You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by yi...@apache.org on 2022/11/01 03:14:16 UTC

[spark-docker] branch master updated: [SPARK-40969] Replace spark TGZ url with apache archive url

This is an automated email from the ASF dual-hosted git repository.

yikun pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark-docker.git


The following commit(s) were added to refs/heads/master by this push:
     new 243ce20  [SPARK-40969] Replace spark TGZ url with apache archive url
243ce20 is described below

commit 243ce201296c20ae48b32a87d254800e8ad197ef
Author: Qian.Sun <qi...@gmail.com>
AuthorDate: Tue Nov 1 11:14:04 2022 +0800

    [SPARK-40969] Replace spark TGZ url with apache archive url
    
    ### What changes were proposed in this pull request?
    
    This PR aims to replace spark TGZ url with apache archive url.
    
    ### Why are the changes needed?
    
    ```
    #13 [linux/amd64 4/9] RUN set -ex;     export SPARK_TMP="$(mktemp -d)";     cd $SPARK_TMP;     wget -nv -O spark.tgz "https://dlcdn.apache.org/spark/spark-3.3.0/spark-3.3.0-bin-hadoop3.tgz";     wget -nv -O spark.tgz.asc "https://downloads.apache.org/spark/spark-3.3.0/spark-3.3.0-bin-hadoop3.tgz.asc";     export GNUPGHOME="$(mktemp -d)";     gpg --keyserver hkps://keys.openpgp.org --recv-key "80FB8EBE8EBA68504989703491B5DC815DBF10D3" ||     gpg --keyserver hkps://keyserver.ubuntu.com  [...]
    #0 0.132 ++ mktemp -d
    #0 0.133 + export SPARK_TMP=/tmp/tmp.oEdW8CyP9h
    #0 0.133 + SPARK_TMP=/tmp/tmp.oEdW8CyP9h
    #0 0.133 + cd /tmp/tmp.oEdW8CyP9h
    #0 0.133 + wget -nv -O spark.tgz https://dlcdn.apache.org/spark/spark-3.3.0/spark-3.3.0-bin-hadoop3.tgz
    #0 0.152 https://dlcdn.apache.org/spark/spark-3.3.0/spark-3.3.0-bin-hadoop3.tgz:
    #0 0.152 2022-10-31 04:06:44 ERROR 404: Not Found.
    #13 ERROR: process "/bin/sh -c set -ex;     export SPARK_TMP=\"$(mktemp -d)\";     cd $SPARK_TMP;     wget -nv -O spark.tgz \"$SPARK_TGZ_URL\";     wget -nv -O spark.tgz.asc \"$SPARK_TGZ_ASC_URL\";     export GNUPGHOME=\"$(mktemp -d)\";     gpg --keyserver hkps://keys.openpgp.org --recv-key \"$GPG_KEY\" ||     gpg --keyserver hkps://keyserver.ubuntu.com --recv-keys \"$GPG_KEY\";     gpg --batch --verify spark.tgz.asc spark.tgz;     gpgconf --kill all;     rm -rf \"$GNUPGHOME\" spark.t [...]
    ```
    Old url `https://dlcdn.apache.org/spark/spark-3.3.0/spark-3.3.0-bin-hadoop3.tgz` is not found. Better to use unity apache archive url.
    
    ### Does this PR introduce _any_ user-facing change?
    
    No.
    
    ### How was this patch tested?
    
    No need to add new tests.
    
    Closes #22 from dcoliversun/SPARK-40969.
    
    Authored-by: Qian.Sun <qi...@gmail.com>
    Signed-off-by: Yikun Jiang <yi...@gmail.com>
---
 3.3.0/scala2.12-java11-python3-r-ubuntu/Dockerfile | 4 ++--
 3.3.0/scala2.12-java11-python3-ubuntu/Dockerfile   | 4 ++--
 3.3.0/scala2.12-java11-r-ubuntu/Dockerfile         | 4 ++--
 3.3.0/scala2.12-java11-ubuntu/Dockerfile           | 4 ++--
 3.3.1/scala2.12-java11-python3-r-ubuntu/Dockerfile | 4 ++--
 3.3.1/scala2.12-java11-python3-ubuntu/Dockerfile   | 4 ++--
 3.3.1/scala2.12-java11-r-ubuntu/Dockerfile         | 4 ++--
 3.3.1/scala2.12-java11-ubuntu/Dockerfile           | 4 ++--
 Dockerfile.template                                | 4 ++--
 9 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/3.3.0/scala2.12-java11-python3-r-ubuntu/Dockerfile b/3.3.0/scala2.12-java11-python3-r-ubuntu/Dockerfile
index 8c2761e..fb48b80 100644
--- a/3.3.0/scala2.12-java11-python3-r-ubuntu/Dockerfile
+++ b/3.3.0/scala2.12-java11-python3-r-ubuntu/Dockerfile
@@ -42,8 +42,8 @@ RUN set -ex && \
 
