Change spark download url to https://dlcdn.apache.org (#1876)

Author: mathbunnyru

pyspark-notebook/Dockerfile

@@ -33,10 +33,12 @@ RUN apt-get update --yes && \
 # Spark installation
 WORKDIR /tmp
 
+# You need to use https://archive.apache.org/dist/ website if you want to download old Spark versions
+# But it seems to be slower, that's why we use recommended site for download
 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"; \
+    wget -qO "spark.tgz" "https://dlcdn.apache.org/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${scala_version}.tgz"; \
+    wget -qO "spark.tgz" "https://dlcdn.apache.org/spark/spark-${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 && \