feat: overhaul Dockerfile for improved developer workflow

WIP
kdmccormick · Oct 3, 2022 · 771c998 · 771c998
1 parent 45316bf
commit 771c998
Show file tree

Hide file tree

Showing 6 changed files with 241 additions and 46 deletions.
diff --git a/tutor/templates/build/openedx/Dockerfile b/tutor/templates/build/openedx/Dockerfile
@@ -1,27 +1,58 @@
+#############################################################################
 ###### Minimal image with base system requirements for most stages
+
 FROM docker.io/ubuntu:20.04 as minimal
 LABEL maintainer="Overhang.io <contact@overhang.io>"
 
 ENV DEBIAN_FRONTEND=noninteractive
+# TODO: Safe/effective to rm var/lib/apt/lists in all these places?
 RUN apt update && \
-    apt install -y build-essential curl git language-pack-en
+    apt install -y \
+	  build-essential \
+	  curl \
+	  language-pack-en \
+	  git \
+	  && \
+	rm -rf /var/lib/apt/lists/*
 ENV LC_ALL en_US.UTF-8
+
 {{ patch("openedx-dockerfile-minimal") }}
 
-###### Install python with pyenv in /opt/pyenv and create virtualenv in /openedx/venv
+#############################################################################
+###### Python with pyenv in /opt/pyenv and create virtualenv in /openedx/venv
+
 FROM minimal as python
+
 # https://github.com/pyenv/pyenv/wiki/Common-build-problems#prerequisites
 RUN apt update && \
-    apt install -y libssl-dev zlib1g-dev libbz2-dev \
-    libreadline-dev libsqlite3-dev wget curl llvm libncurses5-dev libncursesw5-dev \
-    xz-utils tk-dev libffi-dev liblzma-dev python-openssl git
+    apt install -y \
+	  curl \
+	  git \
+	  libbz2-dev \
+	  libffi-dev \
+	  liblzma-dev \
+	  libncurses5-dev \
+	  libncursesw5-dev \
+      libreadline-dev \
+	  libsqlite3-dev \
+	  libssl-dev \
+	  llvm \
+	  python-openssl \
+	  tk-dev \
+	  wget \
+      xz-utils \
+	  zlib1g-dev \
+	  && \
+	rm -rf /var/lib/apt/lists/*
 ARG PYTHON_VERSION=3.8.12
 ENV PYENV_ROOT /opt/pyenv
 RUN git clone https://github.com/pyenv/pyenv $PYENV_ROOT --branch v2.2.2 --depth 1
 RUN $PYENV_ROOT/bin/pyenv install $PYTHON_VERSION
 RUN $PYENV_ROOT/versions/$PYTHON_VERSION/bin/python -m venv /openedx/venv
 
-###### Install Dockerize to wait for mysql DB availability
+#############################################################################
+###### Dockerize stage to wait for mysql DB availability
+
 FROM minimal as dockerize
 # https://github.com/powerman/dockerize/releases
 ARG DOCKERIZE_VERSION=v0.16.0
@@ -30,10 +61,13 @@ RUN dockerize_url="https://github.com/powerman/dockerize/releases/download/$DOCK
     && curl --fail --location --output /usr/local/bin/dockerize $dockerize_url \
     && chmod a+x /usr/local/bin/dockerize
 
-###### Checkout edx-platform code
+#############################################################################
+###### Clone edx-platform in an intermediate stage
+
 FROM minimal as code
 ARG EDX_PLATFORM_REPOSITORY={{ EDX_PLATFORM_REPOSITORY }}
 ARG EDX_PLATFORM_VERSION={{ EDX_PLATFORM_VERSION }}
+RUN echo BREAK CACHE 1
 RUN mkdir -p /openedx/edx-platform && \
     git clone $EDX_PLATFORM_REPOSITORY --branch $EDX_PLATFORM_VERSION --depth 1 /openedx/edx-platform
 WORKDIR /openedx/edx-platform
@@ -52,7 +86,9 @@ RUN git config --global user.email "tutor@overhang.io" \
 {# Example: RUN curl -fsSL https://github.com/openedx/edx-platform/commit/<GITSHA1> | git am #}
 {{ patch("openedx-dockerfile-post-git-checkout") }}
 
