupyterLab or Jupyter notebook: If you plan to run notebook servers locally, install the Jupyter notebook
or JupyterLab:
```bash ```bash
conda install jupyterlab
conda install notebook conda install notebook
conda install jupyterlab
``` ```
#### Using `pip` #### Using `pip`
@@ -103,10 +105,10 @@ npm install -g configurable-http-proxy
python3 -m pip install jupyterhub python3 -m pip install jupyterhub
``` ```
If you plan to run notebook servers locally, you will need to install If you plan to run notebook servers locally, you will need to install the
[JupyterLab or Jupyter notebook](https://jupyter.readthedocs.io/en/latest/install.html): [Jupyter notebook](https://jupyter.readthedocs.io/en/latest/install.html)
package:
python3 -m pip install --upgrade jupyterlab
python3 -m pip install --upgrade notebook python3 -m pip install --upgrade notebook
### Run the Hub server ### Run the Hub server
@@ -118,10 +120,10 @@ To start the Hub server, run the command:
Visit `https://localhost:8000` in your browser, and sign in with your unix Visit `https://localhost:8000` in your browser, and sign in with your unix
PAM credentials. PAM credentials.
_Note_: To allow multiple users to sign in to the server, you will need to *Note*: To allow multiple users to sign into the server, you will need to
run the `jupyterhub` command as a _privileged user_, such as root. run the `jupyterhub` command as a *privileged user*, such as root.
The [wiki](https://github.com/jupyterhub/jupyterhub/wiki/Using-sudo-to-run-JupyterHub-without-root-privileges) The [wiki](https://github.com/jupyterhub/jupyterhub/wiki/Using-sudo-to-run-JupyterHub-without-root-privileges)
describes how to run the server as a _less privileged user_, which requires describes how to run the server as a *less privileged user*, which requires
more configuration of the system. more configuration of the system.
## Configuration ## Configuration
@@ -140,7 +142,7 @@ To generate a default config file with settings and descriptions:
### Start the Hub ### Start the Hub
To start the Hub on a specific url and port `10.0.1.2:443` with **https**: To start the Hub on a specific url and port ``10.0.1.2:443`` with **https**:
jupyterhub --ip 10.0.1.2 --port 443 --ssl-key my_ssl.key --ssl-cert my_ssl.cert jupyterhub --ip 10.0.1.2 --port 443 --ssl-key my_ssl.key --ssl-cert my_ssl.cert
@@ -202,7 +204,7 @@ These accounts will be used for authentication in JupyterHub's default configura
## Contributing ## Contributing
If you would like to contribute to the project, please read our If you would like to contribute to the project, please read our
[contributor documentation](https://jupyter.readthedocs.io/en/latest/contributing/content-contributor.html) [contributor documentation](http://jupyter.readthedocs.io/en/latest/contributor/content-contributor.html)
and the [`CONTRIBUTING.md`](CONTRIBUTING.md). The `CONTRIBUTING.md` file and the [`CONTRIBUTING.md`](CONTRIBUTING.md). The `CONTRIBUTING.md` file
explains how to set up a development installation, how to run the test suite, explains how to set up a development installation, how to run the test suite,
and how to contribute to documentation. and how to contribute to documentation.
@@ -229,17 +231,18 @@ docker container or Linux VM.
We use a shared copyright model that enables all contributors to maintain the We use a shared copyright model that enables all contributors to maintain the
copyright on their contributions. copyright on their contributions.
All code is licensed under the terms of the [revised BSD license](./COPYING.md). All code is licensed under the terms of the revised BSD license.
## Help and resources ## Help and resources
We encourage you to ask questions and share ideas on the [Jupyter community forum](https://discourse.jupyter.org/). We encourage you to ask questions on the [Jupyter mailing list](https://groups.google.com/forum/#!forum/jupyter).
You can also talk with us on our JupyterHub [Gitter](https://gitter.im/jupyterhub/jupyterhub) channel. To participate in development discussions or get help, talk with us on
our JupyterHub [Gitter](https://gitter.im/jupyterhub/jupyterhub) channel.
- [Reporting Issues](https://github.com/jupyterhub/jupyterhub/issues) - [Reporting Issues](https://github.com/jupyterhub/jupyterhub/issues)
- [JupyterHub tutorial](https://github.com/jupyterhub/jupyterhub-tutorial) - [JupyterHub tutorial](https://github.com/jupyterhub/jupyterhub-tutorial)
- [Documentation for JupyterHub](https://jupyterhub.readthedocs.io/en/latest/) | [PDF (latest)](https://media.readthedocs.org/pdf/jupyterhub/latest/jupyterhub.pdf) | [PDF (stable)](https://media.readthedocs.org/pdf/jupyterhub/stable/jupyterhub.pdf) - [Documentation for JupyterHub](https://jupyterhub.readthedocs.io/en/latest/) | [PDF (latest)](https://media.readthedocs.org/pdf/jupyterhub/latest/jupyterhub.pdf) | [PDF (stable)](https://media.readthedocs.org/pdf/jupyterhub/stable/jupyterhub.pdf)
- [Documentation for JupyterHub's REST API](https://petstore3.swagger.io/?url=https://raw.githubusercontent.com/jupyter/jupyterhub/HEAD/docs/rest-api.yml#/default) - [Documentation for JupyterHub's REST API](http://petstore.swagger.io/?url=https://raw.githubusercontent.com/jupyter/jupyterhub/master/docs/rest-api.yml#/default)
- [Documentation for Project Jupyter](http://jupyter.readthedocs.io/en/latest/index.html) | [PDF](https://media.readthedocs.org/pdf/jupyter/latest/jupyter.pdf) - [Documentation for Project Jupyter](http://jupyter.readthedocs.io/en/latest/index.html) | [PDF](https://media.readthedocs.org/pdf/jupyter/latest/jupyter.pdf)
- [Project Jupyter website](https://jupyter.org) - [Project Jupyter website](https://jupyter.org)
- [Project Jupyter community](https://jupyter.org/community) - [Project Jupyter community](https://jupyter.org/community)

View File

@@ -29,5 +29,5 @@ dependencies = package_json['dependencies']
for dep in dependencies: for dep in dependencies:
src = join(node_modules, dep) src = join(node_modules, dep)
dest = join(components, dep) dest = join(components, dep)
print(f"{src} -> {dest}") print("%s -> %s" % (src, dest))
shutil.copytree(src, dest) shutil.copytree(src, dest)

View File

@@ -20,7 +20,7 @@ fi
# Configure a set of databases in the database server for upgrade tests # Configure a set of databases in the database server for upgrade tests
set -x set -x
for SUFFIX in '' _upgrade_100 _upgrade_122 _upgrade_130; do for SUFFIX in '' _upgrade_072 _upgrade_081 _upgrade_094; do
$SQL_CLIENT "DROP DATABASE jupyterhub${SUFFIX};" 2>/dev/null || true $SQL_CLIENT "DROP DATABASE jupyterhub${SUFFIX};" 2>/dev/null || true
$SQL_CLIENT "CREATE DATABASE jupyterhub${SUFFIX} ${EXTRA_CREATE_DATABASE_ARGS:-};" $SQL_CLIENT "CREATE DATABASE jupyterhub${SUFFIX} ${EXTRA_CREATE_DATABASE_ARGS:-};"
done done

View File

@@ -15,7 +15,6 @@ This should only be used for demo or testing purposes!
It shouldn't be used as a base image to build on. It shouldn't be used as a base image to build on.
### Try it ### Try it
1. `cd` to the root of your jupyterhub repo. 1. `cd` to the root of your jupyterhub repo.
2. Build the demo image with `docker build -t jupyterhub-demo demo-image`. 2. Build the demo image with `docker build -t jupyterhub-demo demo-image`.

View File

@@ -10,9 +10,9 @@ html5lib # needed for beautifulsoup
mock mock
notebook notebook
pre-commit pre-commit
pytest>=3.3
pytest-asyncio pytest-asyncio
pytest-cov pytest-cov
pytest>=3.3
requests-mock requests-mock
# blacklist urllib3 releases affected by https://github.com/urllib3/urllib3/issues/1683 # blacklist urllib3 releases affected by https://github.com/urllib3/urllib3/issues/1683
# I *think* this should only affect testing, not production # I *think* this should only affect testing, not production

View File

@@ -1,14 +1,9 @@
FROM alpine:3.13 FROM python:3.6.3-alpine3.6
ENV LANG=en_US.UTF-8
RUN apk add --no-cache \ ARG JUPYTERHUB_VERSION=0.8.1
python3 \
py3-pip \
py3-ruamel.yaml \
py3-cryptography \
py3-sqlalchemy
ARG JUPYTERHUB_VERSION=1.3.0
RUN pip3 install --no-cache jupyterhub==${JUPYTERHUB_VERSION} RUN pip3 install --no-cache jupyterhub==${JUPYTERHUB_VERSION}
ENV LANG=en_US.UTF-8
USER nobody USER nobody
CMD ["jupyterhub"] CMD ["jupyterhub"]

View File

@@ -1,5 +1,4 @@
## What is Dockerfile.alpine ## What is Dockerfile.alpine
Dockerfile.alpine contains base image for jupyterhub. It does not work independently, but only as part of a full jupyterhub cluster Dockerfile.alpine contains base image for jupyterhub. It does not work independently, but only as part of a full jupyterhub cluster
## How to use it? ## How to use it?
@@ -8,13 +7,14 @@ Dockerfile.alpine contains base image for jupyterhub. It does not work independe
2. A jupyterhub_config file. 2. A jupyterhub_config file.
3. Authentication and other libraries required by the specific jupyterhub_config file. 3. Authentication and other libraries required by the specific jupyterhub_config file.
## Steps to test it outside a cluster ## Steps to test it outside a cluster
- start configurable-http-proxy in another container * start configurable-http-proxy in another container
- specify CONFIGPROXY_AUTH_TOKEN env in both containers * specify CONFIGPROXY_AUTH_TOKEN env in both containers
- put both containers on the same network (e.g. docker network create jupyterhub; docker run ... --net jupyterhub) * put both containers on the same network (e.g. docker network create jupyterhub; docker run ... --net jupyterhub)
- tell jupyterhub where CHP is (e.g. c.ConfigurableHTTPProxy.api_url = 'http://chp:8001') * tell jupyterhub where CHP is (e.g. c.ConfigurableHTTPProxy.api_url = 'http://chp:8001')
- tell jupyterhub not to start the proxy itself (c.ConfigurableHTTPProxy.should_start = False) * tell jupyterhub not to start the proxy itself (c.ConfigurableHTTPProxy.should_start = False)
- Use dummy authenticator for ease of testing. Update following in jupyterhub_config file * Use dummy authenticator for ease of testing. Update following in jupyterhub_config file
- c.JupyterHub.authenticator_class = 'dummyauthenticator.DummyAuthenticator' - c.JupyterHub.authenticator_class = 'dummyauthenticator.DummyAuthenticator'
- c.DummyAuthenticator.password = "your strong password" - c.DummyAuthenticator.password = "your strong password"

View File

@@ -66,12 +66,7 @@ metrics: source/reference/metrics.rst
source/reference/metrics.rst: generate-metrics.py source/reference/metrics.rst: generate-metrics.py
python3 generate-metrics.py python3 generate-metrics.py
scopes: source/rbac/scope-table.md html: rest-api metrics
source/rbac/scope-table.md: source/rbac/generate-scope-table.py
python3 source/rbac/generate-scope-table.py
html: rest-api metrics scopes
$(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html $(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html
@echo @echo
@echo "Build finished. The HTML pages are in $(BUILDDIR)/html." @echo "Build finished. The HTML pages are in $(BUILDDIR)/html."

View File

@@ -3,10 +3,10 @@
alabaster_jupyterhub alabaster_jupyterhub
# Temporary fix of #3021. Revert back to released autodoc-traits when # Temporary fix of #3021. Revert back to released autodoc-traits when
# 0.1.0 released. # 0.1.0 released.
https://github.com/jupyterhub/autodoc-traits/archive/d22282c1c18c6865436e06d8b329c06fe12a07f8.zip https://github.com/jupyterhub/autodoc-traits/archive/75885ee24636efbfebfceed1043459715049cd84.zip
myst-parser
pydata-sphinx-theme pydata-sphinx-theme
pytablewriter>=0.56 pytablewriter>=0.56
sphinx>=1.7 recommonmark>=0.6
sphinx-copybutton sphinx-copybutton
sphinx-jsonschema sphinx-jsonschema
sphinx>=1.7

View File

@@ -1,73 +1,20 @@
# see me at: https://petstore3.swagger.io/?url=https://raw.githubusercontent.com/jupyterhub/jupyterhub/HEAD/docs/rest-api.yml#/default # see me at: http://petstore.swagger.io/?url=https://raw.githubusercontent.com/jupyterhub/jupyterhub/master/docs/rest-api.yml#/default
swagger: "2.0" swagger: '2.0'
info: info:
title: JupyterHub title: JupyterHub
description: The REST API for JupyterHub description: The REST API for JupyterHub
version: 1.4.0 version: 1.2.0dev
license: license:
name: BSD-3-Clause name: BSD-3-Clause
schemes: [http, https] schemes:
[http, https]
securityDefinitions: securityDefinitions:
token: token:
type: apiKey type: apiKey
name: Authorization name: Authorization
in: header in: header
oauth2: security:
type: oauth2
flow: accessCode
authorizationUrl: "/hub/api/oauth2/authorize" # what are the absolute URIs here? is oauth2 correct here or shall we use just authorizations?
tokenUrl: "/hub/api/oauth2/token"
scopes: # Generated based on scope table in jupyterhub/scopes.py
(no_scope): Identify the owner of the requesting entity.
self:
The users own resources _(metascope for users, resolves to (no_scope)
for services)_
all: Everything that the token-owning entity can access _(metascope for tokens)_
admin:users:
Read, write, create and delete users and their authentication state,
not including their servers or tokens.
admin:auth_state: Read a users authentication state.
users:
Read and write permissions to user models (excluding servers, tokens
and authentication state).
read:users:
Read user models (excluding including servers, tokens and authentication
state).
read:users:name: Read names of users.
read:users:groups: Read users group membership.
read:users:activity: Read time of last user activity.
read:roles: Read role assignments.
read:roles:users: Read user role assignments.
read:roles:services: Read service role assignments.
read:roles:groups: Read group role assignments.
users:activity: Update time of last user activity.
admin:servers: Read, start, stop, create and delete user servers and their state.
admin:server_state: Read and write users server state.
servers: Start and stop user servers.
read:servers:
Read users names and their server models (excluding the server
state).
tokens: Read, write, create and delete user tokens.
read:tokens: Read user tokens.
admin:groups: Read and write group information, create and delete groups.
groups:
Read and write group information, including adding/removing users to/from
groups.
read:groups: Read group models.
read:groups:name: Read group names.
read:services: Read service models.
read:services:name: Read service names.
read:hub: Read detailed information about the Hub.
access:servers: Access user servers via API or browser.
access:services: Access services via API or browser.
proxy:
Read information about the proxys routing table, sync the Hub with the
proxy and notify the Hub about a new proxy.
shutdown: Shutdown the hub.
security: # global security, do we want to keep only the apiKey (token: []), change to only oauth2 (with scope self) or have both (either can be used)?
- token: [] - token: []
- oauth2:
- self
basePath: /hub/api basePath: /hub/api
produces: produces:
- application/json - application/json
@@ -81,7 +28,7 @@ paths:
This endpoint is not authenticated for the purpose of clients and user This endpoint is not authenticated for the purpose of clients and user
to identify the JupyterHub version before setting up authentication. to identify the JupyterHub version before setting up authentication.
responses: responses:
"200": '200':
description: The JupyterHub version description: The JupyterHub version
schema: schema:
type: object type: object
@@ -92,15 +39,12 @@ paths:
/info: /info:
get: get:
summary: Get detailed info about JupyterHub summary: Get detailed info about JupyterHub
security:
- oauth2:
- read:hub
description: | description: |
Detailed JupyterHub information, including Python version, Detailed JupyterHub information, including Python version,
JupyterHub's version and executable path, JupyterHub's version and executable path,
and which Authenticator and Spawner are active. and which Authenticator and Spawner are active.
responses: responses:
"200": '200':
description: Detailed JupyterHub info description: Detailed JupyterHub info
schema: schema:
type: object type: object
@@ -119,9 +63,7 @@ paths:
properties: properties:
class: class:
type: string type: string
description: description: The Python class currently active for JupyterHub Authentication
The Python class currently active for JupyterHub
Authentication
version: version:
type: string type: string
description: The version of the currently active Authenticator description: The version of the currently active Authenticator
@@ -130,68 +72,22 @@ paths:
properties: properties:
class: class:
type: string type: string
description: description: The Python class currently active for spawning single-user notebook servers
The Python class currently active for spawning single-user
notebook servers
version: version:
type: string type: string
description: The version of the currently active Spawner description: The version of the currently active Spawner
/users: /users:
get: get:
summary: List users summary: List users
security:
- oauth2:
- read:users
- read:users:name
- read:users:groups
- read:users:activity
- read:servers
- read:roles:users
- admin:auth_state
- admin:server_state
parameters:
- name: state
in: query
required: false
type: string
enum: ["inactive", "active", "ready"]
description: |
Return only users who have servers in the given state.
If unspecified, return all users.
active: all users with any active servers (ready OR pending)
ready: all users who have any ready servers (running, not pending)
inactive: all users who have *no* active servers (complement of active)
Added in JupyterHub 1.3
- name: offset
in: query
required: false
type: number
description: |
Return a number users starting at the given offset.
Can be used with limit to paginate.
If unspecified, return all users.
- name: limit
in: query
requred: false
type: number
description: |
Return a finite number of users.
Can be used with offset to paginate.
If unspecified, use api_page_default_limit.
responses: responses:
"200": '200':
description: The Hub's user list description: The Hub's user list
schema: schema:
type: array type: array
items: items:
$ref: "#/definitions/User" $ref: '#/definitions/User'
post: post:
summary: Create multiple users summary: Create multiple users
security:
- oauth2:
- admin:users
parameters: parameters:
- name: body - name: body
in: body in: body
@@ -208,26 +104,16 @@ paths:
description: whether the created users should be admins description: whether the created users should be admins
type: boolean type: boolean
responses: responses:
"201": '201':
description: The users have been created description: The users have been created
schema: schema:
type: array type: array
description: The created users description: The created users
items: items:
$ref: "#/definitions/User" $ref: '#/definitions/User'
/users/{name}: /users/{name}:
get: get:
summary: Get a user by name summary: Get a user by name
security:
- oauth2:
- read:users
- read:users:name
- read:users:groups
- read:users:activity
- read:servers
- read:roles:users
- admin:auth_state
- admin:server_state
parameters: parameters:
- name: name - name: name
description: username description: username
@@ -235,15 +121,12 @@ paths:
required: true required: true
type: string type: string
responses: responses:
"200": '200':
description: The User model description: The User model
schema: schema:
$ref: "#/definitions/User" $ref: '#/definitions/User'
post: post:
summary: Create a single user summary: Create a single user
security:
- oauth2:
- admin:users
parameters: parameters:
- name: name - name: name
description: username description: username
@@ -251,16 +134,13 @@ paths:
required: true required: true
type: string type: string
responses: responses:
"201": '201':
description: The user has been created description: The user has been created
schema: schema:
$ref: "#/definitions/User" $ref: '#/definitions/User'
patch: patch:
summary: Modify a user summary: Modify a user
description: Change a user's name or admin status description: Change a user's name or admin status
security:
- oauth2:
- admin:users
parameters: parameters:
- name: name - name: name
description: username description: username
@@ -270,32 +150,23 @@ paths:
- name: body - name: body
in: body in: body
required: true required: true
description: description: Updated user info. At least one key to be updated (name or admin) is required.
Updated user info. At least one key to be updated (name or admin)
is required.
schema: schema:
type: object type: object
properties: properties:
name: name:
type: string type: string
description: description: the new name (optional, if another key is updated i.e. admin)
the new name (optional, if another key is updated i.e.
admin)
admin: admin:
type: boolean type: boolean
description: description: update admin (optional, if another key is updated i.e. name)
update admin (optional, if another key is updated i.e.
name)
responses: responses:
"200": '200':
description: The updated user info description: The updated user info
schema: schema:
$ref: "#/definitions/User" $ref: '#/definitions/User'
delete: delete:
summary: Delete a user summary: Delete a user
security:
- oauth2:
- admin:users
parameters: parameters:
- name: name - name: name
description: username description: username
@@ -303,17 +174,16 @@ paths:
required: true required: true
type: string type: string
responses: responses:
"204": '204':
description: The user has been deleted description: The user has been deleted
/users/{name}/activity: /users/{name}/activity:
post: post:
summary: Notify Hub of activity for a given user. summary:
Notify Hub of activity for a given user.
description: description:
Notify the Hub of activity by the user, e.g. accessing a service Notify the Hub of activity by the user,
or (more likely) actively using a server. e.g. accessing a service or (more likely)
security: actively using a server.
- oauth2:
- users:activity
parameters: parameters:
- name: name - name: name
description: username description: username
@@ -339,7 +209,7 @@ paths:
The default server has an empty name (''). The default server has an empty name ('').
type: object type: object
properties: properties:
"<server name>": '<server name>':
description: | description: |
Activity for a single server. Activity for a single server.
type: object type: object
@@ -352,23 +222,20 @@ paths:
description: | description: |
Timestamp of last-seen activity on this server. Timestamp of last-seen activity on this server.
example: example:
last_activity: "2019-02-06T12:54:14Z" last_activity: '2019-02-06T12:54:14Z'
servers: servers:
"": '':
last_activity: "2019-02-06T12:54:14Z" last_activity: '2019-02-06T12:54:14Z'
gpu: gpu:
last_activity: "2019-02-06T12:54:14Z" last_activity: '2019-02-06T12:54:14Z'
responses: responses:
"401": '401':
$ref: "#/responses/Unauthorized" $ref: '#/responses/Unauthorized'
"404": '404':
description: No such user description: No such user
/users/{name}/server: /users/{name}/server:
post: post:
summary: Start a user's single-user notebook server summary: Start a user's single-user notebook server
security:
- oauth2:
- servers
parameters: parameters:
- name: name - name: name
description: username description: username
@@ -389,17 +256,12 @@ paths:
type: object type: object
responses: responses:
"201": '201':
description: The user's notebook server has started description: The user's notebook server has started
"202": '202':
description: description: The user's notebook server has not yet started, but has been requested
The user's notebook server has not yet started, but has been
requested
delete: delete:
summary: Stop a user's server summary: Stop a user's server
security:
- oauth2:
- servers
parameters: parameters:
- name: name - name: name
description: username description: username
@@ -407,18 +269,13 @@ paths:
required: true required: true
type: string type: string
responses: responses:
"204": '204':
description: The user's notebook server has stopped description: The user's notebook server has stopped
"202": '202':
description: description: The user's notebook server has not yet stopped as it is taking a while to stop
The user's notebook server has not yet stopped as it is taking
a while to stop
/users/{name}/servers/{server_name}: /users/{name}/servers/{server_name}:
post: post:
summary: Start a user's single-user named-server notebook server summary: Start a user's single-user named-server notebook server
security:
- oauth2:
- servers
parameters: parameters:
- name: name - name: name
description: username description: username
@@ -444,17 +301,12 @@ paths:
schema: schema:
type: object type: object
responses: responses:
"201": '201':
description: The user's notebook named-server has started description: The user's notebook named-server has started
"202": '202':
description: description: The user's notebook named-server has not yet started, but has been requested
The user's notebook named-server has not yet started, but has
been requested
delete: delete:
summary: Stop a user's named-server summary: Stop a user's named-server
security:
- oauth2:
- servers
parameters: parameters:
- name: name - name: name
description: username description: username
@@ -479,12 +331,10 @@ paths:
Removing a server deletes things like the state of the stopped server. Removing a server deletes things like the state of the stopped server.
Default: false. Default: false.
responses: responses:
"204": '204':
description: The user's notebook named-server has stopped description: The user's notebook named-server has stopped
"202": '202':
description: description: The user's notebook named-server has not yet stopped as it is taking a while to stop
The user's notebook named-server has not yet stopped as it
is taking a while to stop
/users/{name}/tokens: /users/{name}/tokens:
parameters: parameters:
- name: name - name: name
@@ -494,25 +344,19 @@ paths:
type: string type: string
get: get:
summary: List tokens for the user summary: List tokens for the user
security:
- oauth2:
- read:tokens
responses: responses:
"200": '200':
description: The list of tokens description: The list of tokens
schema: schema:
type: array type: array
items: items:
$ref: "#/definitions/Token" $ref: '#/definitions/Token'
"401": '401':
$ref: "#/responses/Unauthorized" $ref: '#/responses/Unauthorized'
"404": '404':
description: No such user description: No such user
post: post:
summary: Create a new token for the user summary: Create a new token for the user
security:
- oauth2:
- tokens
parameters: parameters:
- name: token_params - name: token_params
in: body in: body
@@ -522,26 +366,17 @@ paths:
properties: properties:
expires_in: expires_in:
type: number type: number
description: description: lifetime (in seconds) after which the requested token will expire.
lifetime (in seconds) after which the requested token will
expire.
note: note:
type: string type: string
description: A note attached to the token for future bookkeeping description: A note attached to the token for future bookkeeping
roles:
type: array
items:
type: string
description: A list of role names that the token should have
responses: responses:
"201": '201':
description: The newly created token description: The newly created token
schema: schema:
$ref: "#/definitions/Token" $ref: '#/definitions/Token'
"400": '400':
description: Body must be a JSON dict or empty description: Body must be a JSON dict or empty
"403":
description: Requested role does not exist
/users/{name}/tokens/{token_id}: /users/{name}/tokens/{token_id}:
parameters: parameters:
- name: name - name: name
@@ -555,80 +390,37 @@ paths:
type: string type: string
get: get:
summary: Get the model for a token by id summary: Get the model for a token by id
security:
- oauth2:
- read:tokens
responses: responses:
"200": '200':
description: The info for the new token description: The info for the new token
schema: schema:
$ref: "#/definitions/Token" $ref: '#/definitions/Token'
delete: delete:
summary: Delete (revoke) a token by id summary: Delete (revoke) a token by id
security:
- oauth2:
- tokens
responses: responses:
"204": '204':
description: The token has been deleted description: The token has been deleted
/user: /user:
get: get:
summary: Return authenticated user's model summary: Return authenticated user's model
security:
- oauth2:
- read:users
- read:users:name
- read:users:groups
- read:users:activity
- read:servers
- read:roles:users
- admin:auth_state
- admin:server_state
responses: responses:
"200": '200':
description: The authenticated user's model is returned. description: The authenticated user's model is returned.
schema: schema:
$ref: "#/definitions/User" $ref: '#/definitions/User'
/groups: /groups:
get: get:
summary: List groups summary: List groups
security:
- oauth2:
- read:groups
- read:groups:name
- read:roles:groups
parameters:
- name: offset
in: query
required: false
type: number
description: |
Return a number of groups starting at the specified offset.
Can be used with limit to paginate.
If unspecified, return all groups.
- name: limit
in: query
required: false
type: number
description: |
Return a finite number of groups.
Can be used with offset to paginate.
If unspecified, use api_page_default_limit.
responses: responses:
"200": '200':
description: The list of groups description: The list of groups
schema: schema:
type: array type: array
items: items:
$ref: "#/definitions/Group" $ref: '#/definitions/Group'
/groups/{name}: /groups/{name}:
get: get:
summary: Get a group by name summary: Get a group by name
security:
- oauth2:
- read:groups
- read:groups:name
- read:roles:groups
parameters: parameters:
- name: name - name: name
description: group name description: group name
@@ -636,15 +428,12 @@ paths:
required: true required: true
type: string type: string
responses: responses:
"200": '200':
description: The group model description: The group model
schema: schema:
$ref: "#/definitions/Group" $ref: '#/definitions/Group'
post: post:
summary: Create a group summary: Create a group
security:
- oauth2:
- admin:groups
parameters: parameters:
- name: name - name: name
description: group name description: group name
@@ -652,15 +441,12 @@ paths:
required: true required: true
type: string type: string
responses: responses:
"201": '201':
description: The group has been created description: The group has been created
schema: schema:
$ref: "#/definitions/Group" $ref: '#/definitions/Group'
delete: delete:
summary: Delete a group summary: Delete a group
security:
- oauth2:
- admin:groups
parameters: parameters:
- name: name - name: name
description: group name description: group name
@@ -668,14 +454,11 @@ paths:
required: true required: true
type: string type: string
responses: responses:
"204": '204':
description: The group has been deleted description: The group has been deleted
/groups/{name}/users: /groups/{name}/users:
post: post:
summary: Add users to a group summary: Add users to a group
security:
- oauth2:
- groups
parameters: parameters:
- name: name - name: name
description: group name description: group name
@@ -695,15 +478,12 @@ paths:
items: items:
type: string type: string
responses: responses:
"200": '200':
description: The users have been added to the group description: The users have been added to the group
schema: schema:
$ref: "#/definitions/Group" $ref: '#/definitions/Group'
delete: delete:
summary: Remove users from a group summary: Remove users from a group
security:
- oauth2:
- groups
parameters: parameters:
- name: name - name: name
description: group name description: group name
@@ -723,31 +503,21 @@ paths:
items: items:
type: string type: string
responses: responses:
"200": '200':
description: The users have been removed from the group description: The users have been removed from the group
/services: /services:
get: get:
summary: List services summary: List services
security:
- oauth2:
- read:services
- read:services:name
- read:roles:services
responses: responses:
"200": '200':
description: The service list description: The service list
schema: schema:
type: array type: array
items: items:
$ref: "#/definitions/Service" $ref: '#/definitions/Service'
/services/{name}: /services/{name}:
get: get:
summary: Get a service by name summary: Get a service by name
security:
- oauth2:
- read:services
- read:services:name
- read:roles:services
parameters: parameters:
- name: name - name: name
description: service name description: service name
@@ -755,65 +525,33 @@ paths:
required: true required: true
type: string type: string
responses: responses:
"200": '200':
description: The Service model description: The Service model
schema: schema:
$ref: "#/definitions/Service" $ref: '#/definitions/Service'
/proxy: /proxy:
get: get:
summary: Get the proxy's routing table summary: Get the proxy's routing table
description: description: A convenience alias for getting the routing table directly from the proxy
A convenience alias for getting the routing table directly from
the proxy
security:
- oauth2:
- proxy
parameters:
- name: offset
in: query
required: false
type: number
description: |
Return a number of routes starting at the given offset.
Can be used with limit to paginate.
If unspecified, return all routes.
- name: limit
in: query
requred: false
type: number
description: |
Return a finite number of routes.
Can be used with offset to paginate.
If unspecified, use api_page_default_limit
responses: responses:
"200": '200':
description: Routing table description: Routing table
schema: schema:
type: object type: object
description: description: configurable-http-proxy routing table (see configurable-http-proxy docs for details)
configurable-http-proxy routing table (see configurable-http-proxy
docs for details)
post: post:
summary: Force the Hub to sync with the proxy summary: Force the Hub to sync with the proxy
security:
- oauth2:
- proxy
responses: responses:
"200": '200':
description: Success description: Success
patch: patch:
summary: Notify the Hub about a new proxy summary: Notify the Hub about a new proxy
description: Notifies the Hub of a new proxy to use. description: Notifies the Hub of a new proxy to use.
security:
- oauth2:
- proxy
parameters: parameters:
- name: body - name: body
in: body in: body
required: true required: true
description: description: Any values that have changed for the new proxy. All keys are optional.
Any values that have changed for the new proxy. All keys are
optional.
schema: schema:
type: object type: object
properties: properties:
@@ -830,7 +568,7 @@ paths:
type: string type: string
description: CONFIGPROXY_AUTH_TOKEN for the new proxy description: CONFIGPROXY_AUTH_TOKEN for the new proxy
responses: responses:
"200": '200':
description: Success description: Success
/authorizations/token: /authorizations/token:
post: post:
@@ -841,9 +579,6 @@ paths:
in the JSON request body. in the JSON request body.
Logging in via this method is only available when the active Authenticator Logging in via this method is only available when the active Authenticator
accepts passwords (e.g. not OAuth). accepts passwords (e.g. not OAuth).
security:
- oauth2:
- tokens
parameters: parameters:
- name: credentials - name: credentials
in: body in: body
@@ -855,7 +590,7 @@ paths:
password: password:
type: string type: string
responses: responses:
"200": '200':
description: The new API token description: The new API token
schema: schema:
type: object type: object
@@ -863,30 +598,25 @@ paths:
token: token:
type: string type: string
description: The new API token. description: The new API token.
"403": '403':
description: The user can not be authenticated. description: The user can not be authenticated.
/authorizations/token/{token}: /authorizations/token/{token}:
get: get:
summary: Identify a user or service from an API token summary: Identify a user or service from an API token
security:
- oauth2:
- (noscope)
parameters: parameters:
- name: token - name: token
in: path in: path
required: true required: true
type: string type: string
responses: responses:
"200": '200':
description: The user or service identified by the API token description: The user or service identified by the API token
"404": '404':
description: A user or service is not found. description: A user or service is not found.
/authorizations/cookie/{cookie_name}/{cookie_value}: /authorizations/cookie/{cookie_name}/{cookie_value}:
get: get:
summary: Identify a user from a cookie summary: Identify a user from a cookie
description: description: Used by single-user notebook servers to hand off cookie authentication to the Hub
Used by single-user notebook servers to hand off cookie authentication
to the Hub
parameters: parameters:
- name: cookie_name - name: cookie_name
in: path in: path
@@ -897,16 +627,15 @@ paths:
required: true required: true
type: string type: string
responses: responses:
"200": '200':
description: The user identified by the cookie description: The user identified by the cookie
schema: schema:
$ref: "#/definitions/User" $ref: '#/definitions/User'
"404": '404':
description: A user is not found. description: A user is not found.
deprecated: true # minrk: lets not add a scope for this, lets remove it
/oauth2/authorize: /oauth2/authorize:
get: get:
summary: "OAuth 2.0 authorize endpoint" summary: 'OAuth 2.0 authorize endpoint'
description: | description: |
Redirect users to this URL to begin the OAuth process. Redirect users to this URL to begin the OAuth process.
It is not an API endpoint. It is not an API endpoint.
@@ -932,9 +661,9 @@ paths:
required: true required: true
type: string type: string
responses: responses:
"200": '200':
description: Success description: Success
"400": '400':
description: OAuth2Error description: OAuth2Error
/oauth2/token: /oauth2/token:
post: post:
@@ -971,7 +700,7 @@ paths:
required: true required: true
type: string type: string
responses: responses:
"200": '200':
description: JSON response including the token description: JSON response including the token
schema: schema:
type: object type: object
@@ -985,9 +714,6 @@ paths:
/shutdown: /shutdown:
post: post:
summary: Shutdown the Hub summary: Shutdown the Hub
security:
- oauth2:
- shutdown
parameters: parameters:
- name: body - name: body
in: body in: body
@@ -996,18 +722,14 @@ paths:
properties: properties:
proxy: proxy:
type: boolean type: boolean
description: description: Whether the proxy should be shutdown as well (default from Hub config)
Whether the proxy should be shutdown as well (default from
Hub config)
servers: servers:
type: boolean type: boolean
description: description: Whether users' notebook servers should be shutdown as well (default from Hub config)
Whether users' notebook servers should be shutdown as well
(default from Hub config)
responses: responses:
"202": '202':
description: Shutdown successful description: Shutdown successful
"400": '400':
description: Unexpeced value for proxy or servers description: Unexpeced value for proxy or servers
# Descriptions of common responses # Descriptions of common responses
responses: responses:
@@ -1025,11 +747,6 @@ definitions:
admin: admin:
type: boolean type: boolean
description: Whether the user is an admin description: Whether the user is an admin
roles:
type: array
description: The names of roles this user has
items:
type: string
groups: groups:
type: array type: array
description: The names of groups where this user is a member description: The names of groups where this user is a member
@@ -1050,21 +767,13 @@ definitions:
type: array type: array
description: The active servers for this user. description: The active servers for this user.
items: items:
$ref: "#/definitions/Server" $ref: '#/definitions/Server'
auth_state:
type: string
#TODO: will there be predefined states? Should it rather be object instead of string?
description:
Authentication state of the user. Only available with admin:users:auth_state
scope. None otherwise.
Server: Server:
type: object type: object
properties: properties:
name: name:
type: string type: string
description: description: The server's name. The user's default server has an empty name ('')
The server's name. The user's default server has an empty name
('')
ready: ready:
type: boolean type: boolean
description: | description: |
@@ -1095,15 +804,10 @@ definitions:
description: UTC timestamp last-seen activity on this server. description: UTC timestamp last-seen activity on this server.
state: state:
type: object type: object
description: description: Arbitrary internal state from this server's spawner. Only available on the hub's users list or get-user-by-name method, and only if a hub admin. None otherwise.
Arbitrary internal state from this server's spawner. Only available
on the hub's users list or get-user-by-name method, and only with admin:users:server_state
scope. None otherwise.
user_options: user_options:
type: object type: object
description: description: User specified options for the user's spawned instance of a single-user server.
User specified options for the user's spawned instance of a single-user
server.
Group: Group:
type: object type: object
properties: properties:
@@ -1115,11 +819,6 @@ definitions:
description: The names of users who are members of this group description: The names of users who are members of this group
items: items:
type: string type: string
roles:
type: array
description: The names of roles this group has
items:
type: string
Service: Service:
type: object type: object
properties: properties:
@@ -1129,11 +828,6 @@ definitions:
admin: admin:
type: boolean type: boolean
description: Whether the service is an admin description: Whether the service is an admin
roles:
type: array
description: The names of roles this service has
items:
type: string
url: url:
type: string type: string
description: The internal url where the service is running description: The internal url where the service is running
@@ -1158,9 +852,7 @@ definitions:
properties: properties:
token: token:
type: string type: string
description: description: The token itself. Only present in responses to requests for a new token.
The token itself. Only present in responses to requests for a
new token.
id: id:
type: string type: string
description: The id of the API token. Used for modifying or deleting the token. description: The id of the API token. Used for modifying or deleting the token.
@@ -1170,16 +862,9 @@ definitions:
service: service:
type: string type: string
description: The service that owns the token (undefined of owned by a user) description: The service that owns the token (undefined of owned by a user)
roles:
type: array
description: The names of roles this token has
items:
type: string
note: note:
type: string type: string
description: description: A note about the token, typically describing what it was created for.
A note about the token, typically describing what it was created
for.
created: created:
type: string type: string
format: date-time format: date-time

View File

@@ -18,7 +18,7 @@ information on:
- learning more about JupyterHub's API - learning more about JupyterHub's API
The same JupyterHub API spec, as found here, is available in an interactive form The same JupyterHub API spec, as found here, is available in an interactive form
`here (on swagger's petstore) <https://petstore3.swagger.io/?url=https://raw.githubusercontent.com/jupyterhub/jupyterhub/HEAD/docs/rest-api.yml#!/default>`__. `here (on swagger's petstore) <http://petstore.swagger.io/?url=https://raw.githubusercontent.com/jupyterhub/jupyterhub/master/docs/rest-api.yml#!/default>`__.
The `OpenAPI Initiative`_ (fka Swagger™) is a project used to describe The `OpenAPI Initiative`_ (fka Swagger™) is a project used to describe
and document RESTful APIs. and document RESTful APIs.

File diff suppressed because one or more lines are too long

View File

@@ -1,3 +1,4 @@
# -*- coding: utf-8 -*-
# #
import os import os
import sys import sys
@@ -18,20 +19,16 @@ extensions = [
'autodoc_traits', 'autodoc_traits',
'sphinx_copybutton', 'sphinx_copybutton',
'sphinx-jsonschema', 'sphinx-jsonschema',
'myst_parser', 'recommonmark',
] ]
myst_enable_extensions = [
'colon_fence',
'deflist',
]
# The master toctree document. # The master toctree document.
master_doc = 'index' master_doc = 'index'
# General information about the project. # General information about the project.
project = 'JupyterHub' project = u'JupyterHub'
copyright = '2016, Project Jupyter team' copyright = u'2016, Project Jupyter team'
author = 'Project Jupyter team' author = u'Project Jupyter team'
# Autopopulate version # Autopopulate version
from os.path import dirname from os.path import dirname
@@ -55,6 +52,11 @@ todo_include_todos = False
# Set the default role so we can use `foo` instead of ``foo`` # Set the default role so we can use `foo` instead of ``foo``
default_role = 'literal' default_role = 'literal'
# -- Source -------------------------------------------------------------
import recommonmark
from recommonmark.transform import AutoStructify
# -- Config ------------------------------------------------------------- # -- Config -------------------------------------------------------------
from jupyterhub.app import JupyterHub from jupyterhub.app import JupyterHub
from docutils import nodes from docutils import nodes
@@ -109,7 +111,9 @@ class HelpAllDirective(SphinxDirective):
def setup(app): def setup(app):
app.add_config_value('recommonmark_config', {'enable_eval_rst': True}, True)
app.add_css_file('custom.css') app.add_css_file('custom.css')
app.add_transform(AutoStructify)
app.add_directive('jupyterhub-generate-config', ConfigDirective) app.add_directive('jupyterhub-generate-config', ConfigDirective)
app.add_directive('jupyterhub-help-all', HelpAllDirective) app.add_directive('jupyterhub-help-all', HelpAllDirective)
@@ -146,8 +150,8 @@ latex_documents = [
( (
master_doc, master_doc,
'JupyterHub.tex', 'JupyterHub.tex',
'JupyterHub Documentation', u'JupyterHub Documentation',
'Project Jupyter team', u'Project Jupyter team',
'manual', 'manual',
) )
] ]
@@ -164,7 +168,7 @@ latex_documents = [
# One entry per manual page. List of tuples # One entry per manual page. List of tuples
# (source start file, name, description, authors, manual section). # (source start file, name, description, authors, manual section).
man_pages = [(master_doc, 'jupyterhub', 'JupyterHub Documentation', [author], 1)] man_pages = [(master_doc, 'jupyterhub', u'JupyterHub Documentation', [author], 1)]
# man_show_urls = False # man_show_urls = False
@@ -178,7 +182,7 @@ texinfo_documents = [
( (
master_doc, master_doc,
'JupyterHub', 'JupyterHub',
'JupyterHub Documentation', u'JupyterHub Documentation',
author, author,
'JupyterHub', 'JupyterHub',
'One line description of project.', 'One line description of project.',
@@ -215,7 +219,7 @@ if on_rtd:
# build both metrics and rest-api, since RTD doesn't run make # build both metrics and rest-api, since RTD doesn't run make
from subprocess import check_call as sh from subprocess import check_call as sh
sh(['make', 'metrics', 'rest-api', 'scopes'], cwd=docs) sh(['make', 'metrics', 'rest-api'], cwd=docs)
# -- Spell checking ------------------------------------------------------- # -- Spell checking -------------------------------------------------------

View File

@@ -13,7 +13,7 @@ Building documentation locally
We use `sphinx <http://sphinx-doc.org>`_ to build our documentation. It takes We use `sphinx <http://sphinx-doc.org>`_ to build our documentation. It takes
our documentation source files (written in `markdown our documentation source files (written in `markdown
<https://daringfireball.net/projects/markdown/>`_ or `reStructuredText <https://daringfireball.net/projects/markdown/>`_ or `reStructuredText
<https://www.sphinx-doc.org/en/master/usage/restructuredtext/basics.html>`_ & <http://www.sphinx-doc.org/en/master/usage/restructuredtext/basics.html>`_ &
stored under the ``docs/source`` directory) and converts it into various stored under the ``docs/source`` directory) and converts it into various
formats for people to read. To make sure the documentation you write or formats for people to read. To make sure the documentation you write or
change renders correctly, it is good practice to test it locally. change renders correctly, it is good practice to test it locally.

View File

@@ -6,8 +6,8 @@ We want you to contribute to JupyterHub in ways that are most exciting
& useful to you. We value documentation, testing, bug reporting & code equally, & useful to you. We value documentation, testing, bug reporting & code equally,
and are glad to have your contributions in whatever form you wish :) and are glad to have your contributions in whatever form you wish :)
Our `Code of Conduct <https://github.com/jupyter/governance/blob/HEAD/conduct/code_of_conduct.md>`_ Our `Code of Conduct <https://github.com/jupyter/governance/blob/master/conduct/code_of_conduct.md>`_
(`reporting guidelines <https://github.com/jupyter/governance/blob/HEAD/conduct/reporting_online.md>`_) (`reporting guidelines <https://github.com/jupyter/governance/blob/master/conduct/reporting_online.md>`_)
helps keep our community welcoming to as many people as possible. helps keep our community welcoming to as many people as possible.
.. toctree:: .. toctree::

View File

@@ -6,8 +6,8 @@ the community of users, contributors, and maintainers.
The goal is to communicate priorities and upcoming release plans. The goal is to communicate priorities and upcoming release plans.
It is not a aimed at limiting contributions to what is listed here. It is not a aimed at limiting contributions to what is listed here.
## Using the roadmap
## Using the roadmap
### Sharing Feedback on the Roadmap ### Sharing Feedback on the Roadmap
All of the community is encouraged to provide feedback as well as share new All of the community is encouraged to provide feedback as well as share new
@@ -22,17 +22,17 @@ maintainers will help identify what a good next step is for the issue.
When submitting an issue, think about what "next step" category best describes When submitting an issue, think about what "next step" category best describes
your issue: your issue:
- **now**, concrete/actionable step that is ready for someone to start work on. * **now**, concrete/actionable step that is ready for someone to start work on.
These might be items that have a link to an issue or more abstract like These might be items that have a link to an issue or more abstract like
"decrease typos and dead links in the documentation" "decrease typos and dead links in the documentation"
- **soon**, less concrete/actionable step that is going to happen soon, * **soon**, less concrete/actionable step that is going to happen soon,
discussions around the topic are coming close to an end at which point it can discussions around the topic are coming close to an end at which point it can
move into the "now" category move into the "now" category
- **later**, abstract ideas or tasks, need a lot of discussion or * **later**, abstract ideas or tasks, need a lot of discussion or
experimentation to shape the idea so that it can be executed. Can also experimentation to shape the idea so that it can be executed. Can also
contain concrete/actionable steps that have been postponed on purpose contain concrete/actionable steps that have been postponed on purpose
(these are steps that could be in "now" but the decision was taken to work on (these are steps that could be in "now" but the decision was taken to work on
them later) them later)
### Reviewing and Updating the Roadmap ### Reviewing and Updating the Roadmap
@@ -47,8 +47,8 @@ For those please create a
The roadmap should give the reader an idea of what is happening next, what needs The roadmap should give the reader an idea of what is happening next, what needs
input and discussion before it can happen and what has been postponed. input and discussion before it can happen and what has been postponed.
## The roadmap proper
## The roadmap proper
### Project vision ### Project vision
JupyterHub is a dependable tool used by humans that reduces the complexity of JupyterHub is a dependable tool used by humans that reduces the complexity of
@@ -58,8 +58,8 @@ creating the environment in which a piece of software can be executed.
These "Now" items are considered active areas of focus for the project: These "Now" items are considered active areas of focus for the project:
- HubShare - a sharing service for use with JupyterHub. * HubShare - a sharing service for use with JupyterHub.
- Users should be able to: * Users should be able to:
- Push a project to other users. - Push a project to other users.
- Get a checkout of a project from other users. - Get a checkout of a project from other users.
- Push updates to a published project. - Push updates to a published project.
@@ -72,17 +72,19 @@ These "Now" items are considered active areas of focus for the project:
- Adding/removing a user to/from a team gives/removes them access to all projects that team has access to. - Adding/removing a user to/from a team gives/removes them access to all projects that team has access to.
- Build other services, such as static HTML publishing and dashboarding on top of these things. - Build other services, such as static HTML publishing and dashboarding on top of these things.
### Soon ### Soon
These "Soon" items are under discussion. Once an item reaches the point of an These "Soon" items are under discussion. Once an item reaches the point of an
actionable plan, the item will be moved to the "Now" section. Typically, actionable plan, the item will be moved to the "Now" section. Typically,
these will be moved at a future review of the roadmap. these will be moved at a future review of the roadmap.
- resource monitoring and management: * resource monitoring and management:
- (prometheus?) API for resource monitoring - (prometheus?) API for resource monitoring
- tracking activity on single-user servers instead of the proxy - tracking activity on single-user servers instead of the proxy
- notes and activity tracking per API token - notes and activity tracking per API token
### Later ### Later
The "Later" items are things that are at the back of the project's mind. At this The "Later" items are things that are at the back of the project's mind. At this

View File

@@ -1,7 +1,10 @@
Eventlogging and Telemetry Eventlogging and Telemetry
========================== ==========================
JupyterHub can be configured to record structured events from a running server using Jupyter's `Telemetry System`_. The types of events that JupyterHub emits are defined by `JSON schemas`_ listed at the bottom of this page_. JupyterHub can be configured to record structured events from a running server using Jupyter's `Telemetry System`_. The types of events that JupyterHub emits are defined by `JSON schemas`_ listed below_
emitted as JSON data, defined and validated by the JSON schemas listed below.
.. _logging: https://docs.python.org/3/library/logging.html .. _logging: https://docs.python.org/3/library/logging.html
.. _`Telemetry System`: https://github.com/jupyter/telemetry .. _`Telemetry System`: https://github.com/jupyter/telemetry
@@ -35,7 +38,8 @@ Here's a basic example:
The output is a file, ``"event.log"``, with events recorded as JSON data. The output is a file, ``"event.log"``, with events recorded as JSON data.
.. _page:
.. _below:
Event schemas Event schemas
------------- -------------

View File

@@ -8,20 +8,18 @@ high performance computing.
Please submit pull requests to update information or to add new institutions or uses. Please submit pull requests to update information or to add new institutions or uses.
## Academic Institutions, Research Labs, and Supercomputer Centers ## Academic Institutions, Research Labs, and Supercomputer Centers
### University of California Berkeley ### University of California Berkeley
- [BIDS - Berkeley Institute for Data Science](https://bids.berkeley.edu/) - [BIDS - Berkeley Institute for Data Science](https://bids.berkeley.edu/)
- [Teaching with Jupyter notebooks and JupyterHub](https://bids.berkeley.edu/resources/videos/teaching-ipythonjupyter-notebooks-and-jupyterhub) - [Teaching with Jupyter notebooks and JupyterHub](https://bids.berkeley.edu/resources/videos/teaching-ipythonjupyter-notebooks-and-jupyterhub)
- [Data 8](http://data8.org/) - [Data 8](http://data8.org/)
- [GitHub organization](https://github.com/data-8) - [GitHub organization](https://github.com/data-8)
- [NERSC](http://www.nersc.gov/) - [NERSC](http://www.nersc.gov/)
- [Press release on Jupyter and Cori](http://www.nersc.gov/news-publications/nersc-news/nersc-center-news/2016/jupyter-notebooks-will-open-up-new-possibilities-on-nerscs-cori-supercomputer/) - [Press release on Jupyter and Cori](http://www.nersc.gov/news-publications/nersc-news/nersc-center-news/2016/jupyter-notebooks-will-open-up-new-possibilities-on-nerscs-cori-supercomputer/)
- [Moving and sharing data](https://www.nersc.gov/assets/Uploads/03-MovingAndSharingData-Cholia.pdf) - [Moving and sharing data](https://www.nersc.gov/assets/Uploads/03-MovingAndSharingData-Cholia.pdf)
@@ -30,7 +28,7 @@ Please submit pull requests to update information or to add new institutions or
### University of California Davis ### University of California Davis
- [Spinning up multiple Jupyter Notebooks on AWS for a tutorial](https://github.com/mblmicdiv/course2017/blob/HEAD/exercises/sourmash-setup.md) - [Spinning up multiple Jupyter Notebooks on AWS for a tutorial](https://github.com/mblmicdiv/course2017/blob/master/exercises/sourmash-setup.md)
Although not technically a JupyterHub deployment, this tutorial setup Although not technically a JupyterHub deployment, this tutorial setup
may be helpful to others in the Jupyter community. may be helpful to others in the Jupyter community.
@@ -61,13 +59,6 @@ easy to do with RStudio too.
- [jupyterhub-deploy-teaching](https://github.com/jupyterhub/jupyterhub-deploy-teaching) based on work by Brian Granger for Cal Poly's Data Science 301 Course - [jupyterhub-deploy-teaching](https://github.com/jupyterhub/jupyterhub-deploy-teaching) based on work by Brian Granger for Cal Poly's Data Science 301 Course
### Chameleon
[Chameleon](https://www.chameleoncloud.org) is a NSF-funded configurable experimental environment for large-scale computer science systems research with [bare metal reconfigurability](https://chameleoncloud.readthedocs.io/en/latest/technical/baremetal.html). Chameleon users utilize JupyterHub to document and reproduce their complex CISE and networking experiments.
- [Shared JupyterHub](https://jupyter.chameleoncloud.org): provides a common "workbench" environment for any Chameleon user.
- [Trovi](https://www.chameleoncloud.org/experiment/share): a sharing portal of experiments, tutorials, and examples, which users can launch as a dedicated isolated environments on Chameleon's JupyterHub.
### Clemson University ### Clemson University
- Advanced Computing - Advanced Computing
@@ -76,7 +67,6 @@ easy to do with RStudio too.
### University of Colorado Boulder ### University of Colorado Boulder
- (CU Research Computing) CURC - (CU Research Computing) CURC
- [JupyterHub User Guide](https://www.rc.colorado.edu/support/user-guide/jupyterhub.html) - [JupyterHub User Guide](https://www.rc.colorado.edu/support/user-guide/jupyterhub.html)
- Slurm job dispatched on Crestone compute cluster - Slurm job dispatched on Crestone compute cluster
- log troubleshooting - log troubleshooting
@@ -135,7 +125,6 @@ easy to do with RStudio too.
### University of California San Diego ### University of California San Diego
- San Diego Supercomputer Center - Andrea Zonca - San Diego Supercomputer Center - Andrea Zonca
- [Deploy JupyterHub on a Supercomputer with SSH](https://zonca.github.io/2017/05/jupyterhub-hpc-batchspawner-ssh.html) - [Deploy JupyterHub on a Supercomputer with SSH](https://zonca.github.io/2017/05/jupyterhub-hpc-batchspawner-ssh.html)
- [Run Jupyterhub on a Supercomputer](https://zonca.github.io/2015/04/jupyterhub-hpc.html) - [Run Jupyterhub on a Supercomputer](https://zonca.github.io/2015/04/jupyterhub-hpc.html)
- [Deploy JupyterHub on a VM for a Workshop](https://zonca.github.io/2016/04/jupyterhub-sdsc-cloud.html) - [Deploy JupyterHub on a VM for a Workshop](https://zonca.github.io/2016/04/jupyterhub-sdsc-cloud.html)
@@ -154,9 +143,9 @@ easy to do with RStudio too.
- [Teaching with JupyterHub and nbgrader](http://kristenthyng.com/blog/2016/09/07/jupyterhub+nbgrader/) - [Teaching with JupyterHub and nbgrader](http://kristenthyng.com/blog/2016/09/07/jupyterhub+nbgrader/)
### Elucidata ### Elucidata
- What's new in Jupyter Notebooks @[Elucidata](https://elucidata.io/):
- What's new in Jupyter Notebooks @[Elucidata](https://elucidata.io/): - Using Jupyter Notebooks with Jupyterhub on GCP, managed by GKE
- Using Jupyter Notebooks with Jupyterhub on GCP, managed by GKE - https://medium.com/elucidata/why-you-should-be-using-a-jupyter-notebook-8385a4ccd93d - https://medium.com/elucidata/why-you-should-be-using-a-jupyter-notebook-8385a4ccd93d
## Service Providers ## Service Providers
@@ -186,6 +175,7 @@ easy to do with RStudio too.
- [Deploying JupyterHub on Hadoop](https://jupyterhub-on-hadoop.readthedocs.io) - [Deploying JupyterHub on Hadoop](https://jupyterhub-on-hadoop.readthedocs.io)
## Miscellaneous ## Miscellaneous
- https://medium.com/@ybarraud/setting-up-jupyterhub-with-sudospawner-and-anaconda-844628c0dbee#.rm3yt87e1 - https://medium.com/@ybarraud/setting-up-jupyterhub-with-sudospawner-and-anaconda-844628c0dbee#.rm3yt87e1

View File

@@ -9,6 +9,7 @@ with an account and password on the system will be allowed to login.
You can restrict which users are allowed to login with a set, You can restrict which users are allowed to login with a set,
`Authenticator.allowed_users`: `Authenticator.allowed_users`:
```python ```python
c.Authenticator.allowed_users = {'mal', 'zoe', 'inara', 'kaylee'} c.Authenticator.allowed_users = {'mal', 'zoe', 'inara', 'kaylee'}
``` ```
@@ -18,30 +19,22 @@ started.
## Configure admins (`admin_users`) ## Configure admins (`admin_users`)
```{note}
As of JupyterHub 2.0, the full permissions of `admin_users`
should not be required.
Instead, you can assign [roles][] to users or groups
with only the scopes they require.
```
Admin users of JupyterHub, `admin_users`, can add and remove users from Admin users of JupyterHub, `admin_users`, can add and remove users from
the user `allowed_users` set. `admin_users` can take actions on other users' the user `allowed_users` set. `admin_users` can take actions on other users'
behalf, such as stopping and restarting their servers. behalf, such as stopping and restarting their servers.
A set of initial admin users, `admin_users` can be configured as follows: A set of initial admin users, `admin_users` can configured be as follows:
```python ```python
c.Authenticator.admin_users = {'mal', 'zoe'} c.Authenticator.admin_users = {'mal', 'zoe'}
``` ```
Users in the admin set are automatically added to the user `allowed_users` set, Users in the admin set are automatically added to the user `allowed_users` set,
if they are not already present. if they are not already present.
Each authenticator may have different ways of determining whether a user is an Each authenticator may have different ways of determining whether a user is an
administrator. By default JupyterHub uses the PAMAuthenticator which provides the administrator. By default JupyterHub use the PAMAuthenticator which provide the
`admin_groups` option and can set administrator status based on a user `admin_groups` option and can determine administrator status base on a user
group. For example we can let any user in the `wheel` group be admin: groups. For example we can let any users in the `wheel` group be admin:
```python ```python
c.PAMAuthenticator.admin_groups = {'wheel'} c.PAMAuthenticator.admin_groups = {'wheel'}
@@ -49,10 +42,10 @@ c.PAMAuthenticator.admin_groups = {'wheel'}
## Give admin access to other users' notebook servers (`admin_access`) ## Give admin access to other users' notebook servers (`admin_access`)
Since the default `JupyterHub.admin_access` setting is `False`, the admins Since the default `JupyterHub.admin_access` setting is False, the admins
do not have permission to log in to the single user notebook servers do not have permission to log in to the single user notebook servers
owned by _other users_. If `JupyterHub.admin_access` is set to `True`, owned by *other users*. If `JupyterHub.admin_access` is set to True,
then admins have permission to log in _as other users_ on their then admins have permission to log in *as other users* on their
respective machines, for debugging. **As a courtesy, you should make respective machines, for debugging. **As a courtesy, you should make
sure your users know if admin_access is enabled.** sure your users know if admin_access is enabled.**
@@ -60,8 +53,8 @@ sure your users know if admin_access is enabled.**
Users can be added to and removed from the Hub via either the admin Users can be added to and removed from the Hub via either the admin
panel or the REST API. When a user is **added**, the user will be panel or the REST API. When a user is **added**, the user will be
automatically added to the `allowed_users` set and database. Restarting the Hub automatically added to the allowed users set and database. Restarting the Hub
will not require manually updating the `allowed_users` set in your config file, will not require manually updating the allowed users set in your config file,
as the users will be loaded from the database. as the users will be loaded from the database.
After starting the Hub once, it is not sufficient to **remove** a user After starting the Hub once, it is not sufficient to **remove** a user
@@ -98,7 +91,6 @@ JupyterHub's [OAuthenticator][] currently supports the following
popular services: popular services:
- Auth0 - Auth0
- Azure AD
- Bitbucket - Bitbucket
- CILogon - CILogon
- GitHub - GitHub
@@ -114,8 +106,8 @@ with any provider, is also available.
## Use DummyAuthenticator for testing ## Use DummyAuthenticator for testing
The `DummyAuthenticator` is a simple authenticator that The :class:`~jupyterhub.auth.DummyAuthenticator` is a simple authenticator that
allows for any username/password unless a global password has been set. If allows for any username/password unless if a global password has been set. If
set, it will allow for any username as long as the correct password is provided. set, it will allow for any username as long as the correct password is provided.
To set a global password, add this to the config file: To set a global password, add this to the config file:
@@ -123,5 +115,5 @@ To set a global password, add this to the config file:
c.DummyAuthenticator.password = "some_password" c.DummyAuthenticator.password = "some_password"
``` ```
[pam]: https://en.wikipedia.org/wiki/Pluggable_authentication_module [PAM]: https://en.wikipedia.org/wiki/Pluggable_authentication_module
[oauthenticator]: https://github.com/jupyterhub/oauthenticator [OAuthenticator]: https://github.com/jupyterhub/oauthenticator

View File

@@ -44,7 +44,7 @@ jupyterhub -f /etc/jupyterhub/jupyterhub_config.py
``` ```
The IPython documentation provides additional information on the The IPython documentation provides additional information on the
[config system](http://ipython.readthedocs.io/en/stable/development/config.html) [config system](http://ipython.readthedocs.io/en/stable/development/config)
that Jupyter uses. that Jupyter uses.
## Configure using command line options ## Configure using command line options
@@ -56,18 +56,18 @@ To display all command line options that are available for configuration:
``` ```
Configuration using the command line options is done when launching JupyterHub. Configuration using the command line options is done when launching JupyterHub.
For example, to start JupyterHub on `10.0.1.2:443` with https, you For example, to start JupyterHub on ``10.0.1.2:443`` with https, you
would enter: would enter:
```bash ```bash
jupyterhub --ip 10.0.1.2 --port 443 --ssl-key my_ssl.key --ssl-cert my_ssl.cert jupyterhub --ip 10.0.1.2 --port 443 --ssl-key my_ssl.key --ssl-cert my_ssl.cert
``` ```
All configurable options may technically be set on the command line, All configurable options may technically be set on the command-line,
though some are inconvenient to type. To set a particular configuration though some are inconvenient to type. To set a particular configuration
parameter, `c.Class.trait`, you would use the command line option, parameter, `c.Class.trait`, you would use the command line option,
`--Class.trait`, when starting JupyterHub. For example, to configure the `--Class.trait`, when starting JupyterHub. For example, to configure the
`c.Spawner.notebook_dir` trait from the command line, use the `c.Spawner.notebook_dir` trait from the command-line, use the
`--Spawner.notebook_dir` option: `--Spawner.notebook_dir` option:
```bash ```bash
@@ -88,12 +88,12 @@ meant as illustration, are:
## Run the proxy separately ## Run the proxy separately
This is _not_ strictly necessary, but useful in many cases. If you This is *not* strictly necessary, but useful in many cases. If you
use a custom proxy (e.g. Traefik), this is also not needed. use a custom proxy (e.g. Traefik), this also not needed.
Connections to user servers go through the proxy, and _not_ the hub Connections to user servers go through the proxy, and *not* the hub
itself. If the proxy stays running when the hub restarts (for itself. If the proxy stays running when the hub restarts (for
maintenance, re-configuration, etc.), then user connections are not maintenance, re-configuration, etc.), then use connections are not
interrupted. For simplicity, by default the hub starts the proxy interrupted. For simplicity, by default the hub starts the proxy
automatically, so if the hub restarts, the proxy restarts, and user automatically, so if the hub restarts, the proxy restarts, and user
connections are interrupted. It is easy to run the proxy separately, connections are interrupted. It is easy to run the proxy separately,

