From 644b917a302e26cfa3d757a7ebf0430b1e3e679e Mon Sep 17 00:00:00 2001
From: Kent Yao <yao@apache.org>
Date: Thu, 24 Feb 2022 12:07:46 +0800
Subject: [PATCH] [KYUUBI #1970] Replace mirror-cn profile with Apache
 officially suggested dlcdn

### _Why are the changes needed?_

Replace `mirror-cn` profile with Apache officially suggested dlcdn.

mirror-cn is only suite for CN, while dlcdn is much wiser.

### _How was this patch tested?_
- [ ] Add some test cases that check the changes thoroughly including negative and positive cases if possible

- [ ] Add screenshots for manual tests if appropriate

- [x] [Run test](https://kyuubi.apache.org/docs/latest/develop_tools/testing.html#running-tests) locally before make a pull request

Closes #1970 from yaooqinn/cdn.

Closes #1970

a325f828 [Kent Yao] Repalce mirror-cn profile with Apache officially suggested dlcdn
a0756b4f [Kent Yao] Repalce mirror-cn profile with Apache officially suggested dlcdn

Authored-by: Kent Yao <yao@apache.org>
Signed-off-by: Kent Yao <yao@apache.org>
---
 docs/develop_tools/building.md    | 24 ++++++++++--------------
 externals/kyuubi-download/pom.xml | 15 ++++++---------
 pom.xml                           | 11 ++++++-----
 3 files changed, 22 insertions(+), 28 deletions(-)

diff --git a/docs/develop_tools/building.md b/docs/develop_tools/building.md
index e57501ec6..0de86bef9 100644
--- a/docs/develop_tools/building.md
+++ b/docs/develop_tools/building.md
@@ -73,22 +73,18 @@ Profile | Default  | Since
 -Pspark-3.1 | No | 1.1.0
 
 
-## Defining the Apache Mirror for Spark or Flink
+## Building with Apache dlcdn site
 
-By default, we use `https://archive.apache.org/dist/spark/` to download the built-in Spark or 
-use `https://archive.apache.org/dist/flink/` to download the built-in Flink release package,
-but if you find it hard to reach, or the downloading speed is too slow, you can define the `spark.archive.mirror`
-or `flink.archive.mirror` property to a suitable Apache mirror site. For instance,
+By default, we use `https://archive.apache.org/dist/` to download the built-in release packages of engines,
+such as Spark or Flink.
+But sometimes, you may find it hard to reach, or the download speed is too slow,
+then you can define the `apache.archive.dist` by `-Pmirror-cdn` to accelerate to download speed.
+For example,
 
 ```bash
-build/mvn clean package -Dspark.archive.mirror=https://mirrors.bfsu.edu.cn/apache/spark/spark-3.0.1
+build/mvn clean package -Pmirror-cdn
 ```
 
-Visit [Apache Mirrors](http://www.apache.org/mirrors/) and choose a mirror based on your region.
-
-Specifically for developers in China mainland, you can use the pre-defined profile named `mirror-cn` 
- which use `mirrors.bfsu.edu.cn` to speed up Spark Binary downloading. For instance,
-
-```bash
-build/mvn clean package -Pmirror-cn
-```
+The profile migrates your download repo to the Apache offically suggested site - https://dlcdn.apache.org.
+Note that, this site only holds the latest versions of Apache releases. You may fail if the specific version
+defined by `spark.version` or `flink.version` is overdue.
diff --git a/externals/kyuubi-download/pom.xml b/externals/kyuubi-download/pom.xml
index 7758df721..e900af7f4 100644
--- a/externals/kyuubi-download/pom.xml
+++ b/externals/kyuubi-download/pom.xml
@@ -47,11 +47,6 @@
                         <configuration>
                             <skip>${spark.archive.download.skip}</skip>
                             <url>${spark.archive.mirror}/${spark.archive.name}</url>
-                            <!-- sha512>${spark.archive.sha512}</sha512 -->
-                            <outputDirectory>${project.build.directory}</outputDirectory>
-                            <readTimeOut>60000</readTimeOut>
-                            <retries>3</retries>
-                            <unpack>true</unpack>
                         </configuration>
                     </execution>
                     <execution>
@@ -63,13 +58,15 @@
                         <configuration>
                             <skip>${flink.archive.download.skip}</skip>
                             <url>${flink.archive.mirror}/${flink.archive.name}</url>
-                            <outputDirectory>${project.build.directory}</outputDirectory>
-                            <readTimeOut>60000</readTimeOut>
-                            <retries>3</retries>
-                            <unpack>true</unpack>
                         </configuration>
                     </execution>
                 </executions>
+                <configuration>
+                    <outputDirectory>${project.build.directory}</outputDirectory>
+                    <readTimeOut>60000</readTimeOut>
+                    <retries>3</retries>
+                    <unpack>true</unpack>
+                </configuration>
             </plugin>
         </plugins>
     </build>
diff --git a/pom.xml b/pom.xml
index 1ea12aa8a..e9742bb52 100644
--- a/pom.xml
+++ b/pom.xml
@@ -93,6 +93,7 @@
         <scala.binary.version>2.12</scala.binary.version>
 
         <antlr4.version>4.8</antlr4.version>
+        <apache.archive.dist>https://archive.apache.org/dist</apache.archive.dist>
         <bouncycastle.version>1.67</bouncycastle.version>
         <codahale.metrics.version>4.2.8</codahale.metrics.version>
         <commons-codec.version>1.15</commons-codec.version>
@@ -104,7 +105,7 @@
         <delta.version>1.1.0</delta.version>
         <flink.version>1.14.3</flink.version>
         <flink.archive.name>flink-${flink.version}-bin-scala_${scala.binary.version}.tgz</flink.archive.name>
-        <flink.archive.mirror>https://archive.apache.org/dist/flink/flink-${flink.version}</flink.archive.mirror>
+        <flink.archive.mirror>${apache.archive.dist}/flink/flink-${flink.version}</flink.archive.mirror>
         <flink.archive.download.skip>false</flink.archive.download.skip>
         <google.jsr305.version>3.0.2</google.jsr305.version>
         <guava.version>30.1-jre</guava.version>
@@ -140,7 +141,7 @@
           -->
         <spark.version>3.2.1</spark.version>
         <spark.archive.name>spark-${spark.version}-bin-hadoop3.2.tgz</spark.archive.name>
-        <spark.archive.mirror>https://archive.apache.org/dist/spark/spark-${spark.version}</spark.archive.mirror>
+        <spark.archive.mirror>${apache.archive.dist}/spark/spark-${spark.version}</spark.archive.mirror>
         <spark.archive.download.skip>false</spark.archive.download.skip>
         <swagger.version>2.1.11</swagger.version>
         <swagger-ui.version>4.1.3</swagger-ui.version>
@@ -1810,10 +1811,10 @@
 
     <profiles>
         <profile>
-            <id>mirror-cn</id>
+            <id>mirror-cdn</id>
+            <!-- this profile works only for latest apache releases -->
             <properties>
-                <spark.archive.mirror>https://mirrors.bfsu.edu.cn/apache/spark/spark-${spark.version}</spark.archive.mirror>
-                <flink.archive.mirror>https://mirrors.bfsu.edu.cn/apache/flink/flink-${flink.version}</flink.archive.mirror>
+                <apache.archive.dist>https://dlcdn.apache.org</apache.archive.dist>
             </properties>
         </profile>