 # Install Apache Spark
 # https://downloads.apache.org/spark/KEYS
-ENV SPARK_TGZ_URL=https://dlcdn.apache.org/spark/spark-3.3.0/spark-3.3.0-bin-hadoop3.tgz \
-    SPARK_TGZ_ASC_URL=https://downloads.apache.org/spark/spark-3.3.0/spark-3.3.0-bin-hadoop3.tgz.asc \
+ENV SPARK_TGZ_URL=https://archive.apache.org/dist/spark/spark-3.3.0/spark-3.3.0-bin-hadoop3.tgz \
+    SPARK_TGZ_ASC_URL=https://archive.apache.org/dist/spark/spark-3.3.0/spark-3.3.0-bin-hadoop3.tgz.asc \
     GPG_KEY=80FB8EBE8EBA68504989703491B5DC815DBF10D3
 
 RUN set -ex; \
diff --git a/3.3.0/scala2.12-java11-python3-ubuntu/Dockerfile b/3.3.0/scala2.12-java11-python3-ubuntu/Dockerfile
index 6a0017a..1b6a02c 100644
--- a/3.3.0/scala2.12-java11-python3-ubuntu/Dockerfile
+++ b/3.3.0/scala2.12-java11-python3-ubuntu/Dockerfile
@@ -41,8 +41,8 @@ RUN set -ex && \
 
 # Install Apache Spark
 # https://downloads.apache.org/spark/KEYS
-ENV SPARK_TGZ_URL=https://dlcdn.apache.org/spark/spark-3.3.0/spark-3.3.0-bin-hadoop3.tgz \
-    SPARK_TGZ_ASC_URL=https://downloads.apache.org/spark/spark-3.3.0/spark-3.3.0-bin-hadoop3.tgz.asc \
+ENV SPARK_TGZ_URL=https://archive.apache.org/dist/spark/spark-3.3.0/spark-3.3.0-bin-hadoop3.tgz \
+    SPARK_TGZ_ASC_URL=https://archive.apache.org/dist/spark/spark-3.3.0/spark-3.3.0-bin-hadoop3.tgz.asc \
     GPG_KEY=80FB8EBE8EBA68504989703491B5DC815DBF10D3
 
 RUN set -ex; \
diff --git a/3.3.0/scala2.12-java11-r-ubuntu/Dockerfile b/3.3.0/scala2.12-java11-r-ubuntu/Dockerfile
index 975e444..0b49aef 100644
--- a/3.3.0/scala2.12-java11-r-ubuntu/Dockerfile
+++ b/3.3.0/scala2.12-java11-r-ubuntu/Dockerfile
@@ -40,8 +40,8 @@ RUN set -ex && \
 
 # Install Apache Spark
 # https://downloads.apache.org/spark/KEYS
-ENV SPARK_TGZ_URL=https://dlcdn.apache.org/spark/spark-3.3.0/spark-3.3.0-bin-hadoop3.tgz \
-    SPARK_TGZ_ASC_URL=https://downloads.apache.org/spark/spark-3.3.0/spark-3.3.0-bin-hadoop3.tgz.asc \
+ENV SPARK_TGZ_URL=https://archive.apache.org/dist/spark/spark-3.3.0/spark-3.3.0-bin-hadoop3.tgz \
+    SPARK_TGZ_ASC_URL=https://archive.apache.org/dist/spark/spark-3.3.0/spark-3.3.0-bin-hadoop3.tgz.asc \
     GPG_KEY=80FB8EBE8EBA68504989703491B5DC815DBF10D3
 
 RUN set -ex; \
diff --git a/3.3.0/scala2.12-java11-ubuntu/Dockerfile b/3.3.0/scala2.12-java11-ubuntu/Dockerfile
index c38e5dc..cbdf6c5 100644
--- a/3.3.0/scala2.12-java11-ubuntu/Dockerfile
+++ b/3.3.0/scala2.12-java11-ubuntu/Dockerfile
@@ -39,8 +39,8 @@ RUN set -ex && \
 
 # Install Apache Spark
 # https://downloads.apache.org/spark/KEYS
-ENV SPARK_TGZ_URL=https://dlcdn.apache.org/spark/spark-3.3.0/spark-3.3.0-bin-hadoop3.tgz \
-    SPARK_TGZ_ASC_URL=https://downloads.apache.org/spark/spark-3.3.0/spark-3.3.0-bin-hadoop3.tgz.asc \
+ENV SPARK_TGZ_URL=https://archive.apache.org/dist/spark/spark-3.3.0/spark-3.3.0-bin-hadoop3.tgz \
+    SPARK_TGZ_ASC_URL=https://archive.apache.org/dist/spark/spark-3.3.0/spark-3.3.0-bin-hadoop3.tgz.asc \
     GPG_KEY=80FB8EBE8EBA68504989703491B5DC815DBF10D3
 
 RUN set -ex; \
diff --git a/3.3.1/scala2.12-java11-python3-r-ubuntu/Dockerfile b/3.3.1/scala2.12-java11-python3-r-ubuntu/Dockerfile
index b126f1f..def11ff 100644
--- a/3.3.1/scala2.12-java11-python3-r-ubuntu/Dockerfile
+++ b/3.3.1/scala2.12-java11-python3-r-ubuntu/Dockerfile
@@ -42,8 +42,8 @@ RUN set -ex && \
 