View File

@@ -1,6 +1,7 @@
# Frequently asked questions # Frequently asked questions
## How do I share links to notebooks?
### How do I share links to notebooks?
In short, where you see `/user/name/notebooks/foo.ipynb` use `/hub/user-redirect/notebooks/foo.ipynb` (replace `/user/name` with `/hub/user-redirect`). In short, where you see `/user/name/notebooks/foo.ipynb` use `/hub/user-redirect/notebooks/foo.ipynb` (replace `/user/name` with `/hub/user-redirect`).
@@ -10,9 +11,9 @@ Your first instinct might be to copy the URL you see in the browser,
e.g. `hub.jupyter.org/user/yourname/notebooks/coolthing.ipynb`. e.g. `hub.jupyter.org/user/yourname/notebooks/coolthing.ipynb`.
However, let's break down what this URL means: However, let's break down what this URL means:
`hub.jupyter.org/user/yourname/` is the URL prefix handled by _your server_, `hub.jupyter.org/user/yourname/` is the URL prefix handled by *your server*,
which means that sharing this URL is asking the person you share the link with which means that sharing this URL is asking the person you share the link with
to come to _your server_ and look at the exact same file. to come to *your server* and look at the exact same file.
In most circumstances, this is forbidden by permissions because the person you share with does not have access to your server. In most circumstances, this is forbidden by permissions because the person you share with does not have access to your server.
What actually happens when someone visits this URL will depend on whether your server is running and other factors. What actually happens when someone visits this URL will depend on whether your server is running and other factors.
@@ -21,12 +22,12 @@ A typical situation is that you have some shared or common filesystem,
such that the same path corresponds to the same document such that the same path corresponds to the same document
(either the exact same document or another copy of it). (either the exact same document or another copy of it).
Typically, what folks want when they do sharing like this Typically, what folks want when they do sharing like this
is for each visitor to open the same file _on their own server_, is for each visitor to open the same file *on their own server*,
so Breq would open `/user/breq/notebooks/foo.ipynb` and so Breq would open `/user/breq/notebooks/foo.ipynb` and
Seivarden would open `/user/seivarden/notebooks/foo.ipynb`, etc. Seivarden would open `/user/seivarden/notebooks/foo.ipynb`, etc.
JupyterHub has a special URL that does exactly this! JupyterHub has a special URL that does exactly this!
It's called `/hub/user-redirect/...`. It's called `/hub/user-redirect/...` and after the visitor logs in,
So if you replace `/user/yourname` in your URL bar So if you replace `/user/yourname` in your URL bar
with `/hub/user-redirect` any visitor should get the same with `/hub/user-redirect` any visitor should get the same
URL on their own server, rather than visiting yours. URL on their own server, rather than visiting yours.

