apache · terrymanu · Nov 30, 2024 · Nov 28, 2024
diff --git a/RELEASE-NOTES.md b/RELEASE-NOTES.md
@@ -46,6 +46,7 @@
 1. Encrypt: Fix merge exception without encrypt rule in database - [#33708](https://github.com/apache/shardingsphere/pull/33708)
 1. SQL Parser: Fix mysql parse zone unreserved keyword error - [#33720](https://github.com/apache/shardingsphere/pull/33720)
 1. Proxy: Fix BatchUpdateException when execute INSERT INTO ON DUPLICATE KEY UPDATE in proxy adapter - [#33796](https://github.com/apache/shardingsphere/pull/33796)
+1. Infra: Fix the issue that ShardingSphere cannot connect to HiveServer2 using remote Hive Metastore Server - [#33837](https://github.com/apache/shardingsphere/pull/33837)
 
 ### Change Logs
 

diff --git a/...ntent/user-manual/shardingsphere-jdbc/optional-plugins/hiveserver2/_index.cn.md b/...ntent/user-manual/shardingsphere-jdbc/optional-plugins/hiveserver2/_index.cn.md
@@ -40,6 +40,17 @@ ShardingSphere 对 HiveServer2 JDBC Driver 的支持位于可选模块中。
         <artifactId>hive-service</artifactId>
         <version>4.0.1</version>
     </dependency>
+    <dependency>
+        <groupId>org.apache.hadoop</groupId>
+        <artifactId>hadoop-mapreduce-client-core</artifactId>
+        <version>3.3.6</version>
+        <exclusions>
+            <exclusion>
+                <groupId>*</groupId>
+                <artifactId>*</artifactId>
+            </exclusion>
+        </exclusions>
+    </dependency>
 </dependencies>
 ```
 
@@ -81,6 +92,17 @@ ShardingSphere 对 HiveServer2 JDBC Driver 的支持位于可选模块中。
             </exclusion>
         </exclusions>
     </dependency>
+    <dependency>
+        <groupId>org.apache.hadoop</groupId>
+        <artifactId>hadoop-mapreduce-client-core</artifactId>
+        <version>3.3.6</version>
+        <exclusions>
+            <exclusion>
+                <groupId>*</groupId>
+                <artifactId>*</artifactId>
+            </exclusion>
+        </exclusions>
+    </dependency>
 </dependencies>
 ```
 
@@ -427,8 +449,31 @@ ShardingSphere 仅针对 HiveServer2 `4.0.1` 进行集成测试。
 ### Hadoop 限制
 
 用户仅可使用 Hadoop `3.3.6` 来作为 HiveServer2 JDBC Driver `4.0.1` 的底层 Hadoop 依赖。
-HiveServer2 JDBC Driver `4.0.1` 不支持 Hadoop `3.4.1`，
-参考 https://github.com/apache/hive/pull/5500 。
+HiveServer2 JDBC Driver `4.0.1` 不支持 Hadoop `3.4.1`， 参考 https://github.com/apache/hive/pull/5500 。
+
+对于 HiveServer2 JDBC Driver `org.apache.hive:hive-jdbc:4.0.1` 或 `classifier` 为 `standalone` 的 `org.apache.hive:hive-jdbc:4.0.1`，
+实际上并不额外依赖 `org.apache.hadoop:hadoop-mapreduce-client-core:3.3.6`。
+
+但 `org.apache.shardingsphere:shardingsphere-infra-database-hive` 的
+`org.apache.shardingsphere.infra.database.hive.metadata.data.loader.HiveMetaDataLoader` 会使用 `org.apache.hadoop.hive.conf.HiveConf`，
+这进一步使用了 `org.apache.hadoop:hadoop-mapreduce-client-core:3.3.6` 的 `org.apache.hadoop.mapred.JobConf` 类。
+
+ShardingSphere 仅需要使用 `org.apache.hadoop.mapred.JobConf` 类，
+因此排除 `org.apache.hadoop:hadoop-mapreduce-client-core:3.3.6` 的所有额外依赖是合理行为。
+
+```xml
+<dependency>
+    <groupId>org.apache.hadoop</groupId>
+    <artifactId>hadoop-mapreduce-client-core</artifactId>
+    <version>3.3.6</version>
+    <exclusions>
+        <exclusion>
+            <groupId>*</groupId>
+            <artifactId>*</artifactId>
+        </exclusion>
+    </exclusions>
+</dependency>
+```
 
 ### SQL 限制
 

diff --git a/...ntent/user-manual/shardingsphere-jdbc/optional-plugins/hiveserver2/_index.en.md b/...ntent/user-manual/shardingsphere-jdbc/optional-plugins/hiveserver2/_index.en.md
@@ -41,6 +41,17 @@ The possible Maven dependencies are as follows.
         <artifactId>hive-service</artifactId>
         <version>4.0.1</version>
     </dependency>
+    <dependency>
+        <groupId>org.apache.hadoop</groupId>
+        <artifactId>hadoop-mapreduce-client-core</artifactId>
+        <version>3.3.6</version>
+        <exclusions>
+            <exclusion>
+                <groupId>*</groupId>
+                <artifactId>*</artifactId>
+            </exclusion>
+        </exclusions>
+    </dependency>
 </dependencies>
 ```
 
@@ -83,6 +94,17 @@ The following is an example of a possible configuration,
             </exclusion>
         </exclusions>
     </dependency>
+    <dependency>
+        <groupId>org.apache.hadoop</groupId>
+        <artifactId>hadoop-mapreduce-client-core</artifactId>
+        <version>3.3.6</version>
+        <exclusions>
+            <exclusion>
+                <groupId>*</groupId>
+                <artifactId>*</artifactId>
+            </exclusion>
+        </exclusions>
+    </dependency>
 </dependencies>
 ```
 
