Dockerfile

# syntax=docker/dockerfile:1

# tensorflow-notebook:latest installs tensorflow-cpu from PyPI
FROM quay.io/jupyter/tensorflow-notebook:latest AS build

# fix: https://github.com/hadolint/hadolint/wiki/DL4006
# fix: https://github.com/koalaman/shellcheck/wiki/SC3014
SHELL ["/bin/bash", "-o", "pipefail", "-c"]

USER root

RUN apt-get update --yes && \
    apt-get install --yes --no-install-recommends \
    # general purpose utils
    git-lfs \
    htop \
    iputils-ping \
    # R pre-requisites
    fonts-dejavu \
    gcc \
    gfortran \
    r-cran-rodbc \
    unixodbc \
    unixodbc-dev && \
    apt-get clean && rm -rf /var/lib/apt/lists/*

USER ${NB_UID}

# R packages including IRKernel which gets installed globally.
# r-e1071: dependency of the caret R package
RUN mamba install --yes \
    # for VS code
    'r-languageserver' \
    'radian' \
    'r-httpgd' \
    # from Jupyter docker-stacks
    'r-base' \
    'r-caret' \
    'r-crayon' \
    'r-devtools' \
    'r-e1071' \
    'r-forecast' \
    'r-hexbin' \
    'r-htmltools' \
    'r-htmlwidgets' \
    'r-irkernel' \
    'r-nycflights13' \
    'r-randomforest' \
    'r-rcurl' \
    'r-rmarkdown' \
    'r-rodbc' \
    'r-rsqlite' \
    'r-shiny' \
    'r-tidymodels' \
    'r-tidyverse' \
    'unixodbc' && \
    mamba clean --all -f -y && \
    fix-permissions "${CONDA_DIR}" && \
    fix-permissions "/home/${NB_USER}"

USER root

# install code-server and extensions
ENV CODE_VERSION=4.96.2
RUN wget --no-hsts -q https://github.com/coder/code-server/releases/download/v$CODE_VERSION/code-server_${CODE_VERSION}_amd64.deb && \
    dpkg -i code-server_${CODE_VERSION}_amd64.deb && \
    rm -f code-server_${CODE_VERSION}_amd64.deb && \
    code-server --force \
    --install-extension ms-python.python \
    --install-extension ms-toolsai.jupyter \
    --install-extension REditorSupport.r \
    --install-extension RDebugger.r-debugger \
    --install-extension eamodio.gitlens \
    --install-extension gitlab.gitlab-workflow && \
    mkdir -p /usr/local/bin/start-notebook.d && \
    chown -R ${NB_USER} "/home/${NB_USER}/.config" "/home/${NB_USER}/.local" && \
    fix-permissions "/home/${NB_USER}"

# install VS Code CLI
RUN wget --no-hsts -q -O vscode_cli.tar.gz 'https://code.visualstudio.com/sha/download?build=stable&os=cli-alpine-x64' && \
    tar -xf vscode_cli.tar.gz --directory /usr/local/bin && \
    rm vscode_cli.tar.gz && \
    chown ${NB_USER} /usr/local/bin/code && \
    fix-permissions /usr/local/bin/code

# install some packages
USER ${NB_UID}
RUN mamba install --yes \
    # system monitor
    'bpytop' \
    # umap + hdbscan
    'umap-learn' \
    'hdbscan' \
    # gradio
    'gradio' \
    # optuna + plotly
    'optuna' \
    'plotly' \
    # optional dependencies for pandas for read_html and to support Parquet files
    'lxml' \
    'pyarrow' \
    # geopandas
    'geopandas' \
    'pysal' \
    'contextily' \
    # networkx + pyvis + netgraph
    'networkx' \
    'pyvis' \
    'netgraph' \
    # dependencies for gymnasium, install before gymnasium!
    'swig' \
    'moviepy' \
    # dependencies for jupyter-vscode-proxy (?)
    'rfc3339-validator' \
    'rfc3986-validator' \
    'uri-template' \
    'fqdn' \
    'webcolors' \
    'isoduration' \
    'jsonpointer' \
    # provide a way for lecturers to share code
    'nbgitpuller' \
    # integration of VS Code in JupyterLab
    'jupyter-server-proxy' \
    'jupyter-vscode-proxy' \
    # some improvements of jupyterlab
    'jupyterlab_execute_time' \
    'jupyter-archive' \
    'jupyterlab-git' \
    'jupyter-resource-usage' \
    # install opencv headless version
    'py-opencv=*=headless*' && \
    printf '%s\n' \
           "" \
           "# track CPU usage, prevent known bug with prometheus, set default limits if not set by MEM_LIMIT and CPU_LIMIT" \
           "import os" \
           "" \
           "c.ResourceUseDisplay.track_cpu_percent = True" \
           "c.ResourceUseDisplay.enable_prometheus_metrics = False" \
           "c.ResourceUseDisplay.mem_limit = int(os.getenv('MEM_LIMIT', os.sysconf('SC_PAGE_SIZE') * os.sysconf('SC_PHYS_PAGES')))" \
           "c.ResourceUseDisplay.cpu_limit = float(os.getenv('CPU_LIMIT', os.cpu_count()))" \
           >> /etc/jupyter/jupyter_notebook_config.py && \
    mamba clean --all -f -y && \
    fix-permissions "${CONDA_DIR}" && \
    fix-permissions "/home/${NB_USER}"