View File

@@ -11,30 +11,30 @@ Yes! JupyterHub has been used at-scale for large pools of users, as well
as complex and high-performance computing. For example, UC Berkeley uses as complex and high-performance computing. For example, UC Berkeley uses
JupyterHub for its Data Science Education Program courses (serving over JupyterHub for its Data Science Education Program courses (serving over
3,000 students). The Pangeo project uses JupyterHub to provide access 3,000 students). The Pangeo project uses JupyterHub to provide access
to scalable cloud computing with Dask. JupyterHub is stable and customizable to scalable cloud computing with Dask. JupyterHub is stable customizable
to the use-cases of large organizations. to the use-cases of large organizations.
### I keep hearing about Jupyter Notebook, JupyterLab, and now JupyterHub. Whats the difference? ### I keep hearing about Jupyter Notebook, JupyterLab, and now JupyterHub. Whats the difference?
Here is a quick breakdown of these three tools: Here is a quick breakdown of these three tools:
- **The Jupyter Notebook** is a document specification (the `.ipynb`) file that interweaves * **The Jupyter Notebook** is a document specification (the `.ipynb`) file that interweaves
narrative text with code cells and their outputs. It is also a graphical interface narrative text with code cells and their outputs. It is also a graphical interface
that allows users to edit these documents. There are also several other graphical interfaces that allows users to edit these documents. There are also several other graphical interfaces
that allow users to edit the `.ipynb` format (nteract, Jupyter Lab, Google Colab, Kaggle, etc). that allow users to edit the `.ipynb` format (nteract, Jupyter Lab, Google Colab, Kaggle, etc).
- **JupyterLab** is a flexible and extendible user interface for interactive computing. It * **JupyterLab** is a flexible and extendible user interface for interactive computing. It
has several extensions that are tailored for using Jupyter Notebooks, as well as extensions has several extensions that are tailored for using Jupyter Notebooks, as well as extensions
for other parts of the data science stack. for other parts of the data science stack.
- **JupyterHub** is an application that manages interactive computing sessions for **multiple users**. * **JupyterHub** is an application that manages interactive computing sessions for **multiple users**.
It also connects them with infrastructure those users wish to access. It can provide It also connects them with infrastructure those users wish to access. It can provide
remote access to Jupyter Notebooks and JupyterLab for many people. remote access to Jupyter Notebooks and Jupyter Lab for many people.
## For management ## For management
### Briefly, what problem does JupyterHub solve for us? ### Briefly, what problem does JupyterHub solve for us?
JupyterHub provides a shared platform for data science and collaboration. JupyterHub provides a shared platform for data science and collaboration.
It allows users to utilize familiar data science workflows (such as the scientific Python stack, It allows users to utilize familiar data science workflows (such as the scientific python stack,
the R tidyverse, and Jupyter Notebooks) on institutional infrastructure. It also allows administrators the R tidyverse, and Jupyter Notebooks) on institutional infrastructure. It also allows administrators
some control over access to resources, security, environments, and authentication. some control over access to resources, security, environments, and authentication.
@@ -50,20 +50,20 @@ scalable infrastructure, large datasets, and high-performance computing.
JupyterHub is used at a variety of institutions in academia, JupyterHub is used at a variety of institutions in academia,
industry, and government research labs. It is most-commonly used by two kinds of groups: industry, and government research labs. It is most-commonly used by two kinds of groups:
- Small teams (e.g., data science teams, research labs, or collaborative projects) to provide a * Small teams (e.g., data science teams, research labs, or collaborative projects) to provide a
shared resource for interactive computing, collaboration, and analytics. shared resource for interactive computing, collaboration, and analytics.
- Large teams (e.g., a department, a large class, or a large group of remote users) to provide * Large teams (e.g., a department, a large class, or a large group of remote users) to provide
access to organizational hardware, data, and analytics environments at scale. access to organizational hardware, data, and analytics environments at scale.
Here is a sample of organizations that use JupyterHub: Here are a sample of organizations that use JupyterHub:
- **Universities and colleges**: UC Berkeley, UC San Diego, Cal Poly SLO, Harvard University, University of Chicago, * **Universities and colleges**: UC Berkeley, UC San Diego, Cal Poly SLO, Harvard University, University of Chicago,
University of Oslo, University of Sheffield, Université Paris Sud, University of Versailles University of Oslo, University of Sheffield, Université Paris Sud, University of Versailles
- **Research laboratories**: NASA, NCAR, NOAA, the Large Synoptic Survey Telescope, Brookhaven National Lab, * **Research laboratories**: NASA, NCAR, NOAA, the Large Synoptic Survey Telescope, Brookhaven National Lab,
Minnesota Supercomputing Institute, ALCF, CERN, Lawrence Livermore National Laboratory Minnesota Supercomputing Institute, ALCF, CERN, Lawrence Livermore National Laboratory
- **Online communities**: Pangeo, Quantopian, mybinder.org, MathHub, Open Humans * **Online communities**: Pangeo, Quantopian, mybinder.org, MathHub, Open Humans
- **Computing infrastructure providers**: NERSC, San Diego Supercomputing Center, Compute Canada * **Computing infrastructure providers**: NERSC, San Diego Supercomputing Center, Compute Canada
- **Companies**: Capital One, SANDVIK code, Globus * **Companies**: Capital One, SANDVIK code, Globus
See the [Gallery of JupyterHub deployments](../gallery-jhub-deployments.md) for See the [Gallery of JupyterHub deployments](../gallery-jhub-deployments.md) for
a more complete list of JupyterHub deployments at institutions. a more complete list of JupyterHub deployments at institutions.
@@ -95,13 +95,14 @@ The most common way to set up a JupyterHub is to use a JupyterHub distribution,
and opinionated ways to set up a JupyterHub on particular kinds of infrastructure. The two distributions and opinionated ways to set up a JupyterHub on particular kinds of infrastructure. The two distributions
that we currently suggest are: that we currently suggest are:
- [Zero to JupyterHub for Kubernetes](https://z2jh.jupyter.org) is a scalable JupyterHub deployment and * [Zero to JupyterHub for Kubernetes](https://z2jh.jupyter.org) is a scalable JupyterHub deployment and
guide that runs on Kubernetes. Better for larger or dynamic user groups (50-10,000) or more complex guide that runs on Kubernetes. Better for larger or dynamic user groups (50-10,000) or more complex
compute/data needs. compute/data needs.
- [The Littlest JupyterHub](https://tljh.jupyter.org) is a lightweight JupyterHub that runs on a single * [The Littlest JupyterHub](https://tljh.jupyter.org) is a lightweight JupyterHub that runs on a single
single machine (in the cloud or under your desk). Better for smaller user groups (4-80) or more single machine (in the cloud or under your desk). Better for smaller usergroups (4-80) or more
lightweight computational resources. lightweight computational resources.
### Does JupyterHub run well in the cloud? ### Does JupyterHub run well in the cloud?
Yes - most deployments of JupyterHub are run via cloud infrastructure and on a variety of cloud providers. Yes - most deployments of JupyterHub are run via cloud infrastructure and on a variety of cloud providers.
@@ -122,9 +123,9 @@ The short answer: yes. JupyterHub as a standalone application has been battle-te
level for several years, and makes a number of "default" security decisions that are reasonable for most level for several years, and makes a number of "default" security decisions that are reasonable for most
users. users.
- For security considerations in the base JupyterHub application, * For security considerations in the base JupyterHub application,
[see the JupyterHub security page](https://jupyterhub.readthedocs.io/en/stable/reference/websecurity.html). [see the JupyterHub security page](https://jupyterhub.readthedocs.io/en/stable/reference/websecurity.html)
- For security considerations when deploying JupyterHub on Kubernetes, see the * For security considerations when deploying JupyterHub on Kubernetes, see the
[JupyterHub on Kubernetes security page](https://zero-to-jupyterhub.readthedocs.io/en/latest/security.html). [JupyterHub on Kubernetes security page](https://zero-to-jupyterhub.readthedocs.io/en/latest/security.html).
The longer answer: it depends on your deployment. Because JupyterHub is very flexible, it can be used The longer answer: it depends on your deployment. Because JupyterHub is very flexible, it can be used
@@ -136,13 +137,15 @@ If you are worried about security, don't hesitate to reach out to the JupyterHub
[Jupyter Community Forum](https://discourse.jupyter.org/c/jupyterhub). This community of practice has many [Jupyter Community Forum](https://discourse.jupyter.org/c/jupyterhub). This community of practice has many
individuals with experience running secure JupyterHub deployments. individuals with experience running secure JupyterHub deployments.
### Does JupyterHub provide computing or data infrastructure? ### Does JupyterHub provide computing or data infrastructure?
No - JupyterHub manages user sessions and can _control_ computing infrastructure, but it does not provide these No - JupyterHub manages user sessions and can *control* computing infrastructure, but it does not provide these
things itself. You are expected to run JupyterHub on your own infrastructure (local or in the cloud). Moreover, things itself. You are expected to run JupyterHub on your own infrastructure (local or in the cloud). Moreover,
JupyterHub has no internal concept of "data", but is designed to be able to communicate with data repositories JupyterHub has no internal concept of "data", but is designed to be able to communicate with data repositories
(again, either locally or remotely) for use within interactive computing sessions. (again, either locally or remotely) for use within interactive computing sessions.
### How do I manage users? ### How do I manage users?
JupyterHub offers a few options for managing your users. Upon setting up a JupyterHub, you can choose what JupyterHub offers a few options for managing your users. Upon setting up a JupyterHub, you can choose what
@@ -151,7 +154,7 @@ email address, or choose a username / password when they first log-in, or offloa
another service such as an organization's OAuth. another service such as an organization's OAuth.
The users of a JupyterHub are stored locally, and can be modified manually by an administrator of the JupyterHub. The users of a JupyterHub are stored locally, and can be modified manually by an administrator of the JupyterHub.
Moreover, the _active_ users on a JupyterHub can be found on the administrator's page. This page Moreover, the *active* users on a JupyterHub can be found on the administrator's page. This page
gives you the abiltiy to stop or restart kernels, inspect user filesystems, and even take over user gives you the abiltiy to stop or restart kernels, inspect user filesystems, and even take over user
sessions to assist them with debugging. sessions to assist them with debugging.
@@ -179,11 +182,12 @@ connect with other infrastructure tools (like Dask or Spark). This allows users
scalable or high-performance resources from within their JupyterHub sessions. The logic of scalable or high-performance resources from within their JupyterHub sessions. The logic of
how those resources are controlled is taken care of by the non-JupyterHub application. how those resources are controlled is taken care of by the non-JupyterHub application.
### Can JupyterHub be used with my high-performance computing resources? ### Can JupyterHub be used with my high-performance computing resources?
Yes - JupyterHub can provide access to many kinds of computing infrastructure. Yes - JupyterHub can provide access to many kinds of computing infrastructure.
Especially when combined with other open-source schedulers such as Dask, you can manage fairly Especially when combined with other open-source schedulers such as Dask, you can manage fairly
complex computing infrastructures from the interactive sessions of a JupyterHub. For example complex computing infrastructure from the interactive sessions of a JupyterHub. For example
[see the Dask HPC page](https://docs.dask.org/en/latest/setup/hpc.html). [see the Dask HPC page](https://docs.dask.org/en/latest/setup/hpc.html).
### How much resources do user sessions take? ### How much resources do user sessions take?
@@ -192,7 +196,7 @@ This is highly configurable by the administrator. If you wish for your users to
data analytics environments for prototyping and light data exploring, you can restrict their data analytics environments for prototyping and light data exploring, you can restrict their
memory and CPU based on the resources that you have available. If you'd like your JupyterHub memory and CPU based on the resources that you have available. If you'd like your JupyterHub
to serve as a gateway to high-performance compute or data resources, you may increase the to serve as a gateway to high-performance compute or data resources, you may increase the
resources available on user machines, or connect them with computing infrastructures elsewhere. resources available on user machines, or connect them with computing infrastructure elsewhere.
### Can I customize the look and feel of a JupyterHub? ### Can I customize the look and feel of a JupyterHub?
@@ -214,14 +218,16 @@ the technologies your JupyterHub will use (e.g., dev-ops knowledge with cloud co
In general, the base JupyterHub deployment is not the bottleneck for setup, it is connecting In general, the base JupyterHub deployment is not the bottleneck for setup, it is connecting
your JupyterHub with the various services and tools that you wish to provide to your users. your JupyterHub with the various services and tools that you wish to provide to your users.
### How well does JupyterHub scale? What are JupyterHub's limitations? ### How well does JupyterHub scale? What are JupyterHub's limitations?
JupyterHub works well at both a small scale (e.g., a single VM or machine) as well as a JupyterHub works well at both a small scale (e.g., a single VM or machine) as well as a
high scale (e.g., a scalable Kubernetes cluster). It can be used for teams as small as 2, and high scale (e.g., a scalable Kubernetes cluster). It can be used for teams as small a 2, and
for user bases as large as 10,000. The scalability of JupyterHub largely depends on the for user bases as large as 10,000. The scalability of JupyterHub largely depends on the
infrastructure on which it is deployed. JupyterHub has been designed to be lightweight and infrastructure on which it is deployed. JupyterHub has been designed to be lightweight and
flexible, so you can tailor your JupyterHub deployment to your needs. flexible, so you can tailor your JupyterHub deployment to your needs.
### Is JupyterHub resilient? What happens when a machine goes down? ### Is JupyterHub resilient? What happens when a machine goes down?
For JupyterHubs that are deployed in a containerized environment (e.g., Kubernetes), it is For JupyterHubs that are deployed in a containerized environment (e.g., Kubernetes), it is
@@ -249,7 +255,7 @@ share their results with one another.
JupyterHub also provides a computational framework to share computational narratives between JupyterHub also provides a computational framework to share computational narratives between
different levels of an organization. For example, data scientists can share Jupyter Notebooks different levels of an organization. For example, data scientists can share Jupyter Notebooks
rendered as [Voilà dashboards](https://voila.readthedocs.io/en/stable/) with those who are not rendered as [voila dashboards](https://voila.readthedocs.io/en/stable/) with those who are not
familiar with programming, or create publicly-available interactive analyses to allow others to familiar with programming, or create publicly-available interactive analyses to allow others to
interact with your work. interact with your work.

View File

@@ -11,7 +11,7 @@ This section will help you with basic proxy and network configuration to:
The Proxy's main IP address setting determines where JupyterHub is available to users. The Proxy's main IP address setting determines where JupyterHub is available to users.
By default, JupyterHub is configured to be available on all network interfaces By default, JupyterHub is configured to be available on all network interfaces
(`''`) on port 8000. _Note_: Use of `'*'` is discouraged for IP configuration; (`''`) on port 8000. *Note*: Use of `'*'` is discouraged for IP configuration;
instead, use of `'0.0.0.0'` is preferred. instead, use of `'0.0.0.0'` is preferred.
Changing the Proxy's main IP address and port can be done with the following Changing the Proxy's main IP address and port can be done with the following
@@ -43,7 +43,7 @@ port.
By default, this REST API listens on port 8001 of `localhost` only. By default, this REST API listens on port 8001 of `localhost` only.
The Hub service talks to the proxy via a REST API on a secondary port. The The Hub service talks to the proxy via a REST API on a secondary port. The
API URL can be configured separately to override the default settings. API URL can be configured separately and override the default settings.
### Set api_url ### Set api_url
@@ -74,7 +74,7 @@ The Hub service listens only on `localhost` (port 8081) by default.
The Hub needs to be accessible from both the proxy and all Spawners. The Hub needs to be accessible from both the proxy and all Spawners.
When spawning local servers, an IP address setting of `localhost` is fine. When spawning local servers, an IP address setting of `localhost` is fine.
If _either_ the Proxy _or_ (more likely) the Spawners will be remote or If *either* the Proxy *or* (more likely) the Spawners will be remote or
isolated in containers, the Hub must listen on an IP that is accessible. isolated in containers, the Hub must listen on an IP that is accessible.
```python ```python
@@ -82,13 +82,13 @@ c.JupyterHub.hub_ip = '10.0.1.4'
c.JupyterHub.hub_port = 54321 c.JupyterHub.hub_port = 54321
``` ```
**Added in 0.8:** The `c.JupyterHub.hub_connect_ip` setting is the IP address or **Added in 0.8:** The `c.JupyterHub.hub_connect_ip` setting is the ip address or
hostname that other services should use to connect to the Hub. A common hostname that other services should use to connect to the Hub. A common
configuration for, e.g. docker, is: configuration for, e.g. docker, is:
```python ```python
c.JupyterHub.hub_ip = '0.0.0.0' # listen on all interfaces c.JupyterHub.hub_ip = '0.0.0.0' # listen on all interfaces
c.JupyterHub.hub_connect_ip = '10.0.1.4' # IP as seen on the docker network. Can also be a hostname. c.JupyterHub.hub_connect_ip = '10.0.1.4' # ip as seen on the docker network. Can also be a hostname.
``` ```
## Adjusting the hub's URL ## Adjusting the hub's URL