@@ -433,8 +455,31 @@ Reference https://issues.apache.org/jira/browse/HIVE-28418.
 ### Hadoop Limitations
 
 Users can only use Hadoop `3.3.6` as the underlying Hadoop dependency of HiveServer2 JDBC Driver `4.0.1`.
-HiveServer2 JDBC Driver `4.0.1` does not support Hadoop `3.4.1`,
-Reference https://github.com/apache/hive/pull/5500.
+HiveServer2 JDBC Driver `4.0.1` does not support Hadoop `3.4.1`. Reference https://github.com/apache/hive/pull/5500 .
+
+For HiveServer2 JDBC Driver `org.apache.hive:hive-jdbc:4.0.1` or `org.apache.hive:hive-jdbc:4.0.1` with `classifier` as `standalone`,
+there is actually no additional dependency on `org.apache.hadoop:hadoop-mapreduce-client-core:3.3.6`.
+
+But `org.apache.shardingsphere:shardingsphere-infra-database-hive`'s
+`org.apache.shardingsphere.infra.database.hive.metadata.data.loader.HiveMetaDataLoader` uses `org.apache.hadoop.hive.conf.HiveConf`,
+which further uses `org.apache.hadoop:hadoop-mapreduce-client-core:3.3.6`'s `org.apache.hadoop.mapred.JobConf` class.
+
+ShardingSphere only needs to use the `org.apache.hadoop.mapred.JobConf` class,
+so it is reasonable to exclude all additional dependencies of `org.apache.hadoop:hadoop-mapreduce-client-core:3.3.6`.
+
+```xml
+<dependency>
+    <groupId>org.apache.hadoop</groupId>
+    <artifactId>hadoop-mapreduce-client-core</artifactId>
+    <version>3.3.6</version>
+    <exclusions>
+        <exclusion>
+            <groupId>*</groupId>
+            <artifactId>*</artifactId>
+        </exclusion>
+    </exclusions>
+</dependency>
+```
 
 ### SQL Limitations
 

diff --git a/...resources/META-INF/native-image/org.apache.hadoop/hadoop-common/3.3.6/reflect-config.json b/...resources/META-INF/native-image/org.apache.hadoop/hadoop-common/3.3.6/reflect-config.json
@@ -0,0 +1,8 @@
+[
+{
+  "condition":{"typeReachable":"org.apache.hadoop.security.UserGroupInformation"},
+  "name":"org.apache.hadoop.security.UserGroupInformation$UgiMetrics",
+  "allDeclaredFields": true,
+  "allDeclaredMethods": true
+}
+]
diff --git a/...esources/META-INF/native-image/org.apache.hadoop/hadoop-common/3.3.6/resource-config.json b/...esources/META-INF/native-image/org.apache.hadoop/hadoop-common/3.3.6/resource-config.json
@@ -3,12 +3,6 @@
   "includes":[{
     "condition":{"typeReachable":"org.apache.hadoop.conf.Configuration"},
     "pattern":"\\Qhadoop-site.xml\\E"
-  }, {
-    "condition":{"typeReachable":"org.apache.hadoop.conf.Configuration"},
-    "pattern":"\\Qcore-default.xml\\E"
-  }, {
-    "condition":{"typeReachable":"org.apache.hadoop.conf.Configuration"},
-    "pattern":"\\Qcore-site.xml\\E"
   }]},
   "bundles":[]
 }
diff --git a/.../main/resources/META-INF/native-image/org.apache.hive/hive-jdbc/4.0.1/reflect-config.json b/.../main/resources/META-INF/native-image/org.apache.hive/hive-jdbc/4.0.1/reflect-config.json
@@ -0,0 +1,11 @@
+[
+{
+  "condition":{"typeReachable":"org.apache.hadoop.hive.metastore.HiveMetaStoreClient"},
+  "name":"org.apache.hadoop.hive.metastore.DefaultMetaStoreFilterHookImpl",
+  "methods":[{"name":"<init>","parameterTypes":["org.apache.hadoop.conf.Configuration"] }]
+},
+{
+  "condition":{"typeReachable":"org.apache.hadoop.hive.metastore.conf.MetastoreConf"},
+  "name":"org.apache.hadoop.hive.metastore.DefaultMetaStoreFilterHookImpl"
+}
+]
diff --git a/.../native-image/org.apache.shardingsphere/generated-reachability-metadata/proxy-config.json b/.../native-image/org.apache.shardingsphere/generated-reachability-metadata/proxy-config.json
@@ -3,6 +3,10 @@
     "condition":{"typeReachable":"org.apache.shardingsphere.proxy.initializer.BootstrapInitializer"},
     "interfaces":["java.sql.Connection"]
   },
+  {
+    "condition":{"typeReachable":"org.apache.shardingsphere.infra.database.hive.metadata.data.loader.HiveMetaDataLoader"},
+    "interfaces":["org.apache.hadoop.metrics2.MetricsSystem$Callback"]
+  },
   {
     "condition":{"typeReachable":"org.apache.shardingsphere.driver.jdbc.core.datasource.ShardingSphereDataSource"},
     "interfaces":["org.apache.hive.service.rpc.thrift.TCLIService$Iface"]