# default settings and extensions in /etc/skel
USER root
# activate extensions by default
COPY plugin.jupyterlab-settings "/home/${NB_USER}/.jupyter/lab/user-settings/@jupyterlab/extensionmanager-extension/"
COPY plugin.jupyterlab-settings "/home/${NB_USER}/.jupyter/lab/user-settings/@jupyter-server/resource-usage/"
RUN chown -R ${NB_USER} "/home/${NB_USER}/.jupyter" && \
    # history search with Page Up/Down
    sed -i "s/^# \(.*history-search.*\)/\1/" /etc/inputrc && \
    # VS Code Python settings
    mkdir -p "/home/${NB_USER}/.local/share/code-server/User" && \
    echo -e '{\n  "python.defaultInterpreterPath": "/opt/conda/bin/python",\n  "jupyter.sendSelectionToInteractiveWindow": true\n}' > /home/${NB_USER}/.local/share/code-server/User/settings.json && \
    mkdir -p "/home/${NB_USER}/.local/share/code-server/Machine" && \
    cp "/home/${NB_USER}/.local/share/code-server/User/settings.json" "/home/${NB_USER}/.local/share/code-server/Machine/settings.json" && \
    mkdir -p /etc/skel/.local/share/ && \
    cp -r "/home/${NB_USER}/.local/share/code-server" /etc/skel/.local/share/ && \
    # matplotlib cache
    mkdir -p /etc/skel/.cache && \
    cp -r "/home/${NB_USER}/.cache/matplotlib" /etc/skel/.cache/ && \
    # stuff
    cp -r "/home/${NB_USER}/.conda" "/home/${NB_USER}/.config" "/home/${NB_USER}/.jupyter" /etc/skel/ && \
    # VS Code extension "gitlab-workflow", default gitlab server: gitlab.cvh-server.de
    printf '%s\n' \
           '# Set default gitlab server to gitlab.cvh-server.de' \
           'relpath=".local/share/code-server/extensions/gitlab.gitlab-workflow-*/extension.js"' \
           'for abspath in /home/${NB_USER}/${relpath} /etc/skel/${relpath}; do' \
           '  if [[ -e "${abspath}" ]]; then' \
           '    sed -i "s_=\"https://gitlab.com\"_=\"https://gitlab.cvh-server.de\"_g" "${abspath}"' \
           '  fi' \
           'done' \
           >> /usr/local/bin/start-notebook.d/fix-gitlab-server.sh && \
    # source mamba.sh in bash using /etc/profile.d/conda.sh
    mamba init --system && \
    chown -R ${NB_USER} "/home/${NB_USER}/.local" && \
    fix-permissions "/home/${NB_USER}" && \
    fix-permissions "/etc/skel"
# remember to copy back in post start hook


# override maintainer label from Jupyter docker stacks
LABEL maintainer="Christof Kaufmann <christof.kaufmann@hs-bochum.de>"
# OCI annotations, see https://github.com/opencontainers/image-spec/blob/main/annotations.md
ARG LABEL_CREATED
ARG LABEL_REVISION=test-build
LABEL org.opencontainers.image.created=$LABEL_CREATED
LABEL org.opencontainers.image.authors="Christof Kaufmann <christof.kaufmann@hs-bochum.de>"
LABEL org.opencontainers.image.source="https://gitlab.cvh-server.de/ckaufmann/gpu-cluster-images"
LABEL org.opencontainers.image.revision=$LABEL_REVISION
LABEL org.opencontainers.image.vendor="UAS Bochum"
LABEL org.opencontainers.image.licenses=BSD-3-Clause
LABEL org.opencontainers.image.title="Jupyter Notebook Keras 3 CPU image"
LABEL org.opencontainers.image.description="This image includes TensorFlow and Keras 3 without GPU support, VS Code CLI, code-server and nbgitpuller."
LABEL org.opencontainers.image.base.name=quay.io/jupyter/tensorflow-notebook:latest