+#############################################################################
 ###### Download extra locales to /openedx/locale/contrib/locale
+
 FROM minimal as locales
 ARG OPENEDX_I18N_VERSION={{ OPENEDX_COMMON_VERSION }}
 RUN cd /tmp \
@@ -62,38 +98,42 @@ RUN cd /tmp \
     && mv openedx-i18n-*/edx-platform/locale /openedx/locale/contrib \
     && rm -rf openedx-i18n*
 
+#############################################################################
 ###### Install python requirements in virtualenv
+
 FROM python as python-requirements
 ENV PATH /openedx/venv/bin:${PATH}
 ENV VIRTUAL_ENV /openedx/venv/
 
-RUN apt update && apt install -y software-properties-common libmysqlclient-dev libxmlsec1-dev libgeos-dev
-
-# Note that this means that we need to reinstall all requirements whenever there is a
-# change in edx-platform, which sucks. Yet, we must do it, because edx-platform installs some
-# Python projects from within the edx-platform repo itself. This is being fixed upstream.
-# TODO: https://github.com/overhangio/2u-tutor-adoption/issues/86
-COPY --from=code /openedx/edx-platform /openedx/edx-platform
-WORKDIR /openedx/edx-platform
+# TODO: Why are these here instead of an earlier stage?
+RUN apt update && \
+    apt install -y \
+	  software-properties-common \
+	  libmysqlclient-dev \
+	  libxmlsec1-dev \
+	  libgeos-dev \
+      && \
+    rm -rf /var/lib/apt/lists/*
 
 # Install the right version of pip/setuptools
 # https://pypi.org/project/setuptools/
 # https://pypi.org/project/pip/
 # https://pypi.org/project/wheel/
 RUN pip install setuptools==62.1.0 pip==22.0.4 wheel==0.37.1
 
-# Install base requirements
-RUN pip install -r ./requirements/edx/base.txt
-RUN pip install -e .
-
-# Install django-redis for using redis as a django cache
+# Iedxnstall django-redis for using redis as a django cache
 # https://pypi.org/project/django-redis/
 RUN pip install django-redis==5.2.0
 
 # Install uwsgi
 # https://pypi.org/project/uWSGI/
 RUN pip install uwsgi==2.0.20
 
+# Install base requirements
+COPY --from=code /openedx/edx-platform/requirements /openedx/edx-platform/requirements
+WORKDIR /openedx/edx-platform
+RUN pip install -r ./requirements/edx/base.txt
+
 {{ patch("openedx-dockerfile-post-python-requirements") }}
 
 # Install private requirements: this is useful for installing custom xblocks.
@@ -105,7 +145,9 @@ RUN cd /openedx/requirements/ \
 {% for extra_requirements in OPENEDX_EXTRA_PIP_REQUIREMENTS %}RUN pip install '{{ extra_requirements }}'
 {% endfor %}
 
+#############################################################################
 ###### Install nodejs with nodeenv in /openedx/nodeenv
+
 FROM python as nodejs-requirements
 ENV PATH /openedx/nodeenv/bin:/openedx/venv/bin:${PATH}
 
@@ -120,36 +162,66 @@ COPY --from=code /openedx/edx-platform/package-lock.json /openedx/edx-platform/p
 WORKDIR /openedx/edx-platform
 RUN npm install --verbose --registry=$NPM_REGISTRY
 
+#############################################################################
 ###### Production image with system and python requirements
+
 FROM minimal as production
 
