From e760b10bdaf5b892aa14d25e336d25467179c7be Mon Sep 17 00:00:00 2001 From: Gilles Dartiguelongue Date: Thu, 10 Mar 2022 17:40:11 +0100 Subject: [PATCH 1/5] Use archives URL to download specific releases of Hadoop --- base/Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/base/Dockerfile b/base/Dockerfile index dec673e2..4f8ff2aa 100644 --- a/base/Dockerfile +++ b/base/Dockerfile @@ -19,7 +19,7 @@ RUN curl -O https://dist.apache.org/repos/dist/release/hadoop/common/KEYS RUN gpg --import KEYS ENV HADOOP_VERSION 3.2.1 -ENV HADOOP_URL https://www.apache.org/dist/hadoop/common/hadoop-$HADOOP_VERSION/hadoop-$HADOOP_VERSION.tar.gz +ENV HADOOP_URL https://archive.apache.org/dist/hadoop/common/hadoop-${HADOOP_VERSION}/hadoop-${HADOOP_VERSION}.tar.gz RUN set -x \ && curl -fSL "$HADOOP_URL" -o /tmp/hadoop.tar.gz \ From f0df8b351a0bf3eb8052dc87086f1d8a1ae7db10 Mon Sep 17 00:00:00 2001 From: Gilles Dartiguelongue Date: Thu, 10 Mar 2022 17:55:17 +0100 Subject: [PATCH 2/5] Import gpg key in a single layer --- base/Dockerfile | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/base/Dockerfile b/base/Dockerfile index 4f8ff2aa..20ac8a50 100644 --- a/base/Dockerfile +++ b/base/Dockerfile @@ -14,9 +14,7 @@ RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-ins ENV JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64/ -RUN curl -O https://dist.apache.org/repos/dist/release/hadoop/common/KEYS - -RUN gpg --import KEYS +RUN curl -fsSL https://dist.apache.org/repos/dist/release/hadoop/common/KEYS | gpg --import - ENV HADOOP_VERSION 3.2.1 ENV HADOOP_URL https://archive.apache.org/dist/hadoop/common/hadoop-${HADOOP_VERSION}/hadoop-${HADOOP_VERSION}.tar.gz From 3b9666558f28342ef5a7c19d93bd4b53d8bd49f2 Mon Sep 17 00:00:00 2001 From: Gilles Dartiguelongue Date: Thu, 10 Mar 2022 17:56:13 +0100 Subject: [PATCH 3/5] Use COPY instead of ADD See Docker best practices documentation. --- base/Dockerfile | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/base/Dockerfile b/base/Dockerfile index 20ac8a50..3bcc21b4 100644 --- a/base/Dockerfile +++ b/base/Dockerfile @@ -38,8 +38,7 @@ ENV MULTIHOMED_NETWORK=1 ENV USER=root ENV PATH $HADOOP_HOME/bin/:$PATH -ADD entrypoint.sh /entrypoint.sh - +COPY entrypoint.sh /entrypoint.sh RUN chmod a+x /entrypoint.sh ENTRYPOINT ["/entrypoint.sh"] From 425aba824ef62f72ccc4939c25caf26580adad19 Mon Sep 17 00:00:00 2001 From: Gilles Dartiguelongue Date: Thu, 10 Mar 2022 18:39:38 +0100 Subject: [PATCH 4/5] Pass target Hadoop version via build arguments --- base/Dockerfile | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/base/Dockerfile b/base/Dockerfile index 3bcc21b4..faa3cdae 100644 --- a/base/Dockerfile +++ b/base/Dockerfile @@ -16,7 +16,8 @@ ENV JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64/ RUN curl -fsSL https://dist.apache.org/repos/dist/release/hadoop/common/KEYS | gpg --import - -ENV HADOOP_VERSION 3.2.1 +ARG HADOOP_VERSION=3.2.1 +ENV HADOOP_VERSION $HADOOP_VERSION ENV HADOOP_URL https://archive.apache.org/dist/hadoop/common/hadoop-${HADOOP_VERSION}/hadoop-${HADOOP_VERSION}.tar.gz RUN set -x \ From 4703dcf6ffdee25acfe5b645bbc1be1ca8f4b43d Mon Sep 17 00:00:00 2001 From: Gilles Dartiguelongue Date: Fri, 11 Mar 2022 16:31:12 +0100 Subject: [PATCH 5/5] Add org.opencontainers.image.version to hadoop-client Also add licenses LABEL. --- base/Dockerfile | 3 +++ 1 file changed, 3 insertions(+) diff --git a/base/Dockerfile b/base/Dockerfile index faa3cdae..a22e6ba4 100644 --- a/base/Dockerfile +++ b/base/Dockerfile @@ -20,6 +20,9 @@ ARG HADOOP_VERSION=3.2.1 ENV HADOOP_VERSION $HADOOP_VERSION ENV HADOOP_URL https://archive.apache.org/dist/hadoop/common/hadoop-${HADOOP_VERSION}/hadoop-${HADOOP_VERSION}.tar.gz +LABEL org.opencontainers.image.version=$HADOOP_VERSION +LABEL org.opencontainers.image.licenses=Apache-2.0 + RUN set -x \ && curl -fSL "$HADOOP_URL" -o /tmp/hadoop.tar.gz \ && curl -fSL "$HADOOP_URL.asc" -o /tmp/hadoop.tar.gz.asc \