From 9eeaf6ee974d3593fa2afafb06a2e9ec2a62a4db Mon Sep 17 00:00:00 2001 From: Michael Kamprath Date: Wed, 5 Oct 2022 20:45:25 +0000 Subject: [PATCH] updated to debian 10 and java 11 --- spark-qfs-swarm/qfs-master/Dockerfile | 6 ++++-- spark-qfs-swarm/qfs-master/start-qfs-master.sh | 2 +- spark-qfs-swarm/worker-node/Dockerfile | 8 ++++---- .../worker-node/spark-conf/spark-defaults.conf | 7 ++++--- 4 files changed, 13 insertions(+), 10 deletions(-) diff --git a/spark-qfs-swarm/qfs-master/Dockerfile b/spark-qfs-swarm/qfs-master/Dockerfile index e6939c8..fa1f69a 100644 --- a/spark-qfs-swarm/qfs-master/Dockerfile +++ b/spark-qfs-swarm/qfs-master/Dockerfile @@ -9,7 +9,7 @@ FROM worker-node:latest USER root RUN apt-get update \ - && apt-get install -y wget vim openssh-client \ + && apt-get install -y wget vim openssh-client python2.7-minimal \ && apt-get clean \ && rm -rf /var/lib/apt/lists/* @@ -19,8 +19,10 @@ COPY start-qfs-master.sh / USER spark # create some useful bash aliases for when at bash shell prompt of this image +# && echo 'alias qfs="qfs -fs qfs://qfs-master:20000 -D fs.trash.minPathDepth=2 -D fs.createParams=2"' >> ~/.bash_aliases \ + RUN echo 'export PATH=$PATH:$QFS_HOME/bin/:$QFS_HOME/bin/tools/' >> ~/.bash_aliases \ - && echo 'alias qfs="qfs -fs qfs://qfs-master:20000 -D fs.trash.minPathDepth=2 -D fs.createParams=2"' >> ~/.bash_aliases \ + && echo 'alias qfs="qfs -fs qfs://qfs-master:20000 -D fs.trash.minPathDepth=2"' >> ~/.bash_aliases \ && echo 'alias cptoqfs="cptoqfs -s qfs-master -p 20000"' >> ~/.bash_aliases \ && echo 'alias cpfromqfs="cpfromqfs -s qfs-master -p 20000"' >> ~/.bash_aliases \ && echo 'alias qfsshell="qfsshell -s qfs-master -p 20000"' >> ~/.bash_aliases \ diff --git a/spark-qfs-swarm/qfs-master/start-qfs-master.sh b/spark-qfs-swarm/qfs-master/start-qfs-master.sh index 15ce05f..010ef79 100755 --- a/spark-qfs-swarm/qfs-master/start-qfs-master.sh +++ b/spark-qfs-swarm/qfs-master/start-qfs-master.sh @@ -2,7 +2,7 @@ $QFS_HOME/bin/metaserver $QFS_HOME/conf/Metaserver.prp &> $QFS_LOGS_DIR/metaserver.log & -python2 $QFS_HOME/webui/qfsstatus.py $QFS_HOME/conf/webUI.cfg &> $QFS_LOGS_DIR/webui.log & +python2.7 $QFS_HOME/webui/qfsstatus.py $QFS_HOME/conf/webUI.cfg &> $QFS_LOGS_DIR/webui.log & $QFS_HOME/bin/tools/qfs -fs qfs://qfs-master:20000 -D fs.trash.minPathDepth=2 -runEmptier & diff --git a/spark-qfs-swarm/worker-node/Dockerfile b/spark-qfs-swarm/worker-node/Dockerfile index 77e01dc..c4a8fd5 100644 --- a/spark-qfs-swarm/worker-node/Dockerfile +++ b/spark-qfs-swarm/worker-node/Dockerfile @@ -1,4 +1,4 @@ -FROM python:3.7-stretch +FROM python:3.10-slim-buster MAINTAINER Michael Kamprath "https://github.com/michaelkamprath" # # Base image for Apache Spark standalone cluster with QFS @@ -47,7 +47,7 @@ ENV PIP_DISABLE_PIP_VERSION_CHECK 1 # JAVA & SCALA RUN apt-get update \ - && apt-get install -y openjdk-8-jre \ + && apt-get install -y openjdk-11-jre \ && apt-get remove scala-library scala \ && curl -o scala-${SCALA_VERSION}.deb https://www.scala-lang.org/files/archive/scala-${SCALA_VERSION}.deb \ && dpkg -i scala-${SCALA_VERSION}.deb \ @@ -59,11 +59,11 @@ RUN apt-get update \ RUN useradd -m -s /bin/bash spark # QFS -ARG QFS_PACKAGE=qfs-debian-9-${QFS_VERSION}-x86_64 +ARG QFS_PACKAGE=qfs-debian-10-${QFS_VERSION}-x86_64 ENV QFS_HOME /usr/qfs-${QFS_VERSION} ENV QFS_LOGS_DIR /data/qfs/logs ENV LD_LIBRARY_PATH ${QFS_HOME}/lib -ARG QFS_DOWNLOAD_URL="https://s3.amazonaws.com/quantcast-qfs/qfs-debian-9-${QFS_VERSION}-x86_64.tgz" +ARG QFS_DOWNLOAD_URL="https://s3.amazonaws.com/quantcast-qfs/qfs-debian-10-${QFS_VERSION}-x86_64.tgz" RUN echo "Downloading QFS from : ${QFS_DOWNLOAD_URL}\n" \ && curl -L --retry 3 -k \ $QFS_DOWNLOAD_URL \ diff --git a/spark-qfs-swarm/worker-node/spark-conf/spark-defaults.conf b/spark-qfs-swarm/worker-node/spark-conf/spark-defaults.conf index aacb301..36c6694 100644 --- a/spark-qfs-swarm/worker-node/spark-conf/spark-defaults.conf +++ b/spark-qfs-swarm/worker-node/spark-conf/spark-defaults.conf @@ -17,8 +17,9 @@ spark.driver.extraJavaOptions -XX:+UseG1GC # operational configurations -spark.logConf true -spark.worker.cleanup.enabled true +spark.logConf true +spark.worker.cleanup.enabled true +spark.cleaner.referenceTracking.cleanCheckpoints true # This setting is to tell the class loaders in Spark that they # only need to load the QFS access libraries once @@ -41,4 +42,4 @@ spark.hadoop.fs.qfs.metaServerPort 20000 # this spark.hadoop.fs.qfs.createParams configure causes files written by Spark to # QFS to be 2x replicated rather than using Reed-Solomon encoding. If you have at # least 9 chunkservers, remove this configuration to instead use Reed-Solomon encoding. -spark.hadoop.fs.qfs.createParams 2 +# spark.hadoop.fs.qfs.createParams 2