From f26ae464c5daab57850a036b6de92c186e4cd26e Mon Sep 17 00:00:00 2001
From: Michael Kamprath <michael@kamprath.net>
Date: Sun, 26 Jul 2020 22:50:45 -0700
Subject: [PATCH] updated pyspark cluster to use python3.7

---
 spark-qfs-swarm/qfs-master/Dockerfile  | 6 ++----
 spark-qfs-swarm/worker-node/Dockerfile | 8 +++-----
 2 files changed, 5 insertions(+), 9 deletions(-)

diff --git a/spark-qfs-swarm/qfs-master/Dockerfile b/spark-qfs-swarm/qfs-master/Dockerfile
index 47abc49..e6939c8 100644
--- a/spark-qfs-swarm/qfs-master/Dockerfile
+++ b/spark-qfs-swarm/qfs-master/Dockerfile
@@ -4,14 +4,12 @@ FROM worker-node:latest
 # Expected volumes:
 #	/data/qfs - this is where QFS will store its data
 #
-# Instance should run on the swam's master node so as to persist configuration
+# Instance should run on the swarm's master node so as to persist configuration
 #
 
-# need python 2 for webserver
 USER root
 RUN apt-get update \
- && apt-get install -y python2.7 wget vim openssh-client \
- && ln -s /usr/bin/python2.7 /usr/bin/python2 \
+ && apt-get install -y wget vim openssh-client \
  && apt-get clean \
  && rm -rf /var/lib/apt/lists/*
 
diff --git a/spark-qfs-swarm/worker-node/Dockerfile b/spark-qfs-swarm/worker-node/Dockerfile
index 51f9cb0..1e03819 100644
--- a/spark-qfs-swarm/worker-node/Dockerfile
+++ b/spark-qfs-swarm/worker-node/Dockerfile
@@ -1,7 +1,7 @@
-FROM debian:stretch
+FROM python:3.7-stretch
 MAINTAINER Michael Kamprath "https://github.com/michaelkamprath"
 #
-# Base image for Apace Spak standalone cluster with QFS
+# Base image for Apache Spark standalone cluster with QFS
 #
 # Inspired by https://hub.docker.com/r/gettyimages/spark/dockerfile
 #
@@ -37,10 +37,8 @@ ENV LC_ALL en_US.UTF-8
 
 RUN apt-get update \
  && apt-get install -y less curl unzip procps \
-    python3 python3-setuptools \
     libboost-regex-dev \
- && ln -s /usr/bin/python3 /usr/bin/python \
- && easy_install3 pip py4j \
+ && pip3 install py4j \
  && apt-get clean \
  && rm -rf /var/lib/apt/lists/*