 # Install system requirements
 RUN apt update && \
-    apt install -y gettext gfortran graphviz graphviz-dev libffi-dev libfreetype6-dev libgeos-dev libjpeg8-dev liblapack-dev libmysqlclient-dev libpng-dev libsqlite3-dev libxmlsec1-dev lynx ntp pkg-config rdfind && \
+    apt install -y \
+	  gettext \
+	  gfortran \
+	  graphviz \
+	  graphviz-dev \
+	  libffi-dev \
+	  libfreetype6-dev \
+	  libgeos-dev \
+	  libjpeg8-dev \
+	  liblapack-dev \
+	  libmysqlclient-dev \
+	  libpng-dev \
+	  libsqlite3-dev \
+	  libxmlsec1-dev \
+	  lynx \
+	  ntp \
+	  pkg-config \
+	  rdfind \
+	  && \
     rm -rf /var/lib/apt/lists/*
 
-# From then on, run as unprivileged "app" user
+# From here on, run as unprivileged "app" user
 # Note that this must always be different from root (APP_USER_ID=0)
 ARG APP_USER_ID=1000
 RUN if [ "$APP_USER_ID" = 0 ]; then echo "app user may not be root" && false; fi
 RUN useradd --home-dir /openedx --create-home --shell /bin/bash --uid ${APP_USER_ID} app
 USER ${APP_USER_ID}
 
-COPY --from=dockerize /usr/local/bin/dockerize /usr/local/bin/dockerize
+# Copy in everything we need from the intermediate build stages
+COPY                 --from=dockerize /usr/local/bin/dockerize /usr/local/bin/dockerize
 COPY --chown=app:app --from=code /openedx/edx-platform /openedx/edx-platform
 COPY --chown=app:app --from=locales /openedx/locale /openedx/locale
 COPY --chown=app:app --from=python /opt/pyenv /opt/pyenv
 COPY --chown=app:app --from=python-requirements /openedx/venv /openedx/venv
 COPY --chown=app:app --from=python-requirements /openedx/requirements /openedx/requirements
 COPY --chown=app:app --from=nodejs-requirements /openedx/nodeenv /openedx/nodeenv
-COPY --chown=app:app --from=nodejs-requirements /openedx/edx-platform/node_modules /openedx/edx-platform/node_modules
+COPY --chown=app:app --from=nodejs-requirements /openedx/edx-platform/node_modules /openedx/node_modules
+RUN mv /openedx/node_modules/.bin /openedx/node_modules/bin
 
-ENV PATH /openedx/venv/bin:./node_modules/.bin:/openedx/nodeenv/bin:${PATH}
+# Enable venv & nodeenv
+ENV PATH /openedx/venv/bin:/openedx/node_modules/bin:/openedx/nodeenv/bin:${PATH}
 ENV VIRTUAL_ENV /openedx/venv/
 WORKDIR /openedx/edx-platform
 
-# Re-install local requirements, otherwise egg-info folders are missing
-RUN pip install -r requirements/edx/local.in
+# Copy scripts and put them on the path.
+COPY --chown=app:app ./bin /openedx/bin
+RUN chmod a+x /openedx/bin/*
+ENV PATH /openedx/bin:${PATH}
+
+# Generate Open-edX.egg_info by installing edx-platform itself.
+# Ensures entrypoints & console scripts from setup.py are registered.
+# TODO: Is it worth fixing up setup.py so that we can just run `pip install .` ?
+RUN pip install -e .
 
 # Create folder that will store lms/cms.env.yml files, as well as
 # the tutor-specific settings files.
@@ -173,11 +245,6 @@ RUN cd /openedx/locale/user && \
 RUN ./manage.py lms --settings=tutor.i18n compilejsi18n
 RUN ./manage.py cms --settings=tutor.i18n compilejsi18n
 
-# Copy scripts
-COPY --chown=app:app ./bin /openedx/bin
-RUN chmod a+x /openedx/bin/*
-ENV PATH /openedx/bin:${PATH}
-
 {{ patch("openedx-dockerfile-pre-assets") }}
 