View File

@@ -2,7 +2,7 @@
When working with JupyterHub, a **Service** is defined as a process When working with JupyterHub, a **Service** is defined as a process
that interacts with the Hub's REST API. A Service may perform a specific that interacts with the Hub's REST API. A Service may perform a specific
action or task. For example, shutting down individuals' single user or action or task. For example, shutting down individuals' single user
notebook servers that have been idle for some time is a good example of notebook servers that have been idle for some time is a good example of
a task that could be automated by a Service. Let's look at how the a task that could be automated by a Service. Let's look at how the
[jupyterhub_idle_culler][] script can be used as a Service. [jupyterhub_idle_culler][] script can be used as a Service.
@@ -93,40 +93,18 @@ In `jupyterhub_config.py`, add the following dictionary for the
c.JupyterHub.services = [ c.JupyterHub.services = [
{ {
'name': 'idle-culler', 'name': 'idle-culler',
'admin': True,
'command': [sys.executable, '-m', 'jupyterhub_idle_culler', '--timeout=3600'], 'command': [sys.executable, '-m', 'jupyterhub_idle_culler', '--timeout=3600'],
} }
] ]
c.JupyterHub.load_roles = [
{
"name": "list-and-cull", # name the role
"services": [
"idle-culler", # assign the service to this role
],
"scopes": [
# declare what permissions the service should have
"list:users", # list users
"read:users:activity", # read user last-activity
"admin:servers", # start/stop servers
],
}
]
``` ```
where: where:
- `command` indicates that the Service will be launched as a - `'admin': True` indicates that the Service has 'admin' permissions, and
- `'command'` indicates that the Service will be launched as a
subprocess, managed by the Hub. subprocess, managed by the Hub.
```{versionchanged} 2.0
Prior to 2.0, the idle-culler required 'admin' permissions.
It now needs the scopes:
- `list:users` to access the user list endpoint
- `read:users:activity` to read activity info
- `admin:servers` to start/stop servers
```
## Run `cull-idle` manually as a standalone script ## Run `cull-idle` manually as a standalone script
Now you can run your script by providing it Now you can run your script by providing it
@@ -136,8 +114,7 @@ interact with it.
This will run the idle culler service manually. It can be run as a standalone This will run the idle culler service manually. It can be run as a standalone
script anywhere with access to the Hub, and will periodically check for idle script anywhere with access to the Hub, and will periodically check for idle
servers and shut them down via the Hub's REST API. In order to shutdown the servers and shut them down via the Hub's REST API. In order to shutdown the
servers, the token given to `cull-idle` must have permission to list users servers, the token given to cull-idle must have admin privileges.
and admin their servers.
Generate an API token and store it in the `JUPYTERHUB_API_TOKEN` environment Generate an API token and store it in the `JUPYTERHUB_API_TOKEN` environment
variable. Run `jupyterhub_idle_culler` manually. variable. Run `jupyterhub_idle_culler` manually.

View File

@@ -1,8 +1,8 @@
# Spawners and single-user notebook servers # Spawners and single-user notebook servers
Since the single-user server is an instance of `jupyter notebook`, an entire separate Since the single-user server is an instance of `jupyter notebook`, an entire separate
multi-process application, there are many aspects of that server that can be configured, and a lot multi-process application, there are many aspect of that server can configure, and a lot of ways
of ways to express that configuration. to express that configuration.
At the JupyterHub level, you can set some values on the Spawner. The simplest of these is At the JupyterHub level, you can set some values on the Spawner. The simplest of these is
`Spawner.notebook_dir`, which lets you set the root directory for a user's server. This root `Spawner.notebook_dir`, which lets you set the root directory for a user's server. This root
@@ -14,7 +14,7 @@ expanded to the user's home directory.
c.Spawner.notebook_dir = '~/notebooks' c.Spawner.notebook_dir = '~/notebooks'
``` ```
You can also specify extra command line arguments to the notebook server with: You can also specify extra command-line arguments to the notebook server with:
```python ```python
c.Spawner.args = ['--debug', '--profile=PHYS131'] c.Spawner.args = ['--debug', '--profile=PHYS131']

Binary file not shown.

Before

Width:  |  Height:  |  Size: 446 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 483 KiB

View File

@@ -108,14 +108,6 @@ API Reference
api/index api/index
RBAC Reference
--------------
.. toctree::
:maxdepth: 2
rbac/index
Contributing Contributing
------------ ------------
@@ -123,8 +115,8 @@ We want you to contribute to JupyterHub in ways that are most exciting
& useful to you. We value documentation, testing, bug reporting & code equally, & useful to you. We value documentation, testing, bug reporting & code equally,
and are glad to have your contributions in whatever form you wish :) and are glad to have your contributions in whatever form you wish :)
Our `Code of Conduct <https://github.com/jupyter/governance/blob/HEAD/conduct/code_of_conduct.md>`_ Our `Code of Conduct <https://github.com/jupyter/governance/blob/master/conduct/code_of_conduct.md>`_
(`reporting guidelines <https://github.com/jupyter/governance/blob/HEAD/conduct/reporting_online.md>`_) (`reporting guidelines <https://github.com/jupyter/governance/blob/master/conduct/reporting_online.md>`_)
helps keep our community welcoming to as many people as possible. helps keep our community welcoming to as many people as possible.
.. toctree:: .. toctree::
@@ -155,4 +147,4 @@ Questions? Suggestions?
.. _JupyterHub: https://github.com/jupyterhub/jupyterhub .. _JupyterHub: https://github.com/jupyterhub/jupyterhub
.. _Jupyter notebook: https://jupyter-notebook.readthedocs.io/en/latest/ .. _Jupyter notebook: https://jupyter-notebook.readthedocs.io/en/latest/
.. _REST API: https://petstore3.swagger.io/?url=https://raw.githubusercontent.com/jupyterhub/jupyterhub/HEAD/docs/rest-api.yml#!/default .. _REST API: http://petstore.swagger.io/?url=https://raw.githubusercontent.com/jupyterhub/jupyterhub/master/docs/rest-api.yml#!/default

View File

@@ -0,0 +1,347 @@
# Install JupyterHub and JupyterLab from the ground up
The combination of [JupyterHub](https://jupyterhub.readthedocs.io) and [JupyterLab](https://jupyterlab.readthedocs.io)
is a great way to make shared computing resources available to a group.
These instructions are a guide for a manual, 'bare metal' install of [JupyterHub](https://jupyterhub.readthedocs.io)
and [JupyterLab](https://jupyterlab.readthedocs.io). This is ideal for running on a single server: build a beast
of a machine and share it within your lab, or use a virtual machine from any VPS or cloud provider.
This guide has similar goals to [The Littlest JupyterHub](https://the-littlest-jupyterhub.readthedocs.io) setup
script. However, instead of bundling all these step for you into one installer, we will perform every step manually.
This makes it easy to customize any part (e.g. if you want to run other services on the same system and need to make them
work together), as well as giving you full control and understanding of your setup.
## Prerequisites
Your own server with administrator (root) access. This could be a local machine, a remotely hosted one, or a cloud instance
or VPS. Each user who will access JupyterHub should have a standard user account on the machine. The install will be done
through the command line - useful if you log into your machine remotely using SSH.
This tutorial was tested on **Ubuntu 18.04**. No other Linux distributions have been tested, but the instructions
should be reasonably straightforward to adapt.
## Goals
JupyterLab enables access to a multiple 'kernels', each one being a given environment for a given language. The most
common is a Python environment, for scientific computing usually one managed by the `conda` package manager.
This guide will set up JupyterHub and JupyterLab seperately from the Python environment. In other words, we treat
JupyterHub+JupyterLab as a 'app' or webservice, which will connect to the kernels available on the system. Specifically:
- We will create an installation of JupyterHub and JupyterLab using a virtualenv under `/opt` using the system Python.
- We will install conda globally.
- We will create a shared conda environment which can be used (but not modified) by all users.
- We will show how users can create their own private conda environments, where they can install whatever they like.
The default JupyterHub Authenticator uses PAM to authenticate system users with their username and password. One can
[choose the authenticator](https://jupyterhub.readthedocs.io/en/stable/reference/authenticators.html#authenticators)
that best suits their needs. In this guide we will use the default Authenticator because it makes it easy for everyone to manage data
in their home folder and to mix and match different services and access methods (e.g. SSH) which all work using the
Linux system user accounts. Therefore, each user of JupyterHub will need a standard system user account.
Another goal of this guide is to use system provided packages wherever possible. This has the advantage that these packages
get automatic patches and security updates (be sure to turn on automatic updates in Ubuntu). This means less maintenance
work and a more reliable system.
## Part 1: JupyterHub and JupyterLab
### Setup the JupyterHub and JupyterLab in a virtual environment
First we create a virtual environment under '/opt/jupyterhub'. The '/opt' folder is where apps not belonging to the operating
system are [commonly installed](https://unix.stackexchange.com/questions/11544/what-is-the-difference-between-opt-and-usr-local).
Both jupyterlab and jupyterhub will be installed into this virtualenv. Create it with the command:
```sh
sudo python3 -m venv /opt/jupyterhub/
```
Now we use pip to install the required Python packages into the new virtual environment. Be sure to install
`wheel` first. Since we are separating the user interface from the computing kernels, we don't install
any Python scientific packages here. The only exception is `ipywidgets` because this is needed to allow connection
between interactive tools running in the kernel and the user interface.
Note that we use `/opt/jupyterhub/bin/python3 -m pip install` each time - this [makes sure](https://snarky.ca/why-you-should-use-python-m-pip/)
that the packages are installed to the correct virtual environment.
Perform the install using the following commands:
```sh
sudo /opt/jupyterhub/bin/python3 -m pip install wheel
sudo /opt/jupyterhub/bin/python3 -m pip install jupyterhub jupyterlab
sudo /opt/jupyterhub/bin/python3 -m pip install ipywidgets
```
JupyterHub also currently defaults to requiring `configurable-http-proxy`, which needs `nodejs` and `npm`. The versions
of these available in Ubuntu therefore need to be installed first (they are a bit old but this is ok for our needs):
```sh
sudo apt install nodejs npm
```
Then install `configurable-http-proxy`:
```sh
sudo npm install -g configurable-http-proxy
```
### Create the configuration for JupyterHub
Now we start creating configuration files. To keep everything together, we put all the configuration into the folder
created for the virtualenv, under `/opt/jupyterhub/etc/`. For each thing needing configuration, we will create a further
subfolder and necessary files.
First create the folder for the JupyterHub configuration and navigate to it:
```sh
sudo mkdir -p /opt/jupyterhub/etc/jupyterhub/
cd /opt/jupyterhub/etc/jupyterhub/
```
Then generate the default configuration file
```sh
sudo /opt/jupyterhub/bin/jupyterhub --generate-config
```
This will produce the default configuration file `/opt/jupyterhub/etc/jupyterhub/jupyterhub_config.py`
You will need to edit the configuration file to make the JupyterLab interface by the default.
Set the following configuration option in your `jupyterhub_config.py` file:
```python
c.Spawner.default_url = '/lab'
```
Further configuration options may be found in the documentation.
### Setup Systemd service
We will setup JupyterHub to run as a system service using Systemd (which is responsible for managing all services and
servers that run on startup in Ubuntu). We will create a service file in a suitable location in the virtualenv folder
and then link it to the system services. First create the folder for the service file:
```sh
sudo mkdir -p /opt/jupyterhub/etc/systemd
```
Then create the following text file using your [favourite editor](https://micro-editor.github.io/) at
```sh
/opt/jupyterhub/etc/systemd/jupyterhub.service
```
Paste the following service unit definition into the file:
```
[Unit]
Description=JupyterHub
After=syslog.target network.target
[Service]
User=root
Environment="PATH=/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/opt/jupyterhub/bin"
ExecStart=/opt/jupyterhub/bin/jupyterhub -f /opt/jupyterhub/etc/jupyterhub/jupyterhub_config.py
[Install]
WantedBy=multi-user.target
```
This sets up the environment to use the virtual environment we created, tells Systemd how to start jupyterhub using
the configuration file we created, specifies that jupyterhub will be started as the `root` user (needed so that it can
start jupyter on behalf of other logged in users), and specifies that jupyterhub should start on boot after the network
is enabled.
Finally, we need to make systemd aware of our service file. First we symlink our file into systemd's directory:
```sh
sudo ln -s /opt/jupyterhub/etc/systemd/jupyterhub.service /etc/systemd/system/jupyterhub.service
```
Then tell systemd to reload its configuration files
```sh
sudo systemctl daemon-reload
```
And finally enable the service
```sh
sudo systemctl enable jupyterhub.service
```
The service will start on reboot, but we can start it straight away using:
```sh
sudo systemctl start jupyterhub.service
```
...and check that it's running using:
```sh
sudo systemctl status jupyterhub.service
```
You should now be already be able to access jupyterhub using `<your servers ip>:8000` (assuming you haven't already set
up a firewall or something). However, when you log in the jupyter notebooks will be trying to use the Python virtualenv
that was created to install JupyterHub, this is not what we want. So on to part 2
## Part 2: Conda environments
### Install conda for the whole system
We will use `conda` to manage Python environments. We will install the officially maintained `conda` packages for Ubuntu,
this means they will get automatic updates with the rest of the system. Setup repo for the official Conda debian packages,
instructions are copied from [here](https://docs.conda.io/projects/conda/en/latest/user-guide/install/rpm-debian.html):
Install Anacononda public gpg key to trusted store
```sh
curl https://repo.anaconda.com/pkgs/misc/gpgkeys/anaconda.asc | gpg --dearmor > conda.gpg
sudo install -o root -g root -m 644 conda.gpg /etc/apt/trusted.gpg.d/
```
Add Debian repo
```sh
echo "deb [arch=amd64] https://repo.anaconda.com/pkgs/misc/debrepo/conda stable main" | sudo tee /etc/apt/sources.list.d/conda.list
```
Install conda
```sh
sudo apt update
sudo apt install conda
```
This will install conda into the folder `/opt/conda/`, with the conda command available at `/opt/conda/bin/conda`.
Finally, we can make conda more easily available to users by symlinking the conda shell setup script to the profile
'drop in' folder so that it gets run on login
```sh
sudo ln -s /opt/conda/etc/profile.d/conda.sh /etc/profile.d/conda.sh
```
### Install a default conda environment for all users
First create a folder for conda envs (might exist already):
```sh
sudo mkdir /opt/conda/envs/
```
Then create a conda environment to your liking within that folder. Here we have called it 'python' because it will
be the obvious default - call it whatever you like. You can install whatever you like into this environment, but you MUST at least install `ipykernel`.
```sh
sudo /opt/conda/bin/conda create --prefix /opt/conda/envs/python python=3.7 ipykernel
```
Once your env is set up as desired, make it visible to Jupyter by installing the kernel spec. There are two options here:
1 ) Install into the JupyterHub virtualenv - this ensures it overrides the default python version. It will only be visible
to the JupyterHub installation we have just created. This is useful to avoid conda environments appearing where they are not expected.
```sh
sudo /opt/conda/envs/python/bin/python -m ipykernel install --prefix=/opt/jupyterhub/ --name 'python' --display-name "Python (default)"
```
2 ) Install it system-wide by putting it into `/usr/local`. It will be visible to any parallel install of JupyterHub or
JupyterLab, and will persist even if you later delete or modify the JupyterHub installation. This is useful if the kernels
might be used by other services, or if you want to modify the JupyterHub installation independently from the conda environments.
```sh
sudo /opt/conda/envs/python/bin/python -m ipykernel install --prefix /usr/local/ --name 'python' --display-name "Python (default)"
````
### Setting up users' own conda environments
There is relatively little for the administrator to do here, as users will have to set up their own environments using the shell.
On login they should run `conda init` or `/opt/conda/bin/conda`. The can then use conda to set up their environment,
although they must also install `ipykernel`. Once done, they can enable their kernel using:
```sh
/path/to/kernel/env/bin/python -m ipykernel install --name 'python-my-env' --display-name "Python My Env"
```
This will place the kernel spec into their home folder, where Jupyter will look for it on startup.
## Setting up a reverse proxy
The guide so far results in JupyterHub running on port 8000. It is not generally advisable to run open web services in
this way - instead, use a reverse proxy running on standard HTTP/HTTPS ports.
> **Important**: Be aware of the security implications especially if you are running a server that is accessible from the open internet
> i.e. not protected within an institutional intranet or private home/office network. You should set up a firewall and
> HTTPS encryption, which is outside of the scope of this guide. For HTTPS consider using [LetsEncrypt](https://letsencrypt.org/)
> or setting up a [self-signed certificate](https://www.digitalocean.com/community/tutorials/how-to-create-a-self-signed-ssl-certificate-for-nginx-in-ubuntu-18-04).
> Firewalls may be set up using `ufw` or `firewalld` and combined with `fail2ban`.
### Using Nginx
Nginx is a mature and established web server and reverse proxy and is easy to install using `sudo apt install nginx`.
Details on using Nginx as a reverse proxy can be found elsewhere. Here, we will only outline the additional steps needed
to setup JupyterHub with Nginx and host it at a given URL e.g. `<your-server-ip-or-url>/jupyter`.
This could be useful for example if you are running several services or web pages on the same server.
To achieve this needs a few tweaks to both the JupyterHub configuration and the Nginx config. First, edit the
configuration file `/opt/jupyterhub/etc/jupyterhub/jupyterhub_config.py` and add the line:
```python
c.JupyterHub.bind_url = 'http://:8000/jupyter'
```
where `/jupyter` will be the relative URL of the JupyterHub.
Now Nginx must be configured with a to pass all traffic from `/jupyter` to the the local address `127.0.0.1:8000`.
Add the following snippet to your nginx configuration file (e.g. `/etc/nginx/sites-available/default`).
```
location /jupyter/ {
# NOTE important to also set base url of jupyterhub to /jupyter in its config
proxy_pass http://127.0.0.1:8000;
proxy_redirect off;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header Host $host;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto $scheme;
# websocket headers
proxy_set_header Upgrade $http_upgrade;
proxy_set_header Connection $connection_upgrade;
}
```
Also add this snippet before the *server* block:
```
map $http_upgrade $connection_upgrade {
default upgrade;
'' close;
}
```
Nginx will not run if there are errors in the configuration, check your configuration using:
```sh
nginx -t
```
If there are no errors, you can restart the Nginx service for the new configuration to take effect.
```sh
sudo systemctl restart nginx.service
```
## Getting started using your new JupyterHub
Once you have setup JupyterHub and Nginx proxy as described, you can browse to your JupyterHub IP or URL
(e.g. if your server IP address is `123.456.789.1` and you decided to host JupyterHub at the `/jupyter` URL, browse
to `123.456.789.1/jupyter`). You will find a login page where you enter your Linux username and password. On login
you will be presented with the JupyterLab interface, with the file browser pane showing the contents of your users'
home directory on the server.

View File

@@ -1,6 +0,0 @@
:orphan:
JupyterHub the hard way
=======================
This guide has moved to https://github.com/jupyterhub/jupyterhub-the-hard-way/blob/HEAD/docs/installation-guide-hard.md

View File

@@ -11,3 +11,4 @@ running on your own infrastructure.
quickstart quickstart
quickstart-docker quickstart-docker
installation-basics installation-basics
installation-guide-hard

View File

@@ -12,10 +12,10 @@ Before installing JupyterHub, you will need:
- [nodejs/npm](https://www.npmjs.com/). [Install nodejs/npm](https://docs.npmjs.com/getting-started/installing-node), - [nodejs/npm](https://www.npmjs.com/). [Install nodejs/npm](https://docs.npmjs.com/getting-started/installing-node),
using your operating system's package manager. using your operating system's package manager.
- If you are using **`conda`**, the nodejs and npm dependencies will be installed for * If you are using **`conda`**, the nodejs and npm dependencies will be installed for
you by conda. you by conda.
- If you are using **`pip`**, install a recent version of * If you are using **`pip`**, install a recent version of
[nodejs/npm](https://docs.npmjs.com/getting-started/installing-node). [nodejs/npm](https://docs.npmjs.com/getting-started/installing-node).
For example, install it on Linux (Debian/Ubuntu) using: For example, install it on Linux (Debian/Ubuntu) using:
@@ -78,12 +78,12 @@ Visit `https://localhost:8000` in your browser, and sign in with your unix
credentials. credentials.
To **allow multiple users to sign in** to the Hub server, you must start To **allow multiple users to sign in** to the Hub server, you must start
`jupyterhub` as a _privileged user_, such as root: `jupyterhub` as a *privileged user*, such as root:
```bash ```bash
sudo jupyterhub sudo jupyterhub
``` ```
The [wiki](https://github.com/jupyterhub/jupyterhub/wiki/Using-sudo-to-run-JupyterHub-without-root-privileges) The [wiki](https://github.com/jupyterhub/jupyterhub/wiki/Using-sudo-to-run-JupyterHub-without-root-privileges)
describes how to run the server as a _less privileged user_. This requires describes how to run the server as a *less privileged user*. This requires
additional configuration of the system. additional configuration of the system.

View File

@@ -1,126 +0,0 @@
import os
from collections import defaultdict
from pathlib import Path
from pytablewriter import MarkdownTableWriter
from ruamel.yaml import YAML
from jupyterhub.scopes import scope_definitions
HERE = os.path.abspath(os.path.dirname(__file__))
PARENT = Path(HERE).parent.parent.absolute()
class ScopeTableGenerator:
def __init__(self):
self.scopes = scope_definitions
@classmethod
def create_writer(cls, table_name, headers, values):
writer = MarkdownTableWriter()
writer.table_name = table_name
writer.headers = headers
writer.value_matrix = values
writer.margin = 1
return writer
def _get_scope_relationships(self):
"""Returns a tuple of dictionary of all scope-subscope pairs and a list of just subscopes:
({scope: subscope}, [subscopes])
used for creating hierarchical scope table in _parse_scopes()
"""
pairs = []
for scope, data in self.scopes.items():
subscopes = data.get('subscopes')
if subscopes is not None:
for subscope in subscopes:
pairs.append((scope, subscope))
else:
pairs.append((scope, None))
subscopes = [pair[1] for pair in pairs]
pairs_dict = defaultdict(list)
for scope, subscope in pairs:
pairs_dict[scope].append(subscope)
return pairs_dict, subscopes
def _get_top_scopes(self, subscopes):
"""Returns a list of highest level scopes
(not a subscope of any other scopes)"""
top_scopes = []
for scope in self.scopes.keys():
if scope not in subscopes:
top_scopes.append(scope)
return top_scopes
def _parse_scopes(self):
"""Returns a list of table rows where row:
[indented scopename string, scope description string]"""
scope_pairs, subscopes = self._get_scope_relationships()
top_scopes = self._get_top_scopes(subscopes)
table_rows = []
md_indent = "&nbsp;&nbsp;&nbsp;"
def _add_subscopes(table_rows, scopename, depth=0):
description = self.scopes[scopename]['description']
doc_description = self.scopes[scopename].get('doc_description', '')
if doc_description:
description = doc_description
table_row = [f"{md_indent * depth}`{scopename}`", description]
table_rows.append(table_row)
for subscope in scope_pairs[scopename]:
if subscope:
_add_subscopes(table_rows, subscope, depth + 1)
for scope in top_scopes:
_add_subscopes(table_rows, scope)
return table_rows
def write_table(self):
"""Generates the scope table in markdown format and writes it into `scope-table.md`"""
filename = f"{HERE}/scope-table.md"
table_name = ""
headers = ["Scope", "Grants permission to:"]
values = self._parse_scopes()
writer = self.create_writer(table_name, headers, values)
title = "Table 1. Available scopes and their hierarchy"
content = f"{title}\n{writer.dumps()}"
with open(filename, 'w') as f:
f.write(content)
print(f"Generated {filename}.")
print(
"Run 'make clean' before 'make html' to ensure the built scopes.html contains latest scope table changes."
)
def write_api(self):
"""Generates the API description in markdown format and writes it into `rest-api.yml`"""
filename = f"{PARENT}/rest-api.yml"
yaml = YAML(typ='rt')
yaml.preserve_quotes = True
scope_dict = {}
with open(filename, 'r+') as f:
content = yaml.load(f.read())
f.seek(0)
for scope in self.scopes:
description = self.scopes[scope]['description']
doc_description = self.scopes[scope].get('doc_description', '')
if doc_description:
description = doc_description
scope_dict[scope] = description
content['securityDefinitions']['oauth2']['scopes'] = scope_dict
yaml.dump(content, f)
f.truncate()
def main():
table_generator = ScopeTableGenerator()
table_generator.write_table()
table_generator.write_api()
if __name__ == "__main__":
main()

View File

@@ -1,37 +0,0 @@
# JupyterHub RBAC
Role Based Access Control (RBAC) in JupyterHub serves to provide fine grained control of access to Jupyterhub's API resources.
RBAC is new in JupyterHub 2.0.
## Motivation
The JupyterHub API requires authorization to access its APIs.
This ensures that an arbitrary user, or even an unauthenticated third party, are not allowed to perform such actions.
For instance, the behaviour prior to adoption of RBAC is that creating or deleting users requires _admin rights_.
The prior system is functional, but lacks flexibility. If your Hub serves a number of users in different groups, you might want to delegate permissions to other users or automate certain processes.
Prior to RBAC, appointing a 'group-only admin' or a bot that culls idle servers, requires granting full admin rights to all actions. This poses a risk of the user or service intentionally or unintentionally accessing and modifying any data within the Hub and violates the [principle of least privilege](https://en.wikipedia.org/wiki/Principle_of_least_privilege).
To remedy situations like this, JupyterHub is transitioning to an RBAC system. By equipping users, groups and services with _roles_ that supply them with a collection of permissions (_scopes_), administrators are able to fine-tune which parties are granted access to which resources.
## Definitions
**Scopes** are specific permissions used to evaluate API requests. For example: the API endpoint `users/servers`, which enables starting or stopping user servers, is guarded by the scope `servers`.
Scopes are not directly assigned to requesters. Rather, when a client performs an API call, their access will be evaluated based on their assigned roles.
**Roles** are collections of scopes that specify the level of what a client is allowed to do. For example, a group administrator may be granted permission to control the servers of group members, but not to create, modify or delete group members themselves.
Within the RBAC framework, this is achieved by assigning a role to the administrator that covers exactly those privileges.
## Technical Overview
```{toctree}
:maxdepth: 2
roles
scopes
use-cases
tech-implementation
upgrade
```

View File

@@ -1,162 +0,0 @@
(roles)=
# Roles
JupyterHub provides four roles that are available by default:
```{admonition} **Default roles**
- `user` role provides a {ref}`default user scope <default-user-scope-target>` `self` that grants access to the user's own resources.
- `admin` role contains all available scopes and grants full rights to all actions. This role **cannot be edited**.
- `token` role provides a {ref}`default token scope <default-token-scope-target>` `all` that resolves to the same permissions as the owner of the token has.
- `server` role allows for posting activity of "itself" only.
**These roles cannot be deleted.**
```
These default roles have a default collection of scopes,
but you can define the scopes associated with each role (excluding admin) to suit your needs,
as seen [below](overriding-default-roles).
The `user`, `admin`, and `token` roles by default all preserve the permissions prior to RBAC.
Only the `server` role is changed from pre-2.0, to reduce its permissions to activity-only
instead of the default of a full access token.
Additional custom roles can also be defined (see {ref}`define-role-target`).
Roles can be assigned to the following entities:
- Users
- Services
- Groups
- Tokens
An entity can have zero, one, or multiple roles, and there are no restrictions on which roles can be assigned to which entity. Roles can be added to or removed from entities at any time.
**Users** \
When a new user gets created, they are assigned their default role `user`. Additionaly, if the user is created with admin privileges (via `c.Authenticator.admin_users` in `jupyterhub_config.py` or `admin: true` via API), they will be also granted `admin` role. If existing user's admin status changes via API or `jupyterhub_config.py`, their default role will be updated accordingly (after next startup for the latter).
**Services** \
Services do not have a default role. Services without roles have no access to the guarded API end-points, so most services will require assignment of a role in order to function.
**Groups** \
A group does not require any role, and has no roles by default. If a user is a member of a group, they automatically inherit any of the group's permissions (see {ref}`resolving-roles-scopes-target` for more details). This is useful for assigning a set of common permissions to several users.
**Tokens** \
A tokens permissions are evaluated based on their owning entity. Since a token is always issued for a user or service, it can never have more permissions than its owner. If no specific role is requested for a new token, the token is assigned the `token` role.
(define-role-target)=
## Defining Roles
Roles can be defined or modified in the configuration file as a list of dictionaries. An example:
% TODO: think about loading users into roles if membership has been changed via API.
% What should be the result?
```python
# in jupyterhub_config.py
c.JupyterHub.load_roles = [
{
'name': 'server-rights',
'description': 'Allows parties to start and stop user servers',
'scopes': ['servers'],
'users': ['alice', 'bob'],
'services': ['idle-culler'],
'groups': ['admin-group'],
}
]
```
The role `server-rights` now allows the starting and stopping of servers by any of the following:
- users `alice` and `bob`
- the service `idle-culler`
- any member of the `admin-group`.
```{attention}
Tokens cannot be assigned roles through role definition but may be assigned specific roles when requested via API (see {ref}`requesting-api-token-target`).
```
Another example:
```python
# in jupyterhub_config.py
c.JupyterHub.load_roles = [
{
'description': 'Read-only user models',
'name': 'reader',
'scopes': ['read:users'],
'services': ['external'],
'users': ['maria', 'joe']
}
]
```
The role `reader` allows users `maria` and `joe` and service `external` to read (but not modify) any users model.
```{admonition} Requirements
:class: warning
In a role definition, the `name` field is required, while all other fields are optional.\
**Role names must:**
- be 3 - 255 characters
- use ascii lowercase, numbers, 'unreserved' URL punctuation `-_.~`
- start with a letter
- end with letter or number.
`users`, `services`, and `groups` only accept objects that already exist in the database or are defined previously in the file.
It is not possible to implicitly add a new user to the database by defining a new role.
```
If no scopes are defined for _new role_, JupyterHub will raise a warning. Providing non-existing scopes will result in an error.
In case the role with a certain name already exists in the database, its definition and scopes will be overwritten. This holds true for all roles except the `admin` role, which cannot be overwritten; an error will be raised if trying to do so. All the role bearers permissions present in the definition will change accordingly.
(overriding-default-roles)=
### Overriding default roles
Role definitions can include those of the "default" roles listed above (admin excluded),
if the default scopes associated with those roles do not suit your deployment.
For example, to specify what permissions the $JUPYTERHUB_API_TOKEN issued to all single-user servers
has,
define the `server` role.
To restore the JupyterHub 1.x behavior of servers being able to do anything their owners can do,
use the scope `all`:
```python
c.JupyterHub.load_roles = [
{
'name': 'server',
'scopes': ['all'],
}
]
```
or, better yet, identify the specific [scopes][] you want server environments to have access to.
[scopes]: available-scopes-target
If you don't want to get too detailed,
one option is the `self` scope,
which will have no effect on non-admin users,
but will restrict the token issued to admin user servers to only have access to their own resources,
instead of being able to take actions on behalf of all other users.
```python
c.JupyterHub.load_roles = [
{
'name': 'server',
'scopes': ['self'],
}
]
```
(removing-roles-target)=
## Removing roles
Only the entities present in the role definition in the `jupyterhub_config.py` remain the role bearers. If a user, service or group is removed from the role definition, they will lose the role on the next startup.
Once a role is loaded, it remains in the database until removing it from the `jupyterhub_config.py` and restarting the Hub. All previously defined role bearers will lose the role and associated permissions. Default roles, even if previously redefined through the config file and removed, will not be deleted from the database.

View File

@@ -1,126 +0,0 @@
# Scopes in JupyterHub
A scope has a syntax-based design that reveals which resources it provides access to. Resources are objects with a type, associated data, relationships to other resources, and a set of methods that operate on them (see [RESTful API](https://restful-api-design.readthedocs.io/en/latest/resources.html) documentation for more information).
`<resource>` in the RBAC scope design refers to the resource name in the [JupyterHub's API](../reference/rest-api.rst) endpoints in most cases. For instance, `<resource>` equal to `users` corresponds to JupyterHub's API endpoints beginning with _/users_.
(scope-conventions-target)=
## Scope conventions
- `<resource>` \
The top-level `<resource>` scopes, such as `users` or `groups`, grant read, write, and list permissions to the resource itself as well as its sub-resources. For example, the scope `users:activity` is included in the scope `users`.
- `read:<resource>` \
Limits permissions to read-only operations on single resources.
- `list:<resource>` \
Read-only access to listing endpoints.
Use `read:<resource>:<subresource>` to control what fields are returned.
- `admin:<resource>` \
Grants additional permissions such as create/delete on the corresponding resource in addition to read and write permissions.
- `access:<resource>` \
Grants access permissions to the `<resource>` via API or browser.
- `<resource>:<subresource>` \
The {ref}`vertically filtered <vertical-filtering-target>` scopes provide access to a subset of the information granted by the `<resource>` scope. E.g., the scope `users:activity` only provides permission to post user activity.
- `<resource>!<object>=<objectname>` \
{ref}`horizontal-filtering-target` is implemented by the `!<object>=<objectname>`scope structure. A resource (or sub-resource) can be filtered based on `user`, `server`, `group` or `service` name. For instance, `<resource>!user=charlie` limits access to only return resources of user `charlie`. \
Only one filter per scope is allowed, but filters for the same scope have an additive effect; a larger filter can be used by supplying the scope multiple times with different filters.
By adding a scope to an existing role, all role bearers will gain the associated permissions.
## Metascopes
Metascopes do not follow the general scope syntax. Instead, a metascope resolves to a set of scopes, which can refer to different resources, based on their owning entity. In JupyterHub, there are currently two metascopes:
1. default user scope `self`, and
2. default token scope `all`.
(default-user-scope-target)=
### Default user scope
Access to the user's own resources and subresources is covered by metascope `self`. This metascope includes the user's model, activity, servers and tokens. For example, `self` for a user named "gerard" includes:
- `users!user=gerard` where the `users` scope provides access to the full user model and activity. The filter restricts this access to the user's own resources.
- `servers!user=gerard` which grants the user access to their own servers without being able to create/delete any.
- `tokens!user=gerard` which allows the user to access, request and delete their own tokens.
- `access:servers!user=gerard` which allows the user to access their own servers via API or browser.
The `self` scope is only valid for user entities. In other cases (e.g., for services) it resolves to an empty set of scopes.
(default-token-scope-target)=
### Default token scope
The token metascope `all` covers the same scopes as the token owner's scopes during requests. For example, if a token owner has roles containing the scopes `read:groups` and `read:users`, the `all` scope resolves to the set of scopes `{read:groups, read:users}`.
If the token owner has default `user` role, the `all` scope resolves to `self`, which will subsequently be expanded to include all the user-specific scopes (or empty set in the case of services).
If the token owner is a member of any group with roles, the group scopes will also be included in resolving the `all` scope.
(horizontal-filtering-target)=
## Horizontal filtering
Horizontal filtering, also called _resource filtering_, is the concept of reducing the payload of an API call to cover only the subset of the _resources_ that the scopes of the client provides them access to.
Requested resources are filtered based on the filter of the corresponding scope. For instance, if a service requests a user list (guarded with scope `read:users`) with a role that only contains scopes `read:users!user=hannah` and `read:users!user=ivan`, the returned list of user models will be an intersection of all users and the collection `{hannah, ivan}`. In case this intersection is empty, the API call returns an HTTP 404 error, regardless if any users exist outside of the clients scope filter collection.
In case a user resource is being accessed, any scopes with _group_ filters will be expanded to filters for each _user_ in those groups.
### `!user` filter
The `!user` filter is a special horizontal filter that strictly refers to the **"owner only"** scopes, where _owner_ is a user entity. The filter resolves internally into `!user=<ownerusername>` ensuring that only the owner's resources may be accessed through the associated scopes.
For example, the `server` role assigned by default to server tokens contains `access:servers!user` and `users:activity!user` scopes. This allows the token to access and post activity of only the servers owned by the token owner.
The filter can be applied to any scope.
(vertical-filtering-target)=
## Vertical filtering
Vertical filtering, also called _attribute filtering_, is the concept of reducing the payload of an API call to cover only the _attributes_ of the resources that the scopes of the client provides them access to. This occurs when the client scopes are subscopes of the API endpoint that is called.
For instance, if a client requests a user list with the only scope being `read:users:groups`, the returned list of user models will contain only a list of groups per user.
In case the client has multiple subscopes, the call returns the union of the data the client has access to.
The payload of an API call can be filtered both horizontally and vertically simultaneously. For instance, performing an API call to the endpoint `/users/` with the scope `users:name!user=juliette` returns a payload of `[{name: 'juliette'}]` (provided that this name is present in the database).
(available-scopes-target)=
## Available scopes
Table below lists all available scopes and illustrates their hierarchy. Indented scopes indicate subscopes of the scope(s) above them.
There are four exceptions to the general {ref}`scope conventions <scope-conventions-target>`:
- `read:users:name` is a subscope of both `read:users` and `read:servers`. \
The `read:servers` scope requires access to the user name (server owner) due to named servers distinguished internally in the form `!server=username/servername`.
- `read:users:activity` is a subscope of both `read:users` and `users:activity`. \
Posting activity via the `users:activity`, which is not included in `users` scope, needs to check the last valid activity of the user.
- `read:roles:users` is a subscope of both `read:roles` and `admin:users`. \
Admin privileges to the _users_ resource include the information about user roles.
- `read:roles:groups` is a subscope of both `read:roles` and `admin:groups`. \
Similar to the `read:roles:users` above.
```{include} scope-table.md
```
```{Caution}
Note that only the {ref}`horizontal filtering <horizontal-filtering-target>` can be added to scopes to customize them. \
Metascopes `self` and `all`, `<resource>`, `<resource>:<subresource>`, `read:<resource>`, `admin:<resource>`, and `access:<resource>` scopes are predefined and cannot be changed otherwise.
```
### Scopes and APIs
The scopes are also listed in the [](../reference/rest-api.rst) documentation. Each API endpoint has a list of scopes which can be used to access the API; if no scopes are listed, the API is not authenticated and can be accessed without any permissions (i.e., no scopes).
Listed scopes by each API endpoint reflect the "lowest" permissions required to gain any access to the corresponding API. For example, posting user's activity (_POST /users/:name/activity_) needs `users:activity` scope. If scope `users` is passed during the request, the access will be granted as the required scope is a subscope of the `users` scope. If, on the other hand, `read:users:activity` scope is passed, the access will be denied.

View File

@@ -1,80 +0,0 @@
# Technical Implementation
Roles are stored in the database, where they are associated with users, services, etc., and can be added or modified as explained in {ref}`define-role-target` section. Users, services, groups, and tokens can gain, change, and lose roles. This is currently achieved via `jupyterhub_config.py` (see {ref}`define-role-target`) and will be made available via API in future. The latter will allow for changing a token's role, and thereby its permissions, without the need to issue a new token.
Roles and scopes utilities can be found in `roles.py` and `scopes.py` modules. Scope variables take on five different formats which is reflected throughout the utilities via specific nomenclature:
```{admonition} **Scope variable nomenclature**
:class: tip
- _scopes_ \
List of scopes with abbreviations (used in role definitions). E.g., `["users:activity!user"]`.
- _expanded scopes_ \
Set of expanded scopes without abbreviations (i.e., resolved metascopes, filters and subscopes). E.g., `{"users:activity!user=charlie", "read:users:activity!user=charlie"}`.
- _parsed scopes_ \
Dictionary JSON like format of expanded scopes. E.g., `{"users:activity": {"user": ["charlie"]}, "read:users:activity": {"users": ["charlie"]}}`.
- _intersection_ \
Set of expanded scopes as intersection of 2 expanded scope sets.
- _identify scopes_ \
Set of expanded scopes needed for identify (whoami) endpoints.
```
(resolving-roles-scopes-target)=
## Resolving roles and scopes
**Resolving roles** refers to determining which roles a user, service, token, or group has, extracting the list of scopes from each role and combining them into a single set of scopes.
**Resolving scopes** involves expanding scopes into all their possible subscopes (_expanded scopes_), parsing them into format used for access evaluation (_parsed scopes_) and, if applicable, comparing two sets of scopes (_intersection_). All procedures take into account the scope hierarchy, {ref}`vertical <vertical-filtering-target>` and {ref}`horizontal filtering <horizontal-filtering-target>`, limiting or elevated permissions (`read:<resource>` or `admin:<resource>`, respectively), and metascopes.
Roles and scopes are resolved on several occasions, for example when requesting an API token with specific roles or making an API request. The following sections provide more details.
(requesting-api-token-target)=
### Requesting API token with specific roles
API tokens grant access to JupyterHub's APIs. The RBAC framework allows for requesting tokens with specific existing roles. To date, it is only possible to add roles to a token through the _POST /users/:name/tokens_ API where the roles can be specified in the token parameters body (see [](../reference/rest-api.rst)).
RBAC adds several steps into the token issue flow.
If no roles are requested, the token is issued with the default `token` role (providing the requester is allowed to create the token).
If the token is requested with any roles, the permissions of requesting entity are checked against the requested permissions to ensure the token would not grant its owner additional privileges.
If, due to modifications of roles or entities, at API request time a token has any scopes that its owner does not, those scopes are removed. The API request is resolved without additional errors using the scopes _intersection_, but the Hub logs a warning (see {ref}`Figure 2 <api-request-chart>`).
Resolving a token's roles (yellow box in {ref}`Figure 1 <token-request-chart>`) corresponds to resolving all the token's owner roles (including the roles associated with their groups) and the token's requested roles into a set of scopes. The two sets are compared (Resolve the scopes box in orange in {ref}`Figure 1 <token-request-chart>`), taking into account the scope hierarchy but, solely for role assignment, omitting any {ref}`horizontal filter <horizontal-filtering-target>` comparison. If the token's scopes are a subset of the token owner's scopes, the token is issued with the requested roles; if not, JupyterHub will raise an error.
{ref}`Figure 1 <token-request-chart>` below illustrates the steps involved. The orange rectangles highlight where in the process the roles and scopes are resolved.
```{figure} ../images/rbac-token-request-chart.png
:align: center
:name: token-request-chart
Figure 1. Resolving roles and scopes during API token request
```
### Making an API request
With the RBAC framework each authenticated JupyterHub API request is guarded by a scope decorator that specifies which scopes are required to gain the access to the API.
When an API request is performed, the requesting API token's roles are again resolved (yellow box in {ref}`Figure 2 <api-request-chart>`) to ensure the token does not grant more permissions than its owner has at the request time (e.g., due to changing/losing roles).
If the owner's roles do not include some scopes of the token's scopes, only the _intersection_ of the token's and owner's scopes will be used. For example, using a token with scope `users` whose owner's role scope is `read:users:name` will result in only the `read:users:name` scope being passed on. In the case of no _intersection_, an empty set of scopes will be used.
The passed scopes are compared to the scopes required to access the API as follows:
- if the API scopes are present within the set of passed scopes, the access is granted and the API returns its "full" response
- if that is not the case, another check is utilized to determine if subscopes of the required API scopes can be found in the passed scope set:
- if found, the RBAC framework employs the {ref}`filtering <vertical-filtering-target>` procedures to refine the API response to access only resource attributes corresponding to the passed scopes. For example, providing a scope `read:users:activity!group=class-C` for the _GET /users_ API will return a list of user models from group `class-C` containing only the `last_activity` attribute for each user model
- if not found, the access to API is denied
{ref}`Figure 2 <api-request-chart>` illustrates this process highlighting the steps where the role and scope resolutions as well as filtering occur in orange.
```{figure} ../images/rbac-api-request-chart.png
:align: center
:name: api-request-chart
Figure 2. Resolving roles and scopes when an API request is made
```

View File

@@ -1,54 +0,0 @@
# Upgrading JupyterHub with RBAC framework
RBAC framework requires different database setup than any previous JupyterHub versions due to eliminating the distinction between OAuth and API tokens (see {ref}`oauth-vs-api-tokens-target` for more details). This requires merging the previously two different database tables into one. By doing so, all existing tokens created before the upgrade no longer comply with the new database version and must be replaced.
This is achieved by the Hub deleting all existing tokens during the database upgrade and recreating the tokens loaded via the `jupyterhub_config.py` file with updated structure. However, any manually issued or stored tokens are not recreated automatically and must be manually re-issued after the upgrade.
No other database records are affected.
(rbac-upgrade-steps-target)=
## Upgrade steps
1. All running **servers must be stopped** before proceeding with the upgrade.
2. To upgrade the Hub, follow the [Upgrading JupyterHub](../admin/upgrading.rst) instructions.
```{attention}
We advise against defining any new roles in the `jupyterhub.config.py` file right after the upgrade is completed and JupyterHub restarted for the first time. This preserves the 'current' state of the Hub. You can define and assign new roles on any other following startup.
```
3. After restarting the Hub **re-issue all tokens that were previously issued manually** (i.e., not through the `jupyterhub_config.py` file).
When the JupyterHub is restarted for the first time after the upgrade, all users, services and tokens stored in the database or re-loaded through the configuration file will be assigned their default role. Any newly added entities after that will be assigned their default role only if no other specific role is requested for them.
## Changing the permissions after the upgrade
Once all the {ref}`upgrade steps <rbac-upgrade-steps-target>` above are completed, the RBAC framework will be available for utilization. You can define new roles, modify default roles (apart from `admin`) and assign them to entities as described in the {ref}`define-role-target` section.
We recommended the following procedure to start with RBAC:
1. Identify which admin users and services you would like to grant only the permissions they need through the new roles.
2. Strip these users and services of their admin status via API or UI. This will change their roles from `admin` to `user`.
```{note}
Stripping entities of their roles is currently available only via `jupyterhub_config.py` (see {ref}`removing-roles-target`).
```
3. Define new roles that you would like to start using with appropriate scopes and assign them to these entities in `jupyterhub_config.py`.
4. Restart the JupyterHub for the new roles to take effect.
(oauth-vs-api-tokens-target)=
## OAuth vs API tokens
### Before RBAC
Previous JupyterHub versions utilize two types of tokens, OAuth token and API token.
OAuth token is issued by the Hub to a single-user server when the user logs in. The token is stored in the browser cookie and is used to identify the user who owns the server during the OAuth flow. This token by default expires when the cookie reaches its expiry time of 2 weeks (or after 1 hour in JupyterHub versions < 1.3.0).
API token is issued by the Hub to a single-user server when launched and is used to communicate with the Hub's APIs such as posting activity or completing the OAuth flow. This token has no expiry by default.
API tokens can also be issued to users via API ([_/hub/token_](../reference/urls.md) or [_POST /users/:username/tokens_](../reference/rest-api.rst)) and services via `jupyterhub_config.py` to perform API requests.
### With RBAC
The RBAC framework allows for granting tokens different levels of permissions via scopes attached to roles. The 'only identify' purpose of the separate OAuth tokens is no longer required. API tokens can be used used for every action, including the login and authentication, for which an API token with no role (i.e., no scope in {ref}`available-scopes-target`) is used.
OAuth tokens are therefore dropped from the Hub upgraded with the RBAC framework.

View File

@@ -1,130 +0,0 @@
# Use Cases
To determine which scopes a role should have, one can follow these steps:
1. Determine what actions the role holder should have/have not access to
2. Match the actions against the [JupyterHub's APIs](../reference/rest-api.rst)
3. Check which scopes are required to access the APIs
4. Combine scopes and subscopes if applicable
5. Customize the scopes with filters if needed
6. Define the role with required scopes and assign to users/services/groups/tokens
Below, different use cases are presented on how to use the RBAC framework.
## Service to cull idle servers
Finding and shutting down idle servers can save a lot of computational resources.
We can make use of [jupyterhub-idle-culler](https://github.com/jupyterhub/jupyterhub-idle-culler) to manage this for us.
Below follows a short tutorial on how to add a cull-idle service in the RBAC system.
1. Install the cull-idle server script with `pip install jupyterhub-idle-culler`.
2. Define a new service `idle-culler` and a new role for this service:
```python
# in jupyterhub_config.py
c.JupyterHub.services = [
{
"name": "idle-culler",
"command": [
sys.executable, "-m",
"jupyterhub_idle_culler",
"--timeout=3600"
],
}
]
c.JupyterHub.load_roles = [
{
"name": "idle-culler",
"description": "Culls idle servers",
"scopes": ["read:users:name", "read:users:activity", "servers"],
"services": ["idle-culler"],
}
]
```
```{important}
Note that in the RBAC system the `admin` field in the `idle-culler` service definition is omitted. Instead, the `idle-culler` role provides the service with only the permissions it needs.
If the optional actions of deleting the idle servers and/or removing inactive users are desired, **change the following scopes** in the `idle-culler` role definition:
- `servers` to `admin:servers` for deleting servers
- `read:users:name`, `read:users:activity` to `admin:users` for deleting users.
```
3. Restart JupyterHub to complete the process.
## API launcher
A service capable of creating/removing users and launching multiple servers should have access to:
1. _POST_ and _DELETE /users_
2. _POST_ and _DELETE /users/:name/server_ or _/users/:name/servers/:server_name_
3. Creating/deleting servers
The scopes required to access the API enpoints:
1. `admin:users`
2. `servers`
3. `admin:servers`
From the above, the role definition is:
```python
# in jupyterhub_config.py
c.JupyterHub.load_roles = [
{
"name": "api-launcher",
"description": "Manages servers",
"scopes": ["admin:users", "admin:servers"],
"services": [<service_name>]
}
]
```
If needed, the scopes can be modified to limit the permissions to e.g. a particular group with `!group=groupname` filter.
## Group admin roles
Roles can be used to specify different group member privileges.
For example, a group of students `class-A` may have a role allowing all group members to access information about their group. Teacher `johan`, who is a student of `class-A` but a teacher of another group of students `class-B`, can have additional role permitting him to access information about `class-B` students as well as start/stop their servers.
The roles can then be defined as follows:
```python
# in jupyterhub_config.py
c.JupyterHub.load_groups = {
'class-A': ['johan', 'student1', 'student2'],
'class-B': ['student3', 'student4']
}
c.JupyterHub.load_roles = [
{
'name': 'class-A-student',
'description': 'Grants access to information about the group',
'scopes': ['read:groups!group=class-A'],
'groups': ['class-A']
},
{
'name': 'class-B-student',
'description': 'Grants access to information about the group',
'scopes': ['read:groups!group=class-B'],
'groups': ['class-B']
},
{
'name': 'teacher',
'description': 'Allows for accessing information about teacher group members and starting/stopping their servers',
'scopes': [ 'read:users!group=class-B', 'servers!group=class-B'],
'users': ['johan']
}
]
```
In the above example, `johan` has privileges inherited from `class-A-student` role and the `teacher` role on top of those.
```{note}
The scope filters (`!group=`) limit the privileges only to the particular groups. `johan` can access the servers and information of `class-B` group members only.
```

View File

@@ -37,7 +37,7 @@ with any provider, is also available.
## The Dummy Authenticator ## The Dummy Authenticator
When testing, it may be helpful to use the When testing, it may be helpful to use the
{class}`jupyterhub.auth.DummyAuthenticator`. This allows for any username and :class:`~jupyterhub.auth.DummyAuthenticator`. This allows for any username and
password unless if a global password has been set. Once set, any username will password unless if a global password has been set. Once set, any username will
still be accepted but the correct password will need to be provided. still be accepted but the correct password will need to be provided.
@@ -89,6 +89,7 @@ class DictionaryAuthenticator(Authenticator):
return data['username'] return data['username']
``` ```
#### Normalize usernames #### Normalize usernames
Since the Authenticator and Spawner both use the same username, Since the Authenticator and Spawner both use the same username,
@@ -111,9 +112,10 @@ normalize usernames using PAM (basically round-tripping them: username
to uid to username), which is useful in case you use some external to uid to username), which is useful in case you use some external
service that allows multiple usernames mapping to the same user (such service that allows multiple usernames mapping to the same user (such
as ActiveDirectory, yes, this really happens). When as ActiveDirectory, yes, this really happens). When
`pam_normalize_username` is on, usernames are _not_ normalized to `pam_normalize_username` is on, usernames are *not* normalized to
lowercase. lowercase.
#### Validate usernames #### Validate usernames
In most cases, there is a very limited set of acceptable usernames. In most cases, there is a very limited set of acceptable usernames.
@@ -130,6 +132,7 @@ To only allow usernames that start with 'w':
c.Authenticator.username_pattern = r'w.*' c.Authenticator.username_pattern = r'w.*'
``` ```
### How to write a custom authenticator ### How to write a custom authenticator
You can use custom Authenticator subclasses to enable authentication You can use custom Authenticator subclasses to enable authentication
@@ -142,6 +145,7 @@ and [post_spawn_stop(user, spawner)][], are hooks that can be used to do
auth-related startup (e.g. opening PAM sessions) and cleanup auth-related startup (e.g. opening PAM sessions) and cleanup
(e.g. closing PAM sessions). (e.g. closing PAM sessions).
See a list of custom Authenticators [on the wiki](https://github.com/jupyterhub/jupyterhub/wiki/Authenticators). See a list of custom Authenticators [on the wiki](https://github.com/jupyterhub/jupyterhub/wiki/Authenticators).
If you are interested in writing a custom authenticator, you can read If you are interested in writing a custom authenticator, you can read
@@ -182,6 +186,7 @@ Additionally, configurable attributes for your authenticator will
appear in jupyterhub help output and auto-generated configuration files appear in jupyterhub help output and auto-generated configuration files
via `jupyterhub --generate-config`. via `jupyterhub --generate-config`.
### Authentication state ### Authentication state
JupyterHub 0.8 adds the ability to persist state related to authentication, JupyterHub 0.8 adds the ability to persist state related to authentication,
@@ -215,10 +220,12 @@ To store auth_state, two conditions must be met:
export JUPYTERHUB_CRYPT_KEY=$(openssl rand -hex 32) export JUPYTERHUB_CRYPT_KEY=$(openssl rand -hex 32)
``` ```
JupyterHub uses [Fernet](https://cryptography.io/en/latest/fernet/) to encrypt auth_state. JupyterHub uses [Fernet](https://cryptography.io/en/latest/fernet/) to encrypt auth_state.
To facilitate key-rotation, `JUPYTERHUB_CRYPT_KEY` may be a semicolon-separated list of encryption keys. To facilitate key-rotation, `JUPYTERHUB_CRYPT_KEY` may be a semicolon-separated list of encryption keys.
If there are multiple keys present, the **first** key is always used to persist any new auth_state. If there are multiple keys present, the **first** key is always used to persist any new auth_state.
#### Using auth_state #### Using auth_state
Typically, if `auth_state` is persisted it is desirable to affect the Spawner environment in some way. Typically, if `auth_state` is persisted it is desirable to affect the Spawner environment in some way.
@@ -228,9 +235,10 @@ to Spawner environment:
```python ```python
class MyAuthenticator(Authenticator): class MyAuthenticator(Authenticator):
async def authenticate(self, handler, data=None): @gen.coroutine
username = await identify_user(handler, data) def authenticate(self, handler, data=None):
upstream_token = await token_for_user(username) username = yield identify_user(handler, data)
upstream_token = yield token_for_user(username)
return { return {
'name': username, 'name': username,
'auth_state': { 'auth_state': {
@@ -238,9 +246,10 @@ class MyAuthenticator(Authenticator):
}, },
} }
async def pre_spawn_start(self, user, spawner): @gen.coroutine
def pre_spawn_start(self, user, spawner):
"""Pass upstream_token to spawner via environment variable""" """Pass upstream_token to spawner via environment variable"""
auth_state = await user.get_auth_state() auth_state = yield user.get_auth_state()
if not auth_state: if not auth_state:
# auth_state not enabled # auth_state not enabled
return return
@@ -259,10 +268,11 @@ PAM session.
Beginning with version 0.8, JupyterHub is an OAuth provider. Beginning with version 0.8, JupyterHub is an OAuth provider.
[authenticator]: https://github.com/jupyterhub/jupyterhub/blob/HEAD/jupyterhub/auth.py
[pam]: https://en.wikipedia.org/wiki/Pluggable_authentication_module [Authenticator]: https://github.com/jupyterhub/jupyterhub/blob/master/jupyterhub/auth.py
[oauth]: https://en.wikipedia.org/wiki/OAuth [PAM]: https://en.wikipedia.org/wiki/Pluggable_authentication_module
[github oauth]: https://developer.github.com/v3/oauth/ [OAuth]: https://en.wikipedia.org/wiki/OAuth
[oauthenticator]: https://github.com/jupyterhub/oauthenticator [GitHub OAuth]: https://developer.github.com/v3/oauth/
[OAuthenticator]: https://github.com/jupyterhub/oauthenticator
[pre_spawn_start(user, spawner)]: https://jupyterhub.readthedocs.io/en/latest/api/auth.html#jupyterhub.auth.Authenticator.pre_spawn_start [pre_spawn_start(user, spawner)]: https://jupyterhub.readthedocs.io/en/latest/api/auth.html#jupyterhub.auth.Authenticator.pre_spawn_start
[post_spawn_stop(user, spawner)]: https://jupyterhub.readthedocs.io/en/latest/api/auth.html#jupyterhub.auth.Authenticator.post_spawn_stop [post_spawn_stop(user, spawner)]: https://jupyterhub.readthedocs.io/en/latest/api/auth.html#jupyterhub.auth.Authenticator.post_spawn_stop

View File

@@ -3,17 +3,18 @@
In this example, we show a configuration file for a fairly standard JupyterHub In this example, we show a configuration file for a fairly standard JupyterHub
deployment with the following assumptions: deployment with the following assumptions:
- Running JupyterHub on a single cloud server * Running JupyterHub on a single cloud server
- Using SSL on the standard HTTPS port 443 * Using SSL on the standard HTTPS port 443
- Using GitHub OAuth (using oauthenticator) for login * Using GitHub OAuth (using oauthenticator) for login
- Using the default spawner (to configure other spawners, uncomment and edit * Using the default spawner (to configure other spawners, uncomment and edit
`spawner_class` as well as follow the instructions for your desired spawner) `spawner_class` as well as follow the instructions for your desired spawner)
- Users exist locally on the server * Users exist locally on the server
- Users' notebooks to be served from `~/assignments` to allow users to browse * Users' notebooks to be served from `~/assignments` to allow users to browse
for notebooks within other users' home directories for notebooks within other users' home directories
- You want the landing page for each user to be a `Welcome.ipynb` notebook in * You want the landing page for each user to be a `Welcome.ipynb` notebook in
their assignments directory. their assignments directory.
- All runtime files are put into `/srv/jupyterhub` and log files in `/var/log`. * All runtime files are put into `/srv/jupyterhub` and log files in `/var/log`.
The `jupyterhub_config.py` file would have these settings: The `jupyterhub_config.py` file would have these settings:

View File

@@ -6,12 +6,12 @@ SSL port `443`. This could be useful if the JupyterHub server machine is also
hosting other domains or content on `443`. The goal in this example is to hosting other domains or content on `443`. The goal in this example is to
satisfy the following: satisfy the following:
- JupyterHub is running on a server, accessed _only_ via `HUB.DOMAIN.TLD:443` * JupyterHub is running on a server, accessed *only* via `HUB.DOMAIN.TLD:443`
- On the same machine, `NO_HUB.DOMAIN.TLD` strictly serves different content, * On the same machine, `NO_HUB.DOMAIN.TLD` strictly serves different content,
also on port `443` also on port `443`
- `nginx` or `apache` is used as the public access point (which means that * `nginx` or `apache` is used as the public access point (which means that
only nginx/apache will bind to `443`) only nginx/apache will bind to `443`)
- After testing, the server in question should be able to score at least an A on the * After testing, the server in question should be able to score at least an A on the
Qualys SSL Labs [SSL Server Test](https://www.ssllabs.com/ssltest/) Qualys SSL Labs [SSL Server Test](https://www.ssllabs.com/ssltest/)
Let's start out with needed JupyterHub configuration in `jupyterhub_config.py`: Let's start out with needed JupyterHub configuration in `jupyterhub_config.py`:
@@ -86,7 +86,6 @@ server {
proxy_http_version 1.1; proxy_http_version 1.1;
proxy_set_header Upgrade $http_upgrade; proxy_set_header Upgrade $http_upgrade;
proxy_set_header Connection $connection_upgrade; proxy_set_header Connection $connection_upgrade;
proxy_set_header X-Scheme $scheme;
proxy_buffering off; proxy_buffering off;
} }
@@ -144,7 +143,6 @@ Now restart `nginx`, restart the JupyterHub, and enjoy accessing
`https://NO_HUB.DOMAIN.TLD`. `https://NO_HUB.DOMAIN.TLD`.
### SELinux permissions for nginx ### SELinux permissions for nginx
On distributions with SELinux enabled (e.g. Fedora), one may encounter permission errors On distributions with SELinux enabled (e.g. Fedora), one may encounter permission errors
when the nginx service is started. when the nginx service is started.
@@ -156,9 +154,9 @@ semanage port -a -t http_port_t -p tcp 8000
setsebool -P httpd_can_network_relay 1 setsebool -P httpd_can_network_relay 1
setsebool -P httpd_can_network_connect 1 setsebool -P httpd_can_network_connect 1
``` ```
Replace 8000 with the port the jupyterhub server is running from. Replace 8000 with the port the jupyterhub server is running from.
## Apache ## Apache
As with nginx above, you can use [Apache](https://httpd.apache.org) as the reverse proxy. As with nginx above, you can use [Apache](https://httpd.apache.org) as the reverse proxy.
@@ -212,24 +210,22 @@ Listen 443
</VirtualHost> </VirtualHost>
``` ```
In case of the need to run the jupyterhub under /jhub/ or other location please use the below configurations:
In case of the need to run the jupyterhub under /jhub/ or other location please use the below configurations:
- JupyterHub running locally at http://127.0.0.1:8000/jhub/ or other location - JupyterHub running locally at http://127.0.0.1:8000/jhub/ or other location
httpd.conf amendments: httpd.conf amendments:
```bash ```bash
RewriteRule /jhub/(.*) ws://127.0.0.1:8000/jhub/$1 [NE.P,L] RewriteRule /jhub/(.*) ws://127.0.0.1:8000/jhub/$1 [NE.P,L]
RewriteRule /jhub/(.*) http://127.0.0.1:8000/jhub/$1 [NE,P,L] RewriteRule /jhub/(.*) http://127.0.0.1:8000/jhub/$1 [NE,P,L]
ProxyPass /jhub/ http://127.0.0.1:8000/jhub/ ProxyPass /jhub/ http://127.0.0.1:8000/jhub/
ProxyPassReverse /jhub/ http://127.0.0.1:8000/jhub/ ProxyPassReverse /jhub/ http://127.0.0.1:8000/jhub/
``` ```
jupyterhub_config.py amendments: jupyterhub_config.py amendments:
```bash
```bash
--The public facing URL of the whole JupyterHub application. --The public facing URL of the whole JupyterHub application.
--This is the address on which the proxy will bind. Sets protocol, ip, base_url --This is the address on which the proxy will bind. Sets protocol, ip, base_url
c.JupyterHub.bind_url = 'http://127.0.0.1:8000/jhub/' c.JupyterHub.bind_url = 'http://127.0.0.1:8000/jhub/'
``` ```

