Bump to spark 2.4.5 + minor improvements

Author: romainx

Makefile

@@ -90,7 +90,7 @@ tx-en: ## rebuild en locale strings and push to master (req: GH_TOKEN)
 
 
 test/%: ## run tests against a stack
-	@TEST_IMAGE="$(OWNER)/$(notdir $@)" pytest test
+	@TEST_IMAGE="$(OWNER)/$(notdir $@)" pytest test $(notdir $@)/test
 
 test/base-notebook: ## test supported options in the base notebook
 	@TEST_IMAGE="$(OWNER)/$(notdir $@)" pytest test base-notebook/test

base-notebook/test/test_container_options.py

@@ -78,6 +78,20 @@ def test_chown_extra(container):
     assert '/opt/conda/LICENSE.txt:1010:101' in c.logs(stdout=True).decode('utf-8')
 
 
+def test_chown_home(container):
+    """Container should change the NB_USER home directory owner and 
+    group to the current value of NB_UID and NB_GID."""
+    c = container.run(
+        tty=True,
+        user='root',
+        environment=['CHOWN_HOME=yes',
+                     'CHOWN_HOME_OPTS=-R',
+        ],
+        command=['start.sh', 'bash', '-c', 'chown root:root /home/jovyan && ls -alsh /home']
+    )
+    assert "Changing ownership of /home/jovyan to 1000:100 with options '-R'" in c.logs(stdout=True).decode('utf-8')
+
+
 def test_sudo(container):
     """Container should grant passwordless sudo to the default user."""
     c = container.run(

conftest.py

@@ -1,6 +1,7 @@
 # Copyright (c) Jupyter Development Team.
 # Distributed under the terms of the Modified BSD License.
 import os
+import logging
 
 import docker
 import pytest
@@ -10,6 +11,8 @@
 from requests.adapters import HTTPAdapter
 
 
+LOGGER = logging.getLogger(__name__)
+
 @pytest.fixture(scope='session')
 def http_client():
     """Requests session with retries and backoff."""
@@ -72,9 +75,10 @@ def run(self, **kwargs):
         all_kwargs = {}
         all_kwargs.update(self.kwargs)
         all_kwargs.update(kwargs)
+        LOGGER.info(f"Running {self.image_name} with args {all_kwargs} ...")
         self.container = self.docker_client.containers.run(self.image_name, **all_kwargs)
         return self.container
-
+    
     def remove(self):
         """Kills and removes the tracked docker container."""
         if self.container:

pyspark-notebook/Dockerfile

@@ -8,16 +8,16 @@ LABEL maintainer="Jupyter Project <[email protected]>"
 USER root
 
 # Spark dependencies
-ENV APACHE_SPARK_VERSION 2.4.4
-ENV HADOOP_VERSION 2.7
+ENV APACHE_SPARK_VERSION=2.4.5 \
+    HADOOP_VERSION=2.7
 
 RUN apt-get -y update && \
     apt-get install --no-install-recommends -y openjdk-8-jre-headless ca-certificates-java && \
     rm -rf /var/lib/apt/lists/*
 
 RUN cd /tmp && \
     wget -q http://mirrors.ukfast.co.uk/sites/ftp.apache.org/spark/spark-${APACHE_SPARK_VERSION}/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz && \
-    echo "2E3A5C853B9F28C7D4525C0ADCB0D971B73AD47D5CCE138C85335B9F53A6519540D3923CB0B5CEE41E386E49AE8A409A51AB7194BA11A254E037A848D0C4A9E5 *spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz" | sha512sum -c - && \
+    echo "2426a20c548bdfc07df288cd1d18d1da6b3189d0b78dee76fa034c52a4e02895f0ad460720c526f163ba63a17efae4764c46a1cd8f9b04c60f9937a554db85d2 *spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz" | sha512sum -c - && \
     tar xzf spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz -C /usr/local --owner root --group root --no-same-owner && \
     rm spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz
 RUN cd /usr/local && ln -s spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION} spark
@@ -36,10 +36,11 @@ RUN apt-get -y update && \
     rm -rf /var/lib/apt/lists/*
 
 # Spark and Mesos config
-ENV SPARK_HOME /usr/local/spark
-ENV PYTHONPATH $SPARK_HOME/python:$SPARK_HOME/python/lib/py4j-0.10.7-src.zip
-ENV MESOS_NATIVE_LIBRARY /usr/local/lib/libmesos.so
-ENV SPARK_OPTS --driver-java-options=-Xms1024M --driver-java-options=-Xmx4096M --driver-java-options=-Dlog4j.logLevel=info
+ENV SPARK_HOME=/usr/local/spark \
+    PYTHONPATH=$SPARK_HOME/python:$SPARK_HOME/python/lib/py4j-0.10.7-src.zip \
+    MESOS_NATIVE_LIBRARY=/usr/local/lib/libmesos.so \
+    SPARK_OPTS="--driver-java-options=-Xms1024M --driver-java-options=-Xmx4096M --driver-java-options=-Dlog4j.logLevel=info" \
+    PATH=$PATH:/usr/local/spark/bin
 
 USER $NB_UID
 

pyspark-notebook/test/test_spark.py

@@ -0,0 +1,19 @@
+# Copyright (c) Jupyter Development Team.
+# Distributed under the terms of the Modified BSD License.
+import time
+import logging
+
+import pytest
+
+LOGGER = logging.getLogger(__name__)
+
+def test_spark_shell(container):
+    """Checking if Spark (spark-shell) is running properly"""
+    c = container.run(
+        tty=True,
+        command=['start.sh', 'bash', '-c', 'spark-shell <<< "1+1"']
+    )
+    c.wait(timeout=30)
+    logs = c.logs(stdout=True).decode('utf-8')
+    LOGGER.debug(logs)
+    assert 'res0: Int = 2' in logs

pytest.ini

@@ -0,0 +1,5 @@
+[pytest]
+log_cli = 1
+log_cli_level = INFO
+log_cli_format = %(asctime)s [%(levelname)8s] %(message)s (%(filename)s:%(lineno)s)
+log_cli_date_format=%Y-%m-%d %H:%M:%S