Merge branch 'main' into asalikhov/ubuntu_jammy

This commit is contained in:
Ayaz Salikhov
2022-07-28 10:25:37 +04:00
13 changed files with 44 additions and 39 deletions

View File

@@ -10,7 +10,7 @@ inputs:
runs:
using: composite
steps:
# actions/setup-python doesn't suport Linux aarch64 runners
# actions/setup-python doesn't support Linux aarch64 runners
# See: https://github.com/actions/setup-python/issues/108
# python3 is manually preinstalled in the aarch64 VM self-hosted runner
- name: Set Up Python 🐍

View File

@@ -11,7 +11,6 @@ on:
- "docs/**"
- "README.md"
- ".readthedocs.yaml"
- "requirements-docs.txt"
push:
branches:
- main
@@ -21,7 +20,6 @@ on:
- "docs/**"
- "README.md"
- ".readthedocs.yaml"
- "requirements-docs.txt"
workflow_dispatch:
jobs:
@@ -44,7 +42,7 @@ jobs:
- name: Install Doc Dependencies 📦
run: |
pip install --upgrade pip
pip install --upgrade -r requirements-docs.txt
pip install --upgrade -r docs/requirements.txt
- name: Build Documentation 📖
run: make docs

View File

@@ -14,7 +14,7 @@
repos:
# Autoupdate: Python code
- repo: https://github.com/asottile/pyupgrade
rev: v2.34.0
rev: v2.37.2
hooks:
- id: pyupgrade
args: [--py39-plus]
@@ -35,7 +35,7 @@ repos:
# Check python code static typing
- repo: https://github.com/pre-commit/mirrors-mypy
rev: v0.961
rev: v0.971
hooks:
- id: mypy
args: [--config, ./mypy.ini]
@@ -74,7 +74,7 @@ repos:
# Lint: YAML
- repo: https://github.com/adrienverge/yamllint.git
rev: v1.26.3
rev: v1.27.1
hooks:
- id: yamllint
args: ["-d {extends: relaxed, rules: {line-length: disable}}", "-s"]
@@ -102,21 +102,21 @@ repos:
# Lint: Markdown
- repo: https://github.com/igorshubovych/markdownlint-cli
rev: v0.31.1
rev: v0.32.1
hooks:
- id: markdownlint
args: ["--fix"]
# Strip output from Jupyter notebooks
- repo: https://github.com/kynan/nbstripout
rev: 0.5.0
rev: 0.6.0
hooks:
- id: nbstripout
# nbQA provides tools from the Python ecosystem like
# pyupgrade, isort, black, and flake8, adjusted for notebooks.
- repo: https://github.com/nbQA-dev/nbQA
rev: 1.3.1
rev: 1.4.0
hooks:
- id: nbqa-pyupgrade
args: [--py39-plus]

View File

@@ -27,4 +27,4 @@ sphinx:
# Optionally declare the Python requirements required to build your docs
python:
install:
- requirements: requirements-docs.txt
- requirements: docs/requirements.txt

View File

@@ -67,10 +67,9 @@ linkcheck-docs: ## check broken links
hook/%: WIKI_PATH?=wiki
hook/%: ## run post-build hooks for an image
python3 -m tagging.tag_image --short-image-name "$(notdir $@)" --owner "$(OWNER)" && \
python3 -m tagging.write_manifest --short-image-name "$(notdir $@)" --owner "$(OWNER)" --wiki-path "$(WIKI_PATH)"
python3 -m tagging.write_manifest --short-image-name "$(notdir $@)" --hist-line-dir /tmp/hist_lines/ --manifest-dir /tmp/manifests/ --owner "$(OWNER)"
hook-all: $(foreach I, $(ALL_IMAGES), hook/$(I)) ## run post-build hooks for all images