View File

@@ -53,6 +53,7 @@ To do this we add to `/etc/sudoers` (use `visudo` for safe editing of sudoers):
- give `rhea` permission to run `JUPYTER_CMD` on behalf of `JUPYTER_USERS` - give `rhea` permission to run `JUPYTER_CMD` on behalf of `JUPYTER_USERS`
without entering a password without entering a password
For example: For example:
```bash ```bash
@@ -90,7 +91,7 @@ $ adduser -G jupyterhub newuser
Test that the new user doesn't need to enter a password to run the sudospawner Test that the new user doesn't need to enter a password to run the sudospawner
command. command.
This should prompt for your password to switch to rhea, but _not_ prompt for This should prompt for your password to switch to rhea, but *not* prompt for
any password for the second switch. It should show some help output about any password for the second switch. It should show some help output about
logging options: logging options:
@@ -156,7 +157,6 @@ then you will need to give `node` permission to do so:
```bash ```bash
sudo setcap 'cap_net_bind_service=+ep' /usr/bin/node sudo setcap 'cap_net_bind_service=+ep' /usr/bin/node
``` ```
However, you may want to further understand the consequences of this. However, you may want to further understand the consequences of this.
You may also be interested in limiting the amount of CPU any process can use You may also be interested in limiting the amount of CPU any process can use
@@ -165,6 +165,7 @@ distributions' packaging system. This can be used to keep any user's process
from using too much CPU cycles. You can configure it accoring to [these from using too much CPU cycles. You can configure it accoring to [these
instructions](http://ubuntuforums.org/showthread.php?t=992706). instructions](http://ubuntuforums.org/showthread.php?t=992706).
### Shadow group (FreeBSD) ### Shadow group (FreeBSD)
**NOTE:** This has not been tested and may not work as expected. **NOTE:** This has not been tested and may not work as expected.

View File

@@ -22,18 +22,20 @@ This section will focus on user environments, including:
- Installing kernelspecs - Installing kernelspecs
- Using containers vs. multi-user hosts - Using containers vs. multi-user hosts
## Installing packages ## Installing packages
To make packages available to users, you generally will install packages To make packages available to users, you generally will install packages
system-wide or in a shared environment. system-wide or in a shared environment.
This installation location should always be in the same environment that This installation location should always be in the same environment that
`jupyterhub-singleuser` itself is installed in, and must be _readable and `jupyterhub-singleuser` itself is installed in, and must be *readable and
executable_ by your users. If you want users to be able to install additional executable* by your users. If you want users to be able to install additional
packages, it must also be _writable_ by your users. packages, it must also be *writable* by your users.
If you are using a standard system Python install, you would use: If you are using a standard system Python install, you would use:
```bash ```bash
sudo python3 -m pip install numpy sudo python3 -m pip install numpy
``` ```
@@ -45,6 +47,7 @@ You may also use conda to install packages. If you do, you should make sure
that the conda environment has appropriate permissions for users to be able to that the conda environment has appropriate permissions for users to be able to
run Python code in the env. run Python code in the env.
## Configuring Jupyter and IPython ## Configuring Jupyter and IPython
[Jupyter](https://jupyter-notebook.readthedocs.io/en/stable/config_overview.html) [Jupyter](https://jupyter-notebook.readthedocs.io/en/stable/config_overview.html)
@@ -61,7 +64,6 @@ users. It's generally more efficient to configure user environments "system-wide
and it's a good idea to avoid creating files in users' home directories. and it's a good idea to avoid creating files in users' home directories.
The typical locations for these config files are: The typical locations for these config files are:
- **system-wide** in `/etc/{jupyter|ipython}` - **system-wide** in `/etc/{jupyter|ipython}`
- **env-wide** (environment wide) in `{sys.prefix}/etc/{jupyter|ipython}`. - **env-wide** (environment wide) in `{sys.prefix}/etc/{jupyter|ipython}`.
@@ -89,6 +91,7 @@ c.MappingKernelManager.cull_idle_timeout = 20 * 60
c.MappingKernelManager.cull_interval = 2 * 60 c.MappingKernelManager.cull_interval = 2 * 60
``` ```
## Installing kernelspecs ## Installing kernelspecs
You may have multiple Jupyter kernels installed and want to make sure that You may have multiple Jupyter kernels installed and want to make sure that
@@ -116,6 +119,7 @@ sure are available, I can install their specs system-wide (in /usr/local) with:
/path/to/python2 -m IPython kernel install --prefix=/usr/local /path/to/python2 -m IPython kernel install --prefix=/usr/local
``` ```
## Multi-user hosts vs. Containers ## Multi-user hosts vs. Containers
There are two broad categories of user environments that depend on what There are two broad categories of user environments that depend on what
@@ -137,8 +141,8 @@ When JupyterHub uses **container-based** Spawners (e.g. KubeSpawner or
DockerSpawner), the 'system-wide' environment is really the container image DockerSpawner), the 'system-wide' environment is really the container image
which you are using for users. which you are using for users.
In both cases, you want to _avoid putting configuration in user home In both cases, you want to *avoid putting configuration in user home
directories_ because users can change those configuration settings. Also, directories* because users can change those configuration settings. Also,
home directories typically persist once they are created, so they are home directories typically persist once they are created, so they are
difficult for admins to update later. difficult for admins to update later.
@@ -175,13 +179,3 @@ The number of named servers per user can be limited by setting
```python ```python
c.JupyterHub.named_server_limit_per_user = 5 c.JupyterHub.named_server_limit_per_user = 5
``` ```
## Switching to Jupyter Server
[Jupyter Server](https://jupyter-server.readthedocs.io/en/latest/) is a new Tornado Server backend for Jupyter web applications (e.g. JupyterLab 3.0 uses this package as its default backend).
By default, the single-user notebook server uses the (old) `NotebookApp` from the [notebook](https://github.com/jupyter/notebook) package. You can switch to using Jupyter Server's `ServerApp` backend (this will likely become the default in future releases) by setting the `JUPYTERHUB_SINGLEUSER_APP` environment variable to:
```bash
export JUPYTERHUB_SINGLEUSER_APP='jupyter_server.serverapp.ServerApp'
```

View File

@@ -16,7 +16,6 @@ what happens under-the-hood when you deploy and configure your JupyterHub.
proxy proxy
separate-proxy separate-proxy
rest rest
server-api
monitoring monitoring
database database
templates templates
@@ -27,4 +26,3 @@ what happens under-the-hood when you deploy and configure your JupyterHub.
config-proxy config-proxy
config-sudo config-sudo
config-reference config-reference
oauth

View File

@@ -1,373 +0,0 @@
# JupyterHub and OAuth
JupyterHub uses OAuth 2 internally as a mechanism for authenticating users.
As such, JupyterHub itself always functions as an OAuth **provider**.
More on what that means [below](oauth-terms).
Additionally, JupyterHub is _often_ deployed with [oauthenticator](https://oauthenticator.readthedocs.io),
where an external identity provider, such as GitHub or KeyCloak, is used to authenticate users.
When this is the case, there are _two_ nested oauth flows:
an _internal_ oauth flow where JupyterHub is the **provider**,
and and _external_ oauth flow, where JupyterHub is a **client**.
This means that when you are using JupyterHub, there is always _at least one_ and often two layers of OAuth involved in a user logging in and accessing their server.
Some relevant points:
- Single-user servers _never_ need to communicate with or be aware of the upstream provider configured in your Authenticator.
As far as they are concerned, only JupyterHub is an OAuth provider,
and how users authenticate with the Hub itself is irrelevant.
- When talking to a single-user server,
there are ~always two tokens:
a token issued to the server itself to communicate with the Hub API,
and a second per-user token in the browser to represent the completed login process and authorized permissions.
More on this [later](two-tokens).
(oauth-terms)=
## Key OAuth terms
Here are some key definitions to keep in mind when we are talking about OAuth.
You can also read more detail [here](https://www.oauth.com/oauth2-servers/definitions/).
- **provider** the entity responsible for managing identity and authorization,
always a web server.
JupyterHub is _always_ an oauth provider for JupyterHub's components.
When OAuthenticator is used, an external service, such as GitHub or KeyCloak, is also an oauth provider.
- **client** An entity that requests OAuth **tokens** on a user's behalf,
generally a web server of some kind.
OAuth **clients** are services that _delegate_ authentication and/or authorization
to an OAuth **provider**.
JupyterHub _services_ or single-user _servers_ are OAuth **clients** of the JupyterHub **provider**.
When OAuthenticator is used, JupyterHub is itself _also_ an OAuth **client** for the external oauth **provider**, e.g. GitHub.
- **browser** A user's web browser, which makes requests and stores things like cookies
- **token** The secret value used to represent a user's authorization. This is the final product of the OAuth process.
- **code** A short-lived temporary secret that the **client** exchanges
for a **token** at the conclusion of oauth,
in what's generally called the "oauth callback handler."
## One oauth flow
OAuth **flow** is what we call the sequence of HTTP requests involved in authenticating a user and issuing a token, ultimately used for authorized access to a service or single-user server.
A single oauth flow generally goes like this:
### OAuth request and redirect
1. A **browser** makes an HTTP request to an oauth **client**.
2. There are no credentials, so the client _redirects_ the browser to an "authorize" page on the oauth **provider** with some extra information:
- the oauth **client id** of the client itself
- the **redirect uri** to be redirected back to after completion
- the **scopes** requested, which the user should be presented with to confirm.
This is the "X would like to be able to Y on your behalf. Allow this?" page you see on all the "Login with ..." pages around the Internet.
3. During this authorize step,
the browser must be _authenticated_ with the provider.
This is often already stored in a cookie,
but if not the provider webapp must begin its _own_ authentication process before serving the authorization page.
This _may_ even begin another oauth flow!
4. After the user tells the provider that they want to proceed with the authorization,
the provider records this authorization in a short-lived record called an **oauth code**.
5. Finally, the oauth provider redirects the browser _back_ to the oauth client's "redirect uri"
(or "oauth callback uri"),
with the oauth code in a url parameter.
That's the end of the requests made between the **browser** and the **provider**.
### State after redirect
At this point:
- The browser is authenticated with the _provider_
- The user's authorized permissions are recorded in an _oauth code_
- The _provider_ knows that the given oauth client's requested permissions have been granted, but the client doesn't know this yet.
- All requests so far have been made directly by the browser.
No requests have originated at the client or provider.
### OAuth Client Handles Callback Request
Now we get to finish the OAuth process.
Let's dig into what the oauth client does when it handles
the oauth callback request with the
- The OAuth client receives the _code_ and makes an API request to the _provider_ to exchange the code for a real _token_.
This is the first direct request between the OAuth _client_ and the _provider_.
- Once the token is retrieved, the client _usually_
makes a second API request to the _provider_
to retrieve information about the owner of the token (the user).
This is the step where behavior diverges for different OAuth providers.
Up to this point, all oauth providers are the same, following the oauth specification.
However, oauth does not define a standard for exchanging tokens for information about their owner or permissions ([OpenID Connect](https://openid.net/connect/) does that),
so this step may be different for each OAuth provider.
- Finally, the oauth client stores its own record that the user is authorized in a cookie.
This could be the token itself, or any other appropriate representation of successful authentication.
- Last of all, now that credentials have been established,
the browser can be redirected to the _original_ URL where it started,
to try the request again.
If the client wasn't able to keep track of the original URL all this time
(not always easy!),
you might end up back at a default landing page instead of where you started the login process. This is frustrating!
😮‍💨 _phew_.
So that's _one_ OAuth process.
## Full sequence of OAuth in JupyterHub
Let's go through the above oauth process in JupyterHub,
with specific examples of each HTTP request and what information is contained.
For bonus points, we are using the double-oauth example of JupyterHub configured with GitHubOAuthenticator.
To disambiguate, we will call the OAuth process where JupyterHub is the **provider** "internal oauth,"
and the one with JupyterHub as a **client** "external oauth."
Our starting point:
- a user's single-user server is running. Let's call them `danez`
- jupyterhub is running with GitHub as an oauth provider (this means two full instances of oauth),
- Danez has a fresh browser session with no cookies yet
First request:
- browser->single-user server running JupyterLab or Jupyter Classic
- `GET /user/danez/notebooks/mynotebook.ipynb`
- no credentials, so single-user server (as an oauth **client**) starts internal oauth process with JupyterHub (the **provider**)
- response: 302 redirect -> `/hub/api/oauth2/authorize`
with:
- client-id=`jupyterhub-user-danez`
- redirect-uri=`/user/danez/oauth_callback` (we'll come back later!)
Second request, following redirect:
- browser->jupyterhub
- `GET /hub/api/oauth2/authorize`
- no credentials, so jupyterhub starts external oauth process _with GitHub_
- response: 302 redirect -> `https://github.com/login/oauth/authorize`
with:
- client-id=`jupyterhub-client-uuid`
- redirect-uri=`/hub/oauth_callback` (we'll come back later!)
_pause_ This is where JupyterHub configuration comes into play.
Recall, in this case JupyterHub is using:
```python
c.JupyterHub.authenticator_class = 'github'
```
That means authenticating a request to the Hub itself starts
a _second_, external oauth process with GitHub as a provider.
This external oauth process is optional, though.
If you were using the default username+password PAMAuthenticator,
this redirect would have been to `/hub/login` instead, to present the user
with a login form.
Third request, following redirect:
- browser->GitHub
- `GET https://github.com/login/oauth/authorize`
Here, GitHub prompts for login and asks for confirmation of authorization
(more redirects if you aren't logged in to GitHub yet, but ultimately back to this `/authorize` URL).
After successful authorization
(either by looking up a pre-existing authorization,
or recording it via form submission)
GitHub issues an **oauth code** and redirects to `/hub/oauth_callback?code=github-code`
Next request:
- browser->JupyterHub
- `GET /hub/oauth_callback?code=github-code`
Inside the callback handler, JupyterHub makes two API requests:
The first:
- JupyterHub->GitHub
- `POST https://github.com/login/oauth/access_token`
- request made with oauth **code** from url parameter
- response includes an access **token**
The second:
- JupyterHub->GitHub
- `GET https://api.github.com/user`
- request made with access **token** in the `Authorization` header
- response is the user model, including username, email, etc.
Now the external oauth callback request completes with:
- set cookie on `/hub/` path, recording jupyterhub authentication so we don't need to do external oauth with GitHub again for a while
- redirect -> `/hub/api/oauth2/authorize`
🎉 At this point, we have completed our first OAuth flow! 🎉
Now, we get our first repeated request:
- browser->jupyterhub
- `GET /hub/api/oauth2/authorize`
- this time with credentials,
so jupyterhub either
1. serves the internal authorization confirmation page, or
2. automatically accepts authorization (shortcut taken when a user is visiting their own server)
- redirect -> `/user/danez/oauth_callback?code=jupyterhub-code`
Here, we start the same oauth callback process as before, but at Danez's single-user server for the _internal_ oauth
- browser->single-user server
- `GET /user/danez/oauth_callback`
(in handler)
Inside the internal oauth callback handler,
Danez's server makes two API requests to JupyterHub:
The first:
- single-user server->JupyterHub
- `POST /hub/api/oauth2/token`
- request made with oauth code from url parameter
- response includes an API token
The second:
- single-user server->JupyterHub
- `GET /hub/api/user`
- request made with token in the `Authorization` header
- response is the user model, including username, groups, etc.
Finally completing `GET /user/danez/oauth_callback`:
- response sets cookie, storing encrypted access token
- _finally_ redirects back to the original `/user/danez/notebooks/mynotebook.ipynb`
Final request:
- browser -> single-user server
- `GET /user/danez/notebooks/mynotebook.ipynb`
- encrypted jupyterhub token in cookie
To authenticate this request, the single token stored in the encrypted cookie is passed to the Hub for verification:
- single-user server -> Hub
- `GET /hub/api/user`
- browser's token in Authorization header
- response: user model with name, groups, etc.
If the user model matches who should be allowed (e.g. Danez),
then the request is allowed.
See {doc}`../rbac/scopes` for how JupyterHub uses scopes to determine authorized access to servers and services.
_the end_
## Token caches and expiry
Because tokens represent information from an external source,
they can become 'stale,'
or the information they represent may no longer be accurate.
For example: a user's GitHub account may no longer be authorized to use JupyterHub,
that should ultimately propagate to revoking access and force logging in again.
To handle this, OAuth tokens and the various places they are stored can _expire_,
which should have the same effect as no credentials,
and trigger the authorization process again.
In JupyterHub's internal oauth, we have these layers of information that can go stale:
- The oauth client has a **cache** of Hub responses for tokens,
so it doesn't need to make API requests to the Hub for every request it receives.
This cache has an expiry of five minutes by default,
and is governed by the configuration `HubAuth.cache_max_age` in the single-user server.
- The internal oauth token is stored in a cookie, which has its own expiry (default: 14 days),
governed by `JupyterHub.cookie_max_age_days`.
- The internal oauth token can also itself expire,
which is by default the same as the cookie expiry,
since it makes sense for the token itself and the place it is stored to expire at the same time.
This is governed by `JupyterHub.cookie_max_age_days` first,
or can overridden by `JupyterHub.oauth_token_expires_in`.
That's all for _internal_ auth storage,
but the information from the _external_ authentication provider
(could be PAM or GitHub OAuth, etc.) can also expire.
Authenticator configuration governs when JupyterHub needs to ask again,
triggering the external login process anew before letting a user proceed.
- `jupyterhub-hub-login` cookie stores that a browser is authenticated with the Hub.
This expires according to `JupyterHub.cookie_max_age_days` configuration,
with a default of 14 days.
The `jupyterhub-hub-login` cookie is encrypted with `JupyterHub.cookie_secret`
configuration.
- {meth}`.Authenticator.refresh_user` is a method to refresh a user's auth info.
By default, it does nothing, but it can return an updated user model if a user's information has changed,
or force a full login process again if needed.
- {attr}`.Authenticator.auth_refresh_age` configuration governs how often
`refresh_user()` will be called to check if a user must login again (default: 300 seconds).
- {attr}`.Authenticator.refresh_pre_spawn` configuration governs whether
`refresh_user()` should be called prior to spawning a server,
to force fresh auth info when a server is launched (default: False).
This can be useful when Authenticators pass access tokens to spawner environments, to ensure they aren't getting a stale token that's about to expire.
**So what happens when these things expire or get stale?**
- If the HubAuth **token response cache** expires,
when a request is made with a token,
the Hub is asked for the latest information about the token.
This usually has no visible effect, since it is just refreshing a cache.
If it turns out that the token itself has expired or been revoked,
the request will be denied.
- If the token has expired, but is still in the cookie:
when the token response cache expires,
the next time the server asks the hub about the token,
no user will be identified and the internal oauth process begins again.
- If the token _cookie_ expires, the next browser request will be made with no credentials,
and the internal oauth process will begin again.
This will usually have the form of a transparent redirect browsers won't notice.
However, if this occurs on an API request in a long-lived page visit
such as a JupyterLab session, the API request may fail and require
a page refresh to get renewed credentials.
- If the _JupyterHub_ cookie expires, the next time the browser makes a request to the Hub,
the Hub's authorization process must begin again (e.g. login with GitHub).
Hub cookie expiry on its own **does not** mean that a user can no longer access their single-user server!
- If credentials from the upstream provider (e.g. GitHub) become stale or outdated,
these will not be refreshed until/unless `refresh_user` is called
_and_ `refresh_user()` on the given Authenticator is implemented to perform such a check.
At this point, few Authenticators implement `refresh_user` to support this feature.
If your Authenticator does not or cannot implement `refresh_user`,
the only way to force a check is to reset the `JupyterHub.cookie_secret` encryption key,
which invalidates the `jupyterhub-hub-login` cookie for all users.
### Logging out
Logging out of JupyterHub means clearing and revoking many of these credentials:
- The `jupyterhub-hub-login` cookie is revoked, meaning the next request to the Hub itself will require a new login.
- The token stored in the `jupyterhub-user-username` cookie for the single-user server
will be revoked, based on its associaton with `jupyterhub-session-id`, but the _cookie itself cannot be cleared at this point_
- The shared `jupyterhub-session-id` is cleared, which ensures that the HubAuth **token response cache** will not be used,
and the next request with the expired token will ask the Hub, which will inform the single-user server that the token has expired
## Extra bits
(two-tokens)=
### A tale of two tokens
**TODO**: discuss API token issued to server at startup ($JUPYTERHUB_API_TOKEN)
and oauth-issued token in the cookie,
and some details of how JupyterLab currently deals with that.
They are different, and JupyterLab should be making requests using the token from the cookie,
not the token from the server,
but that is not currently the case.
### Redirect loops
In general, an authenticated web endpoint has this behavior,
based on the authentication/authorization state of the browser:
- If authorized, allow the request to happen
- If authenticated (I know who you are) but not authorized (you are not allowed), fail with a 403 permission denied error
- If not authenticated, start a redirect process to establish authorization,
which should end in a redirect back to the original URL to try again.
**This is why problems in authentication result in redirect loops!**
If the second request fails to detect the authentication that should have been established during the redirect,
it will start the authentication redirect process over again,
and keep redirecting in a loop until the browser balks.

View File

@@ -136,7 +136,7 @@ async def delete_route(self, routespec):
### Retrieving routes ### Retrieving routes
For retrieval, you only _need_ to implement a single method that retrieves all For retrieval, you only *need* to implement a single method that retrieves all
routes. The return value for this function should be a dictionary, keyed by routes. The return value for this function should be a dictionary, keyed by
`routespect`, of dicts whose keys are the same three arguments passed to `routespect`, of dicts whose keys are the same three arguments passed to
`add_route` (`routespec`, `target`, `data`) `add_route` (`routespec`, `target`, `data`)
@@ -220,11 +220,3 @@ previously required.
Additionally, configurable attributes for your proxy will Additionally, configurable attributes for your proxy will
appear in jupyterhub help output and auto-generated configuration files appear in jupyterhub help output and auto-generated configuration files
via `jupyterhub --generate-config`. via `jupyterhub --generate-config`.
### Index of proxies
A list of the proxies that are currently available for JupyterHub (that we know about).
1. [`jupyterhub/configurable-http-proxy`](https://github.com/jupyterhub/configurable-http-proxy) The default proxy which uses node-http-proxy
2. [`jupyterhub/traefik-proxy`](https://github.com/jupyterhub/traefik-proxy) The proxy which configures traefik proxy server for jupyterhub
3. [`AbdealiJK/configurable-http-proxy`](https://github.com/AbdealiJK/configurable-http-proxy) A pure python implementation of the configurable-http-proxy

View File

@@ -17,7 +17,6 @@ such as:
- adding or removing users - adding or removing users
- stopping or starting single user notebook servers - stopping or starting single user notebook servers
- authenticating services - authenticating services
- communicating with an individual Jupyter server's REST API
A [REST](https://en.wikipedia.org/wiki/Representational_state_transfer) A [REST](https://en.wikipedia.org/wiki/Representational_state_transfer)
API provides a standard way for users to get and send information to the API provides a standard way for users to get and send information to the
@@ -28,7 +27,8 @@ Hub.
To send requests using JupyterHub API, you must pass an API token with To send requests using JupyterHub API, you must pass an API token with
the request. the request.
The preferred way of generating an API token is: As of [version 0.6.0](../changelog.md), the preferred way of
generating an API token is:
```bash ```bash
openssl rand -hex 32 openssl rand -hex 32
@@ -48,34 +48,33 @@ jupyterhub token <username>
This command generates a random string to use as a token and registers This command generates a random string to use as a token and registers
it for the given user with the Hub's database. it for the given user with the Hub's database.
In [version 0.8.0](../changelog.md), a token request page for In [version 0.8.0](../changelog.md), a TOKEN request page for
generating an API token is available from the JupyterHub user interface: generating an API token is available from the JupyterHub user interface:
![Request API token page](../images/token-request.png) ![Request API TOKEN page](../images/token-request.png)
![API token success page](../images/token-request-success.png) ![API TOKEN success page](../images/token-request-success.png)
## Assigning permissions to a token ## Add API tokens to the config file
Prior to JupyterHub 2.0, there were two levels of permissions: **This is deprecated. We are in no rush to remove this feature,
but please consider if service tokens are right for you.**
1. user, and You may also add a dictionary of API tokens and usernames to the hub's
2. admin configuration file, `jupyterhub_config.py` (note that
the **key** is the 'secret-token' while the **value** is the 'username'):
where a token would always have full permissions to do whatever its owner could do. ```python
c.JupyterHub.api_tokens = {
In JupyterHub 2.0, 'secret-token': 'username',
specific permissions are now defined as 'scopes', }
and can be assigned both at the user/service level, ```
and at the individual token level.
This allows e.g. a user with full admin permissions to request a token with limited permissions.
### Updating to admin services ### Updating to admin services
The `api_tokens` configuration has been softly deprecated since the introduction of services. The `api_tokens` configuration has been softly deprecated since the introduction of services.
We have no plans to remove it, We have no plans to remove it,
but deployments are encouraged to use service configuration instead. but users are encouraged to use service configuration instead.
If you have been using `api_tokens` to create an admin user If you have been using `api_tokens` to create an admin user
and a token for that user to perform some automations, and a token for that user to perform some automations,
@@ -89,40 +88,19 @@ c.JupyterHub.api_tokens = {
} }
``` ```
This can be updated to create a service, with the following configuration: This can be updated to create an admin service, with the following configuration:
```python ```python
c.JupyterHub.services = [ c.JupyterHub.services = [
{ {
# give the token a name "name": "service-token",
"name": "service-admin", "admin": True,
"api_token": "secret-token", "api_token": "secret-token",
# "admin": True, # if using JupyterHub 1.x
}, },
] ]
# roles are new in JupyterHub 2.0
# prior to 2.0, only 'admin': True or False
# was available
c.JupyterHub.load_roles = [
{
"name": "service-role",
"scopes": [
# specify the permissions the token should have
"admin:users",
"admin:services",
],
"services": [
# assign the service the above permissions
"service-admin",
],
}
]
``` ```
The token will have the permissions listed in the role The token will have the same admin permissions,
(see [scopes][] for a list of available permissions),
but there will no longer be a user account created to house it. but there will no longer be a user account created to house it.
The main noticeable difference is that there will be no notebook server associated with the account The main noticeable difference is that there will be no notebook server associated with the account
and the service will not show up in the various user list pages and APIs. and the service will not show up in the various user list pages and APIs.
@@ -134,7 +112,7 @@ Authorization header.
### Use requests ### Use requests
Using the popular Python [requests](https://docs.python-requests.org) Using the popular Python [requests](http://docs.python-requests.org/en/master/)
library, here's example code to make an API request for the users of a JupyterHub library, here's example code to make an API request for the users of a JupyterHub
deployment. An API GET request is made, and the request sends an API token for deployment. An API GET request is made, and the request sends an API token for
authorization. The response contains information about the users: authorization. The response contains information about the users:
@@ -146,9 +124,9 @@ api_url = 'http://127.0.0.1:8081/hub/api'
r = requests.get(api_url + '/users', r = requests.get(api_url + '/users',
headers={ headers={
'Authorization': f'token {token}', 'Authorization': 'token %s' % token,
} }
) )
r.raise_for_status() r.raise_for_status()
users = r.json() users = r.json()
@@ -166,95 +144,19 @@ data = {'name': 'mygroup', 'users': ['user1', 'user2']}
r = requests.post(api_url + '/groups/formgrade-data301/users', r = requests.post(api_url + '/groups/formgrade-data301/users',
headers={ headers={
'Authorization': f'token {token}', 'Authorization': 'token %s' % token,
}, },
json=data, json=data
) )
r.raise_for_status() r.raise_for_status()
r.json() r.json()
``` ```
The same API token can also authorize access to the [Jupyter Notebook REST API][] The same API token can also authorize access to the [Jupyter Notebook REST API][]
provided by notebook servers managed by JupyterHub if it has the necessary `access:users:servers` scope: provided by notebook servers managed by JupyterHub if one of the following is true:
(api-pagination)= 1. The token is for the same user as the owner of the notebook
2. The token is tied to an admin user or service **and** `c.JupyterHub.admin_access` is set to `True`
## Paginating API requests
```{versionadded} 2.0
```
Pagination is available through the `offset` and `limit` query parameters on
list endpoints, which can be used to return ideally sized windows of results.
Here's example code demonstrating pagination on the `GET /users`
endpoint to fetch the first 20 records.
```python
import os
import requests
api_url = 'http://127.0.0.1:8081/hub/api'
r = requests.get(
api_url + '/users?offset=0&limit=20',
headers={
"Accept": "application/jupyterhub-pagination+json",
"Authorization": f"token {token}",
},
)
r.raise_for_status()
r.json()
```
For backward-compatibility, the default structure of list responses is unchanged.
However, this lacks pagination information (e.g. is there a next page),
so if you have enough users that they won't fit in the first response,
it is a good idea to opt-in to the new paginated list format.
There is a new schema for list responses which include pagination information.
You can request this by including the header:
```
Accept: application/jupyterhub-pagination+json
```
with your request, in which case a response will look like:
```python
{
"items": [
{
"name": "username",
"kind": "user",
...
},
],
"_pagination": {
"offset": 0,
"limit": 20,
"total": 50,
"next": {
"offset": 20,
"limit": 20,
"url": "http://127.0.0.1:8081/hub/api/users?limit=20&offset=20"
}
}
}
```
where the list results (same as pre-2.0) will be in `items`,
and pagination info will be in `_pagination`.
The `next` field will include the offset, limit, and URL for requesting the next page.
`next` will be `null` if there is no next page.
Pagination is governed by two configuration options:
- `JupyterHub.api_page_default_limit` - the page size, if `limit` is unspecified in the request
and the new pagination API is requested
(default: 50)
- `JupyterHub.api_page_max_limit` - the maximum page size a request can ask for (default: 200)
Pagination is enabled on the `GET /users`, `GET /groups`, and `GET /proxy` REST endpoints.
## Enabling users to spawn multiple named-servers via the API ## Enabling users to spawn multiple named-servers via the API
@@ -285,7 +187,6 @@ hub:
``` ```
With that setting in place, a new named-server is activated like this: With that setting in place, a new named-server is activated like this:
```bash ```bash
curl -X POST -H "Authorization: token <token>" "http://127.0.0.1:8081/hub/api/users/<user>/servers/<serverA>" curl -X POST -H "Authorization: token <token>" "http://127.0.0.1:8081/hub/api/users/<user>/servers/<serverA>"
curl -X POST -H "Authorization: token <token>" "http://127.0.0.1:8081/hub/api/users/<user>/servers/<serverB>" curl -X POST -H "Authorization: token <token>" "http://127.0.0.1:8081/hub/api/users/<user>/servers/<serverB>"
@@ -300,6 +201,7 @@ will need to be able to handle the case of multiple servers per user and ensure
uniqueness of names, particularly if servers are spawned via docker containers uniqueness of names, particularly if servers are spawned via docker containers
or kubernetes pods. or kubernetes pods.
## Learn more about the API ## Learn more about the API
You can see the full [JupyterHub REST API][] for details. This REST API Spec can You can see the full [JupyterHub REST API][] for details. This REST API Spec can
@@ -307,7 +209,7 @@ be viewed in a more [interactive style on swagger's petstore][].
Both resources contain the same information and differ only in its display. Both resources contain the same information and differ only in its display.
Note: The Swagger specification is being renamed the [OpenAPI Initiative][]. Note: The Swagger specification is being renamed the [OpenAPI Initiative][].
[interactive style on swagger's petstore]: https://petstore3.swagger.io/?url=https://raw.githubusercontent.com/jupyterhub/jupyterhub/HEAD/docs/rest-api.yml#!/default [interactive style on swagger's petstore]: http://petstore.swagger.io/?url=https://raw.githubusercontent.com/jupyterhub/jupyterhub/master/docs/rest-api.yml#!/default
[openapi initiative]: https://www.openapis.org/ [OpenAPI Initiative]: https://www.openapis.org/
[jupyterhub rest api]: ./rest-api [JupyterHub REST API]: ./rest-api
[jupyter notebook rest api]: https://petstore3.swagger.io/?url=https://raw.githubusercontent.com/jupyter/notebook/HEAD/notebook/services/api/api.yaml [Jupyter Notebook REST API]: http://petstore.swagger.io/?url=https://raw.githubusercontent.com/jupyter/notebook/master/notebook/services/api/api.yaml