 # Install Apache Spark
 # https://downloads.apache.org/spark/KEYS
-ENV SPARK_TGZ_URL=https://dlcdn.apache.org/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz \
-    SPARK_TGZ_ASC_URL=https://downloads.apache.org/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz.asc \
+ENV SPARK_TGZ_URL=https://archive.apache.org/dist/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz \
+    SPARK_TGZ_ASC_URL=https://archive.apache.org/dist/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz.asc \
     GPG_KEY=86727D43E73A415F67A0B1A14E68B3E6CD473653
 
 RUN set -ex; \
diff --git a/3.3.1/scala2.12-java11-python3-ubuntu/Dockerfile b/3.3.1/scala2.12-java11-python3-ubuntu/Dockerfile
index af02e65..3da8521 100644
--- a/3.3.1/scala2.12-java11-python3-ubuntu/Dockerfile
+++ b/3.3.1/scala2.12-java11-python3-ubuntu/Dockerfile
@@ -41,8 +41,8 @@ RUN set -ex && \
 
 # Install Apache Spark
 # https://downloads.apache.org/spark/KEYS
-ENV SPARK_TGZ_URL=https://dlcdn.apache.org/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz \
-    SPARK_TGZ_ASC_URL=https://downloads.apache.org/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz.asc \
+ENV SPARK_TGZ_URL=https://archive.apache.org/dist/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz \
+    SPARK_TGZ_ASC_URL=https://archive.apache.org/dist/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz.asc \
     GPG_KEY=86727D43E73A415F67A0B1A14E68B3E6CD473653
 
 RUN set -ex; \
diff --git a/3.3.1/scala2.12-java11-r-ubuntu/Dockerfile b/3.3.1/scala2.12-java11-r-ubuntu/Dockerfile
index bc2dcf7..04ab3ea 100644
--- a/3.3.1/scala2.12-java11-r-ubuntu/Dockerfile
+++ b/3.3.1/scala2.12-java11-r-ubuntu/Dockerfile
@@ -40,8 +40,8 @@ RUN set -ex && \
 
 # Install Apache Spark
 # https://downloads.apache.org/spark/KEYS
-ENV SPARK_TGZ_URL=https://dlcdn.apache.org/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz \
-    SPARK_TGZ_ASC_URL=https://downloads.apache.org/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz.asc \
+ENV SPARK_TGZ_URL=https://archive.apache.org/dist/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz \
+    SPARK_TGZ_ASC_URL=https://archive.apache.org/dist/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz.asc \
     GPG_KEY=86727D43E73A415F67A0B1A14E68B3E6CD473653
 
 RUN set -ex; \
diff --git a/3.3.1/scala2.12-java11-ubuntu/Dockerfile b/3.3.1/scala2.12-java11-ubuntu/Dockerfile
index c732406..8b342c4 100644
--- a/3.3.1/scala2.12-java11-ubuntu/Dockerfile
+++ b/3.3.1/scala2.12-java11-ubuntu/Dockerfile
@@ -39,8 +39,8 @@ RUN set -ex && \
 
 # Install Apache Spark
 # https://downloads.apache.org/spark/KEYS
-ENV SPARK_TGZ_URL=https://dlcdn.apache.org/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz \
-    SPARK_TGZ_ASC_URL=https://downloads.apache.org/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz.asc \
+ENV SPARK_TGZ_URL=https://archive.apache.org/dist/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz \
+    SPARK_TGZ_ASC_URL=https://archive.apache.org/dist/spark/spark-3.3.1/spark-3.3.1-bin-hadoop3.tgz.asc \
     GPG_KEY=86727D43E73A415F67A0B1A14E68B3E6CD473653
 
 RUN set -ex; \
diff --git a/Dockerfile.template b/Dockerfile.template
index a220247..4819cb2 100644
--- a/Dockerfile.template
+++ b/Dockerfile.template
@@ -48,8 +48,8 @@ RUN set -ex && \
 
 # Install Apache Spark
 # https://downloads.apache.org/spark/KEYS
-ENV SPARK_TGZ_URL=https://dlcdn.apache.org/spark/spark-{{ SPARK_VERSION }}/spark-{{ SPARK_VERSION }}-bin-hadoop3.tgz \
-    SPARK_TGZ_ASC_URL=https://downloads.apache.org/spark/spark-{{ SPARK_VERSION }}/spark-{{ SPARK_VERSION }}-bin-hadoop3.tgz.asc \
+ENV SPARK_TGZ_URL=https://archive.apache.org/dist/spark/spark-{{ SPARK_VERSION }}/spark-{{ SPARK_VERSION }}-bin-hadoop3.tgz \
+    SPARK_TGZ_ASC_URL=https://archive.apache.org/dist/spark/spark-{{ SPARK_VERSION }}/spark-{{ SPARK_VERSION }}-bin-hadoop3.tgz.asc \
     GPG_KEY={{ SPARK_GPG_KEY }}
 
 RUN set -ex; \


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org