View File

@@ -52,7 +52,7 @@ It then starts an _ephemeral_ container running a Jupyter Server and exposes the
docker run -it --rm -p 10000:8888 -v "${PWD}":/home/jovyan/work jupyter/datascience-notebook:807999a41207
```
The use of the `-v` flag in the command mounts the current working directory on the host (`{PWD}` in the example command) as `/home/jovyan/work` in the container.
The use of the `-v` flag in the command mounts the current working directory on the host (`${PWD}` in the example command) as `/home/jovyan/work` in the container.
The server logs appear in the terminal.
Visiting `http://<hostname>:10000/?token=<token>` in a browser loads JupyterLab.

View File

@@ -63,7 +63,7 @@ html_theme = "alabaster"
# so a file named "default.css" will overwrite the builtin "default.css".
html_static_path = ["_static"]
# File above was generated using sphinx 4.3.2 with this command:
# File above was generated using sphinx 4.5.0 with this command:
# sphinx-quickstart --project "docker-stacks" --author "Project Jupyter" -v "latest" -r "latest" -l en --no-sep --no-makefile --no-batchfile
# These are custom options for this project
@@ -73,6 +73,7 @@ html_logo = "_static/jupyter-logo.svg"
html_theme_options = {
"path_to_docs": "docs",
"repository_url": "https://github.com/jupyter/docker-stacks",
"repository_branch": "main",
"use_edit_page_button": True,
"use_issues_button": True,
"use_repository_button": True,

View File

@@ -1,7 +1,7 @@
# ReadTheDocs environment contains old package versions preinstalled
# So, to ensure we have modern packages, we pin minimum versions of the packages we need
docutils>=0.17
myst-parser>=0.16.1
sphinx>=4.4.0
sphinx-book-theme>=0.3.2
docutils>=0.17.1
myst-parser>=0.18.0
sphinx>=4.5.0
sphinx-book-theme>=0.3.3
sphinx-copybutton>=0.5.0

View File

@@ -46,14 +46,13 @@ You can build a `pyspark-notebook` image (and also the downstream `all-spark-not
- `spark_version`: The Spark version to install (`3.3.0`).
- `hadoop_version`: The Hadoop version (`3.2`).
- `scala_version`: The Scala version (`2.13`).
- `scala_version`: The Scala version (`2.13`, optional).
- `spark_checksum`: The package checksum (`BFE4540...`).
- `openjdk_version`: The version of the OpenJDK (JRE headless) distribution (`17`).
- This version needs to match the version supported by the Spark distribution used above.
- See [Spark Overview](https://spark.apache.org/docs/latest/#downloading) and [Ubuntu packages](https://packages.ubuntu.com/search?keywords=openjdk).
- Starting with _Spark >= 3.2_ the distribution file contains Scala version, hence building older Spark will not work.
- Building older version requires modification to the Dockerfile or using it's older version of the Dockerfile.
- Starting with _Spark >= 3.2_ the distribution file might contain Scala version.
For example here is how to build a `pyspark-notebook` image with Spark `3.2.0`, Hadoop `3.2` and OpenJDK `11`.

View File

@@ -17,8 +17,8 @@ USER root
# (ARGS are in lower case to distinguish them from ENV)
ARG spark_version="3.3.0"
ARG hadoop_version="3"
ARG scala_version="2.13"
ARG spark_checksum="4c09dac70e22bf1d5b7b2cabc1dd92aba13237f52a5b682c67982266fc7a0f5e0f964edff9bc76adbd8cb444eb1a00fdc59516147f99e4e2ce068420ff4881f0"
ARG scala_version
ARG spark_checksum="1e8234d0c1d2ab4462d6b0dfe5b54f2851dcd883378e0ed756140e10adfb5be4123961b521140f580e364c239872ea5a9f813a20b73c69cb6d4e95da2575c29c"
ARG openjdk_version="17"
ENV APACHE_SPARK_VERSION="${spark_version}" \
@@ -32,22 +32,29 @@ RUN apt-get update --yes && \
# Spark installation
WORKDIR /tmp
RUN wget -q "https://archive.apache.org/dist/spark/spark-${APACHE_SPARK_VERSION}/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}-scala${scala_version}.tgz" && \
echo "${spark_checksum} *spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}-scala${scala_version}.tgz" | sha512sum -c - && \
tar xzf "spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}-scala${scala_version}.tgz" -C /usr/local --owner root --group root --no-same-owner && \
rm "spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}-scala${scala_version}.tgz"
WORKDIR /usr/local
RUN if [ -z "${scala_version}" ]; then \
wget -qO "spark.tgz" "https://archive.apache.org/dist/spark/spark-${APACHE_SPARK_VERSION}/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz"; \
else \
wget -qO "spark.tgz" "https://archive.apache.org/dist/spark/spark-${APACHE_SPARK_VERSION}/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}-scala${scala_version}.tgz"; \
fi && \
echo "${spark_checksum} *spark.tgz" | sha512sum -c - && \
tar xzf "spark.tgz" -C /usr/local --owner root --group root --no-same-owner && \
rm "spark.tgz"
# Configure Spark
ENV SPARK_HOME=/usr/local/spark
ENV SPARK_OPTS="--driver-java-options=-Xms1024M --driver-java-options=-Xmx4096M --driver-java-options=-Dlog4j.logLevel=info" \
PATH="${PATH}:${SPARK_HOME}/bin"
RUN ln -s "spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}-scala${scala_version}" spark && \
# Add a link in the before_notebook hook in order to source automatically PYTHONPATH
mkdir -p /usr/local/bin/before-notebook.d && \
ln -s "${SPARK_HOME}/sbin/spark-config.sh" /usr/local/bin/before-notebook.d/spark-config.sh
RUN if [ -z "${scala_version}" ]; then \
ln -s "spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}" "${SPARK_HOME}"; \
else \
ln -s "spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}-scala${scala_version}" "${SPARK_HOME}"; \
fi && \
# Add a link in the before_notebook hook in order to source automatically PYTHONPATH && \
mkdir -p /usr/local/bin/before-notebook.d && \
ln -s "${SPARK_HOME}/sbin/spark-config.sh" /usr/local/bin/before-notebook.d/spark-config.sh
# Configure IPython system-wide
COPY ipython_kernel_config.py "/etc/ipython/"

View File

@@ -46,7 +46,7 @@ def test_unsigned_ssl(
# properly while the server is booting up. An SSL handshake error seems to
# abort the retry logic. Forcing a long sleep for the moment until I have
# time to dig more.
time.sleep(5)
time.sleep(1)
resp = http_client.get(f"https://localhost:{host_port}", verify=False)
resp.raise_for_status()
assert "login_submit" in resp.text
@@ -91,9 +91,9 @@ def test_nb_user_change(container: TrackedContainer) -> None:
command=["start.sh", "bash", "-c", "sleep infinity"],
)
# Give the chown time to complete. Use sleep, not wait, because the
# container sleeps forever.
time.sleep(10)
# Give the chown time to complete.
# Use sleep, not wait, because the container sleeps forever.
time.sleep(1)
LOGGER.info(f"Checking if the user is changed to {nb_user} by the start script ...")
output = running_container.logs().decode("utf-8")
assert "ERROR" not in output

View File

@@ -38,7 +38,8 @@ Example:
"""
import logging
from typing import Callable, Iterable
from collections.abc import Iterable
from typing import Callable
import pytest # type: ignore

View File

@@ -50,7 +50,7 @@ def test_start_notebook(
ports={"8888/tcp": host_port},
)
# sleeping some time to let the server start
time.sleep(3)
time.sleep(1)
logs = running_container.logs().decode("utf-8")
LOGGER.debug(logs)
# checking that the expected command is launched