View File

@@ -1,5 +1,6 @@
# Running proxy separately from the hub # Running proxy separately from the hub
## Background ## Background
The thing which users directly connect to is the proxy, by default The thing which users directly connect to is the proxy, by default
@@ -21,6 +22,7 @@ The default JupyterHub proxy is
and that page has some docs. If you are using a different proxy, such and that page has some docs. If you are using a different proxy, such
as Traefik, these instructions are probably not relevant to you. as Traefik, these instructions are probably not relevant to you.
## Configuration options ## Configuration options
`c.JupyterHub.cleanup_servers = False` should be set, which tells the `c.JupyterHub.cleanup_servers = False` should be set, which tells the
@@ -35,12 +37,16 @@ it yourself).
token for authenticating communication with the proxy. token for authenticating communication with the proxy.
`c.ConfigurableHTTPProxy.api_url = 'http://localhost:8001'` should be `c.ConfigurableHTTPProxy.api_url = 'http://localhost:8001'` should be
set to the URL which the hub uses to connect _to the proxy's API_. set to the URL which the hub uses to connect *to the proxy's API*.
## Proxy configuration ## Proxy configuration
You need to configure a service to start the proxy. An example You need to configure a service to start the proxy. An example
command line for this is `configurable-http-proxy --ip=127.0.0.1 --port=8000 --api-ip=127.0.0.1 --api-port=8001 --default-target=http://localhost:8081 --error-target=http://localhost:8081/hub/error`. (Details for how to command line for this is `configurable-http-proxy --ip=127.0.0.1
--port=8000 --api-ip=127.0.0.1 --api-port=8001
--default-target=http://localhost:8081
--error-target=http://localhost:8081/hub/error`. (Details for how to
do this is out of scope for this tutorial - for example it might be a do this is out of scope for this tutorial - for example it might be a
systemd service on within another docker cotainer). The proxy has no systemd service on within another docker cotainer). The proxy has no
configuration files, all configuration is via the command line and configuration files, all configuration is via the command line and
@@ -48,7 +54,7 @@ environment variables.
`--api-ip` and `--api-port` (which tells the proxy where to listen) should match the hub's `ConfigurableHTTPProxy.api_url`. `--api-ip` and `--api-port` (which tells the proxy where to listen) should match the hub's `ConfigurableHTTPProxy.api_url`.
`--ip`, `-port`, and other options configure the _user_ connections to the proxy. `--ip`, `-port`, and other options configure the *user* connections to the proxy.
`--default-target` and `--error-target` should point to the hub, and used when users navigate to the proxy originally. `--default-target` and `--error-target` should point to the hub, and used when users navigate to the proxy originally.
@@ -61,12 +67,14 @@ what other options are needed, for example SSL options. Note that
these are configured in the hub if the hub is starting the proxy - you these are configured in the hub if the hub is starting the proxy - you
need to move the options to here. need to move the options to here.
## Docker image ## Docker image
You can use [jupyterhub configurable-http-proxy docker You can use [jupyterhub configurable-http-proxy docker
image](https://hub.docker.com/r/jupyterhub/configurable-http-proxy/) image](https://hub.docker.com/r/jupyterhub/configurable-http-proxy/)
to run the proxy. to run the proxy.
## See also ## See also
- [jupyterhub configurable-http-proxy](https://github.com/jupyterhub/configurable-http-proxy) * [jupyterhub configurable-http-proxy](https://github.com/jupyterhub/configurable-http-proxy)

View File

@@ -1,369 +0,0 @@
# Starting servers with the JupyterHub API
JupyterHub's [REST API][] allows launching servers on behalf of users
without ever interacting with the JupyterHub UI.
This allows you to build services launching Jupyter-based services for users
without relying on the JupyterHub UI at all,
enabling a variety of user/launch/lifecycle patterns not natively supported by JupyterHub,
without needing to develop all the server management features of JupyterHub Spawners and/or Authenticators.
[BinderHub][] is an example of such an application.
[binderhub]: https://binderhub.readthedocs.io
[rest api]: ../reference/rest.md
This document provides an example of working with the JupyterHub API to
manage servers for users.
In particular, we will cover how to:
1. [check status of servers](checking)
2. [start servers](starting)
3. [wait for servers to be ready](waiting)
4. [communicate with servers](communicating)
5. [stop servers](stopping)
(checking)=
## Checking server status
Requesting information about a user includes a `servers` field,
which is a dictionary.
```
GET /hub/api/users/:username
```
**Required scope: `read:servers`**
```json
{
"admin": false,
"groups": [],
"pending": null,
"server": null,
"name": "test-1",
"kind": "user",
"last_activity": "2021-08-03T18:12:46.026411Z",
"created": "2021-08-03T18:09:59.767600Z",
"roles": ["user"],
"servers": {}
}
```
If the `servers` dict is empty, the user has no running servers.
The keys of the `servers` dict are server names as strings.
Many JupyterHub deployments only use the 'default' server,
which has the empty string `''` for a name.
In this case, the servers dict will always have either zero or one elements.
This is the servers dict when the user's default server is fully running and ready:
```json
"servers": {
"": {
"name": "",
"last_activity": "2021-08-03T18:48:35.934000Z",
"started": "2021-08-03T18:48:29.093885Z",
"pending": null,
"ready": true,
"url": "/user/test-1/",
"user_options": {},
"progress_url": "/hub/api/users/test-1/server/progress"
}
}
```
Key properties of a server:
name
: the server's name. Always the same as the key in `servers`
ready
: boolean. If true, the server can be expected to respond to requests at `url`.
pending
: `null` or a string indicating a transitional state (such as `start` or `stop`).
Will always be `null` if `ready` is true,
and will always be a string if `ready` is false.
url
: The server's url (just the path, e.g. `/users/:name/:servername/`)
where the server can be accessed if `ready` is true.
progress_url
: The API url path (starting with `/hub/api`)
where the progress API can be used to wait for the server to be ready.
See below for more details on the progress API.
last_activity
: ISO8601 timestamp indicating when activity was last observed on the server
started
: ISO801 timestamp indicating when the server was last started
We've seen the `servers` model with no servers and with one `ready` server.
Here is what it looks like immediately after requesting a server launch,
while the server is not ready yet:
```json
"servers": {
"": {
"name": "",
"last_activity": "2021-08-03T18:48:29.093885Z",
"started": "2021-08-03T18:48:29.093885Z",
"pending": "spawn",
"ready": false,
"url": "/user/test-1/",
"user_options": {},
"progress_url": "/hub/api/users/test-1/server/progress"
}
}
```
Note that `ready` is false and `pending` is `spawn`.
This means that the server is not ready
(attempting to access it may not work)
because it isn't finished spawning yet.
We'll get more into that below in [waiting for a server][].
[waiting for a server]: waiting
(starting)=
## Starting servers
To start a server, make the request
```
POST /hub/api/users/:username/servers/[:servername]
```
**Required scope: `servers`**
(omit servername for the default server)
Assuming the request was valid,
there are two possible responses:
201 Created
: This status code means the launch completed and the server is ready.
It should be available at the server's URL immediately.
202 Accepted
: This is the more likely response,
and means that the server has begun launching,
but isn't immediately ready.
The server has `pending: 'spawn'` at this point.
_Aside: how quickly JupyterHub responds with `202 Accepted` is governed by the `slow_spawn_timeout` tornado setting._
(waiting)=
## Waiting for a server
If you are starting a server via the API,
there's a good change you want to know when it's ready.
There are two ways to do with:
1. {ref}`Polling the server model <polling>`
2. the {ref}`progress API <progress>`
(polling)=
### Polling the server model
The simplest way to check if a server is ready
is to request the user model.
If:
1. the server name is in the user's `servers` model, and
2. `servers['servername']['ready']` is true
A Python example, checking if a server is ready:
```python
def server_ready(hub_url, user, server_name="", token):
r = requests.get(
f"{hub_url}/hub/api/users/{user}/servers/{server_name}",
headers={"Authorization": f"token {token}"},
)
r.raise_for_status()
user_model = r.json()
servers = user_model.get("servers", {})
if server_name not in servers:
return False
server = servers[server_name]
if server['ready']:
print(f"Server {user}/{server_name} ready at {server['url']}")
return True
else:
print(f"Server {user}/{server_name} not ready, pending {server['pending']}")
return False
```
You can keep making this check until `ready` is true.
(progress)=
### Progress API
The most _efficient_ way to wait for a server to start is the progress API.
The progress URL is available in the server model under `progress_url`,
and has the form `/hub/api/users/:user/servers/:servername/progress`.
_the default server progress can be accessed at `:user/servers//progress` or `:user/server/progress`_
```
GET /hub/api/users/:user/servers/:servername/progress
```
**Required scope: `read:servers`**
This is an [EventStream][] API.
In an event stream, messages are _streamed_ and delivered on lines of the form:
```
data: {"progress": 10, "message": "...", ...}
```
where the line after `data:` contains a JSON-serialized dictionary.
Lines that do not start with `data:` should be ignored.
[eventstream]: https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#examples
progress events have the form:
```python
{
"progress": 0-100,
"message": "",
"ready": True, # or False
}
```
progress
: integer, 0-100
message
: string message describing progress stages
ready
: present and true only for the last event when the server is ready
url
: only present if `ready` is true; will be the server's url
the progress API can be used even with fully ready servers.
If the server is ready,
there will only be one event that looks like:
```json
{
"progress": 100,
"ready": true,
"message": "Server ready at /user/test-1/",
"html_message": "Server ready at <a href=\"/user/test-1/\">/user/test-1/</a>",
"url": "/user/test-1/"
}
```
where `ready` and `url` are the same as in the server model (`ready` will always be true).
A typical complete stream from the event-stream API:
```
data: {"progress": 0, "message": "Server requested"}
data: {"progress": 50, "message": "Spawning server..."}
data: {"progress": 100, "ready": true, "message": "Server ready at /user/test-user/", "html_message": "Server ready at <a href=\"/user/test-user/\">/user/test-user/</a>", "url": "/user/test-user/"}
```
Here is a Python example for consuming an event stream:
```{literalinclude} ../../../examples/server-api/start-stop-server.py
:language: python
:pyobject: event_stream
```
(stopping)=
## Stopping servers
Servers can be stopped with a DELETE request:
```
DELETE /hub/api/users/:user/servers/[:servername]
```
**Required scope: `servers`**
Like start, delete may not complete immediately.
The DELETE request has two possible response codes:
204 Deleted
: This status code means the delete completed and the server is fully stopped.
It will now be absent from the user `servers` model.
202 Accepted
: Like start, `202` means your request was accepted,
but is not yet complete.
The server has `pending: 'stop'` at this point.
Unlike start, there is no progress API for stop.
To wait for stop to finish, you must poll the user model
and wait for the server to disappear from the user `servers` model.
```{literalinclude} ../../../examples/server-api/start-stop-server.py
:language: python
:pyobject: stop_server
```
(communicating)=
## Communicating with servers
JupyterHub tokens with the the `access:servers` scope
can be used to communicate with servers themselves.
This can be the same token you used to launch your service.
```{note}
Access scopes are new in JupyterHub 2.0.
To access servers in JupyterHub 1.x,
a token must be owned by the same user as the server,
*or* be an admin token if admin_access is enabled.
```
The URL returned from a server model is the url path suffix,
e.g. `/user/:name/` to append to the jupyterhub base URL.
For instance, `{hub_url}{server_url}`,
where `hub_url` would be e.g. `http://127.0.0.1:8000` by default,
and `server_url` `/user/myname`,
for a full url of `http://127.0.0.1:8000/user/myname`.
## Python example
The JupyterHub repo includes a complete example in {file}`examples/server-api`
tying all this together.
To summarize the steps:
1. get user info from `/user/:name`
2. the server model includes a `ready` state to tell you if it's ready
3. if it's not ready, you can follow up with `progress_url` to wait for it
4. if it is ready, you can use the `url` field to link directly to the running server
The example demonstrates starting and stopping servers via the JupyterHub API,
including waiting for them to start via the progress API,
as well as waiting for them to stop via polling the user model.
```{literalinclude} ../../../examples/server-api/start-stop-server.py
:language: python
:start-at: def event_stream
:end-before: def main
```

View File

@@ -50,8 +50,11 @@ A Service may have the following properties:
If a service is also to be managed by the Hub, it has a few extra options: If a service is also to be managed by the Hub, it has a few extra options:
- `command: (str/Popen list)` - Command for JupyterHub to spawn the service. - Only use this if the service should be a subprocess. - If command is not specified, the Service is assumed to be managed - `command: (str/Popen list`) - Command for JupyterHub to spawn the service.
externally. - If a command is specified for launching the Service, the Service will - Only use this if the service should be a subprocess.
- If command is not specified, the Service is assumed to be managed
externally.
- If a command is specified for launching the Service, the Service will
be started and managed by the Hub. be started and managed by the Hub.
- `environment: dict` - additional environment variables for the Service. - `environment: dict` - additional environment variables for the Service.
- `user: str` - the name of a system user to manage the Service. If - `user: str` - the name of a system user to manage the Service. If
@@ -86,20 +89,11 @@ Hub-Managed Service would include:
This example would be configured as follows in `jupyterhub_config.py`: This example would be configured as follows in `jupyterhub_config.py`:
```python ```python
c.JupyterHub.load_roles = [
{
"name": "idle-culler",
"scopes": [
"read:users:activity", # read user last_activity
"servers", # start and stop servers
# 'admin:users' # needed if culling idle users as well
]
}
c.JupyterHub.services = [ c.JupyterHub.services = [
{ {
'name': 'idle-culler', 'name': 'cull-idle',
'command': [sys.executable, '-m', 'jupyterhub_idle_culler', '--timeout=3600'] 'admin': True,
'command': [sys.executable, '/path/to/cull-idle.py', '--timeout']
} }
] ]
``` ```
@@ -123,21 +117,21 @@ JUPYTERHUB_BASE_URL: Base URL of the Hub (https://mydomain[:port]/)
JUPYTERHUB_SERVICE_PREFIX: URL path prefix of this service (/services/:service-name/) JUPYTERHUB_SERVICE_PREFIX: URL path prefix of this service (/services/:service-name/)
JUPYTERHUB_SERVICE_URL: Local URL where the service is expected to be listening. JUPYTERHUB_SERVICE_URL: Local URL where the service is expected to be listening.
Only for proxied web services. Only for proxied web services.
JUPYTERHUB_OAUTH_SCOPES: JSON-serialized list of scopes to use for allowing access to the service.
``` ```
For the previous 'cull idle' Service example, these environment variables For the previous 'cull idle' Service example, these environment variables
would be passed to the Service when the Hub starts the 'cull idle' Service: would be passed to the Service when the Hub starts the 'cull idle' Service:
```bash ```bash
JUPYTERHUB_SERVICE_NAME: 'idle-culler' JUPYTERHUB_SERVICE_NAME: 'cull-idle'
JUPYTERHUB_API_TOKEN: API token assigned to the service JUPYTERHUB_API_TOKEN: API token assigned to the service
JUPYTERHUB_API_URL: http://127.0.0.1:8080/hub/api JUPYTERHUB_API_URL: http://127.0.0.1:8080/hub/api
JUPYTERHUB_BASE_URL: https://mydomain[:port] JUPYTERHUB_BASE_URL: https://mydomain[:port]
JUPYTERHUB_SERVICE_PREFIX: /services/idle-culler/ JUPYTERHUB_SERVICE_PREFIX: /services/cull-idle/
``` ```
See the GitHub repo for additional information about the [jupyterhub_idle_culler][]. See the JupyterHub GitHub repo for additional information about the
[`cull-idle` example](https://github.com/jupyterhub/jupyterhub/tree/master/examples/cull-idle).
## Externally-Managed Services ## Externally-Managed Services
@@ -206,14 +200,16 @@ can be used by services. You may go beyond this reference implementation and
create custom hub-authenticating clients and services. We describe the process create custom hub-authenticating clients and services. We describe the process
below. below.
The reference, or base, implementation is the [`HubAuth`][hubauth] class, The reference, or base, implementation is the [`HubAuth`][HubAuth] class,
which implements the requests to the Hub. which implements the requests to the Hub.
To use HubAuth, you must set the `.api_token`, either programmatically when constructing the class, To use HubAuth, you must set the `.api_token`, either programmatically when constructing the class,
or via the `JUPYTERHUB_API_TOKEN` environment variable. or via the `JUPYTERHUB_API_TOKEN` environment variable.
Most of the logic for authentication implementation is found in the Most of the logic for authentication implementation is found in the
[`HubAuth.user_for_token`][hubauth.user_for_token] [`HubAuth.user_for_cookie`][HubAuth.user_for_cookie]
and in the
[`HubAuth.user_for_token`][HubAuth.user_for_token]
methods, which makes a request of the Hub, and returns: methods, which makes a request of the Hub, and returns:
- None, if no user could be identified, or - None, if no user could be identified, or
@@ -223,9 +219,7 @@ methods, which makes a request of the Hub, and returns:
{ {
"name": "username", "name": "username",
"groups": ["list", "of", "groups"], "groups": ["list", "of", "groups"],
"scopes": [ "admin": False, # or True
"access:users:servers!server=username/",
],
} }
``` ```
@@ -240,17 +234,63 @@ configurable by the `cookie_cache_max_age` setting (default: five minutes).
For example, you have a Flask service that returns information about a user. For example, you have a Flask service that returns information about a user.
JupyterHub's HubAuth class can be used to authenticate requests to the Flask JupyterHub's HubAuth class can be used to authenticate requests to the Flask
service. See the `service-whoami-flask` example in the service. See the `service-whoami-flask` example in the
[JupyterHub GitHub repo](https://github.com/jupyterhub/jupyterhub/tree/HEAD/examples/service-whoami-flask) [JupyterHub GitHub repo](https://github.com/jupyterhub/jupyterhub/tree/master/examples/service-whoami-flask)
for more details. for more details.
```{literalinclude} ../../../examples/service-whoami-flask/whoami-flask.py ```python
:language: python from functools import wraps
import json
import os
from urllib.parse import quote
from flask import Flask, redirect, request, Response
from jupyterhub.services.auth import HubAuth
prefix = os.environ.get('JUPYTERHUB_SERVICE_PREFIX', '/')
auth = HubAuth(
api_token=os.environ['JUPYTERHUB_API_TOKEN'],
cache_max_age=60,
)
app = Flask(__name__)
def authenticated(f):
"""Decorator for authenticating with the Hub"""
@wraps(f)
def decorated(*args, **kwargs):
cookie = request.cookies.get(auth.cookie_name)
token = request.headers.get(auth.auth_header_name)
if cookie:
user = auth.user_for_cookie(cookie)
elif token:
user = auth.user_for_token(token)
else:
user = None
if user:
return f(user, *args, **kwargs)
else:
# redirect to login url on failed auth
return redirect(auth.login_url + '?next=%s' % quote(request.path))
return decorated
@app.route(prefix)
@authenticated
def whoami(user):
return Response(
json.dumps(user, indent=1, sort_keys=True),
mimetype='application/json',
)
``` ```
### Authenticating tornado services with JupyterHub ### Authenticating tornado services with JupyterHub
Since most Jupyter services are written with tornado, Since most Jupyter services are written with tornado,
we include a mixin class, [`HubAuthenticated`][hubauthenticated], we include a mixin class, [`HubAuthenticated`][HubAuthenticated],
for quickly authenticating your own tornado services with JupyterHub. for quickly authenticating your own tornado services with JupyterHub.
Tornado's `@web.authenticated` method calls a Handler's `.get_current_user` Tornado's `@web.authenticated` method calls a Handler's `.get_current_user`
@@ -271,6 +311,7 @@ class MyHandler(HubAuthenticated, web.RequestHandler):
... ...
``` ```
The HubAuth will automatically load the desired configuration from the Service The HubAuth will automatically load the desired configuration from the Service
environment variables. environment variables.
@@ -280,43 +321,31 @@ username and user group list, respectively. If a user matches neither the user
list nor the group list, they will not be allowed access. If both are left list nor the group list, they will not be allowed access. If both are left
undefined, then any user will be allowed. undefined, then any user will be allowed.
### Implementing your own Authentication with JupyterHub ### Implementing your own Authentication with JupyterHub
If you don't want to use the reference implementation If you don't want to use the reference implementation
(e.g. you find the implementation a poor fit for your Flask app), (e.g. you find the implementation a poor fit for your Flask app),
you can implement authentication via the Hub yourself. you can implement authentication via the Hub yourself.
JupyterHub is a standard OAuth2 provider, We recommend looking at the [`HubAuth`][HubAuth] class implementation for reference,
so you can use any OAuth 2 client implementation appropriate for your toolkit.
See the [FastAPI example][] for an example of using JupyterHub as an OAuth provider with [FastAPI][],
without using any code imported from JupyterHub.
On completion of OAuth, you will have an access token for JupyterHub,
which can be used to identify the user and the permissions (scopes)
the user has authorized for your service.
You will only get to this stage if the user has the required `access:services!service=$service-name` scope.
To retrieve the user model for the token, make a request to `GET /hub/api/user` with the token in the Authorization header.
For example, using flask:
```{literalinclude} ../../../examples/service-whoami-flask/whoami-flask.py
:language: python
```
We recommend looking at the [`HubOAuth`][huboauth] class implementation for reference,
and taking note of the following process: and taking note of the following process:
1. retrieve the token from the request. 1. retrieve the cookie `jupyterhub-services` from the request.
2. Make an API request `GET /hub/api/user`, 2. Make an API request `GET /hub/api/authorizations/cookie/jupyterhub-services/cookie-value`,
with the token in the `Authorization` header. where cookie-value is the url-encoded value of the `jupyterhub-services` cookie.
This request must be authenticated with a Hub API token in the `Authorization` header,
for example using the `api_token` from your [external service's configuration](#externally-managed-services).
For example, with [requests][]: For example, with [requests][]:
```python ```python
r = requests.get( r = requests.get(
"http://127.0.0.1:8081/hub/api/user", '/'.join((["http://127.0.0.1:8081/hub/api",
"authorizations/cookie/jupyterhub-services",
quote(encrypted_cookie, safe=''),
]),
headers = { headers = {
'Authorization' : f'token {api_token}', 'Authorization' : 'token %s' % api_token,
}, },
) )
r.raise_for_status() r.raise_for_status()
@@ -325,39 +354,25 @@ and taking note of the following process:
3. On success, the reply will be a JSON model describing the user: 3. On success, the reply will be a JSON model describing the user:
```python ```json
{ {
"name": "inara", "name": "inara",
# groups may be omitted, depending on permissions
"groups": ["serenity", "guild"], "groups": ["serenity", "guild"],
# scopes is new in JupyterHub 2.0
"scopes": [
"access:services",
"read:users:name",
"read:users!user=inara",
"..."
]
} }
``` ```
The `scopes` field can be used to manage access.
Note: a user will have access to a service to complete oauth access to the service for the first time.
Individual permissions may be revoked at any later point without revoking the token,
in which case the `scopes` field in this model should be checked on each access.
The default required scopes for access are available from `hub_auth.oauth_scopes` or `$JUPYTERHUB_OAUTH_SCOPES`.
An example of using an Externally-Managed Service and authentication is An example of using an Externally-Managed Service and authentication is
in [nbviewer README][nbviewer example] section on securing the notebook viewer, in [nbviewer README][nbviewer example] section on securing the notebook viewer,
and an example of its configuration is found [here](https://github.com/jupyter/nbviewer/blob/ed942b10a52b6259099e2dd687930871dc8aac22/nbviewer/providers/base.py#L95). and an example of its configuration is found [here](https://github.com/jupyter/nbviewer/blob/ed942b10a52b6259099e2dd687930871dc8aac22/nbviewer/providers/base.py#L95).
nbviewer can also be run as a Hub-Managed Service as described [nbviewer README][nbviewer example] nbviewer can also be run as a Hub-Managed Service as described [nbviewer README][nbviewer example]
section on securing the notebook viewer. section on securing the notebook viewer.
[requests]: http://docs.python-requests.org/en/master/ [requests]: http://docs.python-requests.org/en/master/
[services_auth]: ../api/services.auth.html [services_auth]: ../api/services.auth.html
[huboauth]: ../api/services.auth.html#jupyterhub.services.auth.HubOAuth [HubAuth]: ../api/services.auth.html#jupyterhub.services.auth.HubAuth
[hubauth.user_for_token]: ../api/services.auth.html#jupyterhub.services.auth.HubAuth.user_for_token [HubAuth.user_for_cookie]: ../api/services.auth.html#jupyterhub.services.auth.HubAuth.user_for_cookie
[hubauthenticated]: ../api/services.auth.html#jupyterhub.services.auth.HubAuthenticated [HubAuth.user_for_token]: ../api/services.auth.html#jupyterhub.services.auth.HubAuth.user_for_token
[HubAuthenticated]: ../api/services.auth.html#jupyterhub.services.auth.HubAuthenticated
[nbviewer example]: https://github.com/jupyter/nbviewer#securing-the-notebook-viewer [nbviewer example]: https://github.com/jupyter/nbviewer#securing-the-notebook-viewer
[fastapi example]: https://github.com/jupyterhub/jupyterhub/tree/HEAD/examples/service-fastapi
[fastapi]: https://fastapi.tiangolo.com
[jupyterhub_idle_culler]: https://github.com/jupyterhub/jupyterhub-idle-culler