# switch back to jovyan to avoid accidental container runs as root
USER ${NB_UID}
WORKDIR "${HOME}"


###################################################################
######################## Testing the image ########################
###################################################################
FROM build AS test

# replace home directory with skel, which is closer to the kubernetes environment
USER root
RUN cd / && \
    rm -r "/home/${NB_USER}" && \
    cp -r /etc/skel "/home/${NB_USER}" && \
    fix-permissions "/home/${NB_USER}"
USER ${NB_UID}

# enable logging for all Jupyter applications
RUN printf '%s\n' \
    "" \
    "# Filter out user connection hint message, which is a CRITICAL logger message" \
    "import logging" \
    "class UserHintFilter(logging.Filter):" \
    "    def filter(self, record):" \
    "        return 'To access the server' not in record.getMessage()" \
    "" \
    "c.Application.logging_config = {" \
    "    'filters': {" \
    "        'user_hint': {" \
    "            '()': UserHintFilter," \
    "        }," \
    "    }," \
    "    'formatters': {" \
    "        'file': {" \
    "            'format': '%(asctime)s %(levelname)-8s %(name)-15s %(message)s'," \
    "        }," \
    "    }," \
    "    'handlers': {" \
    "        'file': {" \
    "            'class': 'logging.FileHandler'," \
    "            'filters': ['user_hint']," \
    "            'formatter': 'file'," \
    "            'level': 'INFO'," \
    "            'filename': '/home/jovyan/jupyter.log'," \
    "        }," \
    "    }," \
    "    'loggers': {" \
    "        'Application': {" \
    "            'level': 'DEBUG'," \
    "            'handlers': ['console', 'file']," \
    "        }," \
    "    }," \
    "    'loggers': {" \
    "        'JupyterApp': {" \
    "            'level': 'DEBUG'," \
    "            'handlers': ['console', 'file']," \
    "        }," \
    "    }," \
    "    'loggers': {" \
    "        'ExtensionApp': {" \
    "            'level': 'DEBUG'," \
    "            'handlers': ['console', 'file']," \
    "        }," \
    "    }," \
    "    'loggers': {" \
    "        'LabServerApp': {" \
    "            'level': 'DEBUG'," \
    "            'handlers': ['console', 'file']," \
    "        }," \
    "    }," \
    "    'loggers': {" \
    "        'LabApp': {" \
    "            'level': 'DEBUG'," \
    "            'handlers': ['console', 'file']," \
    "        }," \
    "    }," \
    "    'loggers': {" \
    "        'NotebookApp': {" \
    "            'level': 'DEBUG'," \
    "            'handlers': ['console', 'file']," \
    "        }," \
    "    }," \
    "    'loggers': {" \
    "        'ServerApp': {" \
    "            'level': 'DEBUG'," \
    "            'handlers': ['console', 'file']," \
    "        }," \
    "    }," \
    "}" \
    >> /etc/jupyter/jupyter_notebook_config.py


# collect lab logs for 4 sec
RUN start-notebook.sh & sleep 4 && kill -INT %1 && sleep 1

# check log file:
    # not existing means some error prevents logging → bad
RUN [[ -f jupyter.log ]] \
    || ( echo "Log file jupyter.log does not exist!" && false ) \
    # existing, contains error → bad, print log file
    && ! grep -qP '(Traceback|ERROR|CRITICAL)' jupyter.log \
    || ( cat jupyter.log && false )


# add some environment variables and collect lab logs again for 4 sec
RUN mv jupyter.log jupyter1.log
ENV MEM_LIMIT=1000000000 \
    CPU_LIMIT=16.0
RUN start-notebook.sh & sleep 4 && kill -INT %1 && sleep 1

# check log file:
    # not existing means some error prevents logging → bad
RUN [[ -f jupyter.log ]] \
    || ( echo "Log file jupyter.log does not exist!" && false ) \
    # existing, contains error → bad, print log file
    && ! grep -qP '(Traceback|ERROR|CRITICAL)' jupyter.log \
    || ( cat jupyter.log && false )