 # Collect production assets. By default, only assets from the default theme
@@ -189,13 +256,19 @@ ENV PATH /openedx/bin:${PATH}
 # /openedx/staticfiles.
 ENV NO_PYTHON_UNINSTALL 1
 ENV NO_PREREQ_INSTALL 1
+
+# TODO: This is necessary for _compile_sass currently but should be removed
+RUN ln -s /openedx/node_modules
+RUN cd node_modules && ln -s bin .bin
+
 # We need to rely on a separate openedx-assets command to accelerate asset processing.
 # For instance, we don't want to run all steps of asset collection every time the theme
 # is modified.
+# TODO: Can we remove the pavelib dependency?
 RUN openedx-assets xmodule \
-    && openedx-assets npm \
-    && openedx-assets webpack --env=prod \
-    && openedx-assets common
+   && openedx-assets npm \
+   && openedx-assets webpack --env=prod \
+   && openedx-assets common
 COPY --chown=app:app ./themes/ /openedx/themes/
 RUN openedx-assets themes \
     && openedx-assets collect --settings=tutor.assets \
@@ -213,37 +286,55 @@ ENV DJANGO_SETTINGS_MODULE lms.envs.tutor.production
 
 EXPOSE 8000
 
+#############################################################################
 ###### Intermediate image with dev/test dependencies
+
 FROM production as development
 
 # Install useful system requirements (as root)
 USER root
 RUN apt update && \
-    apt install -y vim iputils-ping dnsutils telnet \
-    && rm -rf /var/lib/apt/lists/*
+    apt install -y \
+	  dnsutils \
+	  iputils-ping \
+	  telnet \
+	  vim \
+	  && \
+    rm -rf /var/lib/apt/lists/*
 USER app
 
-# Install dev python requirements
-RUN pip install -r requirements/edx/development.txt
-RUN pip install ipdb==0.13.4 ipython==7.27.0
-
 # Add ipdb as default PYTHONBREAKPOINT
+RUN pip install ipdb==0.13.4 ipython==7.27.0
 ENV PYTHONBREAKPOINT=ipdb.set_trace
 
+# Override any edx-platform files, as supplied by build context.
+# Primarily, this allows Tutor to override /openedx/edx-platform/requirements
+# when edx-platform is mounted in order to force a requirements re-install
+# and static asset re-compilation below.
+COPY ./dev/edx-platform-overrides /openedx/edx-platform
+
+# Install dev requirements
+RUN pip install -r requirements/edx/development.txt
+RUN npm install --dev
+
 # Recompile static assets: in development mode all static assets are stored in edx-platform,
 # and the location of these files is stored in webpack-stats.json. If we don't recompile
 # static assets, then production assets will be served instead.
+# TODO: OK to use scripts/update-assets-dev.sh?
 RUN rm -r /openedx/staticfiles && \
     mkdir /openedx/staticfiles && \
     openedx-assets webpack --env=dev
+#	scripts/update-assets-dev.sh
 
 {{ patch("openedx-dev-dockerfile-post-python-requirements") }}
 
 # Default django settings
 ENV DJANGO_SETTINGS_MODULE lms.envs.tutor.development
 
-CMD ./manage.py $SERVICE_VARIANT runserver 0.0.0.0:8000
+COPY ./dev/mounted-requirements.txt /openedx/mounted-requirements.txt
+CMD pip install -r /openedx/mounted-requirements.txt  && ./manage.py $SERVICE_VARIANT runserver 0.0.0.0:8000
 
+#############################################################################
 ###### Final image with production cmd
 FROM production as final
 

diff --git a/tutor/templates/build/openedx/bin/npm b/tutor/templates/build/openedx/bin/npm
@@ -0,0 +1,14 @@
+#!/bin/sh
+#
+# Wrapper around 'npm' for openedx image.
+# Ensures that npm always operates in the 'global' /openedx/node_modules directory,
+# not in the 'local' /openedx/edx-platform/node_modules directory.
+#
+# Rationale: We want node_modules to exist outside of the edx-platform repository.
+# That way, when a developer mounts a fork of edx-platform, they don't need to
+# re-run `npm install` themselves, because the pre-built node_modules folder will
+# still be available on the image.
+
+set -ue            # Fail loudly.
+set -x             # Print next command.
+/openedx/nodeenv/bin/npm --global --prefix=/openedx/node_modules "$@"