View File

@@ -8,17 +8,18 @@ and a custom Spawner needs to be able to take three actions:
- poll whether the process is still running - poll whether the process is still running
- stop the process - stop the process
## Examples ## Examples
Custom Spawners for JupyterHub can be found on the [JupyterHub wiki](https://github.com/jupyterhub/jupyterhub/wiki/Spawners). Custom Spawners for JupyterHub can be found on the [JupyterHub wiki](https://github.com/jupyterhub/jupyterhub/wiki/Spawners).
Some examples include: Some examples include:
- [DockerSpawner](https://github.com/jupyterhub/dockerspawner) for spawning user servers in Docker containers - [DockerSpawner](https://github.com/jupyterhub/dockerspawner) for spawning user servers in Docker containers
- `dockerspawner.DockerSpawner` for spawning identical Docker containers for * `dockerspawner.DockerSpawner` for spawning identical Docker containers for
each users each users
- `dockerspawner.SystemUserSpawner` for spawning Docker containers with an * `dockerspawner.SystemUserSpawner` for spawning Docker containers with an
environment and home directory for each users environment and home directory for each users
- both `DockerSpawner` and `SystemUserSpawner` also work with Docker Swarm for * both `DockerSpawner` and `SystemUserSpawner` also work with Docker Swarm for
launching containers on remote machines launching containers on remote machines
- [SudoSpawner](https://github.com/jupyterhub/sudospawner) enables JupyterHub to - [SudoSpawner](https://github.com/jupyterhub/sudospawner) enables JupyterHub to
run without being root, by spawning an intermediate process via `sudo` run without being root, by spawning an intermediate process via `sudo`
@@ -29,6 +30,7 @@ Some examples include:
- [SSHSpawner](https://github.com/NERSC/sshspawner) to spawn notebooks - [SSHSpawner](https://github.com/NERSC/sshspawner) to spawn notebooks
on a remote server using SSH on a remote server using SSH
## Spawner control methods ## Spawner control methods
### Spawner.start ### Spawner.start
@@ -37,13 +39,14 @@ Some examples include:
Information about the user can be retrieved from `self.user`, Information about the user can be retrieved from `self.user`,
an object encapsulating the user's name, authentication, and server info. an object encapsulating the user's name, authentication, and server info.
The return value of `Spawner.start` should be the `(ip, port)` of the running server, The return value of `Spawner.start` should be the (ip, port) of the running server.
or a full URL as a string.
**NOTE:** When writing coroutines, *never* `yield` in between a database change and a commit.
Most `Spawner.start` functions will look similar to this example: Most `Spawner.start` functions will look similar to this example:
```python ```python
async def start(self): def start(self):
self.ip = '127.0.0.1' self.ip = '127.0.0.1'
self.port = random_port() self.port = random_port()
# get environment variables, # get environment variables,
@@ -55,10 +58,8 @@ async def start(self):
cmd.extend(self.cmd) cmd.extend(self.cmd)
cmd.extend(self.get_args()) cmd.extend(self.get_args())
await self._actually_start_server_somehow(cmd, env) yield self._actually_start_server_somehow(cmd, env)
# url may not match self.ip:self.port, but it could! return (self.ip, self.port)
url = self._get_connectable_url()
return url
``` ```
When `Spawner.start` returns, the single-user server process should actually be running, When `Spawner.start` returns, the single-user server process should actually be running,
@@ -66,48 +67,6 @@ not just requested. JupyterHub can handle `Spawner.start` being very slow
(such as PBS-style batch queues, or instantiating whole AWS instances) (such as PBS-style batch queues, or instantiating whole AWS instances)
via relaxing the `Spawner.start_timeout` config value. via relaxing the `Spawner.start_timeout` config value.
#### Note on IPs and ports
`Spawner.ip` and `Spawner.port` attributes set the _bind_ url,
which the single-user server should listen on
(passed to the single-user process via the `JUPYTERHUB_SERVICE_URL` environment variable).
The _return_ value is the ip and port (or full url) the Hub should _connect to_.
These are not necessarily the same, and usually won't be in any Spawner that works with remote resources or containers.
The default for Spawner.ip, and Spawner.port is `127.0.0.1:{random}`,
which is appropriate for Spawners that launch local processes,
where everything is on localhost and each server needs its own port.
For remote or container Spawners, it will often make sense to use a different value,
such as `ip = '0.0.0.0'` and a fixed port, e.g. `8888`.
The defaults can be changed in the class,
preserving configuration with traitlets:
```python
from traitlets import default
from jupyterhub.spawner import Spawner
class MySpawner(Spawner):
@default("ip")
def _default_ip(self):
return '0.0.0.0'
@default("port")
def _default_port(self):
return 8888
async def start(self):
env = self.get_env()
cmd = []
# get jupyterhub command to run,
# typically ['jupyterhub-singleuser']
cmd.extend(self.cmd)
cmd.extend(self.get_args())
remote_server_info = await self._actually_start_server_somehow(cmd, env)
url = self.get_public_url_from(remote_server_info)
return url
```
### Spawner.poll ### Spawner.poll
`Spawner.poll` should check if the spawner is still running. `Spawner.poll` should check if the spawner is still running.
@@ -121,6 +80,7 @@ to check if the local process is still running. On Windows, it uses `psutil.pid_
`Spawner.stop` should stop the process. It must be a tornado coroutine, which should return when the process has finished exiting. `Spawner.stop` should stop the process. It must be a tornado coroutine, which should return when the process has finished exiting.
## Spawner state ## Spawner state
JupyterHub should be able to stop and restart without tearing down JupyterHub should be able to stop and restart without tearing down
@@ -152,6 +112,7 @@ def clear_state(self):
self.pid = 0 self.pid = 0
``` ```
## Spawner options form ## Spawner options form
(new in 0.4) (new in 0.4)
@@ -168,7 +129,7 @@ If the `Spawner.options_form` is defined, when a user tries to start their serve
If `Spawner.options_form` is undefined, the user's server is spawned directly, and no spawn page is rendered. If `Spawner.options_form` is undefined, the user's server is spawned directly, and no spawn page is rendered.
See [this example](https://github.com/jupyterhub/jupyterhub/blob/HEAD/examples/spawn-form/jupyterhub_config.py) for a form that allows custom CLI args for the local spawner. See [this example](https://github.com/jupyterhub/jupyterhub/blob/master/examples/spawn-form/jupyterhub_config.py) for a form that allows custom CLI args for the local spawner.
### `Spawner.options_from_form` ### `Spawner.options_from_form`
@@ -209,7 +170,8 @@ which would return:
When `Spawner.start` is called, this dictionary is accessible as `self.user_options`. When `Spawner.start` is called, this dictionary is accessible as `self.user_options`.
[spawner]: https://github.com/jupyterhub/jupyterhub/blob/HEAD/jupyterhub/spawner.py
[Spawner]: https://github.com/jupyterhub/jupyterhub/blob/master/jupyterhub/spawner.py
## Writing a custom spawner ## Writing a custom spawner
@@ -250,72 +212,6 @@ Additionally, configurable attributes for your spawner will
appear in jupyterhub help output and auto-generated configuration files appear in jupyterhub help output and auto-generated configuration files
via `jupyterhub --generate-config`. via `jupyterhub --generate-config`.
## Environment variables and command-line arguments
Spawners mainly do one thing: launch a command in an environment.
The command-line is constructed from user configuration:
- Spawner.cmd (default: `['jupterhub-singleuser']`)
- Spawner.args (cli args to pass to the cmd, default: empty)
where the configuration:
```python
c.Spawner.cmd = ["my-singleuser-wrapper"]
c.Spawner.args = ["--debug", "--flag"]
```
would result in spawning the command:
```bash
my-singleuser-wrapper --debug --flag
```
The `Spawner.get_args()` method is how Spawner.args is accessed,
and can be used by Spawners to customize/extend user-provided arguments.
Prior to 2.0, JupyterHub unconditionally added certain options _if specified_ to the command-line,
such as `--ip={Spawner.ip}` and `--port={Spawner.port}`.
These have now all been moved to environment variables,
and from JupyterHub 2.0,
the command-line launched by JupyterHub is fully specified by overridable configuration `Spawner.cmd + Spawner.args`.
Most process configuration is passed via environment variables.
Additional variables can be specified via the `Spawner.environment` configuration.
The process environment is returned by `Spawner.get_env`, which specifies the following environment variables:
- JUPYTERHUB*SERVICE_URL - the \_bind* url where the server should launch its http server (`http://127.0.0.1:12345`).
This includes Spawner.ip and Spawner.port; _new in 2.0, prior to 2.0 ip,port were on the command-line and only if specified_
- JUPYTERHUB_SERVICE_PREFIX - the URL prefix the service will run on (e.g. `/user/name/`)
- JUPYTERHUB_USER - the JupyterHub user's username
- JUPYTERHUB_SERVER_NAME - the server's name, if using named servers (default server has an empty name)
- JUPYTERHUB_API_URL - the full url for the JupyterHub API (http://17.0.0.1:8001/hub/api)
- JUPYTERHUB_BASE_URL - the base url of the whole jupyterhub deployment, i.e. the bit before `hub/` or `user/`,
as set by c.JupyterHub.base_url (default: `/`)
- JUPYTERHUB_API_TOKEN - the API token the server can use to make requests to the Hub.
This is also the OAuth client secret.
- JUPYTERHUB_CLIENT_ID - the OAuth client ID for authenticating visitors.
- JUPYTERHUB_OAUTH_CALLBACK_URL - the callback URL to use in oauth, typically `/user/:name/oauth_callback`
Optional environment variables, depending on configuration:
- JUPYTERHUB*SSL*[KEYFILE|CERTFILE|CLIENT_CI] - SSL configuration, when internal_ssl is enabled
- JUPYTERHUB_ROOT_DIR - the root directory of the server (notebook directory), when Spawner.notebook_dir is defined (new in 2.0)
- JUPYTERHUB_DEFAULT_URL - the default URL for the server (for redirects from /user/:name/),
if Spawner.default_url is defined
(new in 2.0, previously passed via cli)
- JUPYTERHUB_DEBUG=1 - generic debug flag, sets maximum log level when Spawner.debug is True
(new in 2.0, previously passed via cli)
- JUPYTERHUB_DISABLE_USER_CONFIG=1 - disable loading user config,
sets maximum log level when Spawner.debug is True (new in 2.0,
previously passed via cli)
- JUPYTERHUB*[MEM|CPU]*[LIMIT_GUARANTEE] - the values of cpu and memory limits and guarantees.
These are not expected to be enforced by the process,
but are made available as a hint,
e.g. for resource monitoring extensions.
## Spawners, resource limits, and guarantees (Optional) ## Spawners, resource limits, and guarantees (Optional)
@@ -328,9 +224,10 @@ support for them**. For example, LocalProcessSpawner, the default
spawner, does not support limits and guarantees. One of the spawners spawner, does not support limits and guarantees. One of the spawners
that supports limits and guarantees is the `systemdspawner`. that supports limits and guarantees is the `systemdspawner`.
### Memory Limits & Guarantees ### Memory Limits & Guarantees
`c.Spawner.mem_limit`: A **limit** specifies the _maximum amount of memory_ `c.Spawner.mem_limit`: A **limit** specifies the *maximum amount of memory*
that may be allocated, though there is no promise that the maximum amount will that may be allocated, though there is no promise that the maximum amount will
be available. In supported spawners, you can set `c.Spawner.mem_limit` to be available. In supported spawners, you can set `c.Spawner.mem_limit` to
limit the total amount of memory that a single-user notebook server can limit the total amount of memory that a single-user notebook server can
@@ -338,8 +235,8 @@ allocate. Attempting to use more memory than this limit will cause errors. The
single-user notebook server can discover its own memory limit by looking at single-user notebook server can discover its own memory limit by looking at
the environment variable `MEM_LIMIT`, which is specified in absolute bytes. the environment variable `MEM_LIMIT`, which is specified in absolute bytes.
`c.Spawner.mem_guarantee`: Sometimes, a **guarantee** of a _minimum amount of `c.Spawner.mem_guarantee`: Sometimes, a **guarantee** of a *minimum amount of
memory_ is desirable. In this case, you can set `c.Spawner.mem_guarantee` to memory* is desirable. In this case, you can set `c.Spawner.mem_guarantee` to
to provide a guarantee that at minimum this much memory will always be to provide a guarantee that at minimum this much memory will always be
available for the single-user notebook server to use. The environment variable available for the single-user notebook server to use. The environment variable
`MEM_GUARANTEE` will also be set in the single-user notebook server. `MEM_GUARANTEE` will also be set in the single-user notebook server.

View File

@@ -10,7 +10,7 @@ appearance.
JupyterHub will look for custom templates in all of the paths in the JupyterHub will look for custom templates in all of the paths in the
`JupyterHub.template_paths` configuration option, falling back on the `JupyterHub.template_paths` configuration option, falling back on the
[default templates](https://github.com/jupyterhub/jupyterhub/tree/HEAD/share/jupyterhub/templates) [default templates](https://github.com/jupyterhub/jupyterhub/tree/master/share/jupyterhub/templates)
if no custom template with that name is found. This fallback if no custom template with that name is found. This fallback
behavior is new in version 0.9; previous versions searched only those paths behavior is new in version 0.9; previous versions searched only those paths
explicitly included in `template_paths`. You may override as many explicitly included in `template_paths`. You may override as many
@@ -21,7 +21,7 @@ or as few templates as you desire.
Jinja provides a mechanism to [extend templates](http://jinja.pocoo.org/docs/2.10/templates/#template-inheritance). Jinja provides a mechanism to [extend templates](http://jinja.pocoo.org/docs/2.10/templates/#template-inheritance).
A base template can define a `block`, and child templates can replace or A base template can define a `block`, and child templates can replace or
supplement the material in the block. The supplement the material in the block. The
[JupyterHub templates](https://github.com/jupyterhub/jupyterhub/tree/HEAD/share/jupyterhub/templates) [JupyterHub templates](https://github.com/jupyterhub/jupyterhub/tree/master/share/jupyterhub/templates)
make extensive use of blocks, which allows you to customize parts of the make extensive use of blocks, which allows you to customize parts of the
interface easily. interface easily.
@@ -52,7 +52,10 @@ text about the server starting up, place this content in a file named
`JupyterHub.template_paths` configuration option. `JupyterHub.template_paths` configuration option.
```html ```html
{% extends "templates/spawn_pending.html" %} {% block message %} {{ super() }} {% extends "templates/spawn_pending.html" %}
{% block message %}
{{ super() }}
<p>Patience is a virtue.</p> <p>Patience is a virtue.</p>
{% endblock %} {% endblock %}
``` ```
@@ -66,7 +69,8 @@ To add announcements to be displayed on a page, you have two options:
### Announcement Configuration Variables ### Announcement Configuration Variables
If you set the configuration variable `JupyterHub.template_vars = {'announcement': 'some_text'}`, the given `some_text` will be placed on If you set the configuration variable `JupyterHub.template_vars =
{'announcement': 'some_text'}`, the given `some_text` will be placed on
the top of all pages. The more specific variables the top of all pages. The more specific variables
`announcement_login`, `announcement_spawn`, `announcement_home`, and `announcement_login`, `announcement_spawn`, `announcement_home`, and
`announcement_logout` are more specific and only show on their `announcement_logout` are more specific and only show on their
@@ -80,7 +84,8 @@ to update the messages without restarting. Set
template (for example, `login.html`) with: template (for example, `login.html`) with:
```html ```html
{% extends "templates/login.html" %} {% set announcement = 'some message' %} {% extends "templates/login.html" %}
{% set announcement = 'some message' %}
``` ```
Extending `page.html` puts the message on all pages, but note that Extending `page.html` puts the message on all pages, but note that

View File

@@ -11,6 +11,8 @@ All authenticated handlers redirect to `/hub/login` to login users
prior to being redirected back to the originating page. prior to being redirected back to the originating page.
The returned request should preserve all query parameters. The returned request should preserve all query parameters.
## `/` ## `/`
The top-level request is always a simple redirect to `/hub/`, The top-level request is always a simple redirect to `/hub/`,
@@ -59,7 +61,7 @@ for starting and stopping the user's server.
If named servers are enabled, there will be some additional If named servers are enabled, there will be some additional
tools for management of named servers. tools for management of named servers.
_Version added: 1.0_ named server UI is new in 1.0. *Version added: 1.0* named server UI is new in 1.0.
## `/hub/login` ## `/hub/login`
@@ -109,7 +111,7 @@ not the Hub.
The username is the first part and, if using named servers, The username is the first part and, if using named servers,
the server name is the second part. the server name is the second part.
If the user's server is _not_ running, this will be redirected to `/hub/user/:username/...` If the user's server is *not* running, this will be redirected to `/hub/user/:username/...`
## `/hub/user/:username[/:servername]` ## `/hub/user/:username[/:servername]`
@@ -144,7 +146,7 @@ without additional user action (i.e. clicking the link on the page)
![Visiting a URL for a server that's not running](../images/not-running.png) ![Visiting a URL for a server that's not running](../images/not-running.png)
_Version changed: 1.0_ *Version changed: 1.0*
Prior to 1.0, this URL itself was responsible for spawning servers, Prior to 1.0, this URL itself was responsible for spawning servers,
and served the progress page if it was pending, and served the progress page if it was pending,
@@ -163,7 +165,7 @@ indicating how to spawn the server.
This is meant to help applications such as JupyterLab This is meant to help applications such as JupyterLab
that are connected to a server that has stopped. that are connected to a server that has stopped.
_Version changed: 1.0_ *Version changed: 1.0*
JupyterHub 0.9 failed these API requests with status 404, JupyterHub 0.9 failed these API requests with status 404,
but 1.0 uses 503. but 1.0 uses 503.
@@ -205,12 +207,12 @@ and a POST request will trigger the actual spawn and redirect.
![The spawn form](../images/spawn-form.png) ![The spawn form](../images/spawn-form.png)
_Version added: 1.0_ *Version added: 1.0*
1.0 adds the ability to specify username and servername. 1.0 adds the ability to specify username and servername.
Prior to 1.0, only `/hub/spawn` was recognized for the default server. Prior to 1.0, only `/hub/spawn` was recognized for the default server.
_Version changed: 1.0_ *Version changed: 1.0*
Prior to 1.0, this page redirected back to `/hub/user/:username`, Prior to 1.0, this page redirected back to `/hub/user/:username`,
which was responsible for triggering spawn and rendering progress, etc. which was responsible for triggering spawn and rendering progress, etc.
@@ -219,7 +221,7 @@ which was responsible for triggering spawn and rendering progress, etc.
![The spawn pending page](../images/spawn-pending.png) ![The spawn pending page](../images/spawn-pending.png)
_Version added: 1.0_ this URL is new in JupyterHub 1.0. *Version added: 1.0* this URL is new in JupyterHub 1.0.
This page renders the progress view for the given spawn request. This page renders the progress view for the given spawn request.
Once the server is ready, Once the server is ready,

View File

@@ -12,17 +12,17 @@ works.
## Semi-trusted and untrusted users ## Semi-trusted and untrusted users
JupyterHub is designed to be a _simple multi-user server for modestly sized JupyterHub is designed to be a *simple multi-user server for modestly sized
groups_ of **semi-trusted** users. While the design reflects serving semi-trusted groups* of **semi-trusted** users. While the design reflects serving semi-trusted
users, JupyterHub is not necessarily unsuitable for serving **untrusted** users. users, JupyterHub is not necessarily unsuitable for serving **untrusted** users.
Using JupyterHub with **untrusted** users does mean more work by the Using JupyterHub with **untrusted** users does mean more work by the
administrator. Much care is required to secure a Hub, with extra caution on administrator. Much care is required to secure a Hub, with extra caution on
protecting users from each other as the Hub is serving untrusted users. protecting users from each other as the Hub is serving untrusted users.
One aspect of JupyterHub's _design simplicity_ for **semi-trusted** users is that One aspect of JupyterHub's *design simplicity* for **semi-trusted** users is that
the Hub and single-user servers are placed in a _single domain_, behind a the Hub and single-user servers are placed in a *single domain*, behind a
[_proxy_][configurable-http-proxy]. If the Hub is serving untrusted [*proxy*][configurable-http-proxy]. If the Hub is serving untrusted
users, many of the web's cross-site protections are not applied between users, many of the web's cross-site protections are not applied between
single-user servers and the Hub, or between single-user servers and each single-user servers and the Hub, or between single-user servers and each
other, since browsers see the whole thing (proxy, Hub, and single user other, since browsers see the whole thing (proxy, Hub, and single user
@@ -40,7 +40,7 @@ server.
To protect all users from each other, JupyterHub administrators must To protect all users from each other, JupyterHub administrators must
ensure that: ensure that:
- A user **does not have permission** to modify their single-user notebook server, * A user **does not have permission** to modify their single-user notebook server,
including: including:
- A user **may not** install new packages in the Python environment that runs - A user **may not** install new packages in the Python environment that runs
their single-user server. their single-user server.
@@ -49,11 +49,11 @@ ensure that:
directory that precedes the directory containing `jupyterhub-singleuser`. directory that precedes the directory containing `jupyterhub-singleuser`.
- A user may not modify environment variables (e.g. PATH, PYTHONPATH) for - A user may not modify environment variables (e.g. PATH, PYTHONPATH) for
their single-user server. their single-user server.
- A user **may not** modify the configuration of the notebook server * A user **may not** modify the configuration of the notebook server
(the `~/.jupyter` or `JUPYTER_CONFIG_DIR` directory). (the `~/.jupyter` or `JUPYTER_CONFIG_DIR` directory).
If any additional services are run on the same domain as the Hub, the services If any additional services are run on the same domain as the Hub, the services
**must never** display user-authored HTML that is neither _sanitized_ nor _sandboxed_ **must never** display user-authored HTML that is neither *sanitized* nor *sandboxed*
(e.g. IFramed) to any user that lacks authentication as the author of a file. (e.g. IFramed) to any user that lacks authentication as the author of a file.
## Mitigate security issues ## Mitigate security issues
@@ -85,7 +85,7 @@ admin must enforce.
### Prevent spawners from evaluating shell configuration files ### Prevent spawners from evaluating shell configuration files
For most Spawners, `PATH` is not something users can influence, but care should For most Spawners, `PATH` is not something users can influence, but care should
be taken to ensure that the Spawner does _not_ evaluate shell configuration be taken to ensure that the Spawner does *not* evaluate shell configuration
files prior to launching the server. files prior to launching the server.
### Isolate packages using virtualenv ### Isolate packages using virtualenv
@@ -125,12 +125,13 @@ versions up to date.
A handy website for testing your deployment is A handy website for testing your deployment is
[Qualsys' SSL analyzer tool](https://www.ssllabs.com/ssltest/analyze.html). [Qualsys' SSL analyzer tool](https://www.ssllabs.com/ssltest/analyze.html).
[configurable-http-proxy]: https://github.com/jupyterhub/configurable-http-proxy [configurable-http-proxy]: https://github.com/jupyterhub/configurable-http-proxy
## Vulnerability reporting ## Vulnerability reporting
If you believe youve found a security vulnerability in JupyterHub, or any If you believe youve found a security vulnerability in JupyterHub, or any
Jupyter project, please report it to Jupyter project, please report it to
[security@ipython.org](mailto:security@ipython.org). If you prefer to encrypt [security@ipython.org](mailto:security@iypthon.org). If you prefer to encrypt
your security reports, you can use [this PGP public your security reports, you can use [this PGP public
key](https://jupyter-notebook.readthedocs.io/en/stable/_downloads/ipython_security.asc). key](https://jupyter-notebook.readthedocs.io/en/stable/_downloads/ipython_security.asc).

View File

@@ -4,20 +4,17 @@ When troubleshooting, you may see unexpected behaviors or receive an error
message. This section provide links for identifying the cause of the message. This section provide links for identifying the cause of the
problem and how to resolve it. problem and how to resolve it.
[_Behavior_](#behavior) [*Behavior*](#behavior)
- JupyterHub proxy fails to start - JupyterHub proxy fails to start
- sudospawner fails to run - sudospawner fails to run
- What is the default behavior when none of the lists (admin, allowed, - What is the default behavior when none of the lists (admin, allowed,
allowed groups) are set? allowed groups) are set?
- JupyterHub Docker container not accessible at localhost - JupyterHub Docker container not accessible at localhost
[_Errors_](#errors) [*Errors*](#errors)
- 500 error after spawning my single-user server - 500 error after spawning my single-user server
[_How do I...?_](#how-do-i) [*How do I...?*](#how-do-i)
- Use a chained SSL certificate - Use a chained SSL certificate
- Install JupyterHub without a network connection - Install JupyterHub without a network connection
- I want access to the whole filesystem, but still default users to their home directory - I want access to the whole filesystem, but still default users to their home directory
@@ -28,7 +25,7 @@ problem and how to resolve it.
- Toree integration with HDFS rack awareness script - Toree integration with HDFS rack awareness script
- Where do I find Docker images and Dockerfiles related to JupyterHub? - Where do I find Docker images and Dockerfiles related to JupyterHub?
[_Troubleshooting commands_](#troubleshooting-commands) [*Troubleshooting commands*](#troubleshooting-commands)
## Behavior ## Behavior
@@ -37,8 +34,8 @@ problem and how to resolve it.
If you have tried to start the JupyterHub proxy and it fails to start: If you have tried to start the JupyterHub proxy and it fails to start:
- check if the JupyterHub IP configuration setting is - check if the JupyterHub IP configuration setting is
`c.JupyterHub.ip = '*'`; if it is, try `c.JupyterHub.ip = ''` ``c.JupyterHub.ip = '*'``; if it is, try ``c.JupyterHub.ip = ''``
- Try starting with `jupyterhub --ip=0.0.0.0` - Try starting with ``jupyterhub --ip=0.0.0.0``
**Note**: If this occurs on Ubuntu/Debian, check that the you are using a **Note**: If this occurs on Ubuntu/Debian, check that the you are using a
recent version of node. Some versions of Ubuntu/Debian come with a version recent version of node. Some versions of Ubuntu/Debian come with a version
@@ -135,11 +132,11 @@ There are two likely reasons for this:
1. The single-user server cannot connect to the Hub's API (networking 1. The single-user server cannot connect to the Hub's API (networking
configuration problems) configuration problems)
2. The single-user server cannot _authenticate_ its requests (invalid token) 2. The single-user server cannot *authenticate* its requests (invalid token)
#### Symptoms #### Symptoms
The main symptom is a failure to load _any_ page served by the single-user The main symptom is a failure to load *any* page served by the single-user
server, met with a 500 error. This is typically the first page at `/user/<your_name>` server, met with a 500 error. This is typically the first page at `/user/<your_name>`
after logging in or clicking "Start my server". When a single-user notebook server after logging in or clicking "Start my server". When a single-user notebook server
receives a request, the notebook server makes an API request to the Hub to receives a request, the notebook server makes an API request to the Hub to
@@ -201,15 +198,15 @@ your server again.
##### Proxy settings (403 GET) ##### Proxy settings (403 GET)
When your whole JupyterHub sits behind a organization proxy (_not_ a reverse proxy like NGINX as part of your setup and _not_ the configurable-http-proxy) the environment variables `HTTP_PROXY`, `HTTPS_PROXY`, `http_proxy` and `https_proxy` might be set. This confuses the jupyterhub-singleuser servers: When connecting to the Hub for authorization they connect via the proxy instead of directly connecting to the Hub on localhost. The proxy might deny the request (403 GET). This results in the singleuser server thinking it has a wrong auth token. To circumvent this you should add `<hub_url>,<hub_ip>,localhost,127.0.0.1` to the environment variables `NO_PROXY` and `no_proxy`. When your whole JupyterHub sits behind a organization proxy (*not* a reverse proxy like NGINX as part of your setup and *not* the configurable-http-proxy) the environment variables `HTTP_PROXY`, `HTTPS_PROXY`, `http_proxy` and `https_proxy` might be set. This confuses the jupyterhub-singleuser servers: When connecting to the Hub for authorization they connect via the proxy instead of directly connecting to the Hub on localhost. The proxy might deny the request (403 GET). This results in the singleuser server thinking it has a wrong auth token. To circumvent this you should add `<hub_url>,<hub_ip>,localhost,127.0.0.1` to the environment variables `NO_PROXY` and `no_proxy`.
### Launching Jupyter Notebooks to run as an externally managed JupyterHub service with the `jupyterhub-singleuser` command returns a `JUPYTERHUB_API_TOKEN` error ### Launching Jupyter Notebooks to run as an externally managed JupyterHub service with the `jupyterhub-singleuser` command returns a `JUPYTERHUB_API_TOKEN` error
[JupyterHub services](https://jupyterhub.readthedocs.io/en/stable/reference/services.html) allow processes to interact with JupyterHub's REST API. Example use-cases include: [JupyterHub services](https://jupyterhub.readthedocs.io/en/stable/reference/services.html) allow processes to interact with JupyterHub's REST API. Example use-cases include:
- **Secure Testing**: provide a canonical Jupyter Notebook for testing production data to reduce the number of entry points into production systems. * **Secure Testing**: provide a canonical Jupyter Notebook for testing production data to reduce the number of entry points into production systems.
- **Grading Assignments**: provide access to shared Jupyter Notebooks that may be used for management tasks such grading assignments. * **Grading Assignments**: provide access to shared Jupyter Notebooks that may be used for management tasks such grading assignments.
- **Private Dashboards**: share dashboards with certain group members. * **Private Dashboards**: share dashboards with certain group members.
If possible, try to run the Jupyter Notebook as an externally managed service with one of the provided [jupyter/docker-stacks](https://github.com/jupyter/docker-stacks). If possible, try to run the Jupyter Notebook as an externally managed service with one of the provided [jupyter/docker-stacks](https://github.com/jupyter/docker-stacks).
@@ -234,7 +231,7 @@ With a docker container, pass in the environment variable with the run command:
-e JUPYTERHUB_API_TOKEN=my_secret_token \ -e JUPYTERHUB_API_TOKEN=my_secret_token \
jupyter/datascience-notebook:latest jupyter/datascience-notebook:latest
[This example](https://github.com/jupyterhub/jupyterhub/tree/HEAD/examples/service-notebook/external) demonstrates how to combine the use of the `jupyterhub-singleuser` environment variables when launching a Notebook as an externally managed service. [This example](https://github.com/jupyterhub/jupyterhub/tree/master/examples/service-notebook/external) demonstrates how to combine the use of the `jupyterhub-singleuser` environment variables when launching a Notebook as an externally managed service.
## How do I...? ## How do I...?
@@ -253,6 +250,7 @@ You would then set in your `jupyterhub_config.py` file the `ssl_key` and
c.JupyterHub.ssl_cert = your_host-chained.crt c.JupyterHub.ssl_cert = your_host-chained.crt
c.JupyterHub.ssl_key = your_host.key c.JupyterHub.ssl_key = your_host.key
#### Example #### Example
Your certificate provider gives you the following files: `example_host.crt`, Your certificate provider gives you the following files: `example_host.crt`,
@@ -404,8 +402,8 @@ SyntaxError: Missing parentheses in call to 'print'
In order to resolve this issue, there are two potential options. In order to resolve this issue, there are two potential options.
1. Update HDFS core-site.xml, so the parameter "net.topology.script.file.name" points to a custom 1. Update HDFS core-site.xml, so the parameter "net.topology.script.file.name" points to a custom
script (e.g. /etc/hadoop/conf/custom_topology_script.py). Copy the original script and change the first line point script (e.g. /etc/hadoop/conf/custom_topology_script.py). Copy the original script and change the first line point
to a python two installation (e.g. /usr/bin/python). to a python two installation (e.g. /usr/bin/python).
2. In spark-env.sh add a Python 2 installation to your path (e.g. export PATH=/opt/anaconda2/bin:$PATH). 2. In spark-env.sh add a Python 2 installation to your path (e.g. export PATH=/opt/anaconda2/bin:$PATH).
### Where do I find Docker images and Dockerfiles related to JupyterHub? ### Where do I find Docker images and Dockerfiles related to JupyterHub?

View File

@@ -5,22 +5,22 @@ do some preparation work in a bootstrapping process.
Common use cases are: Common use cases are:
_Providing writeable storage for LDAP users_ *Providing writeable storage for LDAP users*
Your Jupyterhub is configured to use the LDAPAuthenticator and DockerSpawer. Your Jupyterhub is configured to use the LDAPAuthenticator and DockerSpawer.
- The user has no file directory on the host since your are using LDAP. * The user has no file directory on the host since your are using LDAP.
- When a user has no directory and DockerSpawner wants to mount a volume, * When a user has no directory and DockerSpawner wants to mount a volume,
the spawner will use docker to create a directory. the spawner will use docker to create a directory.
Since the docker daemon is running as root, the generated directory for the volume Since the docker daemon is running as root, the generated directory for the volume
mount will not be writeable by the `jovyan` user inside of the container. mount will not be writeable by the `jovyan` user inside of the container.
For the directory to be useful to the user, the permissions on the directory For the directory to be useful to the user, the permissions on the directory
need to be modified for the user to have write access. need to be modified for the user to have write access.
_Prepopulating Content_ *Prepopulating Content*
Another use would be to copy initial content, such as tutorial files or reference Another use would be to copy initial content, such as tutorial files or reference
material, into the user's space when a notebook server is newly spawned. material, into the user's space when a notebook server is newly spawned.
You can define your own bootstrap process by implementing a `pre_spawn_hook` on any spawner. You can define your own bootstrap process by implementing a `pre_spawn_hook` on any spawner.
The Spawner itself is passed as parameter to your hook and you can easily get the contextual information out of the spawning process. The Spawner itself is passed as parameter to your hook and you can easily get the contextual information out of the spawning process.
@@ -28,7 +28,7 @@ The Spawner itself is passed as parameter to your hook and you can easily get th
Similarly, there may be cases where you would like to clean up after a spawner stops. Similarly, there may be cases where you would like to clean up after a spawner stops.
You may implement a `post_stop_hook` that is always executed after the spawner stops. You may implement a `post_stop_hook` that is always executed after the spawner stops.
If you implement a hook, make sure that it is _idempotent_. It will be executed every time If you implement a hook, make sure that it is *idempotent*. It will be executed every time
a notebook server is spawned to the user. That means you should somehow a notebook server is spawned to the user. That means you should somehow
ensure that things which should run only once are not running again and again. ensure that things which should run only once are not running again and again.
For example, before you create a directory, check if it exists. For example, before you create a directory, check if it exists.
@@ -148,9 +148,9 @@ else
echo "...initial content loading for user ..." echo "...initial content loading for user ..."
mkdir $USER_DIRECTORY/tutorials mkdir $USER_DIRECTORY/tutorials
cd $USER_DIRECTORY/tutorials cd $USER_DIRECTORY/tutorials
wget https://github.com/jakevdp/PythonDataScienceHandbook/archive/HEAD.zip wget https://github.com/jakevdp/PythonDataScienceHandbook/archive/master.zip
unzip -o HEAD.zip unzip -o master.zip
rm HEAD.zip rm master.zip
fi fi
exit 0 exit 0

View File

@@ -40,9 +40,9 @@ else
echo "...initial content loading for user ..." echo "...initial content loading for user ..."
mkdir $USER_DIRECTORY/tutorials mkdir $USER_DIRECTORY/tutorials
cd $USER_DIRECTORY/tutorials cd $USER_DIRECTORY/tutorials
wget https://github.com/jakevdp/PythonDataScienceHandbook/archive/HEAD.zip wget https://github.com/jakevdp/PythonDataScienceHandbook/archive/master.zip
unzip -o HEAD.zip unzip -o master.zip
rm HEAD.zip rm master.zip
fi fi
exit 0 exit 0

View File

@@ -10,7 +10,7 @@ from jupyter_client.localinterfaces import public_ips
def create_dir_hook(spawner): def create_dir_hook(spawner):
"""Create directory""" """ Create directory """
username = spawner.user.name # get the username username = spawner.user.name # get the username
volume_path = os.path.join('/volumes/jupyterhub', username) volume_path = os.path.join('/volumes/jupyterhub', username)
if not os.path.exists(volume_path): if not os.path.exists(volume_path):
@@ -20,7 +20,7 @@ def create_dir_hook(spawner):
def clean_dir_hook(spawner): def clean_dir_hook(spawner):
"""Delete directory""" """ Delete directory """
username = spawner.user.name # get the username username = spawner.user.name # get the username
temp_path = os.path.join('/volumes/jupyterhub', username, 'temp') temp_path = os.path.join('/volumes/jupyterhub', username, 'temp')
if os.path.exists(temp_path) and os.path.isdir(temp_path): if os.path.exists(temp_path) and os.path.isdir(temp_path):

View File

@@ -47,6 +47,7 @@ After logging in with your local-system credentials, you should see a JSON dump
} }
``` ```
The essential pieces for using JupyterHub as an OAuth provider are: The essential pieces for using JupyterHub as an OAuth provider are:
1. registering your service with jupyterhub: 1. registering your service with jupyterhub:

View File

@@ -13,7 +13,7 @@ if not api_token:
c.JupyterHub.services = [ c.JupyterHub.services = [
{ {
'name': 'external-oauth', 'name': 'external-oauth',
'oauth_client_id': "service-oauth-client-test", 'oauth_client_id': "whoami-oauth-client-test",
'api_token': api_token, 'api_token': api_token,
'oauth_redirect_uri': 'http://127.0.0.1:5555/oauth_callback', 'oauth_redirect_uri': 'http://127.0.0.1:5555/oauth_callback',
} }

View File

@@ -9,7 +9,7 @@ if [[ -z "${JUPYTERHUB_API_TOKEN}" ]]; then
fi fi
# 2. oauth client ID # 2. oauth client ID
export JUPYTERHUB_CLIENT_ID='service-oauth-client-test' export JUPYTERHUB_CLIENT_ID='whoami-oauth-client-test'
# 3. where the Hub is # 3. where the Hub is
export JUPYTERHUB_URL='http://127.0.0.1:8000' export JUPYTERHUB_URL='http://127.0.0.1:8000'

View File

@@ -9,7 +9,7 @@ if [[ -z "${JUPYTERHUB_API_TOKEN}" ]]; then
fi fi
# 2. oauth client ID # 2. oauth client ID
export JUPYTERHUB_CLIENT_ID="service-oauth-client-test" export JUPYTERHUB_CLIENT_ID="whoami-oauth-client-test"
# 3. what URL to run on # 3. what URL to run on
export JUPYTERHUB_SERVICE_PREFIX='/' export JUPYTERHUB_SERVICE_PREFIX='/'
export JUPYTERHUB_SERVICE_URL='http://127.0.0.1:5555' export JUPYTERHUB_SERVICE_URL='http://127.0.0.1:5555'

View File

@@ -4,14 +4,14 @@ This example shows how you can connect Jupyterhub to a Postgres database
instead of the default SQLite backend. instead of the default SQLite backend.
### Running Postgres with Jupyterhub on the host. ### Running Postgres with Jupyterhub on the host.
0. Uncomment and replace `ENV JPY_PSQL_PASSWORD arglebargle` with your own 0. Uncomment and replace `ENV JPY_PSQL_PASSWORD arglebargle` with your own
password in the Dockerfile for `examples/postgres/db`. (Alternatively, pass password in the Dockerfile for `examples/postgres/db`. (Alternatively, pass
-e `JPY_PSQL_PASSWORD=<password>` when you start the db container.) -e `JPY_PSQL_PASSWORD=<password>` when you start the db container.)
1. `cd` to the root of your jupyterhub repo. 1. `cd` to the root of your jupyterhub repo.
2. Build the postgres image with `docker build -t jupyterhub-postgres-db examples/postgres/db`. This may take a minute or two the first time it's 2. Build the postgres image with `docker build -t jupyterhub-postgres-db
examples/postgres/db`. This may take a minute or two the first time it's
run. run.
3. Run the db image with `docker run -d -p 5433:5432 jupyterhub-postgres-db`. 3. Run the db image with `docker run -d -p 5433:5432 jupyterhub-postgres-db`.
@@ -24,18 +24,20 @@ instead of the default SQLite backend.
5. Log in as the user running jupyterhub on your host machine. 5. Log in as the user running jupyterhub on your host machine.
### Running Postgres with Containerized Jupyterhub. ### Running Postgres with Containerized Jupyterhub.
0. Do steps 0-2 in from the above section, ensuring that the values set/passed 0. Do steps 0-2 in from the above section, ensuring that the values set/passed
for `JPY_PSQL_PASSWORD` match for the hub and db containers. for `JPY_PSQL_PASSWORD` match for the hub and db containers.
1. Build the hub image with `docker build -t jupyterhub-postgres-hub examples/postgres/hub`. This may take a minute or two the first time it's 1. Build the hub image with `docker build -t jupyterhub-postgres-hub
examples/postgres/hub`. This may take a minute or two the first time it's
run. run.
2. Run the db image with `docker run -d --name=jpy-db jupyterhub-postgres`. Note that, unlike when connecting to a host machine 2. Run the db image with `docker run -d --name=jpy-db
jupyterhub-postgres`. Note that, unlike when connecting to a host machine
jupyterhub, we don't specify a port-forwarding scheme here, but we do need jupyterhub, we don't specify a port-forwarding scheme here, but we do need
to specify a name for the container. to specify a name for the container.
3. Run the containerized hub with `docker run -it --link jpy-db:postgres jupyterhub-postgres-hub`. This instructs docker to run the hub container 3. Run the containerized hub with `docker run -it --link jpy-db:postgres
jupyterhub-postgres-hub`. This instructs docker to run the hub container
with a link to the already-running db container, which will forward with a link to the already-running db container, which will forward
environment and connection information from the DB to the hub. environment and connection information from the DB to the hub.

View File

@@ -1,23 +1,10 @@
# Configuration file for jupyterhub (postgres example). # Configuration file for jupyterhub (postgres example).
c = get_config() # noqa c = get_config()
# Add some users # Add some users.
c.Authenticator.allowed_users = {'ganymede', 'io', 'rhea'} c.JupyterHub.admin_users = {'rhea'}
c.Authenticator.whitelist = {'ganymede', 'io', 'rhea'}
c.JupyterHub.load_roles = [
{
"name": "user-admin",
"scopes": [
"admin:groups",
"admin:users",
"admin:servers",
],
"users": [
"rhea",
],
}
]
# These environment variables are automatically supplied by the linked postgres # These environment variables are automatically supplied by the linked postgres
# container. # container.

View File

@@ -1,55 +0,0 @@
# create a role with permissions to:
# 1. start/stop servers, and
# 2. access the server API
c.JupyterHub.load_roles = [
{
"name": "launcher",
"scopes": [
"servers", # manage servers
"access:servers", # access servers themselves
],
# assign role to our 'launcher' service
"services": ["launcher"],
}
]
# persist token to a file, to share it with the launch-server.py script
import pathlib
import secrets
here = pathlib.Path(__file__).parent
token_file = here.joinpath("service-token")
if token_file.exists():
with token_file.open("r") as f:
token = f.read()
else:
token = secrets.token_hex(16)
with token_file.open("w") as f:
f.write(token)
# define our service
c.JupyterHub.services = [
{
"name": "launcher",
"api_token": token,
}
]
# ensure spawn requests return immediately,
# rather than waiting up to 10 seconds for spawn to complete
# this ensures that we use the progress API
c.JupyterHub.tornado_settings = {"slow_spawn_timeout": 0}
# create our test-user
c.Authenticator.allowed_users = {
'test-user',
}
# testing boilerplate: fake auth/spawner, localhost. Don't use this for real!
c.JupyterHub.authenticator_class = 'dummy'
c.JupyterHub.spawner_class = 'simple'
c.JupyterHub.ip = '127.0.0.1'

View File

@@ -1,173 +0,0 @@
#!/usr/bin/env python3
"""
Example of starting/stopping a server via the JupyterHub API
1. get user status
2. start server
3. wait for server to be ready via progress api
4. make a request to the server itself
5. stop server via API
6. wait for server to finish stopping
"""
import json
import logging
import pathlib
import time
import requests
log = logging.getLogger(__name__)
def get_token():
"""boilerplate: get token from share file.
Make sure to start jupyterhub in this directory first
"""
here = pathlib.Path(__file__).parent
token_file = here.joinpath("service-token")
log.info(f"Loading token from {token_file}")
with token_file.open("r") as f:
token = f.read()
return token
def make_session(token):
"""Create a requests.Session with our service token in the Authorization header"""
session = requests.Session()
session.headers = {"Authorization": f"token {token}"}
return session
def event_stream(session, url):
"""Generator yielding events from a JSON event stream
For use with the server progress API
"""
r = session.get(url, stream=True)
r.raise_for_status()
for line in r.iter_lines():
line = line.decode('utf8', 'replace')
# event lines all start with `data:`
# all other lines should be ignored (they will be empty)
if line.startswith('data:'):
yield json.loads(line.split(':', 1)[1])
def start_server(session, hub_url, user, server_name=""):
"""Start a server for a jupyterhub user
Returns the full URL for accessing the server
"""
user_url = f"{hub_url}/hub/api/users/{user}"
log_name = f"{user}/{server_name}".rstrip("/")
# step 1: get user status
r = session.get(user_url)
r.raise_for_status()
user_model = r.json()
# if server is not 'active', request launch
if server_name not in user_model.get('servers', {}):
log.info(f"Starting server {log_name}")
r = session.post(f"{user_url}/servers/{server_name}")
r.raise_for_status()
if r.status_code == 201:
log.info(f"Server {log_name} is launched and ready")
elif r.status_code == 202:
log.info(f"Server {log_name} is launching...")
else:
log.warning(f"Unexpected status: {r.status_code}")
r = session.get(user_url)
r.raise_for_status()
user_model = r.json()
# report server status
server = user_model['servers'][server_name]
if server['pending']:
status = f"pending {server['pending']}"
elif server['ready']:
status = "ready"
else:
# shouldn't be possible!
raise ValueError(f"Unexpected server state: {server}")
log.info(f"Server {log_name} is {status}")
# wait for server to be ready using progress API
progress_url = user_model['servers'][server_name]['progress_url']
for event in event_stream(session, f"{hub_url}{progress_url}"):
log.info(f"Progress {event['progress']}%: {event['message']}")
if event.get("ready"):
server_url = event['url']
break
else:
# server never ready
raise ValueError(f"{log_name} never started!")
# at this point, we know the server is ready and waiting to receive requests
# return the full URL where the server can be accessed
return f"{hub_url}{server_url}"
def stop_server(session, hub_url, user, server_name=""):
"""Stop a server via the JupyterHub API
Returns when the server has finished stopping
"""
# step 1: get user status
user_url = f"{hub_url}/hub/api/users/{user}"
server_url = f"{user_url}/servers/{server_name}"
log_name = f"{user}/{server_name}".rstrip("/")
log.info(f"Stopping server {log_name}")
r = session.delete(server_url)
if r.status_code == 404:
log.info(f"Server {log_name} already stopped")
r.raise_for_status()
if r.status_code == 204:
log.info(f"Server {log_name} stopped")
return
# else: 202, stop requested, but not complete
# wait for stop to finish
log.info(f"Server {log_name} stopping...")
# wait for server to be done stopping
while True:
r = session.get(user_url)
r.raise_for_status()
user_model = r.json()
if server_name not in user_model.get("servers", {}):
log.info(f"Server {log_name} stopped")
return
server = user_model["servers"][server_name]
if not server['pending']:
raise ValueError(f"Waiting for {log_name}, but no longer pending.")
log.info(f"Server {log_name} pending: {server['pending']}")
# wait to poll again
time.sleep(1)
def main():
"""Start and stop one server
Uses test-user and hub from jupyterhub_config.py in this directory
"""
user = "test-user"
hub_url = "http://127.0.0.1:8000"
session = make_session(get_token())
server_url = start_server(session, hub_url, user)
r = session.get(f"{server_url}/api/status")
r.raise_for_status()
log.info(f"Server status: {r.text}")
stop_server(session, hub_url, user)
if __name__ == "__main__":
logging.basicConfig(level=logging.INFO)
main()

View File

@@ -1,3 +1,4 @@
# Simple Announcement Service Example # Simple Announcement Service Example
This is a simple service that allows administrators to manage announcements This is a simple service that allows administrators to manage announcements
@@ -6,17 +7,15 @@ that appear when JupyterHub renders pages.
To run the service as a hub-managed service simply include in your JupyterHub To run the service as a hub-managed service simply include in your JupyterHub
configuration file something like: configuration file something like:
```python c.JupyterHub.services = [
c.JupyterHub.services = [
{ {
'name': 'announcement', 'name': 'announcement',
'url': 'http://127.0.0.1:8888', 'url': 'http://127.0.0.1:8888',
'command': [sys.executable, "-m", "announcement", "--port", "8888"], 'command': [sys.executable, "-m", "announcement"],
} }
] ]
```
This starts the announcements service up at `/services/announcement/` when This starts the announcements service up at `/services/announcement` when
JupyterHub launches. By default the announcement text is empty. JupyterHub launches. By default the announcement text is empty.
The `announcement` module has a configurable port (default 8888) and an API The `announcement` module has a configurable port (default 8888) and an API
@@ -25,28 +24,15 @@ that environment variable is set or `/` if it is not.
## Managing the Announcement ## Managing the Announcement
Users with permission can set the announcement text with an API token: Admin users can set the announcement text with an API token:
$ curl -X POST -H "Authorization: token <token>" \ $ curl -X POST -H "Authorization: token <token>" \
-d '{"announcement":"JupyterHub will be upgraded on August 14!"}' \ -d "{'announcement':'JupyterHub will be upgraded on August 14!'}" \
https://.../services/announcement/ https://.../services/announcement
To grant permission, add a role (JupyterHub 2.0) with access to the announcement service:
```python
# grant the 'announcer' permission to access the announcement service
c.JupyterHub.load_roles = [
{
"name": "announcers",
"users": ["announcer"], # or groups
"scopes": ["access:services!service=announcement"],
}
]
```
Anyone can read the announcement: Anyone can read the announcement:
$ curl https://.../services/announcement/ | python -m json.tool $ curl https://.../services/announcement | python -m json.tool
{ {
announcement: "JupyterHub will be upgraded on August 14!", announcement: "JupyterHub will be upgraded on August 14!",
timestamp: "...", timestamp: "...",
@@ -56,11 +42,10 @@ Anyone can read the announcement:
The time the announcement was posted is recorded in the `timestamp` field and The time the announcement was posted is recorded in the `timestamp` field and
the user who posted the announcement is recorded in the `user` field. the user who posted the announcement is recorded in the `user` field.
To clear the announcement text, send a DELETE request. To clear the announcement text, just DELETE. Only admin users can do this.
This has the same permission requirement.
$ curl -X DELETE -H "Authorization: token <token>" \ $ curl -X POST -H "Authorization: token <token>" \
https://.../services/announcement/ https://.../services/announcement
## Seeing the Announcement in JupyterHub ## Seeing the Announcement in JupyterHub

View File

@@ -13,6 +13,9 @@ from jupyterhub.services.auth import HubAuthenticated
class AnnouncementRequestHandler(HubAuthenticated, web.RequestHandler): class AnnouncementRequestHandler(HubAuthenticated, web.RequestHandler):
"""Dynamically manage page announcements""" """Dynamically manage page announcements"""
hub_users = []
allow_admin = True
def initialize(self, storage): def initialize(self, storage):
"""Create storage for announcement text""" """Create storage for announcement text"""
self.storage = storage self.storage = storage

View File

@@ -2,18 +2,11 @@ import sys
# To run the announcement service managed by the hub, add this. # To run the announcement service managed by the hub, add this.
port = 9999
c.JupyterHub.services = [ c.JupyterHub.services = [
{ {
'name': 'announcement', 'name': 'announcement',
'url': f'http://127.0.0.1:{port}', 'url': 'http://127.0.0.1:8888',
'command': [ 'command': [sys.executable, "-m", "announcement"],
sys.executable,
"-m",
"announcement",
'--port',
str(port),
],
} }
] ]
@@ -21,19 +14,3 @@ c.JupyterHub.services = [
# for an example of how to do this. # for an example of how to do this.
c.JupyterHub.template_paths = ["templates"] c.JupyterHub.template_paths = ["templates"]
c.Authenticator.allowed_users = {"announcer", "otheruser"}
# grant the 'announcer' permission to access the announcement service
c.JupyterHub.load_roles = [
{
"name": "announcers",
"users": ["announcer"],
"scopes": ["access:services!service=announcement"],
}
]
# dummy spawner and authenticator for testing, don't actually use these!
c.JupyterHub.authenticator_class = 'dummy'
c.JupyterHub.spawner_class = 'simple'
c.JupyterHub.ip = '127.0.0.1' # let's just run on localhost while dummy auth is enabled

View File

@@ -1,9 +1,14 @@
{% extends "templates/page.html" %} {% block announcement %} {% extends "templates/page.html" %}
<div class="container text-center announcement"></div> {% block announcement %}
{% endblock %} {% block script %} {{ super() }} <div class="container text-center announcement">
</div>
{% endblock %}
{% block script %}
{{ super() }}
<script> <script>
$.get("/services/announcement/", function (data) { $.get("/services/announcement/", function(data) {
$(".announcement").html(data["announcement"]); $(".announcement").html(data["announcement"]);
}); });
</script> </script>
{% endblock %} {% endblock %}

View File

@@ -1,13 +0,0 @@
FROM jupyterhub/jupyterhub
# Create test user (PAM auth) and install single-user Jupyter
RUN useradd testuser --create-home --shell /bin/bash
RUN echo 'testuser:passwd' | chpasswd
RUN pip install jupyter
COPY app ./app
COPY jupyterhub_config.py .
COPY requirements.txt /tmp/requirements.txt
RUN pip install -r /tmp/requirements.txt
CMD ["jupyterhub", "--ip", "0.0.0.0"]

View File

@@ -1,113 +0,0 @@
# Fastapi
[FastAPI](https://fastapi.tiangolo.com/) is a popular new web framework attractive for its type hinting, async support, automatic doc generation (Swagger), and more. Their [Feature highlights](https://fastapi.tiangolo.com/features/) sum it up nicely.
# Swagger UI with OAuth demo
![Fastapi Service Example](./fastapi_example.gif)
# Try it out locally
1. Install `fastapi` and other dependencies, then launch Jupyterhub
```
pip install -r requirements.txt
jupyterhub --ip=127.0.0.1
```
2. Visit http://127.0.0.1:8000/services/fastapi or http://127.0.0.1:8000/services/fastapi/docs
Login with username 'test-user' and any password.
3. Try interacting programmatically. If you create a new token in your control panel or pull out the `JUPYTERHUB_API_TOKEN` in the single user environment, you can skip the third step here.
```
$ curl -X GET http://127.0.0.1:8000/services/fastapi/
{"Hello":"World"}
$ curl -X GET http://127.0.0.1:8000/services/fastapi/me
{"detail":"Must login with token parameter, or Authorization bearer header"}
$ curl -X POST http://127.0.0.1:8000/hub/api/users/test-user/tokens \
-d '{"auth": {"username": "test-user", "password": "mypasswd!"}}' \
| jq '.token'
"3fee13ce6d2845da9bd5f2c2170d3428"
$ curl -X GET http://127.0.0.1:8000/services/fastapi/me \
-H "Authorization: Bearer 3fee13ce6d2845da9bd5f2c2170d3428" \
| jq .
{
"name": "test-user",
"admin": false,
"groups": [],
"server": null,
"pending": null,
"last_activity": "2021-05-21T09:13:00.514309+00:00",
"servers": null,
"scopes": [
"access:services",
"access:servers!user=test-user",
"...",
]
}
```
# Try it out in Docker
1. Build and run the Docker image locally
```bash
sudo docker build . -t service-fastapi
sudo docker run -it -p 8000:8000 service-fastapi
```
2. Visit http://127.0.0.1:8000/services/fastapi/docs. When going through the OAuth flow or getting a token from the control panel, you can log in with `testuser` / `passwd`.
# PUBLIC_HOST
If you are running your service behind a proxy, or on a Docker / Kubernetes infrastructure, you might run into an error during OAuth that says `Mismatching redirect URI`. In the Jupterhub logs, there will be a warning along the lines of: `[W 2021-04-06 23:40:06.707 JupyterHub provider:498] Redirect uri https://jupyterhub.my.cloud/services/fastapi/oauth_callback != /services/fastapi/oauth_callback`. This happens because Swagger UI adds the request host, as seen in the browser, to the Authorization URL.
To solve that problem, the `oauth_redirect_uri` value in the service initialization needs to match what Swagger will auto-generate and what the service will use when POST'ing to `/oauth2/token`. In this example, setting the `PUBLIC_HOST` environment variable to your public-facing Hub domain (e.g. `https://jupyterhub.my.cloud`) should make it work.
# Notes on security.py
FastAPI has a concept of a [dependency injection](https://fastapi.tiangolo.com/tutorial/dependencies) using a `Depends` object (and a subclass `Security`) that is automatically instantiated/executed when it is a parameter for your endpoint routes. You can utilize a `Depends` object for re-useable common parameters or authentication mechanisms like the [`get_user`](https://fastapi.tiangolo.com/tutorial/security/get-current-user) pattern.
JupyterHub OAuth has three ways to authenticate: a `token` url parameter; a `Authorization: Bearer <token>` header; and a (deprecated) `jupyterhub-services` cookie. FastAPI has helper functions that let us create `Security` (dependency injection) objects for each of those. When you need to allow multiple / optional authentication dependencies (`Security` objects), then you can use the argument `auto_error=False` and it will return `None` instead of raising an `HTTPException`.
Endpoints that need authentication (`/me` and `/debug` in this example) can leverage the `get_user` pattern and effectively pull the user model from the Hub API when a request has authenticated with cookie / token / header all using the simple syntax,
```python
from .security import get_current_user
from .models import User
@router.get("/new_endpoint")
async def new_endpoint(user: User = Depends(get_current_user)):
"Function that needs to work with an authenticated user"
return {"Hello": user.name}
```
# Notes on client.py
FastAPI is designed to be an asynchronous web server, so the interactions with the Hub API should be made asynchronously as well. Instead of using `requests` to get user information from a token/cookie, this example uses [`httpx`](https://www.python-httpx.org/). `client.py` defines a small function that creates a `Client` (equivalent of `requests.Session`) with the Hub API url as it's `base_url` and adding the `JUPYTERHUB_API_TOKEN` to every header.
Consider this a very minimal alternative to using `jupyterhub.services.auth.HubOAuth`
```python
# client.py
import os
def get_client():
base_url = os.environ["JUPYTERHUB_API_URL"]
token = os.environ["JUPYTERHUB_API_TOKEN"]
headers = {"Authorization": "Bearer %s" % token}
return httpx.AsyncClient(base_url=base_url, headers=headers)
```
```python
# other modules
from .client import get_client
async with get_client() as client:
resp = await client.get('/endpoint')
...
```

View File

@@ -1 +0,0 @@
from .app import app

View File

@@ -1,25 +0,0 @@
import os
from fastapi import FastAPI
from .service import router
### When managed by Jupyterhub, the actual endpoints
### will be served out prefixed by /services/:name.
### One way to handle this with FastAPI is to use an APIRouter.
### All routes are defined in service.py
app = FastAPI(
title="Example FastAPI Service",
version="0.1",
### Serve out Swagger from the service prefix (<hub>/services/:name/docs)
openapi_url=router.prefix + "/openapi.json",
docs_url=router.prefix + "/docs",
redoc_url=router.prefix + "/redoc",
### Add our service client id to the /docs Authorize form automatically
swagger_ui_init_oauth={"clientId": os.environ["JUPYTERHUB_CLIENT_ID"]},
### Default /docs/oauth2 redirect will cause Hub
### to raise oauth2 redirect uri mismatch errors
swagger_ui_oauth2_redirect_url=os.environ["JUPYTERHUB_OAUTH_CALLBACK_URL"],
)
app.include_router(router)

View File

@@ -1,11 +0,0 @@
import os
import httpx
# a minimal alternative to using HubOAuth class
def get_client():
base_url = os.environ["JUPYTERHUB_API_URL"]
token = os.environ["JUPYTERHUB_API_TOKEN"]
headers = {"Authorization": "Bearer %s" % token}
return httpx.AsyncClient(base_url=base_url, headers=headers)

View File

@@ -1,48 +0,0 @@
from datetime import datetime
from typing import Any
from typing import Dict
from typing import List
from typing import Optional
from pydantic import BaseModel
# https://jupyterhub.readthedocs.io/en/stable/_static/rest-api/index.html
class Server(BaseModel):
name: str
ready: bool
pending: Optional[str]
url: str
progress_url: str
started: datetime
last_activity: datetime
state: Optional[Any]
user_options: Optional[Any]
class User(BaseModel):
name: str
admin: bool
groups: Optional[List[str]]
server: Optional[str]
pending: Optional[str]
last_activity: datetime
servers: Optional[Dict[str, Server]]
scopes: List[str]
# https://stackoverflow.com/questions/64501193/fastapi-how-to-use-httpexception-in-responses
class AuthorizationError(BaseModel):
detail: str
class HubResponse(BaseModel):
msg: str
request_url: str
token: str
response_code: int
hub_response: dict
class HubApiError(BaseModel):
detail: HubResponse

View File

@@ -1,79 +0,0 @@
import json
import os
from fastapi import HTTPException
from fastapi import Security
from fastapi import status
from fastapi.security import OAuth2AuthorizationCodeBearer
from fastapi.security.api_key import APIKeyQuery
from .client import get_client
from .models import User
### Endpoints can require authentication using Depends(get_current_user)
### get_current_user will look for a token in url params or
### Authorization: bearer token (header).
### Hub technically supports cookie auth too, but it is deprecated so
### not being included here.
auth_by_param = APIKeyQuery(name="token", auto_error=False)
auth_url = os.environ["PUBLIC_HOST"] + "/hub/api/oauth2/authorize"
auth_by_header = OAuth2AuthorizationCodeBearer(
authorizationUrl=auth_url, tokenUrl="get_token", auto_error=False
)
### ^^ The flow for OAuth2 in Swagger is that the "authorize" button
### will redirect user (browser) to "auth_url", which is the Hub login page.
### After logging in, the browser will POST to our internal /get_token endpoint
### with the auth code. That endpoint POST's to Hub /oauth2/token with
### our client_secret (JUPYTERHUB_API_TOKEN) and that code to get an
### access_token, which it returns to browser, which places in Authorization header.
if os.environ.get("JUPYTERHUB_OAUTH_SCOPES"):
# typically ["access:services", "access:services!service=$service_name"]
access_scopes = json.loads(os.environ["JUPYTERHUB_OAUTH_SCOPES"])
else:
access_scopes = ["access:services"]
### For consideration: optimize performance with a cache instead of
### always hitting the Hub api?
async def get_current_user(
auth_by_param: str = Security(auth_by_param),
auth_by_header: str = Security(auth_by_header),
):
token = auth_by_param or auth_by_header
if token is None:
raise HTTPException(
status.HTTP_401_UNAUTHORIZED,
detail="Must login with token parameter or Authorization bearer header",
)
async with get_client() as client:
endpoint = "/user"
# normally we auth to Hub API with service api token,
# but this time auth as the user token to get user model
headers = {"Authorization": f"Bearer {token}"}
resp = await client.get(endpoint, headers=headers)
if resp.is_error:
raise HTTPException(
status.HTTP_400_BAD_REQUEST,
detail={
"msg": "Error getting user info from token",
"request_url": str(resp.request.url),
"token": token,
"response_code": resp.status_code,
"hub_response": resp.json(),
},
)
user = User(**resp.json())
if any(scope in user.scopes for scope in access_scopes):
return user
else:
raise HTTPException(
status.HTTP_403_FORBIDDEN,
detail={
"msg": f"User not authorized: {user.name}",
"request_url": str(resp.request.url),
"token": token,
"user": resp.json(),
},
)

View File

@@ -1,70 +0,0 @@
import os
from fastapi import APIRouter
from fastapi import Depends
from fastapi import Form
from fastapi import Request
from .client import get_client
from .models import AuthorizationError
from .models import HubApiError
from .models import User
from .security import get_current_user
# APIRouter prefix cannot end in /
service_prefix = os.getenv("JUPYTERHUB_SERVICE_PREFIX", "").rstrip("/")
router = APIRouter(prefix=service_prefix)
@router.post("/get_token", include_in_schema=False)
async def get_token(code: str = Form(...)):
"Callback function for OAuth2AuthorizationCodeBearer scheme"
# The only thing we need in this form post is the code
# Everything else we can hardcode / pull from env
async with get_client() as client:
redirect_uri = (
os.environ["PUBLIC_HOST"] + os.environ["JUPYTERHUB_OAUTH_CALLBACK_URL"],
)
data = {
"client_id": os.environ["JUPYTERHUB_CLIENT_ID"],
"client_secret": os.environ["JUPYTERHUB_API_TOKEN"],
"grant_type": "authorization_code",
"code": code,
"redirect_uri": redirect_uri,
}
resp = await client.post("/oauth2/token", data=data)
### resp.json() is {'access_token': <token>, 'token_type': 'Bearer'}
return resp.json()
@router.get("/")
async def index():
"Non-authenticated function that returns {'Hello': 'World'}"
return {"Hello": "World"}
# response_model and responses dict translate to OpenAPI (Swagger) hints
# compare and contrast what the /me endpoint looks like in Swagger vs /debug
@router.get(
"/me",
response_model=User,
responses={401: {'model': AuthorizationError}, 400: {'model': HubApiError}},
)
async def me(user: User = Depends(get_current_user)):
"Authenticated function that returns the User model"
return user
@router.get("/debug")
async def index(request: Request, user: User = Depends(get_current_user)):
"""
Authenticated function that returns a few pieces of debug
* Environ of the service process
* Request headers
* User model
"""
return {
"env": dict(os.environ),
"headers": dict(request.headers),
"user": user,
}

Binary file not shown.

Before

Width:  |  Height:  |  Size: 2.7 MiB

View File

@@ -1,44 +0,0 @@
import os
import warnings
# When Swagger performs OAuth2 in the browser, it will set
# the request host + relative path as the redirect uri, causing a
# uri mismatch if the oauth_redirect_uri is just the relative path
# is set in the c.JupyterHub.services entry (as per default).
# Therefore need to know the request host ahead of time.
if "PUBLIC_HOST" not in os.environ:
msg = (
"env PUBLIC_HOST is not set, defaulting to http://127.0.0.1:8000. "
"This can cause problems with OAuth. "
"Set PUBLIC_HOST to your public (browser accessible) host."
)
warnings.warn(msg)
public_host = "http://127.0.0.1:8000"
else:
public_host = os.environ["PUBLIC_HOST"].rstrip('/')
service_name = "fastapi"
oauth_redirect_uri = f"{public_host}/services/{service_name}/oauth_callback"
c.JupyterHub.services = [
{
"name": service_name,
"url": "http://127.0.0.1:10202",
"command": ["uvicorn", "app:app", "--port", "10202"],
"oauth_redirect_uri": oauth_redirect_uri,
"environment": {"PUBLIC_HOST": public_host},
}
]
c.JupyterHub.load_roles = [
{
"name": "user",
# grant all users access to services
"scopes": ["self", "access:services"],
},
]
# dummy for testing, create test-user
c.Authenticator.allowed_users = {"test-user"}
c.JupyterHub.authenticator_class = "dummy"
c.JupyterHub.spawner_class = "simple"

View File

@@ -1,4 +0,0 @@
fastapi
httpx
python-multipart
uvicorn

View File

@@ -20,5 +20,5 @@ In the external example, some extra steps are required to set up supervisor:
1. select a system user to run the service. This is a user on the system, and does not need to be a Hub user. Add this to the user field in `shared-notebook.conf`, replacing `someuser`. 1. select a system user to run the service. This is a user on the system, and does not need to be a Hub user. Add this to the user field in `shared-notebook.conf`, replacing `someuser`.
2. generate a secret token for authentication, and replace the `super-secret` fields in `shared-notebook-service` and `jupyterhub_config.py` 2. generate a secret token for authentication, and replace the `super-secret` fields in `shared-notebook-service` and `jupyterhub_config.py`
3. install `shared-notebook-service` somewhere on your system, and update `/path/to/shared-notebook-service` to the absolute path of this destination 3. install `shared-notebook-service` somewhere on your system, and update `/path/to/shared-notebook-service` to the absolute path of this destination
4. copy `shared-notebook.conf` to `/etc/supervisor/conf.d/` 3. copy `shared-notebook.conf` to `/etc/supervisor/conf.d/`
5. `supervisorctl reload` 4. `supervisorctl reload`

View File

@@ -1,35 +1,15 @@
# our user list # our user list
c.Authenticator.allowed_users = ['minrk', 'ellisonbg', 'willingc'] c.Authenticator.whitelist = ['minrk', 'ellisonbg', 'willingc']
service_name = 'shared-notebook' # ellisonbg and willingc have access to a shared server:
service_port = 9999
group_name = 'shared'
# ellisonbg and willingc are in a group that will access the shared server: c.JupyterHub.load_groups = {'shared': ['ellisonbg', 'willingc']}
c.JupyterHub.load_groups = {group_name: ['ellisonbg', 'willingc']}
# start the notebook server as a service # start the notebook server as a service
c.JupyterHub.services = [ c.JupyterHub.services = [
{ {
'name': service_name, 'name': 'shared-notebook',
'url': f'http://127.0.0.1:{service_port}', 'url': 'http://127.0.0.1:9999',
'api_token': 'c3a29e5d386fd7c9aa1e8fe9d41c282ec8b', 'api_token': 'super-secret',
} }
] ]
# This "role assignment" is what grants members of the group
# access to the service
c.JupyterHub.load_roles = [
{
"name": "shared-notebook",
"groups": [group_name],
"scopes": [f"access:services!service={service_name}"],
},
]
# dummy spawner and authenticator for testing, don't actually use these!
c.JupyterHub.authenticator_class = 'dummy'
c.JupyterHub.spawner_class = 'simple'
c.JupyterHub.ip = '127.0.0.1' # let's just run on localhost while dummy auth is enabled

View File

@@ -1,11 +1,9 @@
#!/bin/bash -l #!/bin/bash -l
set -e set -e
# these must match the values in jupyterhub_config.py export JUPYTERHUB_API_TOKEN=super-secret
export JUPYTERHUB_API_TOKEN=c3a29e5d386fd7c9aa1e8fe9d41c282ec8b
export JUPYTERHUB_SERVICE_URL=http://127.0.0.1:9999 export JUPYTERHUB_SERVICE_URL=http://127.0.0.1:9999
export JUPYTERHUB_SERVICE_NAME=shared-notebook export JUPYTERHUB_SERVICE_NAME=shared-notebook
export JUPYTERHUB_SERVICE_PREFIX="/services/${JUPYTERHUB_SERVICE_NAME}/"
export JUPYTERHUB_CLIENT_ID="service-${JUPYTERHUB_SERVICE_NAME}"
jupyterhub-singleuser jupyterhub-singleuser \
--group='shared'

View File

@@ -1,35 +1,19 @@
# our user list # our user list
c.Authenticator.allowed_users = ['minrk', 'ellisonbg', 'willingc'] c.Authenticator.whitelist = ['minrk', 'ellisonbg', 'willingc']
# ellisonbg and willingc have access to a shared server:
c.JupyterHub.load_groups = {'shared': ['ellisonbg', 'willingc']}
service_name = 'shared-notebook' service_name = 'shared-notebook'
service_port = 9999 service_port = 9999
group_name = 'shared' group_name = 'shared'
# ellisonbg and willingc have access to a shared server:
c.JupyterHub.load_groups = {group_name: ['ellisonbg', 'willingc']}
# start the notebook server as a service # start the notebook server as a service
c.JupyterHub.services = [ c.JupyterHub.services = [
{ {
'name': service_name, 'name': service_name,
'url': f'http://127.0.0.1:{service_port}', 'url': 'http://127.0.0.1:{}'.format(service_port),
'command': ['jupyterhub-singleuser', '--debug'], 'command': ['jupyterhub-singleuser', '--group=shared', '--debug'],
} }
] ]
# This "role assignment" is what grants members of the group
# access to the service
c.JupyterHub.load_roles = [
{
"name": "shared-notebook",
"groups": [group_name],
"scopes": [f"access:services!service={service_name}"],
},
]
# dummy spawner and authenticator for testing, don't actually use these!
c.JupyterHub.authenticator_class = 'dummy'
c.JupyterHub.spawner_class = 'simple'
c.JupyterHub.ip = '127.0.0.1' # let's just run on localhost while dummy auth is enabled

View File

@@ -1,6 +1,6 @@
# Authenticating a flask service with JupyterHub # Authenticating a flask service with JupyterHub
Uses `jupyterhub.services.HubOAuth` to authenticate requests with the Hub in a [flask][] application. Uses `jupyterhub.services.HubAuth` to authenticate requests with the Hub in a [flask][] application.
## Run ## Run
@@ -8,7 +8,7 @@ Uses `jupyterhub.services.HubOAuth` to authenticate requests with the Hub in a [
jupyterhub --ip=127.0.0.1 jupyterhub --ip=127.0.0.1
2. Visit http://127.0.0.1:8000/services/whoami/ 2. Visit http://127.0.0.1:8000/services/whoami/ or http://127.0.0.1:8000/services/whoami-oauth/
After logging in with your local-system credentials, you should see a JSON dump of your user info: After logging in with your local-system credentials, you should see a JSON dump of your user info:
@@ -29,4 +29,5 @@ A similar service could be run externally, by setting the JupyterHub service env
JUPYTERHUB_API_TOKEN JUPYTERHUB_API_TOKEN
JUPYTERHUB_SERVICE_PREFIX JUPYTERHUB_SERVICE_PREFIX
[flask]: http://flask.pocoo.org [flask]: http://flask.pocoo.org

View File

@@ -5,12 +5,10 @@ c.JupyterHub.services = [
'command': ['flask', 'run', '--port=10101'], 'command': ['flask', 'run', '--port=10101'],
'environment': {'FLASK_APP': 'whoami-flask.py'}, 'environment': {'FLASK_APP': 'whoami-flask.py'},
}, },
{
'name': 'whoami-oauth',
'url': 'http://127.0.0.1:10201',
'command': ['flask', 'run', '--port=10201'],
'environment': {'FLASK_APP': 'whoami-oauth.py'},
},
] ]
# dummy auth and simple spawner for testing
# any username and password will work
c.JupyterHub.spawner_class = 'simple'
c.JupyterHub.authenticator_class = 'dummy'
# listen only on localhost while testing with wide-open auth
c.JupyterHub.ip = '127.0.0.1'

View File

@@ -4,48 +4,42 @@ whoami service authentication with the Hub
""" """
import json import json
import os import os
import secrets
from functools import wraps from functools import wraps
from urllib.parse import quote
from flask import Flask from flask import Flask
from flask import make_response
from flask import redirect from flask import redirect
from flask import request from flask import request
from flask import Response from flask import Response
from flask import session
from jupyterhub.services.auth import HubOAuth from jupyterhub.services.auth import HubAuth
prefix = os.environ.get('JUPYTERHUB_SERVICE_PREFIX', '/') prefix = os.environ.get('JUPYTERHUB_SERVICE_PREFIX', '/')
auth = HubOAuth(api_token=os.environ['JUPYTERHUB_API_TOKEN'], cache_max_age=60) auth = HubAuth(api_token=os.environ['JUPYTERHUB_API_TOKEN'], cache_max_age=60)
app = Flask(__name__) app = Flask(__name__)
# encryption key for session cookies
app.secret_key = secrets.token_bytes(32)
def authenticated(f): def authenticated(f):
"""Decorator for authenticating with the Hub via OAuth""" """Decorator for authenticating with the Hub"""
@wraps(f) @wraps(f)
def decorated(*args, **kwargs): def decorated(*args, **kwargs):
token = session.get("token") cookie = request.cookies.get(auth.cookie_name)
token = request.headers.get(auth.auth_header_name)
if token: if cookie:
user = auth.user_for_cookie(cookie)
elif token:
user = auth.user_for_token(token) user = auth.user_for_token(token)
else: else:
user = None user = None
if user: if user:
return f(user, *args, **kwargs) return f(user, *args, **kwargs)
else: else:
# redirect to login url on failed auth # redirect to login url on failed auth
state = auth.generate_state(next_url=request.path) return redirect(auth.login_url + '?next=%s' % quote(request.path))
response = make_response(redirect(auth.login_url + '&state=%s' % state))
response.set_cookie(auth.state_cookie_name, state)
return response
return decorated return decorated
@@ -56,24 +50,3 @@ def whoami(user):
return Response( return Response(
json.dumps(user, indent=1, sort_keys=True), mimetype='application/json' json.dumps(user, indent=1, sort_keys=True), mimetype='application/json'
) )
@app.route(prefix + 'oauth_callback')
def oauth_callback():
code = request.args.get('code', None)
if code is None:
return 403
# validate state field
arg_state = request.args.get('state', None)
cookie_state = request.cookies.get(auth.state_cookie_name)
if arg_state is None or arg_state != cookie_state:
# state doesn't match
return 403
token = auth.token_for_code(code)
# store token in session cookie
session["token"] = token
next_url = auth.get_next_url(cookie_state) or prefix
response = make_response(redirect(next_url))
return response

View File

@@ -0,0 +1,72 @@
#!/usr/bin/env python3
"""
whoami service authentication with the Hub
"""
import json
import os
from functools import wraps
from flask import Flask
from flask import make_response
from flask import redirect
from flask import request
from flask import Response
from jupyterhub.services.auth import HubOAuth
prefix = os.environ.get('JUPYTERHUB_SERVICE_PREFIX', '/')
auth = HubOAuth(api_token=os.environ['JUPYTERHUB_API_TOKEN'], cache_max_age=60)
app = Flask(__name__)
def authenticated(f):
"""Decorator for authenticating with the Hub via OAuth"""
@wraps(f)
def decorated(*args, **kwargs):
token = request.cookies.get(auth.cookie_name)
if token:
user = auth.user_for_token(token)
else:
user = None
if user:
return f(user, *args, **kwargs)
else:
# redirect to login url on failed auth
state = auth.generate_state(next_url=request.path)
response = make_response(redirect(auth.login_url + '&state=%s' % state))
response.set_cookie(auth.state_cookie_name, state)
return response
return decorated
@app.route(prefix)
@authenticated
def whoami(user):
return Response(
json.dumps(user, indent=1, sort_keys=True), mimetype='application/json'
)
@app.route(prefix + 'oauth_callback')
def oauth_callback():
code = request.args.get('code', None)
if code is None:
return 403
# validate state field
arg_state = request.args.get('state', None)
cookie_state = request.cookies.get(auth.state_cookie_name)
if arg_state is None or arg_state != cookie_state:
# state doesn't match
return 403
token = auth.token_for_code(code)
next_url = auth.get_next_url(cookie_state) or prefix
response = make_response(redirect(next_url))
response.set_cookie(auth.cookie_name, token)
return response

View File

@@ -2,15 +2,15 @@
Uses `jupyterhub.services.HubAuthenticated` to authenticate requests with the Hub. Uses `jupyterhub.services.HubAuthenticated` to authenticate requests with the Hub.
There is an implementation each of api-token-based `HubAuthenticated` and OAuth-based `HubOAuthenticated`. There is an implementation each of cookie-based `HubAuthenticated` and OAuth-based `HubOAuthenticated`.
## Run ## Run
1. Launch JupyterHub and the `whoami` services with 1. Launch JupyterHub and the `whoami service` with
jupyterhub --ip=127.0.0.1 jupyterhub --ip=127.0.0.1
2. Visit http://127.0.0.1:8000/services/whoami-oauth 2. Visit http://127.0.0.1:8000/services/whoami or http://127.0.0.1:8000/services/whoami-oauth
After logging in with your local-system credentials, you should see a JSON dump of your user info: After logging in with your local-system credentials, you should see a JSON dump of your user info:
@@ -24,65 +24,15 @@ After logging in with your local-system credentials, you should see a JSON dump
} }
``` ```
The `whoami-api` service powered by the base `HubAuthenticated` class only supports token-authenticated API requests,
not browser visits, because it does not implement OAuth. Visit it by requesting an api token from the tokens page,
and making a direct request:
```bash
$ curl -H "Authorization: token 8630bbd8ef064c48b22c7f122f0cd8ad" http://127.0.0.1:8000/services/whoami-api/ | jq .
{
"admin": false,
"created": "2021-05-21T09:47:41.299400Z",
"groups": [],
"kind": "user",
"last_activity": "2021-05-21T09:49:08.290745Z",
"name": "test",
"pending": null,
"roles": [
"user"
],
"scopes": [
"access:services",
"access:servers!user=test",
"read:users!user=test",
"read:users:activity!user=test",
"read:users:groups!user=test",
"read:users:name!user=test",
"read:servers!user=test",
"read:tokens!user=test",
"users!user=test",
"users:activity!user=test",
"users:groups!user=test",
"users:name!user=test",
"servers!user=test",
"tokens!user=test"
],
"server": null
}
```
This relies on the Hub starting the whoami services, via config (see [jupyterhub_config.py](./jupyterhub_config.py)). This relies on the Hub starting the whoami services, via config (see [jupyterhub_config.py](./jupyterhub_config.py)).
To govern access to the services, create **roles** with the scope `access:services!service=$service-name`, You may set the `hub_users` configuration in the service script
and assign users to the scope. to restrict access to the service to a whitelist of allowed users.
By default, any authenticated user is allowed.
The jupyterhub_config.py grants access for all users to all services via the default 'user' role, with:
```python
c.JupyterHub.load_roles = [
{
"name": "user",
# grant all users access to all services
"scopes": ["access:services", "self"],
}
]
```
A similar service could be run externally, by setting the JupyterHub service environment variables: A similar service could be run externally, by setting the JupyterHub service environment variables:
JUPYTERHUB_API_TOKEN JUPYTERHUB_API_TOKEN
JUPYTERHUB_SERVICE_PREFIX JUPYTERHUB_SERVICE_PREFIX
JUPYTERHUB_OAUTH_SCOPES
JUPYTERHUB_CLIENT_ID # for whoami-oauth only
or instantiating and configuring a HubAuth object yourself, and attaching it as `self.hub_auth` in your HubAuthenticated handlers. or instantiating and configuring a HubAuth object yourself, and attaching it as `self.hub_auth` in your HubAuthenticated handlers.

Some files were not shown because too many files have changed in this diff Show More